Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In this article, we introduce an application, which implements the RBSC-SubGen algorithm on a web platform in an easy-to-use manner. Originally, Furuya et al. proposed this algorithm and demonstrated it on an sample scenario, where a pair of vocabulary decks are constructed with a desired difficulty relation out of a large corpus. In addition to such applications, RBSC-SubGen can be used in a broad range of applications. For instance, studies which require the recruitment of a representative set of human subjects (e.g. drug testing, consumer surveys) may benefit from this method in sampling from the population. However, the deployment of the algorithm in non-technical fields such as medicine or social science may be difficult, since the publicly available algorithm implementation target users skilled in software development. In that respect, with the proposed web application the accessibility and disponibility of the algorithm by users from non-technical fields are expected to be facilitated considerably.

DOI： 10.1109/iiai-aai-winter58034.2022.00021

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Saliency maps show the likelihood of each pixel on the image being looked at. They are often computed considering a neutral human subject, who is considered to be simply observing the image without any particular motivation (e.g, searching, registering etc.) or feelings (e.g, excited, fearful etc.). In this study, we focus on the emotional aspect and investigate whether there is any need to adjust these saliency maps to account for the emotions that they may induce in the viewers. To that end, we choose a set of images from an emotional image data set and display them to human subjects. We register their eye gaze and compute how well empirical gaze data matches the saliency maps. We quantify this based on two distribution-based (AUC, IG) and two location-based saliency metrics (CC and SIM). We see that although there are some parallels in some of these metrics, the evidence is not strong enough to claim a significant contribution due to affective content.

DOI： 10.1109/iiai-aai-winter58034.2022.00030

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In human-computer interaction, it is important that the users sustain their engagement during cognitively demanding tasks. To that end, the system needs first to estimate the level of engagement and detect the declines and then to trigger a support mechanism to recover engagement. In that respect, many studies in the literature propose estimating engagement from facial images. Although these studies have proved that facial landmarks, especially those relating to the eyes (ocular landmarks), serve useful in the estimation of task engagement, they are subject to criticism, since it may make the user uncomfortable to be constantly watched. In addition, the video data needs to be handled very carefully due to privacy issues. In that respect, this study investigates whether it is possible to estimate the level of engagement from anonymous data, specifically from eye gaze. This sort of data is considered to be closely related to the changes in ocular landmark locations and therefore has the potential to involve similar qualities to those of ocular landmarks. In addition, since it is not possible to identify the individuals from gaze fixations, it is not privacy sensitive. Moreover, it is also expected to help relieve users' discomfort due to constant observation and also prevent modifications in their behavior due to their awareness of being observed.

DOI： 10.1109/iiai-aai-winter58034.2022.00041

Scopus

researchmap

Language：English   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (conference, symposium, etc.)  

Most e-learning systems deliver solely visual information, even though they boast a huge potential for supporting the learners using various other capabilities (e.g. camera, speakers) of the hosting platform (i.e. computer, smart phone etc.). In this study, we focus deploying one such potential, namely audio stimuli (informative and non-informative), for supporting rote learning of different types of learning material (i.e. easy verbal, hard verbal and numerical). Our results indicate that audio stimuli do not provide a significant benefit for studying easy verbal content, but there is a big room for improvement concerning other content types (hard verbal and numerical). Interestingly, despite the general implications of dual-coding theory, human-readout of hard verbal contents is observed not to provide any significant improvement over visual-only stimuli. However, to our surprise, non-informative audio stimuli (i.e. bell sound) are observed to provide an improvement, whereas numerical content is observed to benefit in a similar way from informative and non-informative audio. Based on these results, in the future we aim developing an automatic learning support system, which triggers the appropriate audio stimuli, taking in consideration the type of content.

DOI： 10.1109/IIAIAAI55812.2022.00057

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electrical and Electronics Engineers (IEEE)  

Software data sets derived from actual software products and their development processes are widely used for project planning, management, quality assurance and process improvement, etc. Although it is demonstrated that certain data sets are not fit for these purposes, the data quality of data sets is often not assessed before using them. The principal reason for this is that there are not many metrics quantifying fitness of software development data. In that respect, this study makes an effort to fill in the void in literature by devising a new and efficient assessment method of data quality. To that end, we start as a reference from Case Inconsistency Level (CIL), which counts the number of inconsistent project pairs in a data set to evaluate its consistency. Based on a follow-up evaluation with a large sample set, we depict that CIL is not effective in evaluating the quality of certain data sets. By studying the problems associated with CIL and eliminating them, we propose an improved metric called Similar Case Inconsistency Level (SCIL). Our empirical evaluation with 54 data samples derived from six large project data sets shows that SCIL can distinguish between consistent and inconsistent data sets, and that prediction models for software development effort and productivity built from consistent data sets achieve indeed a relatively higher accuracy.

DOI： 10.1109/access.2022.3188246

Scopus

researchmap

Language：English   Publishing type：Research paper (conference, symposium, etc.)  

This study focuses on a specific type of subset selection problem, which is constrained in terms of the rank bi-serial correlation (RBSC) coefficient of the outputs. For solving such problems, we propose an approach with several advantages such as (i) providing a clear insight into the feasibility of the problem with respect to the hyper-parameters, (ii) being non-iterative, (iii) having a foreseeable running time, and (iv) with the potential to yield non-deterministic (diverse) outputs. In particular, the proposed approach is based on starting from a composition of subsets with an extreme value of the RBSC coefficient (e.g. ρ=1) and swapping certain elements of the subsets in order to adjust ρ into the desired range. The proposed method is superior to the previously proposed RBSC-SubGen, which attempts to solve the problem before confirming its feasibility, taking random steps, and has unforeseeable running times and saturation issues.

DOI： 10.1109/IIAIAAI55812.2022.00076

Scopus

researchmap

Publishing type：Research paper (scientific journal)  

In evaluating the performance of software defect prediction models, accuracy measures such as precision and recall are commonly used. However, most of these measures are affected by neg/pos ratio of the data set being predicted, where neg is the number of negative cases (defect-free modules) and pos is the number of positive cases (defective modules). Thus, it is not fair to compare such values across different data sets with different neg/pos ratios and it may even lead to misleading or contradicting conclusions. The objective of this study is to address the class imbalance issue in assessing performance of defect prediction models. The proposed method relies on computation of expected values of accuracy measures based solely on the value of the neg and pos values of the data set. Based on the expected values, we derive the neg/pos-normalized accuracy measures, which are defined as their divergence from the expected value divided by the standard deviation of all possible prediction outcomes. The proposed measures enable us to provide a ranking of predictions across different data sets, which can distinguish between successful predictions and unsuccessful predictions. Our results derived from a case study of defect prediction based on 19 defect data sets indicate that ranking of predictions is significantly different than the ranking of conventional accuracy measures such as precision and recall as well as composite measures F1-value, AUC of ROC, MCC, G-mean and Balance. In addition, we conclude that MCC attains a better defect prediction accuracy than F1-value, AUC of ROC, G-mean and Balance.

