Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209466
M. P. Aghababa, M. Saif
We consider the control design problem for a connected vehicle platoon. It is known that the platooning of vehicles in highways brings several advantages such as reduction of air pollution, increase of safety and facilitating the traffic flow. So, in this paper, a fast control algorithm is proposed to enhance the stability convergence rate of smart platoons. Subsequently, a robust terminal sliding mode controller is derived so that to not only guarantee the finite time fast stability of the connected vehicles, but also to ensure that the global string stability of the platoon is achieved via defining a new spacing error variable. The proposed sliding mode controller gets benefits of a non-singular switching sliding manifold to result in an exact finite time sliding motion dynamics. Considering the effects of uncertainties in the vehicle model as well as time varying external perturbations (such as the effects of wind, snow, etc) affecting the vehicle dynamics, a second-order nonlinear model is adopted for the vehicles and the robustness of the proposed control algorithm is theoretically proved using Lyapunov theory. At last, computer simulations illustrate the effective and fast performance of the introduced platooning strategy.
{"title":"Finite Time Sliding Mode Control of Connected Vehicle Platoons Guaranteeing String Stability","authors":"M. P. Aghababa, M. Saif","doi":"10.1109/ICHMS49158.2020.9209466","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209466","url":null,"abstract":"We consider the control design problem for a connected vehicle platoon. It is known that the platooning of vehicles in highways brings several advantages such as reduction of air pollution, increase of safety and facilitating the traffic flow. So, in this paper, a fast control algorithm is proposed to enhance the stability convergence rate of smart platoons. Subsequently, a robust terminal sliding mode controller is derived so that to not only guarantee the finite time fast stability of the connected vehicles, but also to ensure that the global string stability of the platoon is achieved via defining a new spacing error variable. The proposed sliding mode controller gets benefits of a non-singular switching sliding manifold to result in an exact finite time sliding motion dynamics. Considering the effects of uncertainties in the vehicle model as well as time varying external perturbations (such as the effects of wind, snow, etc) affecting the vehicle dynamics, a second-order nonlinear model is adopted for the vehicles and the robustness of the proposed control algorithm is theoretically proved using Lyapunov theory. At last, computer simulations illustrate the effective and fast performance of the introduced platooning strategy.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"19 23","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113964746","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209340
Thanos G. Stavropoulos, Ioulietta Lazarou, Dimitris Strantsalis, S. Nikolopoulos, Y. Kompatsiaris, G. Koumanakos, Maria Frouda, M. Tsolaki
With the onset of dementia primarily, but not exclusively, on elders and the lack of pharmaceutical treatment, lifestyle monitoring through technology seems to be a prominent solution. The human effort, error and cost imposed by close monitoring can be largely mitigated by promising eHealth technological solutions. Wearable, wristband or wristwatch, trackers are flooding the retail market at affordable prices. However, their acceptability and effectiveness for clinical purposes and especially the growing elderly population and their caregivers are still being investigated. This explorative study aims to answer such questions after carefully designing a questionnaire tailored to 45 end-users distributed in three groups of 15 participants each: healthcare professionals (HCP), caregivers and people with Mild Cognitive impairment (MCI) related to AD. Findings include that HCP, caregivers and MCI participants are willing to adopt eHealth solutions based on wearables in order to assist in daily care through holistic and objective monitoring as well as the difficulties, peculiarities and priorities they are aspiring to alleviate through such systems.
