Demographic-based identification plays an active role in the field of face identification. Over the past decade, machine learning algorithms have been used to investigate challenges surrouding ethnic classification for specific populations, such as African, Asian and Caucasian people. Ethnic classification for individuals of South Asian, Pakistani heritage, however, remains to be addressed. The present paper addresses a two-category (Pakistani Vs Non-Pakistani) classification task from a novel, purpose-built dataset. To the best of our knowledge, this work is the first to report a machine learning ethnic classification task with South Asian (Pakistani) faces. We conduted a series of experiments using deep learning algorithms (ResNet-50, ResNet-101 and ResNet-152) for feature extraction and a linear support vector machine (SVM) for classification. The experimental results demonstrate ResNet-101 achieves the highest performance accuracy of 99.2% for full-face ethnicity classification, followed closely by 91.7% and 95.7% for the nose and mouth respectively.
{"title":"On the Ethnic Classification of Pakistani Face using Deep Learning","authors":"S. Jilani, H. Ugail, A. M. Bukar, Andrew Logan","doi":"10.1109/CW.2019.00039","DOIUrl":"https://doi.org/10.1109/CW.2019.00039","url":null,"abstract":"Demographic-based identification plays an active role in the field of face identification. Over the past decade, machine learning algorithms have been used to investigate challenges surrouding ethnic classification for specific populations, such as African, Asian and Caucasian people. Ethnic classification for individuals of South Asian, Pakistani heritage, however, remains to be addressed. The present paper addresses a two-category (Pakistani Vs Non-Pakistani) classification task from a novel, purpose-built dataset. To the best of our knowledge, this work is the first to report a machine learning ethnic classification task with South Asian (Pakistani) faces. We conduted a series of experiments using deep learning algorithms (ResNet-50, ResNet-101 and ResNet-152) for feature extraction and a linear support vector machine (SVM) for classification. The experimental results demonstrate ResNet-101 achieves the highest performance accuracy of 99.2% for full-face ethnicity classification, followed closely by 91.7% and 95.7% for the nose and mouth respectively.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129100120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
It is important to measure the user's biological information when experiencing virtual reality (VR) content. By measuring such biological information during a VR stimulation, the body's response to the stimulation can be verified. In addition, it is possible to change the stimulation interactively by estimating the feeling from the measured biological information. However, the user load required to mount the sensor for biological information sensing under the existing VR content experience is significant, and the noise due to body movement is also a problem. In this paper, a biometric device that can be mounted on a head mounted display (HMD) was developed. Because an HMD is attached strongly to the face, it is thought to be robust to body movement and thus the mounting load of the sensor can be ignored. The developed device can simply be mounted on an HMD. A pulse waveform can be acquired from the optical pulse wave sensor arranged on the nose side of the HMD, and the respiration waveform can be acquired from a thermopile arranged in the nostril area of the HMD. We condacted the experiment to verified that a pulse wave and the respiration can be measured with sufficient accuracy for a calculation of the tension and excitement of the user. As a result of the experiment, it was confirmed that the pulse wave can be measured with an error of less than 1% in nine out of 14 users and that the respiration can be measured with an error of 0.6% if user does not move. The respiration was measured with high accuracy regardless of the type of HMD used.
{"title":"Development of Easy Attachable Biological Information Measurement Device for Various Head Mounted Displays","authors":"Masahiro Inazawa, Yuki Ban","doi":"10.1109/CW.2019.00009","DOIUrl":"https://doi.org/10.1109/CW.2019.00009","url":null,"abstract":"It is important to measure the user's biological information when experiencing virtual reality (VR) content. By measuring such biological information during a VR stimulation, the body's response to the stimulation can be verified. In addition, it is possible to change the stimulation interactively by estimating the feeling from the measured biological information. However, the user load required to mount the sensor for biological information sensing under the existing VR content experience is significant, and the noise due to body movement is also a problem. In this paper, a biometric device that can be mounted on a head mounted display (HMD) was developed. Because an HMD is attached strongly to the face, it is thought to be robust to body movement and thus the mounting load of the sensor can be ignored. The developed device can simply be mounted on an HMD. A pulse waveform can be acquired from the optical pulse wave sensor arranged on the nose side of the HMD, and the respiration waveform can be acquired from a thermopile arranged in the nostril area of the HMD. We condacted the experiment to verified that a pulse wave and the respiration can be measured with sufficient accuracy for a calculation of the tension and excitement of the user. As a result of the experiment, it was confirmed that the pulse wave can be measured with an error of less than 1% in nine out of 14 users and that the respiration can be measured with an error of 0.6% if user does not move. The respiration was measured with high accuracy regardless of the type of HMD used.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130984756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A font is an important element in designing printed materials including texts, such as documents, posters, leaflets, pamphlets, etc. Recently, many digital fonts with different styles are available for desktop publishing, but the number of Japanese-language fonts is smaller than that of European ones. This causes a problem when designing the materials including Japanese and European letters. Creating a new font is difficult and requires specialized knowledge and experience. Our research goal is to address this problem by transferring styles of the European fonts to Japanese characters by using a neural network. In this paper, we report some experimental results using the well-known deep learning framework called "pix2pix."
