Pub Date : 2023-12-07DOI: 10.3389/fcomp.2023.1304590
Sohail Jabbar, Zain Ul Abideen, S. Khalid, Awais Ahmad, Umar Raza, Sheeraz Akram
Accommodating an increasing number of users in the Blockchain network has moved to the forefront of discussion. It is also evident that without jeopardizing the data security in Blockchain, it is of indispensable need to devise an appropriate method for improving the scalability trait of Blockchain. In this article, we have proposed a consensus method that is having the potential to improve the scalability of the Private Blockchain. The system, at first, mitigates latency arising from kernel schedulers, ensuring that the application consistently has access to an available core for transaction processing. Secondly, the committee system alleviates the network's workload, preventing spurious transactions from monopolizing network resources and impeding its efficiency. Extensive experimentation is made by considering various scenarios of transaction with CPU isolation and application sticking to core 2 with varied priority. Based on the number of transactions performed per second, the proposed system is compared with different existing consensus mechanisms working in various types of Blockchains. Also, a detailed discussion is presented on the critical analysis of the adopted research mechanism. Overall, the proposed systems outperforms to other systems in various parameters of blockchain network scalability.
{"title":"Enhancing computational scalability in Blockchain by leveraging improvement in consensus algorithm","authors":"Sohail Jabbar, Zain Ul Abideen, S. Khalid, Awais Ahmad, Umar Raza, Sheeraz Akram","doi":"10.3389/fcomp.2023.1304590","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1304590","url":null,"abstract":"Accommodating an increasing number of users in the Blockchain network has moved to the forefront of discussion. It is also evident that without jeopardizing the data security in Blockchain, it is of indispensable need to devise an appropriate method for improving the scalability trait of Blockchain. In this article, we have proposed a consensus method that is having the potential to improve the scalability of the Private Blockchain. The system, at first, mitigates latency arising from kernel schedulers, ensuring that the application consistently has access to an available core for transaction processing. Secondly, the committee system alleviates the network's workload, preventing spurious transactions from monopolizing network resources and impeding its efficiency. Extensive experimentation is made by considering various scenarios of transaction with CPU isolation and application sticking to core 2 with varied priority. Based on the number of transactions performed per second, the proposed system is compared with different existing consensus mechanisms working in various types of Blockchains. Also, a detailed discussion is presented on the critical analysis of the adopted research mechanism. Overall, the proposed systems outperforms to other systems in various parameters of blockchain network scalability.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138590913","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 : 2023-12-07DOI: 10.3389/fcomp.2023.1270520
Mélodie Sannier, Stefan Janaqi, Gérard Dray, Pierre Slangen, Benoît G. Bardy
Walking indoors, particularly at home, presents a distinct experience compared to the conventional pedestrian walking classically described. Our homes encompass intricate, confined, and cluttered architectural spaces that necessitate a predominantly curvilinear walking pattern. Despite the growing interest in studying our home, spurred by successive COVID-19 lockdowns, there remains a dearth of information regarding our walking behaviors inside homes, yet rich in data on the physical and sensory links between humans and their daily interior environment.This study presents the outcomes of a controlled experiment conducted in an apartment in Montpellier, France. Participants were tasked with traversing the living room at a natural pace, encountering two natural obstacles-a large dining table and a small coffee table. They then walked back in opposite direction, circumnavigating the same two obstacles. To examine walking behavior within a pseudo-natural context, three conditions were tested: a controlled condition and two conditions that perturbed the natural curvilinear trajectory perceptually, by imposing an unpleasant sound, or physically, by suddenly displacing the coffee table between conditions. Twenty participants performed 30 trials in each condition. We approximated the position of their center of mass and computed various metrics related to their trajectories, including walking speed, obstacle clearance distance, its adaptation over time, and inter-trial trajectory variability.Findings revealed a greater visual clearance distance for the dining table compared to the coffee table, a difference reduced by the perturbation caused by displacing the coffee table. This clearing distance diminished with repetitions, showing that over time we tend to walk closer to obstacles around us. These adaptations were clearly the result of an active visuo-motor regulation, as evidenced by the reduced trajectory variability at, or just before, the location of the obstacles.Collectively, these results demonstrate that walking at home is a flexible behavior necessitating continuous perceptual adaptations in our daily trajectories. These findings could contribute to a detailed analysis of walking indoors under natural conditions, and the investigated metrics could serve as a baseline for comparing the embodiment of physical and mental health in walking patterns, for instance during lockdowns. Furthermore, our findings have consequences for safer mediated human architecture interaction.