{"title":"Human Factors and Requirements of People with Mild Cognitive Impairment, their Caregivers and Healthcare Professionals for eHealth Systems with Wearable Trackers","authors":"Thanos G. Stavropoulos, Ioulietta Lazarou, Dimitris Strantsalis, S. Nikolopoulos, Y. Kompatsiaris, G. Koumanakos, Maria Frouda, M. Tsolaki","doi":"10.1109/ICHMS49158.2020.9209340","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209340","url":null,"abstract":"With the onset of dementia primarily, but not exclusively, on elders and the lack of pharmaceutical treatment, lifestyle monitoring through technology seems to be a prominent solution. The human effort, error and cost imposed by close monitoring can be largely mitigated by promising eHealth technological solutions. Wearable, wristband or wristwatch, trackers are flooding the retail market at affordable prices. However, their acceptability and effectiveness for clinical purposes and especially the growing elderly population and their caregivers are still being investigated. This explorative study aims to answer such questions after carefully designing a questionnaire tailored to 45 end-users distributed in three groups of 15 participants each: healthcare professionals (HCP), caregivers and people with Mild Cognitive impairment (MCI) related to AD. Findings include that HCP, caregivers and MCI participants are willing to adopt eHealth solutions based on wearables in order to assist in daily care through holistic and objective monitoring as well as the difficulties, peculiarities and priorities they are aspiring to alleviate through such systems.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128257101","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209540
Y. Ishiwaka, Kazutaka Izumi, T. Yoshida, Gaku Yasui
Personalized systems are required in many domains. However, gathering training data for personalization from individuals, as is necessary with deep learning, is a difficult and timeconsuming task. With our proposed method, less or no training data is required to adapt to individuals’ preferences, even when they shift over time. We introduce a potential field based method “Dark Side Ternary Stars” which has three components, GAGPL, Wordoids, and EGO. In this paper, we focus on two of them, ”Wordoids”, which adopt extends Boids algorithms to perform individualized classification of keywords by topic and improved our previous work ”GAGPL”, which calculates the individualized semantic orientation of sentences by using learned words per topic. As experimental results, we applied this method to news articles about Japanese professional baseball and we show that our method can obtain individualized semantic orientations and summaries of the article per individual.
{"title":"Wordoids: Boid Based Personalized Word Clustering System in Dark Side Ternary Stars","authors":"Y. Ishiwaka, Kazutaka Izumi, T. Yoshida, Gaku Yasui","doi":"10.1109/ICHMS49158.2020.9209540","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209540","url":null,"abstract":"Personalized systems are required in many domains. However, gathering training data for personalization from individuals, as is necessary with deep learning, is a difficult and timeconsuming task. With our proposed method, less or no training data is required to adapt to individuals’ preferences, even when they shift over time. We introduce a potential field based method “Dark Side Ternary Stars” which has three components, GAGPL, Wordoids, and EGO. In this paper, we focus on two of them, ”Wordoids”, which adopt extends Boids algorithms to perform individualized classification of keywords by topic and improved our previous work ”GAGPL”, which calculates the individualized semantic orientation of sentences by using learned words per topic. As experimental results, we applied this method to news articles about Japanese professional baseball and we show that our method can obtain individualized semantic orientations and summaries of the article per individual.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131380562","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209546
A. Esposito, T. Amorese, M. Cuciniello, M. Riviello, G. Cordasco
The present study investigates the extent to which robots’ 1) degree of human likeness, 2) gender and 3) ethnicity affect elders’ attitude towards using robots as healthcare assistants. To this aim 2 groups of 45 seniors, aged 65 + years, were asked to watch video clips showing three speaking female and male robots, respectively. Each set of stimuli consisted in 2 androids, one with Caucasian and one with Asian aspect, and 1 humanoid robot. After each video clip elders were asked to assess, through the Robot Acceptance Questionnaire (RAQ) their willingness to interact with them, as well as robots’ Pragmatic, Hedonic and Attractive qualities. Through this investigation it was found that male seniors were more proactive than female ones in their attitude toward robots showing more willingness to interact with them and attributing more positive scores to robots’ qualities. It was also observed that androids were clearly more preferred than humanoid robots no matter their gender. Finally, seniors’ preferences were for female android robots with Asian traits and male android with Caucasian traits suggesting that both gender and ethnical features are intermingled in defining robot’s appearance that generate seniors’ acceptance.