{"title":"Fonts Style Transfer using Conditional GAN","authors":"Naho Sakao, Y. Dobashi","doi":"10.1109/CW.2019.00075","DOIUrl":"https://doi.org/10.1109/CW.2019.00075","url":null,"abstract":"A font is an important element in designing printed materials including texts, such as documents, posters, leaflets, pamphlets, etc. Recently, many digital fonts with different styles are available for desktop publishing, but the number of Japanese-language fonts is smaller than that of European ones. This causes a problem when designing the materials including Japanese and European letters. Creating a new font is difficult and requires specialized knowledge and experience. Our research goal is to address this problem by transferring styles of the European fonts to Japanese characters by using a neural network. In this paper, we report some experimental results using the well-known deep learning framework called \"pix2pix.\"","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131773015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Kannappan, Owen Noel Newton Fernando, A. Chattopadhyay, Xavier Tan, Jeffrey Hong, S. H. Soon, Hui En Lye
This research aims to implement the productive failure teaching concept with interactive learning games as a method to nurture innovative teaching and learning. The research also aims to promote innovative approaches to learning and improving students' learning experience, and their understanding of linked list data structure concepts taught in computer science subjects since students do not widely understand this concept. A 2D bridge building puzzle game, “La Petite Fee Cosmo” was developed to assist students in not only understanding the underlying concepts of the linked list but also foster creative usage of the various functionalities of linked list in diverse situations.
本研究旨在透过互动学习游戏，将生产性失败教学理念落实到教学中，以培育创新的教与学。该研究还旨在促进创新的学习方法，提高学生的学习体验，以及他们对计算机科学学科中所教授的链表数据结构概念的理解，因为学生对这一概念的理解并不广泛。“La Petite Fee Cosmo”是一款2D架桥益智游戏，旨在帮助学生了解链表的基本概念，并培养他们在不同情况下创造性地使用链表的各种功能。
{"title":"La Petite Fee Cosmo: Learning Data Structures Through Game-Based Learning","authors":"V. Kannappan, Owen Noel Newton Fernando, A. Chattopadhyay, Xavier Tan, Jeffrey Hong, S. H. Soon, Hui En Lye","doi":"10.1109/CW.2019.00041","DOIUrl":"https://doi.org/10.1109/CW.2019.00041","url":null,"abstract":"This research aims to implement the productive failure teaching concept with interactive learning games as a method to nurture innovative teaching and learning. The research also aims to promote innovative approaches to learning and improving students' learning experience, and their understanding of linked list data structure concepts taught in computer science subjects since students do not widely understand this concept. A 2D bridge building puzzle game, “La Petite Fee Cosmo” was developed to assist students in not only understanding the underlying concepts of the linked list but also foster creative usage of the various functionalities of linked list in diverse situations.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133834919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abir Mhenni, Denis Migdal, E. Cherrier, C. Rosenberger, N. Amara
The attacks considered for keystroke dynamics study especially adaptive strategies have commonly treated impersonation attempts known as zero-effort attacks. These attacks are generally the acquisition of other users of the same database while typing the same password without intending to impersonate the genuine user account. To deal with more realistic scenarios, we are interested in this paper to study the robustness of an adaptive strategy against four types of imposter attacks: zero-effort, spoof, playback and synthetic applied to the WEBGREYC database. Experimental results show that 1) playback and synthetic attacks are the most dangerous and increase the EER rates compared to the other attacks; 2) we also find that the impact of these attacks is more pronounced when the percentages of imposter samples are greater than those of genuine ones; 3) the spoof attacks achieve alarmingly higher FMR, FNMR, and EER rates compared to zero-effort impostor attacks; 4) FMR, FNMR, and EER are higher when the percentage of attacks increases; 5) the attacks belonging to the same user are more dangerous than those of different users in particular when the percentage of the attacks increases. In light of our results, we point out that the traditional attacks considered in research on keystroke-based authentication must evolve according to the evolution of the attacks of nowadays password-based applications.