DOI： 10.1109/ACCESS.2022.3232144

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Last author   Language：English   Publishing type：Research paper (international conference proceedings)  

Software quality assurance (SQA) is a series of activities within the software development lifecycle that repetitively verify or test the software deliverables to ensure their quality. In this paper, we propose a simulation model of SQA to quantitatively demonstrate the positive effect of adding quality assurance (QA) effort especially in early phases of software development. The proposed model can represent the relationship among the number of bugs in each phase, the amount of QA effort, the expected number of detectable bugs and the amount of bug fixing effort. The model can simulate the different QA strategies in a given software development context; thus, it is useful to identify the best or better strategies to improve software quality with smaller QA and bug fixing effort.

DOI： 10.1109/SNPD51163.2021.9704927

Scopus

researchmap

Authorship：Last author   Language：English   Publishing type：Research paper (international conference proceedings)  

The correlation coefficient is commonly used in analyses of software project data sets for the purpose of quantifying the relationship between two variables. However, while there are various types of relationships between two variables, the correlation coefficient cannot distinguish between these types. This study proposes new metrics between two continuous variables that have the potential to characterize the relationship types.

DOI： 10.1109/SNPD51163.2021.9704983

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Last author   Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

Digital tools and services collect a growing amount of log data. In the software development industry, such data are integral and boast valuable information on user and system behaviors with a significant potential of discovering various trends and patterns. In this study, we focus on one of those potential aspects, which is task estimation. In that regard, we perform a case study by analyzing computer recorded activities of employees from a software development company. Specifically, our purpose is to identify the task of each employee. To that end, we build a hierarchical framework with a 2-stage recognition and devise a method relying on Bayesian estimation which accounts for temporal correlation of tasks. After pre-processing, we run the proposed hierarchical scheme to initially distinguish infrequent and frequent tasks. At the second stage, infrequent tasks are discriminated between them such that the task is identified definitively. The higher performance rate of the proposed method makes it favorable against the association rule-based methods and conventional classification algorithms. Moreover, our method offers significant potential to be implemented on similar software engineering problems. Our contributions include a comprehensive evaluation of a Bayesian estimation scheme on real world data and offering reinforcements against several challenges in the data set (samples with different measurement scales, dependence characteristics, imbalance, and with insignificant pieces of information).

DOI： 10.1007/s10664-021-10006-4

Scopus

researchmap

Other Link： https://link.springer.com/article/10.1007/s10664-021-10006-4/fulltext.html

Authorship：Last author   Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Publishing type：Research paper (scientific journal)  

In this study, we quantitatively compare the effects of outlier handling methods in training datasets for model building on eight software effort estimation models (e.g., linear multiple regression, regression trees, random forests, support vector regression, etc.), and we evaluate the effectiveness of the data smoothing method proposed by the authors. In our experiments, we compare three outlier removal methods (outlier removal using Cook's distance, TEAK, and Filter-INC) in addition to the data smoothing method. Experimental results showed that the data smoothing method combined with the outlier detection method in Cook's distance or Filter-INC were found to build a model with good estimation performance.

DOI： 10.11309/jssst.38.3_83

Scopus

researchmap

Publishing type：Research paper (scientific journal)  

Recently, automated machine learning (AutoML), which automates pre-processing, model selection, and hyperparameter adjustment, is becoming more and more popular, and it is expected to provide both ease of model construction and high prediction accuracy. In this study, we apply AutoML to software development effort estimation and experimentally evaluate its effectiveness. In our experiments, we employed auto-sklearn, which is an AutoML library, as well as linear multiple regression, elastic net, and random forest for comparison. A comparison of the estimation accuracy of each model by the win-tie-loss method confirmed that auto-sklearn showed the same or better estimation performance than other models. We also summarize the results of analyzing the effect of search time of auto-sklearn on the estimation accuracy.

DOI： 10.11309/jssst.38.4_46

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Informa UK Limited  

E-learning offers many advantages like being economical, flexible and customizable, but also has challenging aspects such as lack of–social-interaction, which results in contemplation and sense of remoteness. To overcome these and sustain learners’ motivation, various stimuli can be incorporated. Nevertheless, such adjustments initially require an assessment of engagement level. In this respect, we propose estimating engagement level from facial landmarks exploiting the facts that (i) perceptual decoupling is promoted by blinking during mentally demanding tasks; (ii) eye strain increases blinking rate, which also scales with task disengagement; (iii) eye aspect ratio is in close connection with attentional state and (iv) users’ head position is correlated with their level of involvement. Building empirical models of these actions, we devise a probabilistic estimation framework. Our results indicate that high and low levels of engagement are identified with considerable accuracy, whereas medium levels are inherently more challenging, which is also confirmed by inter-rater agreement of expert coders.

DOI： 10.1080/10447318.2020.1768666

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electronics, Information and Communications Engineers (IEICE)  

To conduct empirical research on industry software development, it is necessary to obtain data of real software projects from industry. However, only few such industry data sets are publicly available; and unfortunately, most of them are very old. In addition, most of today’s software companies cannot make their data open, because software development involves many stakeholders, and thus, its data confidentiality must be strongly preserved. To that end, this study proposes a method for artificially generating a “mimic” software project data set, whose characteristics (such as average, standard deviation and correlation coefficients) are very similar to a given confidential data set. Instead of using the original (confidential) data set, researchers are expected to use the mimic data set to produce similar results as the original data set. The proposed method uses the Box-Muller transform for generating normally distributed random numbers; and exponential transformation and number reordering for data mimicry. To evaluate the efficacy of the proposed method, effort estimation is considered as potential application domain for employing mimic data. Estimation models are built from 8 reference data sets and their concerning mimic data. Our experiments confirmed that models built from mimic data sets show similar effort estimation performance as the models built from original data sets, which indicate the capability of the proposed method in generating representative samples.

DOI： 10.1587/transinf.2019edp7150

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This study investigates the effect of stimulus medium on recollection rate of elderly users in computer based flashcard systems. We present several rote learning tasks to 18 elderly participants with different content types and levels of difficulty. We deliver the tasks using three sorts of stimuli as visual (i.e. textonly), audio (i.e. sound-only) and audio-visual (text-and-sound). We evaluate participants' recollection rates using two memory tests, applied (i) freshly upon completing the task and (ii) after a certain time window. Our results indicate that the involvement of audio stimuli results in a higher recollection rate in both tests and a lower forget rate, specifically in relatively easier verbal content and numerical content, independent of participants' age.

DOI： 10.1109/iiai-aai50415.2020.00036

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Forschungszentrum Julich, Zentralbibliothek  

We discuss the development of a robot system able to replicate human group motion and show how a pedestrian model may be converted to a robot control system in order to achieve this goal.

DOI： 10.17815/cd.2020.90

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electronics, Information and Communications Engineers (IEICE)  

This study focuses on computer based foreign language vocabulary learning systems. Our objective is to automatically build vocabulary decks with desired levels of relative difficulty relations. To realize this goal, we exploit the fact that word frequency is a good indicator of vocabulary difficulty. Subsequently, for composing the decks, we pose two requirements as uniformity and diversity. Namely, the difficulty level of the cards in the same deck needs to be uniform enough so that they can be grouped together and difficulty levels of the cards in different decks need to be diverse enough so that they can be grouped in different decks. To assess uniformity and diversity, we use rank-biserial correlation and propose an iterative algorithm, which helps in attaining desired levels of uniformity and diversity based on word frequency in daily use of language. In experiments, we employed a spaced repetition flashcard software and presented users various decks built with the proposed algorithm, which contain cards from different content types. From users' activity logs, we derived several behavioral variables and examined the polyserial correlation between these variables and difficulty levels across different word classes. This analysis confirmed that the decks compiled with the proposed algorithm induce an effect on behavioral variables in line with the expectations. In addition, a series of experiments with decks involving varying content types confirmed that this relation is independent of word class.

