Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665682
Yu-Wei Wen, Chuan-Kang Ting
Facility layout exerts a significant effect on factory operations and performance. Layout problems and floorplanning problems have been studied in the past decades. These problems typically involve locating objects of various sizes in a space for a certain objective. This paper presents a novel layout problem formulation, called the constrained facility layout problem (CFLP), aiming to find the layout with minimal covering area and connection length. In addition, the CFLP includes a hard constraint on the spatial clearance and a soft constraint on the geometrically relative order. The movability of objects is further considered in the CFLP. The formulation of CFLP is pertinent to industrial cases. To solve the CFLP, we adopt the covariance matrix adaptation evolution strategy (CMAES), a powerful evolutionary algorithm on numerical optimization. The proposed CFLP formulation and CMAES are utilized to solve the real-world facility layout problems of CTCI Corporation, which is a world-leading engineering services provider. The results show the high capability and advantages of the proposed approach in producing satisfactory layouts within very competitive time cost, in comparison to the layouts generated by human experts.
{"title":"Designing Facility Layouts with Hard and Soft Constraints by Evolutionary Algorithm","authors":"Yu-Wei Wen, Chuan-Kang Ting","doi":"10.1109/AI4I.2018.8665682","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665682","url":null,"abstract":"Facility layout exerts a significant effect on factory operations and performance. Layout problems and floorplanning problems have been studied in the past decades. These problems typically involve locating objects of various sizes in a space for a certain objective. This paper presents a novel layout problem formulation, called the constrained facility layout problem (CFLP), aiming to find the layout with minimal covering area and connection length. In addition, the CFLP includes a hard constraint on the spatial clearance and a soft constraint on the geometrically relative order. The movability of objects is further considered in the CFLP. The formulation of CFLP is pertinent to industrial cases. To solve the CFLP, we adopt the covariance matrix adaptation evolution strategy (CMAES), a powerful evolutionary algorithm on numerical optimization. The proposed CFLP formulation and CMAES are utilized to solve the real-world facility layout problems of CTCI Corporation, which is a world-leading engineering services provider. The results show the high capability and advantages of the proposed approach in producing satisfactory layouts within very competitive time cost, in comparison to the layouts generated by human experts.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124117197","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 : 2018-09-01DOI: 10.1109/AI4I.2018.8665692
Vagelis Hristidis
Chatbots have recently become popular due to the widespread use of messaging services and the advancement of Natural Language Understanding. In this tutorial, we give an overview of the technologies that drive chatbots, including Information Extraction and Deep Learning. We also discuss the differences between conversational and transactional chatbots - the former are trained on free-form chat logs, whereas the latter are defined manually to achieve a specific goal like booking a flight. We also provide an overview of commercial tools and platforms that can help in creating and deploying chatbots. Finally, we present the limitations and future work challenges in this area.
{"title":"Chatbot Technologies and Challenges","authors":"Vagelis Hristidis","doi":"10.1109/AI4I.2018.8665692","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665692","url":null,"abstract":"Chatbots have recently become popular due to the widespread use of messaging services and the advancement of Natural Language Understanding. In this tutorial, we give an overview of the technologies that drive chatbots, including Information Extraction and Deep Learning. We also discuss the differences between conversational and transactional chatbots - the former are trained on free-form chat logs, whereas the latter are defined manually to achieve a specific goal like booking a flight. We also provide an overview of commercial tools and platforms that can help in creating and deploying chatbots. Finally, we present the limitations and future work challenges in this area.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129107956","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 : 2018-09-01DOI: 10.1109/ai4i.2018.8665710
{"title":"Ai4i 2018 Program Committee","authors":"","doi":"10.1109/ai4i.2018.8665710","DOIUrl":"https://doi.org/10.1109/ai4i.2018.8665710","url":null,"abstract":"","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121049986","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 : 2018-09-01DOI: 10.1109/AI4I.2018.8665698
Louis B. Rosenberg, G. Willcox, David A. Askay, L. Metcalf, Erick Harris
Artificial Swarm Intelligence (ASI) is a method for amplifying the collective intelligence of human groups by connecting networked participants into real-time systems modeled after natural swarms and moderated by AI algorithms. ASI has been shown to amplify performance in a wide range of tasks, from forecasting financial markets to prioritizing conflicting objectives. This study explores the ability of ASI systems to amplify the social intelligence of small teams. A set of 61 teams, each of 3 to 6 members, was administered a standard social sensitivity test -“Reading the Mind in the Eyes” or RME. Subjects took the test both as individuals and as ASI systems (i.e. “swarms”). The average individual scored 24 of 35 correct (32% error) on the RME test, while the average ASI swarm scored 30 of 35 correct (15% error). Statistical analysis found that the groups working as ASI swarms had significantly higher social sensitivity than individuals working alone or groups working together by plurality vote (p
{"title":"Amplifying the Social Intelligence of Teams Through Human Swarming","authors":"Louis B. Rosenberg, G. Willcox, David A. Askay, L. Metcalf, Erick Harris","doi":"10.1109/AI4I.2018.8665698","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665698","url":null,"abstract":"Artificial Swarm Intelligence (ASI) is a method for amplifying the collective intelligence of human groups by connecting networked participants into real-time systems modeled after natural swarms and moderated by AI algorithms. ASI has been shown to amplify performance in a wide range of tasks, from forecasting financial markets to prioritizing conflicting objectives. This study explores the ability of ASI systems to amplify the social intelligence of small teams. A set of 61 teams, each of 3 to 6 members, was administered a standard social sensitivity test -“Reading the Mind in the Eyes” or RME. Subjects took the test both as individuals and as ASI systems (i.e. “swarms”). The average individual scored 24 of 35 correct (32% error) on the RME test, while the average ASI swarm scored 30 of 35 correct (15% error). Statistical analysis found that the groups working as ASI swarms had significantly higher social sensitivity than individuals working alone or groups working together by plurality vote (p<O.OOI). This suggests that when groups reach decisions as real-time ASI swarms, they make better use of their social intelligence than when working alone or by traditional group vote.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123137515","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 : 2018-09-01DOI: 10.1109/AI4I.2018.8665695
Jun Jo, Y. Lee, Jongwoon Hwang
Graphical representation of correlated multi-channel time series signal is studied in this paper. With the proposed multi-layer nested scatter plot (NSP), we can compress multichannel time series signals into static sized data and can obtain advantages inherent in scatter plots.
