Pub Date : 2023-12-13DOI: 10.3389/fcomp.2023.1341692
Andrea Szymkowiak, Lynsay A. Shepherd, Jason R. C. Nurse, P. Brauner, Martina Ziefle
{"title":"Editorial: Technology for the greater good? The influence of (ir)responsible systems on human emotions, thinking and behavior","authors":"Andrea Szymkowiak, Lynsay A. Shepherd, Jason R. C. Nurse, P. Brauner, Martina Ziefle","doi":"10.3389/fcomp.2023.1341692","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1341692","url":null,"abstract":"","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":"48 9","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139006052","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}
In materials informatics, searching for chemical materials with desired properties is challenging due to the vastness of the chemical space. Moreover, the high cost of evaluating properties necessitates a search with a few clues. In practice, there is also a demand for proposing compositions that are easily synthesizable. In the real world, such as in the exploration of chemical materials, it is common to encounter problems targeting black-box objective functions where formalizing the objective function in explicit form is challenging, and the evaluation cost is high. In recent research, a Bayesian optimization method has been proposed to formulate the quadratic unconstrained binary optimization (QUBO) problem as a surrogate model for black-box objective functions with discrete variables. Regarding this method, studies have been conducted using the D-Wave quantum annealer to optimize the acquisition function, which is based on the surrogate model and determines the next exploration point for the black-box objective function. In this paper, we address optimizing a black-box objective function containing discrete variables in the context of actual chemical material exploration. In this optimization problem, we demonstrate results obtaining parameters of the acquisition function by sampling from a probability distribution with variance can explore the solution space more extensively than in the case of no variance. As a result, we found combinations of substituents in compositions with the desired properties, which could only be discovered when we set an appropriate variance.
{"title":"Exploration of new chemical materials using black-box optimization with the D-wave quantum annealer","authors":"Mikiya Doi, Yoshihiro Nakao, Takuro Tanaka, Masami Sako, Masayuki Ohzeki","doi":"10.3389/fcomp.2023.1286226","DOIUrl":"https://doi.org/10.3389/fcomp.2023.1286226","url":null,"abstract":"In materials informatics, searching for chemical materials with desired properties is challenging due to the vastness of the chemical space. Moreover, the high cost of evaluating properties necessitates a search with a few clues. In practice, there is also a demand for proposing compositions that are easily synthesizable. In the real world, such as in the exploration of chemical materials, it is common to encounter problems targeting black-box objective functions where formalizing the objective function in explicit form is challenging, and the evaluation cost is high. In recent research, a Bayesian optimization method has been proposed to formulate the quadratic unconstrained binary optimization (QUBO) problem as a surrogate model for black-box objective functions with discrete variables. Regarding this method, studies have been conducted using the D-Wave quantum annealer to optimize the acquisition function, which is based on the surrogate model and determines the next exploration point for the black-box objective function. In this paper, we address optimizing a black-box objective function containing discrete variables in the context of actual chemical material exploration. In this optimization problem, we demonstrate results obtaining parameters of the acquisition function by sampling from a probability distribution with variance can explore the solution space more extensively than in the case of no variance. As a result, we found combinations of substituents in compositions with the desired properties, which could only be discovered when we set an appropriate variance.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":"47 16","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139006981","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.2023.1304590
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":"29 1","pages":""},"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":"62 3","pages":""},"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":"63 7","pages":""},"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":"83 20","pages":""},"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":"126 32","pages":""},"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":"58 S8","pages":"0"},"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":"177 3","pages":"0"},"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":"28 19","pages":"0"},"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}