{"title":"Vulnerability of Adaptive Strategies of Keystroke Dynamics Based Authentication Against Different Attack Types","authors":"Abir Mhenni, Denis Migdal, E. Cherrier, C. Rosenberger, N. Amara","doi":"10.1109/CW.2019.00052","DOIUrl":"https://doi.org/10.1109/CW.2019.00052","url":null,"abstract":"The attacks considered for keystroke dynamics study especially adaptive strategies have commonly treated impersonation attempts known as zero-effort attacks. These attacks are generally the acquisition of other users of the same database while typing the same password without intending to impersonate the genuine user account. To deal with more realistic scenarios, we are interested in this paper to study the robustness of an adaptive strategy against four types of imposter attacks: zero-effort, spoof, playback and synthetic applied to the WEBGREYC database. Experimental results show that 1) playback and synthetic attacks are the most dangerous and increase the EER rates compared to the other attacks; 2) we also find that the impact of these attacks is more pronounced when the percentages of imposter samples are greater than those of genuine ones; 3) the spoof attacks achieve alarmingly higher FMR, FNMR, and EER rates compared to zero-effort impostor attacks; 4) FMR, FNMR, and EER are higher when the percentage of attacks increases; 5) the attacks belonging to the same user are more dangerous than those of different users in particular when the percentage of the attacks increases. In light of our results, we point out that the traditional attacks considered in research on keystroke-based authentication must evolve according to the evolution of the attacks of nowadays password-based applications.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115298439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daiki Hagimori, N. Isoyama, Shunsuke Yoshimoto, Nobuchika Sakata, K. Kiyokawa
In recent years, human augmentation has attracted much attention. One type of human augmentation, motion augmentation makes perceived motion larger than in reality, and it can be used for a variety of applications such as rehabilitation of motor functions of stroke patients and a more realistic experience in virtual reality (VR) such as redirected walking (RDW). However, as augmented motion becomes larger than the real motion, a variety of senses that accompany will be more inconsistent with those perceived from somatic sensations, which will cause a severe sense of discomfort. To address the problem, we focus on kinesthetic illusions that are psychological phenomena where a person feels as if his or her own body is moving. Kinesthetic illusions are expected to fill the gap between the intended augmented motion and perceived physical motion. However, it has not been explored if and how large kinesthetic illusions are produced while a user is moving their limbs voluntarily in VR. To expand the knowledge on kinesthetic illusions, we have conducted two user studies on the impact of tendon vibration and visual stimuli on kinesthetic illusions. First experiment confirmed that the perceived elbow angle becomes larger than the actual angle when presented with tendon vibration. Second experiment revealed that the increase of the perceived elbow angle was about 20 degrees when both tendon vibration and visual stimuli were presented whereas it was about 10 degrees when only visual stimuli were presented. Through these experiments, it has been confirmed that combining tendon vibration and visual stimulation enhances kinesthetic illusions.