{"title":"Obstacles shape the way we walk at home","authors":"Mélodie Sannier, Stefan Janaqi, Gérard Dray, Pierre Slangen, Benoît G. Bardy","doi":"10.3389/fcomp.2023.1270520","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1270520","url":null,"abstract":"Walking indoors, particularly at home, presents a distinct experience compared to the conventional pedestrian walking classically described. Our homes encompass intricate, confined, and cluttered architectural spaces that necessitate a predominantly curvilinear walking pattern. Despite the growing interest in studying our home, spurred by successive COVID-19 lockdowns, there remains a dearth of information regarding our walking behaviors inside homes, yet rich in data on the physical and sensory links between humans and their daily interior environment.This study presents the outcomes of a controlled experiment conducted in an apartment in Montpellier, France. Participants were tasked with traversing the living room at a natural pace, encountering two natural obstacles-a large dining table and a small coffee table. They then walked back in opposite direction, circumnavigating the same two obstacles. To examine walking behavior within a pseudo-natural context, three conditions were tested: a controlled condition and two conditions that perturbed the natural curvilinear trajectory perceptually, by imposing an unpleasant sound, or physically, by suddenly displacing the coffee table between conditions. Twenty participants performed 30 trials in each condition. We approximated the position of their center of mass and computed various metrics related to their trajectories, including walking speed, obstacle clearance distance, its adaptation over time, and inter-trial trajectory variability.Findings revealed a greater visual clearance distance for the dining table compared to the coffee table, a difference reduced by the perturbation caused by displacing the coffee table. This clearing distance diminished with repetitions, showing that over time we tend to walk closer to obstacles around us. These adaptations were clearly the result of an active visuo-motor regulation, as evidenced by the reduced trajectory variability at, or just before, the location of the obstacles.Collectively, these results demonstrate that walking at home is a flexible behavior necessitating continuous perceptual adaptations in our daily trajectories. These findings could contribute to a detailed analysis of walking indoors under natural conditions, and the investigated metrics could serve as a baseline for comparing the embodiment of physical and mental health in walking patterns, for instance during lockdowns. Furthermore, our findings have consequences for safer mediated human architecture interaction.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138591127","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 : 2023-12-05DOI: 10.3389/fcomp.2023.1326413
Heinrich C. Mayr, B. Thalheim
{"title":"Editorial: Model-centered software and system development","authors":"Heinrich C. Mayr, B. Thalheim","doi":"10.3389/fcomp.2023.1326413","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1326413","url":null,"abstract":"","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2023-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138598522","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 : 2023-12-05DOI: 10.3389/fcomp.2023.1264713
Jennifer Gohumpu, Mengru Xue, Yanchi Bao
Healthcare wearables allow researchers to develop various system approaches that recognize and understand the human emotional experience. Previous research has indicated that machine learning classifiers, such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Decision Tree (DT), can improve the accuracy of physiological signal analysis and emotion recognition. However, various emotions can have distinct effects on physiological signal alterations. Therefore, solely relying on a single type of physiological signal analysis is insufficient for accurately recognizing and understanding human emotional experiences.Research on multi-modal emotion recognition systems (ERS) has commonly gathered physiological signals using expensive devices, which required participants to remain in fixed positions in the lab setting. This limitation restricts the potential for generalizing the ERS technology for peripheral use in daily life. Therefore, considering the convenience of data collection from everyday devices, we propose a multi-modal physiological signals-based ERS based on peripheral signals, utilizing the DEAP database. The physiological signals selected for analysis include photoplethysmography (PPG), galvanic skin response (GSR), and skin temperature (SKT). Signal features were extracted using the “Toolbox for Emotional Feature Extraction from Physiological Signals” (TEAP) library and further analyzed with three classifiers: SVM, KNN, and DT.The results showed improved accuracy in the proposed system compared to a single-modal ERS application, which also outperformed current DEAP multi-modal ERS applications.This study sheds light on the potential of combining multi-modal peripheral physiological signals in ERS for ubiquitous applications in daily life, conveniently captured using smart devices.