DOI： 10.1587/transinf.2019edp7279

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Forschungszentrum Julich, Zentralbibliothek  

This study focuses on social pedestrian groups in public spaces and makes an effort to identify the social relation between the group members. We particularly consider dyads having coalitional or mating relation. We derive several observables from individual and group trajectories, which are suggested to be distinctive for these two sorts of relations and propose a recognition algorithm taking these observables as features and yielding an estimation of social relation in a probabilistic manner at every sampling step. On the average, we detect coalitional relation with 87% and mating relation with 81% accuracy. To the best of our knowledge, this is the first study to infer social relation from joint (loco)motion patterns and we consider the detection rates to be a satisfactory considering the inherent challenge of the problem.

DOI： 10.17815/cd.2020.54

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Forschungszentrum Julich, Zentralbibliothek  

We analysed a set of uninstructed pedestrian trajectories automatically tracked in a public area, and we asked a human coder to assess their group relationships. For those pedestrians who belong to the groups, we asked the coder to identify their apparent purpose of visit to the tracking area and apparent gender. We studied the quantitative dependence of the group dynamics on such properties in the case of triads (three people groups) and compared them to the two pedestrian group case (dyads), studied in a previous work. We found that the group velocity strongly depends on relation and gender for both triads and dyads, while the influence of these properties on spatial structure of groups is less clear in the triadic case. We discussed the relevance of these results to the modelling of pedestrian and crowd dynamics, and examined the possibility of the future works on this subject.

DOI： 10.17815/cd.2020.41

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：International Institute of Applied Informatics  

DOI： 10.52731/ijltle.v3.i1.521

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Part of collection (book)   Publisher：Springer International Publishing  

In traffic safety community, behavioral differences between genders have been attracting considerable attention in recent decades. Various empirical studies have proven that gender has a significant relation to drivers’, cyclists’ or pedestrians’ decision making, route choice, rule compliance, as well as risk taking/perception. However, most studies examine behavior of individuals, and only very few consider (pedestrian) groups with different gender profiles. Therefore, this study investigates effect of gender composition of pedestrian dyads on the tangible dynamics, which may potentially help in automatically understanding and interpreting higher level behaviors such as decision making. We first propose a set of variables to represent dyads’s physical/dynamical state. Observing empirical distributions, we comment on the effect of gender interplay on locomotion preferences. In order to verify our inferences quantitatively, we propose a gender profile recognition algorithm. Removing one variable at a time, contribution of each variable to recognition is evaluated. Our findings indicate that height related variables have a more strict relation to gender, followed by group velocity and inter-personal distance. Moreover, the “male” effect on dyad motion is found to somehow diminish when the male is paired with a female.

DOI： 10.1007/978-3-030-55973-1_37

Scopus

researchmap

Publishing type：Part of collection (book)   Publisher：Springer International Publishing  

We investigate the effect of groups on a bi-directional flow, focusing on self-organisation phenomena, and more specifically on the time needed for the occurrence of pedestrian lanes, their stability and their effect on the velocity-density relation, and the amount of physical contact in the crowd. We use a novel collision avoidance model considering the asymmetrical shape of the human body, and combine it to a mathematical model of group behaviour. The presence of groups results to have a significant effect on velocity and lane organisation, and a dramatic one on collision. Despite the limitations of our approach, we believe that our results show the great theoretical and practical relevance of group behaviour in pedestrian models, and suggest that realistic results may hardly be achieved simply by adding together modular models.

DOI： 10.1007/978-3-030-55973-1_38

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Public Library of Science (PLoS)  

In a follow-up to our work on the dependence of walking dyad dynamics on intrinsic properties of the group, we now analyse how these properties affect groups of three people (triads), taking also in consideration the effect of social interaction on the dynamical properties of the group. We show that there is a strong parallel between triads and dyads. Work-oriented groups are faster and walk at a larger distance between them than leisure-oriented ones, while the latter move in a less ordered way. Such differences are present also when colleagues are contrasted with friends and families; nevertheless the similarity between friend and colleague behaviour is greater than the one between family and colleague behaviour. Male triads walk faster than triads including females, males keep a larger distance than females, and same gender groups are more ordered than mixed ones. Groups including tall people walk faster, while those with elderly or children walk at a slower pace. Groups including children move in a less ordered fashion. Results concerning relation and gender are particularly strong, and we investigated whether they hold also when other properties are kept fixed. While this is clearly true for relation, patterns relating gender often resulted to be diminished. For instance, the velocity difference due to gender is reduced if we compare only triads in the colleague relation. The effects on group dynamics due to intrinsic properties are present regardless of social interaction, but socially interacting groups are found to walk in a more ordered way. This has an opposite effect on the space occupied by non-interacting dyads and triads, since loss of structure makes dyads larger, but causes triads to lose their characteristic V formation and walk in a line (i.e., occupying more space in the direction of movement but less space in the orthogonal one).

DOI： 10.1371/journal.pone.0225704

Web of Science

Scopus

PubMed

researchmap

Authorship：Last author   Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Public Library of Science (PLoS)  

This study focuses on social pedestrian groups in public spaces and makes an effort to identify the type of social relation between the group members. As a first step for this identification problem, we focus on dyads (i.e. 2 people groups). Moreover, as a mutually exclusive categorization of social relations, we consider the domain-based approach of Bugental, which precisely corresponds to social relations of colleagues, couples, friends and families, and identify each dyad with one of those relations. For this purpose, we use anonymized trajectory data and derive a set of observables thereof, namely, inter-personal distance, group velocity, velocity difference and height difference. Subsequently, we use the probability density functions (pdf) of these observables as a tool to understand the nature of the relation between pedestrians. To that end, we propose different ways of using the pdfs. Namely, we introduce a probabilistic Bayesian approach and contrast it to a functional metric one and evaluate the performance of both methods with appropriate assessment measures. This study stands out as the first attempt to automatically recognize social relation between pedestrian groups. Additionally, in doing that it uses completely anonymous data and proves that social relation is still possible to recognize with a good accuracy without invading privacy. In particular, our findings indicate that significant recognition rates can be attained for certain categories and with certain methods. Specifically, we show that a very good recognition rate is achieved in distinguishing colleagues from leisure-oriented dyads (families, couples and friends), whereas the distinction between the leisure-oriented dyads results to be inherently harder, but still possible at reasonable rates, in particular if families are restricted to parent-child groups. In general, we establish that the Bayesian method outperforms the functional metric one due, probably, to the difficulty of the latter to learn observable pdfs from individual trajectories.

DOI： 10.1371/journal.pone.0223656

Web of Science

Scopus

PubMed

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

This study explores estimation of grasping region of objects from gaze data. Our study distinguishes from previous works by accounting for "grasping uniformity" of the objects. In particular, we consider three types of graspable objects: (i) with a well-defined graspable part (e.g. handle), (ii) without a grip but with an intuitive grasping region, (iii) without any grip or intuitive grasping region. We assume that these types define how "uniform" grasping region is across different graspers. In experiments, we use "Learning to grasp" data set and apply the method of [5] for estimating grasping region from gaze data. We compute similarity of estimations and ground truth annotations for the three types of objects regarding subjects (a) who perform free viewing and (b) who view the images with the intention of grasping. In line with many previous studies, similarity is found to be higher for non-graspers. An interesting finding is that the difference in similarity (between free viewing and motivated to grasp) is higher for type-iii objects; and comparable for type-i and ii objects. Based on this, we believe that estimation of grasping region from gaze data offers a larger potential to "learn" particularly grasping of type-iii objects.