{"title":"How Human Likeness, Gender and Ethnicity affect Elders’Acceptance of Assistive Robots","authors":"A. Esposito, T. Amorese, M. Cuciniello, M. Riviello, G. Cordasco","doi":"10.1109/ICHMS49158.2020.9209546","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209546","url":null,"abstract":"The present study investigates the extent to which robots’ 1) degree of human likeness, 2) gender and 3) ethnicity affect elders’ attitude towards using robots as healthcare assistants. To this aim 2 groups of 45 seniors, aged 65 + years, were asked to watch video clips showing three speaking female and male robots, respectively. Each set of stimuli consisted in 2 androids, one with Caucasian and one with Asian aspect, and 1 humanoid robot. After each video clip elders were asked to assess, through the Robot Acceptance Questionnaire (RAQ) their willingness to interact with them, as well as robots’ Pragmatic, Hedonic and Attractive qualities. Through this investigation it was found that male seniors were more proactive than female ones in their attitude toward robots showing more willingness to interact with them and attributing more positive scores to robots’ qualities. It was also observed that androids were clearly more preferred than humanoid robots no matter their gender. Finally, seniors’ preferences were for female android robots with Asian traits and male android with Caucasian traits suggesting that both gender and ethnical features are intermingled in defining robot’s appearance that generate seniors’ acceptance.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128902560","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209354
I. Liu, S. Ni, K. Peng
Heart rate variability (HRV) provides essential mental health information for clinical diagnosis, telemedicine, preventive medicine, and public health. However, the lack of a convenient detection method limits its potential. This study aimed to investigate the feasibility and credibility of using smartphone Photoplethysmogram (PPG)-based HRV analysis for personality prediction. Ninety-five records were collected from students and university employees in Shenzhen, China. An app recorded five-minute films of their fingertips and converted the frames into HRV measures. Participants who were more extraverted and stable had a higher root mean square of successive differences (rMSSD; p=0.03 and 0.005, respectively), and a higher percentage of successive normal-to-normal (NN) intervals that differed by more than 50 ms (pNN50; p=0.05 and 0.004, respectively), and standard deviation of NN intervals (SDNN; p=0.02 and 0.01, respectively). Stable people also had higher log high-frequency HRV (p=0.008). The results from correlation coefficients and the Bland–Altman analysis verified the accuracy of smartphone PPG in HRV assessment. The correlation coefficients of all HRV measures obtained using smartphone PPG and reference ECG were higher than 0.9. Moreover, the Bland–Altman ratios were less than 0.2 for all HRV measures except pNN50. Taken together, the results of this study provide the first empirical evidence that supports the usability of smartphone PPG as a predictor of personality.
{"title":"Predicting Personality with Smartphone Cameras: A Pilot Study","authors":"I. Liu, S. Ni, K. Peng","doi":"10.1109/ICHMS49158.2020.9209354","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209354","url":null,"abstract":"Heart rate variability (HRV) provides essential mental health information for clinical diagnosis, telemedicine, preventive medicine, and public health. However, the lack of a convenient detection method limits its potential. This study aimed to investigate the feasibility and credibility of using smartphone Photoplethysmogram (PPG)-based HRV analysis for personality prediction. Ninety-five records were collected from students and university employees in Shenzhen, China. An app recorded five-minute films of their fingertips and converted the frames into HRV measures. Participants who were more extraverted and stable had a higher root mean square of successive differences (rMSSD; p=0.03 and 0.005, respectively), and a higher percentage of successive normal-to-normal (NN) intervals that differed by more than 50 ms (pNN50; p=0.05 and 0.004, respectively), and standard deviation of NN intervals (SDNN; p=0.02 and 0.01, respectively). Stable people also had higher log high-frequency HRV (p=0.008). The results from correlation coefficients and the Bland–Altman analysis verified the accuracy of smartphone PPG in HRV assessment. The correlation coefficients of all HRV measures obtained using smartphone PPG and reference ECG were higher than 0.9. Moreover, the Bland–Altman ratios were less than 0.2 for all HRV measures except pNN50. Taken together, the results of this study provide the first empirical evidence that supports the usability of smartphone PPG as a predictor of personality.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121150058","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209398
G. Fortino, A. Guzzo, M. Ianni, F. Leotta, Massimo Mecella
The increasingly large availability of sensors in modern houses, due to the establishment of home assistants, allow to think in terms of smart houses where behaviours can be automatized based on user habits. Common tasks required to this aim include activity prediction, i.e., the task of forecasting what is the next activity a human is going to perform in the smart space based on past sensor logs. In this paper, we propose a novel activity prediction method for smart houses based on the seminal probabilistic method named Marked Temporal Point Process Prediction.