{"title":"Combining Tendon Vibration and Visual Stimulation Enhances Kinesthetic Illusions","authors":"Daiki Hagimori, N. Isoyama, Shunsuke Yoshimoto, Nobuchika Sakata, K. Kiyokawa","doi":"10.1109/CW.2019.00029","DOIUrl":"https://doi.org/10.1109/CW.2019.00029","url":null,"abstract":"In recent years, human augmentation has attracted much attention. One type of human augmentation, motion augmentation makes perceived motion larger than in reality, and it can be used for a variety of applications such as rehabilitation of motor functions of stroke patients and a more realistic experience in virtual reality (VR) such as redirected walking (RDW). However, as augmented motion becomes larger than the real motion, a variety of senses that accompany will be more inconsistent with those perceived from somatic sensations, which will cause a severe sense of discomfort. To address the problem, we focus on kinesthetic illusions that are psychological phenomena where a person feels as if his or her own body is moving. Kinesthetic illusions are expected to fill the gap between the intended augmented motion and perceived physical motion. However, it has not been explored if and how large kinesthetic illusions are produced while a user is moving their limbs voluntarily in VR. To expand the knowledge on kinesthetic illusions, we have conducted two user studies on the impact of tendon vibration and visual stimuli on kinesthetic illusions. First experiment confirmed that the perceived elbow angle becomes larger than the actual angle when presented with tendon vibration. Second experiment revealed that the increase of the perceived elbow angle was about 20 degrees when both tendon vibration and visual stimuli were presented whereas it was about 10 degrees when only visual stimuli were presented. Through these experiments, it has been confirmed that combining tendon vibration and visual stimulation enhances kinesthetic illusions.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127327985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kazi Mahmudul Hassan, M. Islam, Toshihisa Tanaka, M. I. Molla
Electroencephalography (EEG) is considered as a potential tool for diagnosis of epilepsy in clinical applications. Epileptic seizures occur irregularly and unpredictably. Its automatic detection in EEG recordings is highly demanding. In this work, multiband features are used to detect seizure with feedforward neural network (FfNN). The EEG signal is segmented into epochs of short duration and each epoch is decomposed into a number of subbands using discrete wavelet transform (DWT). Three features namely ellipse area of second-order difference plot, coefficient of variation and fluctuation index are computed from each subband signal. The features obtained from all subbands are combined to construct the feature vector. The FfNN is trained using the derived feature vector and seizure detection is performed with test data. The experiment is performed with publicly available dataset to evaluate the performance of the proposed method. The experimental results show the superiority of this method compared to the recently developed algorithms.
{"title":"Epileptic Seizure Detection from EEG Signals Using Multiband Features with Feedforward Neural Network","authors":"Kazi Mahmudul Hassan, M. Islam, Toshihisa Tanaka, M. I. Molla","doi":"10.1109/CW.2019.00046","DOIUrl":"https://doi.org/10.1109/CW.2019.00046","url":null,"abstract":"Electroencephalography (EEG) is considered as a potential tool for diagnosis of epilepsy in clinical applications. Epileptic seizures occur irregularly and unpredictably. Its automatic detection in EEG recordings is highly demanding. In this work, multiband features are used to detect seizure with feedforward neural network (FfNN). The EEG signal is segmented into epochs of short duration and each epoch is decomposed into a number of subbands using discrete wavelet transform (DWT). Three features namely ellipse area of second-order difference plot, coefficient of variation and fluctuation index are computed from each subband signal. The features obtained from all subbands are combined to construct the feature vector. The FfNN is trained using the derived feature vector and seizure detection is performed with test data. The experiment is performed with publicly available dataset to evaluate the performance of the proposed method. The experimental results show the superiority of this method compared to the recently developed algorithms.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116327530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The inability to recognise the value of data in the form of digital objects and digital assets held in virtual social environments amplifies the data loss legacy challenges for older adults. This study examines the data storage and transfer issues that arise when people pass away. Older people experience data loss when they engage with social digital environments. Social computing has different legacy practices for the transfer and mobility of digital assets to physical assets. Recognizing the value of digital assets in their monetary, historical, sentimental, and legal characteristics is critical to the reduction of unnecessary data loss under legacy conditions.
