Pub Date : 2022-12-13DOI: 10.48550/arXiv.2212.06451
Olivier Moulin, Vincent François-Lavet, M. Hoogendoorn
An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments. In such an approach, new agents are regularly added to the eco-system when encountering a new environment that is outside of the scope of the eco-system. The speed of adaptation and general effectiveness of the eco-system approach highly depends on the initialization of new agents. In this paper we propose different initialization techniques, inspired from Deep Neural Network initialization and transfer learning, and study their impact.
{"title":"Improving generalization in reinforcement learning through forked agents","authors":"Olivier Moulin, Vincent François-Lavet, M. Hoogendoorn","doi":"10.48550/arXiv.2212.06451","DOIUrl":"https://doi.org/10.48550/arXiv.2212.06451","url":null,"abstract":"An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments. In such an approach, new agents are regularly added to the eco-system when encountering a new environment that is outside of the scope of the eco-system. The speed of adaptation and general effectiveness of the eco-system approach highly depends on the initialization of new agents. In this paper we propose different initialization techniques, inspired from Deep Neural Network initialization and transfer learning, and study their impact.","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122333304","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 : 2022-04-04DOI: 10.48550/arXiv.2204.01292
C. Wehner, Francis Powlesland, Bashar Altakrouri, Ute Schmid
Artificial Intelligence and Digital Twins play an integral role in driving innovation in the domain of intelligent driving. Long short-term memory (LSTM) is a leading driver in the field of lane change prediction for manoeuvre anticipation. However, the decision-making process of such models is complex and non-transparent, hence reducing the trustworthiness of the smart solution. This work presents an innovative approach and a technical implementation for explaining lane change predictions of layer normalized LSTMs using Layer-wise Relevance Propagation (LRP). The core implementation includes consuming live data from a digital twin on a German highway, live predictions and explanations of lane changes by extending LRP to layer normalized LSTMs, and an interface for communicating and explaining the predictions to a human user. We aim to demonstrate faithful, understandable, and adaptable explanations of lane change prediction to increase the adoption and trustworthiness of AI systems that involve humans. Our research also emphases that explainability and state-of-the-art performance of ML models for manoeuvre anticipation go hand in hand without negatively affecting predictive effectiveness.
{"title":"Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagation","authors":"C. Wehner, Francis Powlesland, Bashar Altakrouri, Ute Schmid","doi":"10.48550/arXiv.2204.01292","DOIUrl":"https://doi.org/10.48550/arXiv.2204.01292","url":null,"abstract":"Artificial Intelligence and Digital Twins play an integral role in driving innovation in the domain of intelligent driving. Long short-term memory (LSTM) is a leading driver in the field of lane change prediction for manoeuvre anticipation. However, the decision-making process of such models is complex and non-transparent, hence reducing the trustworthiness of the smart solution. This work presents an innovative approach and a technical implementation for explaining lane change predictions of layer normalized LSTMs using Layer-wise Relevance Propagation (LRP). The core implementation includes consuming live data from a digital twin on a German highway, live predictions and explanations of lane changes by extending LRP to layer normalized LSTMs, and an interface for communicating and explaining the predictions to a human user. We aim to demonstrate faithful, understandable, and adaptable explanations of lane change prediction to increase the adoption and trustworthiness of AI systems that involve humans. Our research also emphases that explainability and state-of-the-art performance of ML models for manoeuvre anticipation go hand in hand without negatively affecting predictive effectiveness.","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116794098","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 : 2022-03-28DOI: 10.1007/978-3-030-79457-6_33
A. Priyadarshi, K. Kochut
{"title":"WawPart: Workload-Aware Partitioning of Knowledge Graphs","authors":"A. Priyadarshi, K. Kochut","doi":"10.1007/978-3-030-79457-6_33","DOIUrl":"https://doi.org/10.1007/978-3-030-79457-6_33","url":null,"abstract":"","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"1068 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123167826","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 : 2022-03-18DOI: 10.48550/arXiv.2203.09663
Van-Tu Ninh, Manh-Duy Nguyen, Sinéad Smyth, Minh-Triet Tran, G. Healy, Binh T. Nguyen, C. Gurrin
Stress is a complex issue with wide-ranging physical and psychological impacts on human daily performance. Specifically, acute stress detection is becoming a valuable application in contextual human understanding. Two common approaches to training a stress detection model are subject-dependent and subject-independent training methods. Although subject-dependent training methods have proven to be the most accurate approach to build stress detection models, subject-independent models are a more practical and cost-efficient method, as they allow for the deployment of stress level detection and management systems in consumer-grade wearable devices without requiring training data for the end-user. To improve the performance of subject-independent stress detection models, in this paper, we introduce a stress-related bio-signal processing pipeline with a simple neural network architecture using statistical features extracted from multimodal contextual sensing sources including Electrodermal Activity (EDA), Blood Volume Pulse (BVP), and Skin Temperature (ST) captured from a consumer-grade wearable device. Using our proposed model architecture, we compare the accuracy between stress detection models that use measures from each individual signal source, and one model employing the fusion of multiple sensor sources. Extensive experiments on the publicly available WESAD dataset demonstrate that our proposed model outperforms conventional methods as well as providing 1.63% higher mean accuracy score compared to the state-of-the-art model while maintaining a low standard deviation. Our experiments also show that combining features from multiple sources produce more accurate predictions than using only one sensor source individually.