医疗可穿戴设备允许研究人员开发各种系统方法来识别和理解人类的情感体验。已有研究表明，支持向量机(SVM)、k近邻(KNN)和决策树(DT)等机器学习分类器可以提高生理信号分析和情绪识别的准确性。然而，不同的情绪会对生理信号的改变产生不同的影响。因此，仅仅依靠单一类型的生理信号分析不足以准确地识别和理解人类的情感体验。多模态情绪识别系统(ERS)的研究通常使用昂贵的设备来收集生理信号，这些设备要求参与者在实验室环境中保持固定的位置。这一限制限制了将ERS技术推广到日常生活中外围设备使用的潜力。因此，考虑到从日常设备收集数据的便利性，我们提出了一种基于周边信号的多模态生理信号的ERS，利用DEAP数据库。选择用于分析的生理信号包括光容积脉搏波(PPG)、皮肤电反应(GSR)和皮肤温度(SKT)。使用“Toolbox for Emotional Feature Extraction from Physiological Signals”(TEAP)库提取信号特征，并使用SVM、KNN和DT三种分类器进行分析。结果表明，与单模态ERS应用相比，该系统的精度有所提高，也优于当前的DEAP多模态ERS应用。这项研究揭示了将ERS中的多模态外周生理信号结合起来用于日常生活中无处不在的应用的潜力，这些应用可以通过智能设备方便地捕获。
{"title":"Emotion recognition with multi-modal peripheral physiological signals","authors":"Jennifer Gohumpu, Mengru Xue, Yanchi Bao","doi":"10.3389/fcomp.2023.1264713","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1264713","url":null,"abstract":"Healthcare wearables allow researchers to develop various system approaches that recognize and understand the human emotional experience. Previous research has indicated that machine learning classifiers, such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Decision Tree (DT), can improve the accuracy of physiological signal analysis and emotion recognition. However, various emotions can have distinct effects on physiological signal alterations. Therefore, solely relying on a single type of physiological signal analysis is insufficient for accurately recognizing and understanding human emotional experiences.Research on multi-modal emotion recognition systems (ERS) has commonly gathered physiological signals using expensive devices, which required participants to remain in fixed positions in the lab setting. This limitation restricts the potential for generalizing the ERS technology for peripheral use in daily life. Therefore, considering the convenience of data collection from everyday devices, we propose a multi-modal physiological signals-based ERS based on peripheral signals, utilizing the DEAP database. The physiological signals selected for analysis include photoplethysmography (PPG), galvanic skin response (GSR), and skin temperature (SKT). Signal features were extracted using the “Toolbox for Emotional Feature Extraction from Physiological Signals” (TEAP) library and further analyzed with three classifiers: SVM, KNN, and DT.The results showed improved accuracy in the proposed system compared to a single-modal ERS application, which also outperformed current DEAP multi-modal ERS applications.This study sheds light on the potential of combining multi-modal peripheral physiological signals in ERS for ubiquitous applications in daily life, conveniently captured using smart devices.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2023-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138600387","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 : 2023-12-05DOI: 10.3389/fcomp.2023.1265399
Yanchi Bao, Mengru Xue, Jennifer Gohumpu, Yumeng Cao, Jun Hu
Excessive work stress on office workers will affect people's health and work efficiency, and organizational stress management is becoming more and more critical. Current studies focus on the management of individual stress. The collective nature of stress and coping needs further exploration.This paper proposes the PopStress system, which converts the negative stress of an office group into the energy of a popcorn machine. When the organizational stress accumulates to the threshold, the popcorn machine will start making popcorn and attract office workers to take a break and eat. Through multisensory stimuli such as visual, audio, and olfaction, the system encourages natural and entertaining social stress-relieving behaviors within the office.Twenty-four office workers were recruited and divided into six groups for the user study. The results showed that PopStress enables users to understand the collective stress status, and successfully relieved the individual's physiological and psychological stress. This work provides insights into organizational stress management, health product design, and social design.