{"title":"Exploiting Marked Temporal Point Processes for Predicting Activities of Daily Living","authors":"G. Fortino, A. Guzzo, M. Ianni, F. Leotta, Massimo Mecella","doi":"10.1109/ICHMS49158.2020.9209398","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209398","url":null,"abstract":"The increasingly large availability of sensors in modern houses, due to the establishment of home assistants, allow to think in terms of smart houses where behaviours can be automatized based on user habits. Common tasks required to this aim include activity prediction, i.e., the task of forecasting what is the next activity a human is going to perform in the smart space based on past sensor logs. In this paper, we propose a novel activity prediction method for smart houses based on the seminal probabilistic method named Marked Temporal Point Process Prediction.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126573621","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209353
Naveed Ahmed, H. Kharoub, S. Medjden, Areej Alsaafin, M. Lataifeh
This work presents a new comparative study for manipulating animated 3D content on a large scale display using two user interaction mechanisms. The first interaction mechanism relies on a traditional cursor-based user interface (UI) with onscreen interaction elements. The second interaction mechanism adopts a gesture-based UI without any visible interaction elements. The user’s distance from the display is significantly farther compared to a traditional desktop to correctly gauge the impact of a cursor-based UI compared to a gesture-based UI on a large scale display. Both interaction mechanisms are extensively evaluated via a user study in terms of usability, user experience (UX), and ergonomics. Through both quantitative and the qualitative evaluation, the results show that a gesture-based interface is a preferred method to manipulate animated 3D content compared to a cursor-based UI on a large scale display in terms of usability and UX. The results also demonstrate that using a gesture-based UI does not rank higher in terms of physical and cognitive ergonomics compared to a cursor-based UI.
{"title":"A Comparative Study to Assess Human Machine Interaction Mechanisms for Large Scale Displays","authors":"Naveed Ahmed, H. Kharoub, S. Medjden, Areej Alsaafin, M. Lataifeh","doi":"10.1109/ICHMS49158.2020.9209353","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209353","url":null,"abstract":"This work presents a new comparative study for manipulating animated 3D content on a large scale display using two user interaction mechanisms. The first interaction mechanism relies on a traditional cursor-based user interface (UI) with onscreen interaction elements. The second interaction mechanism adopts a gesture-based UI without any visible interaction elements. The user’s distance from the display is significantly farther compared to a traditional desktop to correctly gauge the impact of a cursor-based UI compared to a gesture-based UI on a large scale display. Both interaction mechanisms are extensively evaluated via a user study in terms of usability, user experience (UX), and ergonomics. Through both quantitative and the qualitative evaluation, the results show that a gesture-based interface is a preferred method to manipulate animated 3D content compared to a cursor-based UI on a large scale display in terms of usability and UX. The results also demonstrate that using a gesture-based UI does not rank higher in terms of physical and cognitive ergonomics compared to a cursor-based UI.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127045415","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209524
Holly Zelnio, Mary E. Frame, Mary E. Fendley
This research project examines the effectiveness of Decision Support Systems (DSS) to improve object classification performance of imagery from three different image sensor types. Eye tracking analyses provide evidence that individuals are able to focus on information that is most crucial to classification while ignoring information that is less diagnostic within a DSS, without jeopardizing performance. This analysis augments previous work on this problem that addressed accuracy, confidence, and trust.