DOI： 10.1145/3349537.3352787

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：SAGE PUBLICATIONS LTD  

Web of Science

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

The goal of this paper is to improve the estimation performance of software development effort by mitigating the problem caused by outliers in a historical software project data set, which is used to construct an effort estimation model. To date, outlier removal methods have been proposed to solve this problem; however, they are not always effective because removing outliers reduces the number of data points (= software projects in our case) in a data set, and a model built from a small data set often suffers from lack of generality. In such a case, estimation performance can become even worse. In this paper we propose a method called data smoothing to mitigate the problem of outliers without reducing the number of data points. We consider that data points are outliers if they do not meet the assumption of Analogy-Based Estimation (ABE) such that 'projects with similar features require similar development efforts.' The proposed method changes the effort values (person-months or person-hours) in a data set so as to satisfy this assumption; and by this way, all outliers become non-outliers without decreasing the data points. As a result of experimental evaluation using 8 software development data sets, we found that the proposed data smoothing showed the same or higher effort estimation accuracy than the non-smoothing case, while conventional outlier removal method showed worse accuracy in some data set.

DOI： 10.1109/snpd.2019.8935841

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

The effectiveness of defect prediction depends on modeling techniques as well as their parameter optimization, data preprocessing and ensemble development. This paper focuses on auto-sklearn, which is a recently-developed software library for automated machine learning, that can automatically select appropriate prediction models, hyperparameters and data preprocessing techniques for a given data set and develop their ensemble with optimized weights. In this paper we empirically evaluate the effectiveness of auto-sklearn in predicting the number of defects in software modules. In the experiment, we used software metrics of 20 OSS projects for cross-release defect prediction and compared auto-sklearn with random forest, decision tree and linear discriminant analysis by using Norm(Popt) as a performance measure. As a result, auto-sklearn showed similar prediction performance as random forest, which is one of the best prediction models for defect prediction in past studies. This indicates that auto-sklearn can obtain good prediction performance for defect prediction without any knowledge of machine learning techniques and models.

DOI： 10.1109/snpd.2019.8935839

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

While various software obfuscation techniques have been proposed to protect software, new types of threats keep emerging such as the symbolic execution attacks. Such attacks automatically analyze programs and are not accounted for by many of the existing obfuscation methods. Nevertheless, several methods against symbolic execution attacks exist such as linear obfuscation methods relying on Collatz conjuncture or obfuscation methods based on one-way hash functions. However, these methods bear several issues. Namely, linear obfuscation is weak against manual analysis due to its deterministic output. On the other hand, SHA-1 requires significant computational cost; and thus, it can be applied to only a limited number of targets. Therefore, in this research, we propose to employ a combination of several computationally cheap (arithmetic) obfuscating operations for preventing symbolic execution attacks. Through an experiment using angr and KLEE as symbolic execution tools, we demonstrate that obfuscation operation using array reference, bit rotation and XOR effectively prevents symbolic execution attacks at a low computational cost.

DOI： 10.1109/snpd.2019.8935642

Web of Science

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This study focuses on foreign language vocabulary learning in computerized medium and seeks for any possibility of adaptation with respect to background information on word classes. To that end, we employ a spaced repetition flashcard software and display English vocabulary belonging to three word classes as (i) abstract noun, (ii) concrete noun, and (iii) verb. Regarding each word class, we deploy three sets of words with difficulty levels of (i) easy, (ii) medium, and (iii) hard. Through log file analysis, we derive several behavioral variables and examine the polyserial correlation between these variables and difficulty levels across different word classes. It is found that abstract and concrete nouns do not have any significant difference in terms of the correlation for the five kinds of behavioral variables in focus. However, it is noted that front sides of the cards involving verbs are observed relatively longer, while back sides are observed for somewhat shorter duration.

DOI： 10.1109/iiai-aai.2019.00052

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Forschungszentrum Julich, Zentralbibliothek  

This article presents a glossary of terms that are frequently used in research on human crowds. This topic is inherently multidisciplinary as it includes work in and across computer science, engineering, mathematics, physics, psychology and social science, for example. We do not view the glossary presented here as a collection of finalised and formal definitions. Instead, we suggest it is a snapshot of current views and the starting point of an ongoing process that we hope will be useful in providing some guidance on the use of terminology to develop a mutual understanding across disciplines. The glossary was developed collaboratively during a multidisciplinary meeting. We deliberately allow several definitions of terms, to reflect the confluence of disciplines in the field. This also reflects the fact not all contributors necessarily agree with all definitions in this glossary.

DOI： 10.17815/cd.2019.19

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Part of collection (book)   Publisher：Springer International Publishing  

This study focuses on gesture recognition in mobile interaction settings, i.e. when the interacting partners are walking. This kind of interaction requires a particular coordination, e.g. by staying in the field of view of the partner, avoiding obstacles without disrupting group composition and sustaining joint attention during motion. In literature, various studies have proven that gestures are in close relation in achieving such goals. Thus, a mobile robot moving in a group with human pedestrians, has to identify such gestures to sustain group coordination. However, decoupling of the inherent -walking- oscillations and gestures, is a big challenge for the robot. To that end, we employ video data recorded in uncontrolled settings and detect arm gestures performed by human-human pedestrian pairs by adopting a signal processing approach. Namely, we exploit the fact that there is an inherent oscillatory motion at the upper limbs arising from the gait, independent of the view angle or distance of the user to the camera. We identify arm gestures as disturbances on these oscillations. In doing that, we use a simple pitch detection method from speech processing and assume data involving a low frequency periodicity to be free of gestures. In testing, we employ a video data set recorded in uncontrolled settings and show that we achieve a detection rate of 0.80.

DOI： 10.1007/978-3-030-26118-4_8

Scopus

researchmap

Publishing type：Research paper (scientific journal)  

In this paper, we propose an association rule A ) Correl(X, Y ) that handles a correlation function, where A is the prerequisite and Correl(X, Y ) is the correlation between variables X and Y . With this extension, we can find conditions whose correlation of arbitrary two variables is high (or low) from a given data set. Furthermore, in order to distinguish statistically significant correlation, we define the rule A ) TestCorrel(X, Y ) which holds the result of the correlation significance test in the conclusion section, where TestCorrel(X, Y ) is a p-value of no-correlation test between X and Y . In order to confirm the feasibility of the proposed method, a case study using software development data was conducted. We found that it is possible to distinguish projects that are suitable for predicting development effort and those that are not.

DOI： 10.11309/jssst.36.3_47

Scopus

researchmap

Publishing type：Research paper (scientific journal)  

Auto-sklearn is a recent attention-gathering software library for automated machine learning that can au-tomatically select appropriate prediction models and hyper parameters for a given data set. In this paper we empirically evaluate the effectiveness of auto-sklearn in software bug prediction. In the experiment, we used software metrics of 20 OSS projects for inter-version bug prediction and compared auto-sklearn with random forrest, decision tree and linear descriminat analysis by using AUC of ROC curve as a performance measure. As a result, auto-sklearn showed similar prediction performance as random forrest. We conclude that, although auto-sklearn is useful for bug prediction, we cannot expect better prediction performance than conventional modeling techniques.