{"title":"An Improved Subject-Independent Stress Detection Model Applied to Consumer-grade Wearable Devices","authors":"Van-Tu Ninh, Manh-Duy Nguyen, Sinéad Smyth, Minh-Triet Tran, G. Healy, Binh T. Nguyen, C. Gurrin","doi":"10.48550/arXiv.2203.09663","DOIUrl":"https://doi.org/10.48550/arXiv.2203.09663","url":null,"abstract":"Stress is a complex issue with wide-ranging physical and psychological impacts on human daily performance. Specifically, acute stress detection is becoming a valuable application in contextual human understanding. Two common approaches to training a stress detection model are subject-dependent and subject-independent training methods. Although subject-dependent training methods have proven to be the most accurate approach to build stress detection models, subject-independent models are a more practical and cost-efficient method, as they allow for the deployment of stress level detection and management systems in consumer-grade wearable devices without requiring training data for the end-user. To improve the performance of subject-independent stress detection models, in this paper, we introduce a stress-related bio-signal processing pipeline with a simple neural network architecture using statistical features extracted from multimodal contextual sensing sources including Electrodermal Activity (EDA), Blood Volume Pulse (BVP), and Skin Temperature (ST) captured from a consumer-grade wearable device. Using our proposed model architecture, we compare the accuracy between stress detection models that use measures from each individual signal source, and one model employing the fusion of multiple sensor sources. Extensive experiments on the publicly available WESAD dataset demonstrate that our proposed model outperforms conventional methods as well as providing 1.63% higher mean accuracy score compared to the state-of-the-art model while maintaining a low standard deviation. Our experiments also show that combining features from multiple sources produce more accurate predictions than using only one sensor source individually.","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114436178","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 : 2021-07-26DOI: 10.1007/978-3-030-79457-6_3
R. Penugonda, Likhitha Palla, Uday Kiran Rage, Y. Watanobe, K. Zettsu
{"title":"Towards Efficient Discovery of Periodic-Frequent Patterns in Columnar Temporal Databases","authors":"R. Penugonda, Likhitha Palla, Uday Kiran Rage, Y. Watanobe, K. Zettsu","doi":"10.1007/978-3-030-79457-6_3","DOIUrl":"https://doi.org/10.1007/978-3-030-79457-6_3","url":null,"abstract":"","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132354743","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 : 2021-07-26DOI: 10.1007/978-3-030-79457-6_16
Iker Esnaola-Gonzalez, Unai Garciarena, J. Bermúdez
{"title":"Semantic Technologies Towards Missing Values Imputation","authors":"Iker Esnaola-Gonzalez, Unai Garciarena, J. Bermúdez","doi":"10.1007/978-3-030-79457-6_16","DOIUrl":"https://doi.org/10.1007/978-3-030-79457-6_16","url":null,"abstract":"","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133951690","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 : 2021-07-07DOI: 10.1007/978-3-030-79457-6_51
Quan Duong, Dang-Quan Nguyen, Q. Nguyen
{"title":"Hub and Spoke Logistics Network Design for Urban Region with Clustering-Based Approach","authors":"Quan Duong, Dang-Quan Nguyen, Q. Nguyen","doi":"10.1007/978-3-030-79457-6_51","DOIUrl":"https://doi.org/10.1007/978-3-030-79457-6_51","url":null,"abstract":"","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123676532","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 : 2021-04-06DOI: 10.1007/978-3-030-79457-6_4
H. Jayasinghe, Tarindu Jayatilaka, Ravin Gunawardena, Uthayasanker Thayasivam
{"title":"Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning","authors":"H. Jayasinghe, Tarindu Jayatilaka, Ravin Gunawardena, Uthayasanker Thayasivam","doi":"10.1007/978-3-030-79457-6_4","DOIUrl":"https://doi.org/10.1007/978-3-030-79457-6_4","url":null,"abstract":"","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124107487","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 : 2021-03-18DOI: 10.1007/978-3-030-79457-6_49
Luan Thanh Nguyen, Kiet Van Nguyen, N. Nguyen
{"title":"Constructive and Toxic Speech Detection for Open-domain Social Media Comments in Vietnamese","authors":"Luan Thanh Nguyen, Kiet Van Nguyen, N. Nguyen","doi":"10.1007/978-3-030-79457-6_49","DOIUrl":"https://doi.org/10.1007/978-3-030-79457-6_49","url":null,"abstract":"","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128112351","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 : 2020-09-22DOI: 10.1007/978-3-030-55789-8_49
Dai Tho Dang, Z. Mazur, D. Hwang
{"title":"A New Approach to Determine 2-Optimality Consensus for Collectives","authors":"Dai Tho Dang, Z. Mazur, D. Hwang","doi":"10.1007/978-3-030-55789-8_49","DOIUrl":"https://doi.org/10.1007/978-3-030-55789-8_49","url":null,"abstract":"","PeriodicalId":357450,"journal":{"name":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125146681","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：