{"title":"Using Eye Tracking to Evaluate Decision Support Systems of Imagery Classification","authors":"Holly Zelnio, Mary E. Frame, Mary E. Fendley","doi":"10.1109/ICHMS49158.2020.9209524","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209524","url":null,"abstract":"This research project examines the effectiveness of Decision Support Systems (DSS) to improve object classification performance of imagery from three different image sensor types. Eye tracking analyses provide evidence that individuals are able to focus on information that is most crucial to classification while ignoring information that is less diagnostic within a DSS, without jeopardizing performance. This analysis augments previous work on this problem that addressed accuracy, confidence, and trust.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133648891","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209499
Pierangela Bruno, Francesco Calimeri, Alexandre Sébastien Kitanidis, E. Momi
Providing accurate diagnosis of diseases generally requires complex analyses of many clinical, biological and pathological variables. In this context, solutions based on machine learning techniques achieved relevant results in specific disease detection and classification, and can hence provide significant clinical decision support. However, such approaches suffer from the lack of proper means for interpreting the choices made by the models, especially in case of deep-learning ones. In order to improve interpretability and explainability in the process of making qualified decisions, we designed a system that allows for a partial opening of this black box by means of proper investigations on the rationale behind the decisions; this can provide improved understandings into which pre-processing steps are crucial for better performance. We tested our approach over artificial neural networks trained for automatic medical diagnosis based on high-dimensional gene expression and clinical data. Our tool analyzed the internal processes performed by the networks during the classification tasks in order to identify the most important elements involved in the training process that influence the network’s decisions.We report the results of an experimental analysis aimed at assessing the viability of the proposed approach.
{"title":"Understanding Automatic Diagnosis and Classification Processes with Data Visualization","authors":"Pierangela Bruno, Francesco Calimeri, Alexandre Sébastien Kitanidis, E. Momi","doi":"10.1109/ICHMS49158.2020.9209499","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209499","url":null,"abstract":"Providing accurate diagnosis of diseases generally requires complex analyses of many clinical, biological and pathological variables. In this context, solutions based on machine learning techniques achieved relevant results in specific disease detection and classification, and can hence provide significant clinical decision support. However, such approaches suffer from the lack of proper means for interpreting the choices made by the models, especially in case of deep-learning ones. In order to improve interpretability and explainability in the process of making qualified decisions, we designed a system that allows for a partial opening of this black box by means of proper investigations on the rationale behind the decisions; this can provide improved understandings into which pre-processing steps are crucial for better performance. We tested our approach over artificial neural networks trained for automatic medical diagnosis based on high-dimensional gene expression and clinical data. Our tool analyzed the internal processes performed by the networks during the classification tasks in order to identify the most important elements involved in the training process that influence the network’s decisions.We report the results of an experimental analysis aimed at assessing the viability of the proposed approach.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122235745","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}
Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209473
Christopher S. Calhoun, Joshua Reinhart, Gene A. Alarcon, August A. Capiola
The current exploratory study examined software programmer trust in binary analysis techniques used to evaluate and understand binary code components. Experienced software developers participated in knowledge elicitations to identify factors affecting trust in tools and methods used for understanding binary code behavior and minimizing potential security vulnerabilities. Developer perceptions of trust in those tools to assess implementation risk in binary components were captured across a variety of application contexts. The software developers reported source security and vulnerability reports provided the best insight and awareness of potential issues or shortcomings in binary code. Further, applications where the potential impact to systems and data loss is high require relying on more than one type of analysis to ensure the binary component is sound. The findings suggest binary analysis is viable for identifying issues and potential vulnerabilities as part of a comprehensive solution for understanding binary code behavior and security vulnerabilities, but relying simply on binary analysis tools and binary release metadata appears insufficient to ensure a secure solution.
{"title":"Establishing Trust in Binary Analysis in Software Development and Applications","authors":"Christopher S. Calhoun, Joshua Reinhart, Gene A. Alarcon, August A. Capiola","doi":"10.1109/ICHMS49158.2020.9209473","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209473","url":null,"abstract":"The current exploratory study examined software programmer trust in binary analysis techniques used to evaluate and understand binary code components. Experienced software developers participated in knowledge elicitations to identify factors affecting trust in tools and methods used for understanding binary code behavior and minimizing potential security vulnerabilities. Developer perceptions of trust in those tools to assess implementation risk in binary components were captured across a variety of application contexts. The software developers reported source security and vulnerability reports provided the best insight and awareness of potential issues or shortcomings in binary code. Further, applications where the potential impact to systems and data loss is high require relying on more than one type of analysis to ensure the binary component is sound. The findings suggest binary analysis is viable for identifying issues and potential vulnerabilities as part of a comprehensive solution for understanding binary code behavior and security vulnerabilities, but relying simply on binary analysis tools and binary release metadata appears insufficient to ensure a secure solution.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131447780","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：