{"title":"Multi-Layer Nested Scatter Plot a Data Wrangling Method for Correlated Multi-Channel Time Series Signals","authors":"Jun Jo, Y. Lee, Jongwoon Hwang","doi":"10.1109/AI4I.2018.8665695","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665695","url":null,"abstract":"Graphical representation of correlated multi-channel time series signal is studied in this paper. With the proposed multi-layer nested scatter plot (NSP), we can compress multichannel time series signals into static sized data and can obtain advantages inherent in scatter plots.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117338934","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 : 2018-09-01DOI: 10.1109/AI4I.2018.8665684
Jake Fitzsimmons, P. Moscato
Big pharmaceutical companies require to innovate by applying new machine learning and artificial intelligence methods to understand the large datasets produced by high-throughput technologies. In addition to reduce development costs for these industries, regression and classification models of drug response are needed for the final quest of delivering personalized treatment for cancer. An emphasis exists in developing models that allow for both prediction and ease of interpretation. In this contribution we present results obtained by symbolic regression. We employ a public domain dataset of drug responses on a large cancer cell line panel and compare with a previous method based on binarization of the response data and the use of integer linear programming to find logic models. We present derived models of drug response for the drugs Afatinib, Dactolisib (BEZ235), Cytarabine, and Paclitaxel as well as for AZD6244, JQ12, KIN001-102, and PLX4720. We provide indication of the interpretability with a biological analysis of the results for Afatnib and Dactolisib, showing that our models introduce variables that point at known mechanisms of action of these drugs.
{"title":"Symbolic Regression Modeling of Drug Responses","authors":"Jake Fitzsimmons, P. Moscato","doi":"10.1109/AI4I.2018.8665684","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665684","url":null,"abstract":"Big pharmaceutical companies require to innovate by applying new machine learning and artificial intelligence methods to understand the large datasets produced by high-throughput technologies. In addition to reduce development costs for these industries, regression and classification models of drug response are needed for the final quest of delivering personalized treatment for cancer. An emphasis exists in developing models that allow for both prediction and ease of interpretation. In this contribution we present results obtained by symbolic regression. We employ a public domain dataset of drug responses on a large cancer cell line panel and compare with a previous method based on binarization of the response data and the use of integer linear programming to find logic models. We present derived models of drug response for the drugs Afatinib, Dactolisib (BEZ235), Cytarabine, and Paclitaxel as well as for AZD6244, JQ12, KIN001-102, and PLX4720. We provide indication of the interpretability with a biological analysis of the results for Afatnib and Dactolisib, showing that our models introduce variables that point at known mechanisms of action of these drugs.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133898476","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 : 2018-09-01DOI: 10.1109/AI4I.2018.8665688
Xinyuan Huang, Amit Kumar Saha, Debojyoti Dutta, Ce Gao
Machine Learning (ML) workloads are becoming mainstream in the enterprise but the plethora of choices around ML toolkits and multi-cloud infrastructure make it difficult to compare their performance and costs. In this paper, we motivate the need for benchmarking ML systems in a consistent way, discuss the requirements of an ML benchmarking platform, and propose a design that satisfies the requirements. We present Kubebench, an example open-source implementation of an ML benchmarking platform based on Kubeflow, itself an open-source project for managing any ML stack on Kubernetes, a widely used container management platform.