DOI： 10.11309/jssst.36.4_46

Scopus

researchmap

Authorship：Last author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

To avoid software development project failure, accurate estimation of software development effort is necessary at the beginning of a software project. This paper proposes to adjust the kurtosis and the skewness of project feature variables for better fitting of software estimation models. The proposed method conducts logarithmic transformation of variables, then conducts the kurtosis and skewness transformation to make the variable distribution closer to the normal distribution. To empirically evaluate the effectiveness of the proposed method, we employed three industry data sets and linear regression models with three-fold cross validation. The result of the evaluation showed that the models with the proposed method were better in both the goodness of fit and the estimation accuracy in terms of MMRE compared to log-log regression.

DOI： 10.1109/apsec.2018.00065

Web of Science

Scopus

researchmap

Authorship：Last author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：CEUR-WS.org  

—To conduct empirical research on industry software development, it is necessary to obtain data of real software projects from industry. However, only few such industry data sets are publicly available; and unfortunately, most of them are very old. In addition, most of today’s software companies cannot make their data open, because software development involves many stakeholders, and thus, its data confidentiality must be strongly preserved. This paper proposes a method to artificially generate a “mimic” software project data set whose characteristics (such as average, standard deviation and correlation coefficients) are very similar to a given confidential data set. The proposed method uses the Box–Muller method for generating normally distributed random numbers, then, exponential transformation and number reordering are used for data mimicry. Instead of using the original (confidential) data set, researchers are expected to use the mimic data set to produce similar results as the original data set. To evaluate the usefulness of the proposed method, effort estimation models were built from an industry data set and its mimic data set. We confirmed that two models are very similar to each other, which suggests the usefulness of our proposal.

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electronics, Information and Communications Engineers (IEICE)  

Association rule mining discovers relationships among variables in a data set, representing them as rules. These are expected to often have predictive abilities, that is, to be able to predict future events, but commonly used rule interestingness measures, such as support and confidence, do not directly assess their predictive power. This paper proposes a cross-validation-based metric that quantifies the predictive power of such rules for characterizing software defects. The results of evaluation this metric experimentally using four open-source data sets (Mylyn, NetBeans, Apache Ant and jEdit) show that it can improve rule prioritization performance over conventional metrics (support, confidence and odds ratio) by 72.8%for Mylyn, 15.0%for NetBeans, 10.5%for Apache Ant and 0 for jEdit in terms of SumNormPre(100) precision criterion. This suggests that the proposed metric can provide better rule prioritization performance than conventional metrics and can at least provide similar performance even in the worst case.

DOI： 10.1587/transinf.2018edp7020

Web of Science

Scopus

researchmap

Authorship：Last author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper proposes extended association rule mining that can deal with correlation functions. The extended association rule is expressed in the form of: A →Correl(X, Y ) where Correl(X, Y ) is a correlation function with two variables X and Y. By this extension, data analysts can discover the condition A that lead to low (or high) correlation between two given variables from a large dataset. In order to show the efficacy of the proposed method, a case study is performed on an industry dataset of software developments, assuming the scenario of discovering a condition, where software development effort is predictable (or unpredictable) from the size of the project, i.e. there exists a significantly high (or low) correlation between size and effort. Since such a condition cannot be obtained by conventional association rule mining, we confirm the efficiency of the proposed extended association rule mining.

DOI： 10.1109/bcd2018.2018.00020

Web of Science

Scopus

researchmap

Authorship：Last author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In this paper, focusing on the problem that estimation accuracy of software development effort greatly varies among software projects, we propose a predictability classification method for software projects before conducting effort estimation. In the proposed method, given a project to be estimated, we first evaluate whether the effort can be accurately estimated or not by identifying the project as 'predictable' or 'unpredictable'. In case of predictable projects, we conduct the effort estimation. Otherwise, estimation is avoided. As a result of an experiment to assess the effectiveness of the proposed method using six industry datasets, (i) the mean square residual and residual variance are shown to be suitable measures for recognition of predictability; and (ii) the average absolute error is significantly reduced in five datasets, by avoiding the estimation when a project belongs to the unpredictable class, which proves the effectiveness of the proposed method. By using the proposed method, practitioners become aware of cases when they can rely on the estimation and when they cannot.

DOI： 10.1109/bcd2018.2018.00015

Web of Science

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Informa UK Limited  

Mobile social robots aimed at interacting with and assisting humans in pedestrian areas need to understand the dynamics of pedestrian social interaction. In this work, we investigate the effect of interaction on pedestrian group motion by defining three motion models to represent (1) interpersonal-distance, (2) relative orientation and (3) absolute difference of velocities; and model them using a dataset of 12000+ pedestrian trajectories recorded in uncontrolled settings. Our contributions include: (i) Demonstrating that interaction has a prominent effect on the empirical distributions of the proposed joint motion attributes, where increasing levels of interaction lead to more regular behavior (ii) Developing analytic motion models of such distributions and reflect the effect of interaction on model parameters (iii) Detecting the social groups in a crowd with almost perfect accuracy utilizing the proposed models, despite the constant flow direction in the environment which causes unrelated pedestrians to move in a correlated way, and thus makes group recognition more difficult (iv) Estimating the level of intensity with considerable rates utilizing the proposed models.

DOI： 10.1080/01691864.2017.1421481

Scopus

researchmap

Publishing type：Research paper (scientific journal)  

This paper presents a feasibility study to predict software bugs in statement level. The proposed method uses a window to inspect a given source file containing a bug. By moving the window from the top to the end of a source file, a set of buggy windows and non-buggy windows are derived. Then, we construct a spam filter-based bug prediction model, whose input is a set of tokens in a window and output is the probability of containing a bug in the window. Finally, we integrate bug prediction results on these windows to compute the probability of containing a bug in each statement. We conducted a feasibility study using 593 source files each containing one bug, and found that, by using the size=3 window, we could identify 67.1% of bugs in top 10 buggy statements of each source file prioritized by our bug prediction, which suggests that the bug pinpointing is feasible.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Forschungszentrum Julich, Zentralbibliothek  

The 8th International Conference on Pedestrian and Evacuation Dynamics (PED 2016) has been held on October 17–21, 2016 in Hefei, China. PED 2016 Conference offered an opportunity for professionals and scientists with different backgrounds to present and discuss new findings and applications in the field of pedestrian and evacuation dynamics and associated human behavior. The conference aims to provide suggestions for policy makers, planners, designers and emergency management to solve real world problems.Conference topics included, but was not limited to:Pedestrian movement mechanismsPedestrian behavior during disasters: theories, analysis, conclusionsEvacuation and pedestrian data collection from experiments and real eventsData collection techniquesModel developmentLarge-scale and transport modeling methodsModel validation/calibrationPublic transport transfer terminalsRegional evacuationOperational management of highly populated facilitiesEngineering guidanceCitation:Please cite the full conference proceedings as follows:Song, W., Ma, J., Fu, L.; Proceedings of Pedestrian and Evacuation Dynamics 2016, Collective Dynamics, A11, 1-618 (2016). DOI 10.17815/CD.2016.11Single articles inside the proceedings should be cited as:Authors; Title.In: Proceedings of Pedestrian and Evacuation Dynamics 2016, Collective Dynamics, pages (2016)Example:Dambalmath, P., Muhamad, B., Haug, E., Löhner, R.; Fundamental Diagrams for Specific Very High Density Crowds. In: Proceedings of Pedestrian and Evacuation Dynamics 2016, Collective Dynamics, 6-11 (2016)