{"title":"PopStress: designing organizational stress intervention for office workers","authors":"Yanchi Bao, Mengru Xue, Jennifer Gohumpu, Yumeng Cao, Jun Hu","doi":"10.3389/fcomp.2023.1265399","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1265399","url":null,"abstract":"Excessive work stress on office workers will affect people's health and work efficiency, and organizational stress management is becoming more and more critical. Current studies focus on the management of individual stress. The collective nature of stress and coping needs further exploration.This paper proposes the PopStress system, which converts the negative stress of an office group into the energy of a popcorn machine. When the organizational stress accumulates to the threshold, the popcorn machine will start making popcorn and attract office workers to take a break and eat. Through multisensory stimuli such as visual, audio, and olfaction, the system encourages natural and entertaining social stress-relieving behaviors within the office.Twenty-four office workers were recruited and divided into six groups for the user study. The results showed that PopStress enables users to understand the collective stress status, and successfully relieved the individual's physiological and psychological stress. This work provides insights into organizational stress management, health product design, and social design.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2023-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138599029","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 : 2023-11-07DOI: 10.3389/fcomp.2023.1125895
Mira El Kamali, Leonardo Angelini, Denis Lalanne, Omar Abou Khaled, Elena Mugellini
Introduction The use of multiple interfaces may improve the perception of a stronger relationship between a conversational virtual coach and older adults. The purpose of this paper is to show the effect of output combinations [single-interface (chatbot, tangible coach), multi-interface (assignment, redundant-complementary)] of two distinct conversational agent interfaces (chatbot and tangible coach) on the eCoach-user relationship (closeness, commitment, complementarity) and the older adults' feeling of social presence of the eCoach. Methods Our study was conducted with two different study settings: an online web survey and a face to face experiment. Results Our online study with 59 seniors shows that the output modes in multi-interface redundant-complementary manner significantly improves the eCoach-user relationship and social presence of the eCoach compared to only using single-interfaces outputs. Whereas in our face to face experiment with 15 seniors, significant results were found only in terms of higher social presence of multi-interface redundant complementary manner compared to chatbot only. Discussion We also investigated the effect of each study design on our results, using both quantitative and qualitative methods.