{"title":"Social Computing and Older Adults: Challenges with Data Loss and Digital Legacies","authors":"D. Dissanayake, David M. Cook","doi":"10.1109/CW.2019.00035","DOIUrl":"https://doi.org/10.1109/CW.2019.00035","url":null,"abstract":"The inability to recognise the value of data in the form of digital objects and digital assets held in virtual social environments amplifies the data loss legacy challenges for older adults. This study examines the data storage and transfer issues that arise when people pass away. Older people experience data loss when they engage with social digital environments. Social computing has different legacy practices for the transfer and mobility of digital assets to physical assets. Recognizing the value of digital assets in their monetary, historical, sentimental, and legal characteristics is critical to the reduction of unnecessary data loss under legacy conditions.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"39 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127158536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yisi Liu, Zirui Lan, Jian Cui, O. Sourina, W. Müller-Wittig
Mental fatigue is common at work places, and it can lead to decreased attention, vigilance and cognitive performance, which is dangerous in the situations such as driving, vessel maneuvering, etc. By directly measuring the neurophysiological activities happening in the brain, electroencephalography (EEG) signal can be used as a good indicator of mental fatigue. A classic EEG-based brain state recognition system requires labeled data from the user to calibrate the classifier each time before the use. For fatigue recognition, we argue that it is not practical to do so since the induction of fatigue state is usually long and weary. It is desired that the system can be calibrated using readily available fatigue data, and be applied to a new user with adequate recognition accuracy. In this paper, we explore performance of cross-subject fatigue recognition algorithms using the recently published EEG dataset labeled with two levels of fatigue. We evaluate three categories of classification method: classic classifier such as logistic regression, transfer learning-enabled classifier using transfer component analysis, and deep-learning based classifier such as EEGNet. Our results show that transfer learning-enabled classifier can outperform the other two for cross-subject fatigue recognition on a consistent basis. Specifically, transfer component analysis (TCA) improves the cross-subject recognition accuracy to 72.70 % that is higher than using just logistic regression (LR) by 9.08 % and EEGNet by 8.72 - 12.86 %.
{"title":"EEG-Based Cross-Subject Mental Fatigue Recognition","authors":"Yisi Liu, Zirui Lan, Jian Cui, O. Sourina, W. Müller-Wittig","doi":"10.1109/CW.2019.00048","DOIUrl":"https://doi.org/10.1109/CW.2019.00048","url":null,"abstract":"Mental fatigue is common at work places, and it can lead to decreased attention, vigilance and cognitive performance, which is dangerous in the situations such as driving, vessel maneuvering, etc. By directly measuring the neurophysiological activities happening in the brain, electroencephalography (EEG) signal can be used as a good indicator of mental fatigue. A classic EEG-based brain state recognition system requires labeled data from the user to calibrate the classifier each time before the use. For fatigue recognition, we argue that it is not practical to do so since the induction of fatigue state is usually long and weary. It is desired that the system can be calibrated using readily available fatigue data, and be applied to a new user with adequate recognition accuracy. In this paper, we explore performance of cross-subject fatigue recognition algorithms using the recently published EEG dataset labeled with two levels of fatigue. We evaluate three categories of classification method: classic classifier such as logistic regression, transfer learning-enabled classifier using transfer component analysis, and deep-learning based classifier such as EEGNet. Our results show that transfer learning-enabled classifier can outperform the other two for cross-subject fatigue recognition on a consistent basis. Specifically, transfer component analysis (TCA) improves the cross-subject recognition accuracy to 72.70 % that is higher than using just logistic regression (LR) by 9.08 % and EEGNet by 8.72 - 12.86 %.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115769923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many studies propose strong user authentication based on biometric modalities. However, they often either, assume a trusted component, are modality-dependant, use only one biometric modality, are reversible, or does not enable the service to adapt the security on-the-fly. A recent work introduced the concept of Personal Identity Code Respecting Privacy (PICRP), a non-cryptographic and non-reversible signature computed from any arbitrary information. In this paper, we extend this concept with the use of Keystroke Dynamics, IP and GPS geo-location by optimizing the pre-processing and merging of collected information. We demonstrate the performance of the proposed approach through experimental results and we present an example of its usage.
{"title":"My Behavior is my Privacy & Secure Password !","authors":"Denis Migdal, C. Rosenberger","doi":"10.1109/CW.2019.00056","DOIUrl":"https://doi.org/10.1109/CW.2019.00056","url":null,"abstract":"Many studies propose strong user authentication based on biometric modalities. However, they often either, assume a trusted component, are modality-dependant, use only one biometric modality, are reversible, or does not enable the service to adapt the security on-the-fly. A recent work introduced the concept of Personal Identity Code Respecting Privacy (PICRP), a non-cryptographic and non-reversible signature computed from any arbitrary information. In this paper, we extend this concept with the use of Keystroke Dynamics, IP and GPS geo-location by optimizing the pre-processing and merging of collected information. We demonstrate the performance of the proposed approach through experimental results and we present an example of its usage.","PeriodicalId":117409,"journal":{"name":"2019 International Conference on Cyberworlds (CW)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131952086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：