DOI： 10.17815/cd.2016.11

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Public Library of Science (PLoS)  

Being determined by human social behaviour, pedestrian group dynamics may depend on “intrinsic properties” such as the purpose of the pedestrians, their personal relation, gender, age, and body size. In this work we investigate the dynamical properties of pedestrian dyads (distance, spatial formation and velocity) by analysing a large data set of automatically tracked pedestrian trajectories in an unconstrained “ecological” setting (a shopping mall), whose apparent physical and social group properties have been analysed by three different human coders. We observed that females walk slower and closer than males, that workers walk faster, at a larger distance and more abreast than leisure oriented people, and that inter-group relation has a strong effect on group structure, with couples walking very close and abreast, colleagues walking at a larger distance, and friends walking more abreast than family members. Pedestrian height (obtained automatically through our tracking system) influences velocity and abreast distance, both growing functions of the average group height. Results regarding pedestrian age show that elderly people walk slowly, while active age adults walk at the maximum velocity. Groups with children have a strong tendency to walk in a non-abreast formation, with a large distance (despite a low abreast distance). A cross-analysis of the interplay between these intrinsic features, taking in account also the effect of an “extrinsic property” such as crowd density, confirms these major results but reveals also a richer structure. An interesting and unexpected result, for example, is that the velocity of groups with children increases with density, at least in the low-medium density range found under normal conditions in shopping malls. Children also appear to behave differently according to the gender of the parent.

DOI： 10.1371/journal.pone.0187253

Scopus

PubMed

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Part of collection (book)   Publisher：Springer International Publishing  

This study aims at describing navigation guidelines and concerning analytic motion models for a mobile interaction robot, which moves together with a human partner. We address particularly the impact of gestures on the coupled motion of this human-robot pair. We pose that the robot needs to adjust its navigation in accordance to its gestures in a natural manner (mimicking human-human locomotion). In order to justify this suggestion, we first examine the motion patterns of real-world pedestrian dyads in accordance to 4 affective components of interaction (i.e. gestures). Three benchmark variables are derived from pedestrian trajectories and their behavior is investigated with respect to three conditions: (i) presence/absence of isolated gestures, (ii) varying number of simultaneously performed (i.e. concurring) gestures, (iii) varying size of the environment. It is observed empirically and proven quantitatively that there is a significant difference in the benchmark variables between presence and absence of the gestures, whereas no prominent variation exists in regard to the type of gesture or the number of concurring gestures. Moreover, size of the environment is shown to be a crucial factor in sustainability of the group structure. Subsequently, we propose analytic models to represent these behavioral variations and prove that our models attain significant accuracy in reflecting the distinctions. Finally, we propose an implementation scheme for integrating the analytic models to practical applications. Our results bear the potential of serving as navigation guidelines for the robot so as to provide a more natural interaction experience for the human counterpart of a robot-pedestrian group on-the-move.

DOI： 10.1007/978-3-319-70022-9_22

Scopus

researchmap

Language：English   Publishing type：Part of collection (book)   Publisher：Springer International Publishing  

Mobile social robots and (semi-)autonomous small size vehicles such as robotic wheelchairs need to understand and replicate pedestrian behaviour, in order to move safely in the crowd and to interact with, move along with and transport humans. A large amount of research about pedestrian behaviour has been undertaken by the crowd simulation community, but such results cannot be trivially adapted to robot applications. We discuss a simple but general recipe to apply an acceleration based pedestrian model (“Social Force Model”) to mobile robots, and, as a specific example, we show how to replicate in a group of robots the behaviour of social pedestrian groups.

DOI： 10.1007/978-3-319-70022-9_47

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Association for Computing Machinery (ACM)  

Common periodical health check-ups include several clinical test items with affordable cost. However, these standard tests do not directly indicate signs of most lifestyle diseases. In order to detect such diseases, a number of additional specific clinical tests are required, which increase the cost of the health check-up. This study aims to enrich our understanding of the common health check-ups and proposes a way to estimate the signs of several lifestyle diseases based on the standard tests in common examinations without performing any additional specific tests. In this manner, we enable a diagnostic process, where the physician may prefer to perform or avoid a costly test according to the estimation carried out through a set of common affordable tests. To that end, the relation between standard and specific test results is modeled with a multivariate kernel density estimate. The condition of the patient regarding a specific test is assessed following a Bayesian framework. Our results indicate that the proposed method achieves an overall estimation accuracy of 84%. In addition, an outstanding estimation accuracy is achieved for a subset of high-cost tests. Moreover, comparison with standard artificial intelligence methods suggests that our algorithm outperforms the conventional methods.


Our contributions are as follows: (i) promotion of affordable health check-ups, (ii) high estimation accuracy in certain tests, (iii) generalization capability due to ease of implementation on different platforms and institutions, (iv) flexibility to apply to various tests and potential to improve early detection rates.

DOI： 10.1145/2517084

Scopus

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electrical and Electronics Engineers (IEEE)  

Joint attention, which is the ability of coordination of a common point of reference with the communicating party, emerges as a key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between an experimenter and a robot. The precise analysis of the experimenter's eye region requires stability and high-resolution image acquisition, which is not always available. We investigate regression-based interpolation of the gaze direction from the head pose of the experimenter, which is easier to track. Gaussian process regression and neural networks are contrasted to interpolate the gaze direction. Then, we combine gaze interpolation with image-based saliency to improve the target point estimates and test three different saliency schemes. We demonstrate the proposed method on a human-robot interaction scenario. Cross-subject evaluations, as well as experiments under adverse conditions (such as dimmed or artificial illumination or motion blur), show that our method generalizes well and achieves rapid gaze estimation for establishing joint attention. © 2012 IEEE.

DOI： 10.1109/tsmcb.2012.2216979

Web of Science

Scopus

PubMed

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

Associating attributes to pedestrians in a crowd is relevant for various areas like surveillance, customer profiling and service providing. The attributes of interest greatly depend on the application domain and might involve such social relations as friends or family as well as the hierarchy of the group including the leader or subordinates. Nevertheless, the complex social setting inherently complicates this task. We attack this problem by exploiting the small group structures in the crowd. The relations among individuals and their peers within a social group are reliable indicators of social attributes. To that end, this paper identifies social groups based on explicit motion models integrated through a hypothesis testing scheme. We develop two models relating positional and directional relations. A pair of pedestrians is identified as belonging to the same group or not by utilizing the two models in parallel, which defines a compound hypothesis testing scheme. By testing the proposed approach on three datasets with different environmental properties and group characteristics, it is demonstrated that we achieve an identification accuracy of 87% to 99%. The contribution of this study lies in its definition of positional and directional relation models, its description of compound evaluations, and the resolution of ambiguities with our proposed uncertainty measure based on the local and global indicators of group relation. © 2013 by the authors; licensee MDPI, Basel, Switzerland.