{"title":"Older adults' perspectives on multimodal interaction with a conversational virtual coach","authors":"Mira El Kamali, Leonardo Angelini, Denis Lalanne, Omar Abou Khaled, Elena Mugellini","doi":"10.3389/fcomp.2023.1125895","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1125895","url":null,"abstract":"Introduction The use of multiple interfaces may improve the perception of a stronger relationship between a conversational virtual coach and older adults. The purpose of this paper is to show the effect of output combinations [single-interface (chatbot, tangible coach), multi-interface (assignment, redundant-complementary)] of two distinct conversational agent interfaces (chatbot and tangible coach) on the eCoach-user relationship (closeness, commitment, complementarity) and the older adults' feeling of social presence of the eCoach. Methods Our study was conducted with two different study settings: an online web survey and a face to face experiment. Results Our online study with 59 seniors shows that the output modes in multi-interface redundant-complementary manner significantly improves the eCoach-user relationship and social presence of the eCoach compared to only using single-interfaces outputs. Whereas in our face to face experiment with 15 seniors, significant results were found only in terms of higher social presence of multi-interface redundant complementary manner compared to chatbot only. Discussion We also investigated the effect of each study design on our results, using both quantitative and qualitative methods.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135544588","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 : 2023-11-02DOI: 10.3389/fcomp.2023.1279800
Jorge Bejarano, Daniel Barón, Oscar González-Rojas, Manuel Camargo
Introduction Data-driven simulation allows the discovery of process simulation models from event logs. The generated model can be used to simulate changes in the process configuration and to evaluate the expected performance of the processes before they are executed. Currently, these what-if scenarios are defined and assessed manually by the analysts. Besides the complexity of finding a suitable scenario for a desired performance, existing approaches simulate scenarios based on flow and data patterns leaving aside a resource-based analysis. Resources are critical on the process performance since they carry out costs, time, and quality. Methods This paper proposes a method to automate the discovery of optimal resource allocations to improve the performance of simulated what-if scenarios. We describe a model for individual resource allocation only to activities they fit. Then, we present how what-if scenarios are generated based on preference and collaboration allocation policies. The optimal resource allocations are discovered based on a user-defined multi-objective optimization function. Results and discussion This method is integrated with a simulation environment to compare the trade-off in the performance of what-if scenarios when changing allocation policies. An experimental evaluation of multiple real-life and synthetic event logs shows that optimal resource allocations improve the simulation performance.
{"title":"Discovering optimal resource allocations for what-if scenarios using data-driven simulation","authors":"Jorge Bejarano, Daniel Barón, Oscar González-Rojas, Manuel Camargo","doi":"10.3389/fcomp.2023.1279800","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1279800","url":null,"abstract":"Introduction Data-driven simulation allows the discovery of process simulation models from event logs. The generated model can be used to simulate changes in the process configuration and to evaluate the expected performance of the processes before they are executed. Currently, these what-if scenarios are defined and assessed manually by the analysts. Besides the complexity of finding a suitable scenario for a desired performance, existing approaches simulate scenarios based on flow and data patterns leaving aside a resource-based analysis. Resources are critical on the process performance since they carry out costs, time, and quality. Methods This paper proposes a method to automate the discovery of optimal resource allocations to improve the performance of simulated what-if scenarios. We describe a model for individual resource allocation only to activities they fit. Then, we present how what-if scenarios are generated based on preference and collaboration allocation policies. The optimal resource allocations are discovered based on a user-defined multi-objective optimization function. Results and discussion This method is integrated with a simulation environment to compare the trade-off in the performance of what-if scenarios when changing allocation policies. An experimental evaluation of multiple real-life and synthetic event logs shows that optimal resource allocations improve the simulation performance.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135974888","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 : 2023-11-02DOI: 10.3389/fcomp.2023.1253682
Peter Tu, Zhaoyuan Yang, Richard Hartley, Zhiwei Xu, Jing Zhang, Yiwei Fu, Dylan Campbell, Jaskirat Singh, Tianyu Wang
This paper begins with a description of methods for estimating probability density functions for images that reflects the observation that such data is usually constrained to lie in restricted regions of the high-dimensional image space—not every pattern of pixels is an image. It is common to say that images lie on a lower-dimensional manifold in the high-dimensional space. However, although images may lie on such lower-dimensional manifolds, it is not the case that all points on the manifold have an equal probability of being images. Images are unevenly distributed on the manifold, and our task is to devise ways to model this distribution as a probability distribution. In pursuing this goal, we consider generative models that are popular in AI and computer vision community. For our purposes, generative/probabilistic models should have the properties of (1) sample generation: it should be possible to sample from this distribution according to the modeled density function, and (2) probability computation: given a previously unseen sample from the dataset of interest, one should be able to compute the probability of the sample, at least up to a normalizing constant. To this end, we investigate the use of methods such as normalizing flow and diffusion models. We then show how semantic interpretations are used to describe points on the manifold. To achieve this, we consider an emergent language framework that makes use of variational encoders to produce a disentangled representation of points that reside on a given manifold. Trajectories between points on a manifold can then be described in terms of evolving semantic descriptions. In addition to describing the manifold in terms of density and semantic disentanglement, we also show that such probabilistic descriptions (bounded) can be used to improve semantic consistency by constructing defenses against adversarial attacks. We evaluate our methods on CelebA and point samples for likelihood estimation with improved semantic robustness and out-of-distribution detection capability, MNIST and CelebA for semantic disentanglement with explainable and editable semantic interpolation, and CelebA and Fashion-MNIST to defend against patch attacks with significantly improved classification accuracy. We also discuss the limitations of applying our likelihood estimation to 2D images in diffusion models.