{"title":"Kubebench: A Benchmarking Platform for ML Workloads","authors":"Xinyuan Huang, Amit Kumar Saha, Debojyoti Dutta, Ce Gao","doi":"10.1109/AI4I.2018.8665688","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665688","url":null,"abstract":"Machine Learning (ML) workloads are becoming mainstream in the enterprise but the plethora of choices around ML toolkits and multi-cloud infrastructure make it difficult to compare their performance and costs. In this paper, we motivate the need for benchmarking ML systems in a consistent way, discuss the requirements of an ML benchmarking platform, and propose a design that satisfies the requirements. We present Kubebench, an example open-source implementation of an ML benchmarking platform based on Kubeflow, itself an open-source project for managing any ML stack on Kubernetes, a widely used container management platform.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132838822","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 : 2018-09-01DOI: 10.1109/AI4I.2018.8665686
Rua Alsuroji, N. Bouguila, Nuha Zamzami
Effective prediction of defect-prone software modules enables software developers to avoid the expensive costs in resources and efforts they might expense, and focus efficiently on quality assurance activities. Different classification methods have been applied previously to categorize a module in a system into two classes; defective or non-defective. Among the successful approaches, finite mixture modeling has been efficiently applied for solving this problem. This paper proposes the shifted-scaled Dirichlet model (SSDM) and evaluates its capability in predicting defect-prone software modules in the context of four NASA datasets. The results indicate that the prediction performance of SSDM is competitive to some previously used generative models.
{"title":"Predicting Defect-Prone Software Modules Using Shifted-Scaled Dirichlet Distribution","authors":"Rua Alsuroji, N. Bouguila, Nuha Zamzami","doi":"10.1109/AI4I.2018.8665686","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665686","url":null,"abstract":"Effective prediction of defect-prone software modules enables software developers to avoid the expensive costs in resources and efforts they might expense, and focus efficiently on quality assurance activities. Different classification methods have been applied previously to categorize a module in a system into two classes; defective or non-defective. Among the successful approaches, finite mixture modeling has been efficiently applied for solving this problem. This paper proposes the shifted-scaled Dirichlet model (SSDM) and evaluates its capability in predicting defect-prone software modules in the context of four NASA datasets. The results indicate that the prediction performance of SSDM is competitive to some previously used generative models.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131105229","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 : 2018-09-01DOI: 10.1109/AI4I.2018.8665696
Chia-Ruei Liu, L. Duan, Po-Wei Chen, Chao-Chun Yang
Using the three-dimensional acceleration sensor and the current sensor to collect vibration data and current data to get information from machine tools without Programmable Logic Controller(PLC) is the direct method. Processing the data by characteristic extraction engineering, and building models by machine learning algorithms. So it can identify the status of machine tools from this models accurately. Then, it can help the small-and medium sized enterprises to monitor machine tools with high scalability and portability.
{"title":"Monitoring Machine Tool Based on External Physical Characteristics of the Machine Tool Using Machine Learning Algorithm","authors":"Chia-Ruei Liu, L. Duan, Po-Wei Chen, Chao-Chun Yang","doi":"10.1109/AI4I.2018.8665696","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665696","url":null,"abstract":"Using the three-dimensional acceleration sensor and the current sensor to collect vibration data and current data to get information from machine tools without Programmable Logic Controller(PLC) is the direct method. Processing the data by characteristic extraction engineering, and building models by machine learning algorithms. So it can identify the status of machine tools from this models accurately. Then, it can help the small-and medium sized enterprises to monitor machine tools with high scalability and portability.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122829401","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 : 2018-09-01DOI: 10.1109/AI4I.2018.8665701
Jérôme Mendes, Ricardo Maia, R. Araújo, G. Gouveia
This paper proposes a self-evolving intelligent controller, tested under a proof of concept of a purely virtual test platform for critical cyberphysical systems in closed-loop. The controller is a fuzzy logic controller, whose structure is designed offline using only the information of the range of the variables, and then, it is online designed in an evolving way, where parameters are adjusted, and new control rules are added based on a novelty detection criterion. The controller is tested on a Two-Tank system in a closed-loop networked environmentunder a proof-of-concept platform for testing cyberphysical systems, named KhronoSim. The proposed self-evolving controller has been successfully evolved/designed, controlling the system on initially unknown regions of operation.
{"title":"Intelligent Controller for Industrial Processes Applied to a Distributed Two-Tank System","authors":"Jérôme Mendes, Ricardo Maia, R. Araújo, G. Gouveia","doi":"10.1109/AI4I.2018.8665701","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665701","url":null,"abstract":"This paper proposes a self-evolving intelligent controller, tested under a proof of concept of a purely virtual test platform for critical cyberphysical systems in closed-loop. The controller is a fuzzy logic controller, whose structure is designed offline using only the information of the range of the variables, and then, it is online designed in an evolving way, where parameters are adjusted, and new control rules are added based on a novelty detection criterion. The controller is tested on a Two-Tank system in a closed-loop networked environmentunder a proof-of-concept platform for testing cyberphysical systems, named KhronoSim. The proposed self-evolving controller has been successfully evolved/designed, controlling the system on initially unknown regions of operation.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125875790","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：