DOI： 10.3390/s130100875

Web of Science

Scopus

PubMed

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper addresses the problem of identification of pedestrian groups in crowded environments. To that end, positional and directional relations are modeled accounting for different environmental features and group configurations. Subsequently, a pair of simultaneously observed pedestrians is identified to belong to the same group or not utilizing these models in a parallel manner, which defines a compound hypothesis testing scheme. In case of ambiguities, local and global indicators of group relation are employed in quantifying the reliabilities of the two individual decisions. The contribution of this study lies in the improvement in positional and directional relation models to adjust to different environments and group configurations, description of compound evaluation, as well as resolution of ambiguities proposing uncertainty measures based on local and global indicators of group relation.

Web of Science

researchmap

Other Link： http://dblp.uni-trier.de/db/conf/icpr/icpr2012.html#conf/icpr/YiicelMH12

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/iros.2012.6385744

Web of Science

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper proposes a simple yet novel method for recognition of certain sorts of moving entities incorporating their shape and motion patterns. Although shape features have been commonly employed in object recognition, motion characteristics are in general not integrated to geometric models. In the interest of utilizing the motion attributes, the trajectories are investigated to extract the 'coherence quality' of the entities. Besides, at every step a geometric shape model is adopted and the parameters defining the shape model are utilized in obtaining the prior probabilities of the entities being a member of a particular class of interest. The coherence quality is used to get the posterior probabilities through a Bayesian approach. The main contribution of this paper is the incorporation of coherence quality in identification of moving entities. The proposed method is tested against clutter and occlusion in an uncontrolled environment with patterns collected from over 500 entities. It is shown to yield a satisfactory performance rate of 92% over the entire dataset with significant generalization capabilities without any restrictions on the application setting and with considerable occlusion and clutter. © 2011 IEEE.

DOI： 10.1109/iros.2011.6094852

Web of Science

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier BV  

In order to identify the owner and distributor of digital data, a watermarking scheme in frequency domain for multimedia files is proposed. The scheme satisfies the imperceptibility and persistence requirements and it is robust against additive noise. It consists of a few stages of wavelet decomposition of several subblocks of the original signal using special zero assigned filter banks. By assigning zeros to filters on the high frequency portion of the spectrum, filter banks with frequency selective response are obtained. The information is then inserted in the wavelet-decomposed and compressed signal. Several robustness tests are performed on male voice, female voice, and music files, color and gray level images. The algorithm is tested under white Gaussian noise and against JPEG compression and it is observed to be robust even when exposed to high levels of corruption. © 2009 Elsevier B.V. All rights reserved.

DOI： 10.1016/j.sigpro.2009.07.012

Web of Science

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper elaborates on mechanisms for establishing visual joint attention for the design of robotic agents that learn through natural interfaces, following a developmental trajectory not unlike infants. We describe first the evolution of cognitive skills in infants and then the adaptation of cognitive development patterns in robotic design. A comprehensive outlook for cognitively inspired robotic design schemes pertaining to joint attention is presented for the last decade, with particular emphasis on practical implementation issues. A novel cognitively inspired joint attention fixation mechanism is defined for robotic agents. © 2009 IEEE.

DOI： 10.1109/iscis.2009.5291820

Web of Science

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Modeling the user's attention is useful for responsive and interactive systems. This paper proposes a method for establishing joint visual attention between an experimenter and an intelligent agent. A rapid procedure is described to track the 3D head pose of the experimenter, which is used to approximate the gaze direction. The head is modeled with a sparse grid of points sampled from the surface of a cylinder. We then propose to employ a bottom-up saliency model to single out interesting objects in the neighborhood of the estimated focus of attention. We report results on a series of experiments, where a human experimenter looks at objects placed at different locations of the visual field, and the proposed algorithm is used to locate target objects automatically. Our results indicate that the proposed approach achieves high localization accuracy and thus constitutes a useful tool for the construction of natural human-computer interfaces. ©2009 IEEE.

DOI： 10.1109/acii.2009.5349547

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Head pose and eye location estimation are two closely related issues which refer to similar application areas. In recent years, these problems have been studied individually in numerous works in the literature. Previous research shows that cylindrical head models and isophote based schemes provide satisfactory precision in head pose and eye location estimation, respectively. However, the eye locator is not adequate to accurately locate eye in the presence of extreme head poses. Therefore, head pose cues may be suited to enhance the accuracy of eye localization in the presence of severe head poses. In this paper, a hybrid scheme is proposed in which the transformation matrix obtained from the head pose is used to normalize the eye regions and, in turn the transformation matrix generated by the found eye location is used to correct the pose estimation procedure. The scheme is designed to (1) enhance the accuracy of eye location estimations in low resolution videos, (2) to extend the operating range of the eye locator and (3) to improve the accuracy and re-initialization capabilities of the pose tracker. From the experimental results it can be derived that the proposed unified scheme improves the accuracy of eye estimations by 16% to 23%. Further, it considerably extends its operating range by more than 15°, by overcoming the problems introduced by extreme head poses. Finally, the accuracy of the head pose tracker is improved by 12% to 24%. ©2009 IEEE.

DOI： 10.1109/cvpr.2009.5206640

Web of Science

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：ELSEVIER SCIENCE BV  

We developed an inexpensive computer vision-based method utilizing an algorithm which differentiates drug-induced behavioral alterations. The mice were observed in an open-field arena and their activity was recorded for 100 min. For each animal the first 50 min of observation were regarded as the drug-free period. Each animal was exposed to only one drug and they were injected (i.p.) with either amphetamine or cocaine as the stimulant drugs or morphine or diazepam as the inhibitory agents. The software divided the arena into virtual grids and calculated the number of visits (sojourn counts) to the grids and instantaneous speeds within these grids by analyzing video data. These spatial distributions of sojourn counts and instantaneous speeds were used to construct feature vectors which were fed to the classifier algorithms for the final step of matching the animals and the drugs. The software decided which of the animals were drug-treated at a rate of 96%. The algorithm achieved 92% accuracy in sorting the data according to the increased or decreased activity and then determined which drug was delivered. The method differentiated the type of psychostimulant or inhibitory drugs with a success ratio of 70% and 80%, respectively. This method provides a new way to automatically evaluate and classify drug-induced behaviors in mice. Crown Copyright (C) 2009 Published by Elsevier B.V. All rights reserved.

DOI： 10.1016/j.jneumeth.2009.03.014

Web of Science

Scopus

PubMed

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Symptoms of epilepsy, which is characterized by abnormal brain electrical activity, can be observed on electroencephalography (EEG) signal. This paper employs models of chaotic measures on standard clinical subbands of EEG and aims to help detection of epilepsy seizures and diagnosis of epileptic indicators in interictal signals. copyright by EURASIP.

Scopus

researchmap

Other Link： http://dblp.uni-trier.de/db/conf/eusipco/eusipco2008.html#conf/eusipco/YucelO08

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In this paper a new method for digital image watermarking based on Zero Assigned Filter Banks and Embedded Zero Tree Wavelet (EZW) algorithm is presented. An image is partitioned into 128 × 128 subblocks and each block is processed in a three stage decomposition structure by a filter bank which is assigned a zero around the stop band. The coefficients to be marked are chosen according to the EZW algorithm. This method not only provides a robust watermarking scheme but may also be used as an effective compression strategy. The algorithm is tested under white Gaussian noise and against JPEG compression and it is observed to be robust even when exposed to high levels of corruption. © 2005 IEEE.