{"title":"Probabilistic and semantic descriptions of image manifolds and their applications","authors":"Peter Tu, Zhaoyuan Yang, Richard Hartley, Zhiwei Xu, Jing Zhang, Yiwei Fu, Dylan Campbell, Jaskirat Singh, Tianyu Wang","doi":"10.3389/fcomp.2023.1253682","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1253682","url":null,"abstract":"This paper begins with a description of methods for estimating probability density functions for images that reflects the observation that such data is usually constrained to lie in restricted regions of the high-dimensional image space—not every pattern of pixels is an image. It is common to say that images lie on a lower-dimensional manifold in the high-dimensional space. However, although images may lie on such lower-dimensional manifolds, it is not the case that all points on the manifold have an equal probability of being images. Images are unevenly distributed on the manifold, and our task is to devise ways to model this distribution as a probability distribution. In pursuing this goal, we consider generative models that are popular in AI and computer vision community. For our purposes, generative/probabilistic models should have the properties of (1) sample generation: it should be possible to sample from this distribution according to the modeled density function, and (2) probability computation: given a previously unseen sample from the dataset of interest, one should be able to compute the probability of the sample, at least up to a normalizing constant. To this end, we investigate the use of methods such as normalizing flow and diffusion models. We then show how semantic interpretations are used to describe points on the manifold. To achieve this, we consider an emergent language framework that makes use of variational encoders to produce a disentangled representation of points that reside on a given manifold. Trajectories between points on a manifold can then be described in terms of evolving semantic descriptions. In addition to describing the manifold in terms of density and semantic disentanglement, we also show that such probabilistic descriptions (bounded) can be used to improve semantic consistency by constructing defenses against adversarial attacks. We evaluate our methods on CelebA and point samples for likelihood estimation with improved semantic robustness and out-of-distribution detection capability, MNIST and CelebA for semantic disentanglement with explainable and editable semantic interpolation, and CelebA and Fashion-MNIST to defend against patch attacks with significantly improved classification accuracy. We also discuss the limitations of applying our likelihood estimation to 2D images in diffusion models.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135972671","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 : 2023-11-02DOI: 10.3389/fcomp.2023.1135201
Björn W. Schuller, Shahin Amiriparian, Anton Batliner, Alexander Gebhard, Maurice Gerczuk, Vincent Karas, Alexander Kathan, Lennart Seizer, Johanna Löchner
Charisma is considered as one's ability to attract and potentially influence others. Clearly, there can be considerable interest from an artificial intelligence's (AI) perspective to provide it with such skill. Beyond, a plethora of use cases opens up for computational measurement of human charisma, such as for tutoring humans in the acquisition of charisma, mediating human-to-human conversation, or identifying charismatic individuals in big social data. While charisma is a subject of research in its own right, a number of models exist that base it on various “pillars,” that is, dimensions, often following the idea that charisma is given if someone could and would help others. Examples of such pillars, therefore, include influence (could help) and affability (would help) in scientific studies, or power (could help), presence, and warmth (both would help) as a popular concept. Modeling high levels in these dimensions, i. e., high influence and high affability, or high power, presence, and warmth for charismatic AI of the future, e. g., for humanoid robots or virtual agents, seems accomplishable. Beyond, also automatic measurement appears quite feasible with the recent advances in the related fields of Affective Computing and Social Signal Processing. Here, we therefore present a brick by brick blueprint for building machines that can appear charismatic, but also analyse the charisma of others. We first approach the topic very broadly and discuss how the foundation of charisma is defined from a psychological perspective. Throughout the manuscript, the building blocks (bricks) then become more specific and provide concrete groundwork for capturing charisma through artificial intelligence (AI). Following the introduction of the concept of charisma, we switch to charisma in spoken language as an exemplary modality that is essential for human-human and human-computer conversations. The computational perspective then deals with the recognition and generation of charismatic behavior by AI. This includes an overview of the state of play in the field and the aforementioned blueprint. We then list exemplary use cases of computational charismatic skills. The building blocks of application domains and ethics conclude the article.
{"title":"Computational charisma—A brick by brick blueprint for building charismatic artificial intelligence","authors":"Björn W. Schuller, Shahin Amiriparian, Anton Batliner, Alexander Gebhard, Maurice Gerczuk, Vincent Karas, Alexander Kathan, Lennart Seizer, Johanna Löchner","doi":"10.3389/fcomp.2023.1135201","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1135201","url":null,"abstract":"Charisma is considered as one's ability to attract and potentially influence others. Clearly, there can be considerable interest from an artificial intelligence's (AI) perspective to provide it with such skill. Beyond, a plethora of use cases opens up for computational measurement of human charisma, such as for tutoring humans in the acquisition of charisma, mediating human-to-human conversation, or identifying charismatic individuals in big social data. While charisma is a subject of research in its own right, a number of models exist that base it on various “pillars,” that is, dimensions, often following the idea that charisma is given if someone could and would help others. Examples of such pillars, therefore, include influence (could help) and affability (would help) in scientific studies, or power (could help), presence, and warmth (both would help) as a popular concept. Modeling high levels in these dimensions, i. e., high influence and high affability, or high power, presence, and warmth for charismatic AI of the future, e. g., for humanoid robots or virtual agents, seems accomplishable. Beyond, also automatic measurement appears quite feasible with the recent advances in the related fields of Affective Computing and Social Signal Processing. Here, we therefore present a brick by brick blueprint for building machines that can appear charismatic, but also analyse the charisma of others. We first approach the topic very broadly and discuss how the foundation of charisma is defined from a psychological perspective. Throughout the manuscript, the building blocks (bricks) then become more specific and provide concrete groundwork for capturing charisma through artificial intelligence (AI). Following the introduction of the concept of charisma, we switch to charisma in spoken language as an exemplary modality that is essential for human-human and human-computer conversations. The computational perspective then deals with the recognition and generation of charismatic behavior by AI. This includes an overview of the state of play in the field and the aforementioned blueprint. We then list exemplary use cases of computational charismatic skills. The building blocks of application domains and ethics conclude the article.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135974885","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 : 2023-10-30DOI: 10.3389/fcomp.2023.1149305
Fengxiang Li, Siska Fitrianie, Merijn Bruijnes, Amal Abdulrahman, Fu Guo, Willem-Paul Brinkman
The Artificial-Social-Agent (ASA) questionnaire is an instrument for evaluating human-ASA interaction. It consists of 19 constructs and related dimensions measured by either 24 questionnaire items (short version) or 90 questionnaire items (long version). The questionnaire was built and validated by a research community effort to make evaluation results more comparable between agents and findings more generalizable. The current questionnaire is in English, which limits its use to only a population with an adequate command of the English language. Translating the questionnaire into more languages allows for the inclusion of other populations and the possibility of comparing them. Therefore, this paper presents a Mandarin Chinese translation of the questionnaire. After three construction cycles that included forward and backward translation, we gave both the final version of the translated and original English questionnaire to 242 bilingual crowd-workers to evaluate 14 ASAs. Results show on average a good level of correlation on the construct/dimension level (ICC M = 0.79, SD = 0.09, range [0.61, 0.95]) and on the item level (ICC M = 0.62, SD = 0.14, range [0.19, 0.92]) between the two languages for the long version, and for the short version (ICC M = 0.66, SD = 0.12, range [0.41, 0.92]). The analysis also established correction values for converting questionnaire item scores between Chinese and English questionnaires. Moreover, we also found systematic differences in English questionnaire scores between the bilingual sample and a previously collected mixed-international English-speaking sample. We hope this and the Chinese questionnaire translation will motivate researchers to study human-ASA interaction among a Chinese literate population and to study cultural similarities and differences in this area.