DOI： 10.1109/isspit.2005.1577124

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)  

In order to identify the owner and distributor of digital data, a watermarking scheme for audio files is proposed in frequency domain. The scheme satisfies the imperceptibility and persistence requirements and is robust against additive noise. It consists of a few stages of wavelet decomposition of several frames of the original signal using special zero assigned filter banks. By assigning zeros to filters on the high frequency portion of the spectrum, filter banks with frequency selective response is obtained. Text information is then inserted in the wavelet-decomposed and compressed signal. Several robustness tests are performed on male voice, female voice, and music files.

Scopus

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

researchmap

Language：English   Publishing type：Research paper, summary (international conference)  

researchmap

Authorship：Lead author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Authorship：Lead author,　Corresponding author   Language：Turkish   Publisher：IEEE  

Automatic estimation of gaze direction information is important for certain applications of human-robot and human-computer interaction. Depending on the properties of the specific application, it may be required to derive this information in real time from low resolution visual inputs, with as much precision as possible. In this paper we present an algorithm for transforming head pose estimates to gaze direction estimates. The main contribution of this study lies in the fact that it makes a clear distinction between head pose and gaze direction. Unlike some of the previous works in this field, we do not correct the head pose to correspond to a possible attention fixation point in accordance with the experiment scenario. Instead we propose using a concrete and environment-independent method for this purpose. To transform the head pose estimates into gaze direction, a Gaussian process regression model is proposed and the reasons validating this choice are discussed in detail. ©2010 IEEE.

DOI： 10.1109/siu.2010.5652736

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：Turkish   Publisher：IEEE  

The application of action recognition algorithms onto driving safety systems is still an open area of research. In terms of driving safety, identification of head movements present more significant information in comparison to other actions of the driver. Therefore, in this study, we developed a cylindrical model based head pose estimator to track drivers' head movements. The experiments indicate that the proposed scheme presents significant accuracy in estimation of head pose. ©2009 IEEE.

DOI： 10.1109/siu.2009.5136370

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：Turkish   Publisher：IEEE  

Symptoms of epilepsy, which is characterized by abnormal brain electrical activity, can be observed on electroencephalography (EEG) signal. This paper employs models of chaotic measures of EEG and aims to help detection of epilepsy seizures and diagnosis of epileptic indicators in seizure-free signals. ©2008 IEEE.

DOI： 10.1109/siu.2008.4632759

Web of Science

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：Turkish   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Language：Turkish   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Authorship：Lead author,　Corresponding author   Language：Turkish   Publishing type：Research paper, summary (national, other academic conference)   Publisher：IEEE  

DOI： 10.1109/siu.2006.1659862

researchmap

Event date： 2022.10.15 - 2022.10.17

Language：English   Presentation type：Oral presentation (general)  

researchmap

Event date： 2022.10.15 - 2022.10.17

Language：English   Presentation type：Oral presentation (general)  

researchmap

Event date： 2020.9

Language：English   Presentation type：Oral presentation (general)  

researchmap

Event date： 2020.8.12

Language：English   Presentation type：Oral presentation (general)  

We discuss the development of a robot system able to replicate human group motion and show how a pedestrian model may be converted to a robot control system in order to achieve this goal.

researchmap

Event date： 2020.3.27

Language：English  

We analysed a set of uninstructed pedestrian trajectories automatically tracked in a public area, and we asked a human coder to assess their group relationships. For those pedestrians who belong to the groups, we asked the coder to identify their apparent purpose of visit to the tracking area and apparent gender. We studied the quantitative dependence of the group dynamics on such properties in the case of triads (three people groups) and compared them to the two pedestrian group case (dyads), studied in a previous work. We found that the group velocity strongly depends on relation and gender for both triads and dyads, while the influence of these properties on spatial structure of groups is less clear in the triadic case. We discussed the relevance of these results to the modelling of pedestrian and crowd dynamics, and examined the possibility of the future works on this subject.

researchmap

Event date： 2020.3.27

Language：English   Presentation type：Oral presentation (general)  

This study focuses on social pedestrian groups in public spaces and makes an effort to identify the social relation between the group members. We particularly consider dyads having coalitional or mating relation. We derive several observables from individual and group trajectories, which are suggested to be distinctive for these two sorts of relations and propose a recognition algorithm taking these observables as features and yielding an estimation of social relation in a probabilistic manner at every sampling step. On the average, we detect coalitional relation with 87% and mating relation with 81% accuracy. To the best of our knowledge, this is the first study to infer social relation from joint (loco)motion patterns and we consider the detection rates to be a satisfactory considering the inherent challenge of the problem.

researchmap

Event date： 2020

Language：English  

researchmap

Event date： 2019.9.25

Language：English  

researchmap

Event date： 2019.9

Language：English  

researchmap

Event date： 2019.7

Language：English  

researchmap

Event date： 2019.7

Language：English  

researchmap

Event date： 2019.7

Language：English  

researchmap

Event date： 2019.7

Language：English  

researchmap

Event date： 2019

Language：English  

researchmap

Event date： 2018.12

Language：English  

researchmap

Event date： 2018.12

Language：English  

researchmap

Event date： 2018.7

Language：English  

researchmap

Event date： 2018.7

Language：English  

researchmap

Event date： 2017

Language：English  

researchmap

Event date： 2017

Language：English  

researchmap

Event date： 2012.11

Language：English  

This paper addresses the problem of identification of pedestrian groups in crowded environments. To that end, positional and directional relations are modeled accounting for different environmental features and group configurations. Subsequently, a pair of simultaneously observed pedestrians is identified to belong to the same group or not utilizing these models in a parallel manner, which defines a compound hypothesis testing scheme. In case of ambiguities, local and global indicators of group relation are employed in quantifying the reliabilities of the two individual decisions. The contribution of this study lies in the improvement in positional and directional relation models to adjust to different environments and group configurations, description of compound evaluation, as well as resolution of ambiguities proposing uncertainty measures based on local and global indicators of group relation.

researchmap

Other Link： http://dblp.uni-trier.de/db/conf/icpr/icpr2012.html#conf/icpr/YiicelMH12

Event date： 2012.10

Language：English  

researchmap

Event date： 2011.9

Language：English  

researchmap

Event date： 2009.9

Language：English  

researchmap

Event date： 2009.9

Language：English  

researchmap

Event date： 2009.7

Language：English  

researchmap

Event date： 2009.6

Language：English  

researchmap

Event date： 2008.8

Language：English  

researchmap

Other Link： http://dblp.uni-trier.de/db/conf/eusipco/eusipco2008.html#conf/eusipco/YucelO08

Event date： 2005.9

Language：English  

researchmap

Event date： 2005.8

Language：English  

researchmap

Language：English   Presentation type：Oral presentation (invited, special)  

researchmap

Language：English   Presentation type：Oral presentation (invited, special)  

researchmap

Language：English   Presentation type：Oral presentation (invited, special)  

researchmap

Language：English   Presentation type：Oral presentation (invited, special)  

researchmap

Language：English   Presentation type：Oral presentation (invited, special)  

researchmap

Language：English   Presentation type：Oral presentation (invited, special)  

researchmap

researchmap