人工-社会-代理(ASA)问卷是评估人类-社会-代理互动的工具。它由19个构式和相关维度组成，由24个问卷项目(短版)或90个问卷项目(长版)测量。调查问卷是由一个研究团体努力建立和验证的，以使评估结果在药物和发现之间更具可比性。目前的调查问卷是用英语编写的，这限制了它的使用范围，只有掌握英语语言的人群才能使用。将调查问卷翻译成更多的语言，可以纳入其他人群，并有可能对他们进行比较。因此，本文提出了一份调查问卷的中文翻译。经过前向翻译和后向翻译的三个构建周期，我们将翻译后的最终版本和原始英文问卷交给了242名双语人群工作者，以评估14个asa。结果显示，两种语言在长版本和短版本(ICC M = 0.66, SD = 0.12，范围[0.41,0.92])的结构/维度水平(ICC M = 0.79, SD = 0.09，范围[0.61,0.95])和项目水平(ICC M = 0.62, SD = 0.14，范围[0.19,0.92])上平均具有良好的相关性。分析还建立了中英文问卷项目得分转换的校正值。此外，我们还发现双语样本与先前收集的混合国际英语样本之间的英语问卷得分存在系统性差异。我们希望这一发现和中文问卷翻译能够激励研究人员在中国识字人群中研究人类与asa的互动，并研究这一领域的文化异同。
{"title":"Mandarin Chinese translation of the Artificial-Social-Agent questionnaire instrument for evaluating human-agent interaction","authors":"Fengxiang Li, Siska Fitrianie, Merijn Bruijnes, Amal Abdulrahman, Fu Guo, Willem-Paul Brinkman","doi":"10.3389/fcomp.2023.1149305","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1149305","url":null,"abstract":"The Artificial-Social-Agent (ASA) questionnaire is an instrument for evaluating human-ASA interaction. It consists of 19 constructs and related dimensions measured by either 24 questionnaire items (short version) or 90 questionnaire items (long version). The questionnaire was built and validated by a research community effort to make evaluation results more comparable between agents and findings more generalizable. The current questionnaire is in English, which limits its use to only a population with an adequate command of the English language. Translating the questionnaire into more languages allows for the inclusion of other populations and the possibility of comparing them. Therefore, this paper presents a Mandarin Chinese translation of the questionnaire. After three construction cycles that included forward and backward translation, we gave both the final version of the translated and original English questionnaire to 242 bilingual crowd-workers to evaluate 14 ASAs. Results show on average a good level of correlation on the construct/dimension level (ICC M = 0.79, SD = 0.09, range [0.61, 0.95]) and on the item level (ICC M = 0.62, SD = 0.14, range [0.19, 0.92]) between the two languages for the long version, and for the short version (ICC M = 0.66, SD = 0.12, range [0.41, 0.92]). The analysis also established correction values for converting questionnaire item scores between Chinese and English questionnaires. Moreover, we also found systematic differences in English questionnaire scores between the bilingual sample and a previously collected mixed-international English-speaking sample. We hope this and the Chinese questionnaire translation will motivate researchers to study human-ASA interaction among a Chinese literate population and to study cultural similarities and differences in this area.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136103968","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：