Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00141
Yann Bernard, Emeline Buoy, Adrien Fois, B. Girau
Self-organizing maps (SOM) are a well-known and biologically plausible model of input-driven self-organization that has shown to be effective in a wide range of applications. We want to use SOMs to control the processing cores of a massively parallel digital reconfigurable hardware, taking into account the communication constraints of its underlying network-on-chip (NoC) thanks to bio-inspired principles of structural plasticity. Although the SOM accounts for synaptic plasticity, it doesn't address structural plasticity. Therefore we have developed a model, namely the NP-SOM (network programmable self-organizing map), able to define SOMs with different underlying topologies as the result of a specific configuration of the associated NoC. To gain insights on a future introduction of advanced structural plasticity rules that will induce dynamic topological modifications, we investigate and quantify the effects of different hardware-compatible topologies on the SOM performance. To perform our tests we consider a lossy image compression as an illustrative application.
{"title":"NP-SOM: Network Programmable Self-Organizing Maps","authors":"Yann Bernard, Emeline Buoy, Adrien Fois, B. Girau","doi":"10.1109/ICTAI.2018.00141","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00141","url":null,"abstract":"Self-organizing maps (SOM) are a well-known and biologically plausible model of input-driven self-organization that has shown to be effective in a wide range of applications. We want to use SOMs to control the processing cores of a massively parallel digital reconfigurable hardware, taking into account the communication constraints of its underlying network-on-chip (NoC) thanks to bio-inspired principles of structural plasticity. Although the SOM accounts for synaptic plasticity, it doesn't address structural plasticity. Therefore we have developed a model, namely the NP-SOM (network programmable self-organizing map), able to define SOMs with different underlying topologies as the result of a specific configuration of the associated NoC. To gain insights on a future introduction of advanced structural plasticity rules that will induce dynamic topological modifications, we investigate and quantify the effects of different hardware-compatible topologies on the SOM performance. To perform our tests we consider a lossy image compression as an illustrative application.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115148291","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 : 2018-11-01DOI: 10.1109/ICTAI.2018.00149
G. Anand, R. Nayak
With the advancements in computing and location-acquisition technologies, large volumes of spatio-temporal tra-jectory data are being generated and stored. Anomaly detection in trajectory data is significant for several applications. Using a data-driven spatio-temporal context in the form of geographical sub-regions and different time-periods can enhance the relevance of detected anomalies. We propose a novel scalable contextual anomaly detection method for trajectory data using the regional density information. The effectiveness and scalability of the proposed method is shown through the empirical analysis and benchmarking with the state-of-the-art method.
{"title":"Contextual Anomaly Detection in Spatio-Temporal Data Using Locally Dense Regions","authors":"G. Anand, R. Nayak","doi":"10.1109/ICTAI.2018.00149","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00149","url":null,"abstract":"With the advancements in computing and location-acquisition technologies, large volumes of spatio-temporal tra-jectory data are being generated and stored. Anomaly detection in trajectory data is significant for several applications. Using a data-driven spatio-temporal context in the form of geographical sub-regions and different time-periods can enhance the relevance of detected anomalies. We propose a novel scalable contextual anomaly detection method for trajectory data using the regional density information. The effectiveness and scalability of the proposed method is shown through the empirical analysis and benchmarking with the state-of-the-art method.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125821467","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 : 2018-11-01DOI: 10.1109/ICTAI.2018.00080
Cosmin Pascaru, Paul Diac
We propose our solution to a particular practical problem in the domain of vehicle routing and scheduling. The generic task is finding the best allocation of minimum number of mobile resources that can provide periodical services in remote locations. These mobile resources are based at a single central location. Specifications have been defined initially for a real-life application that is the starting point of an ongoing project. Particularly, the goal is to mitigate health problems in rural areas around a city in Romania. Medically equipped vans are programmed to start daily routes from county capital, provide a given number of examinations in townships within the county and return to the capital city in the same day. From healthcare perspective, each van is equipped with an ultrasound scanner and they are scheduled to investigate pregnant woman each trimester aiming to diagnose potential problems. The project is motivated by reports currently ranking Romania as the country with the highest infant mortality rate in European Union. Our solution was developed in two phases: first modeling of the most relevant parameters and data available for our goal and second, design and implement an algorithm that provides an optimized solution. The most important metric of a scheduling is the number of vans that are necessary to provide a given amount of examination time per township, followed by total travel time or fuel consumption, number of different routes, etc. Our solution implements two probabilistic algorithms out of which the best was chosen.
{"title":"Vehicle Routing and Scheduling for Regular Mobile Healthcare Services","authors":"Cosmin Pascaru, Paul Diac","doi":"10.1109/ICTAI.2018.00080","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00080","url":null,"abstract":"We propose our solution to a particular practical problem in the domain of vehicle routing and scheduling. The generic task is finding the best allocation of minimum number of mobile resources that can provide periodical services in remote locations. These mobile resources are based at a single central location. Specifications have been defined initially for a real-life application that is the starting point of an ongoing project. Particularly, the goal is to mitigate health problems in rural areas around a city in Romania. Medically equipped vans are programmed to start daily routes from county capital, provide a given number of examinations in townships within the county and return to the capital city in the same day. From healthcare perspective, each van is equipped with an ultrasound scanner and they are scheduled to investigate pregnant woman each trimester aiming to diagnose potential problems. The project is motivated by reports currently ranking Romania as the country with the highest infant mortality rate in European Union. Our solution was developed in two phases: first modeling of the most relevant parameters and data available for our goal and second, design and implement an algorithm that provides an optimized solution. The most important metric of a scheduling is the number of vans that are necessary to provide a given amount of examination time per township, followed by total travel time or fuel consumption, number of different routes, etc. Our solution implements two probabilistic algorithms out of which the best was chosen.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125542000","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 : 2018-11-01DOI: 10.1109/ICTAI.2018.00047
Yang Fan, Jungang Xu, Yingfei Sun, Ben He
Language models based on Recurrent Neural Networks, e.g. Long Short Term Memory Network (LSTM), have shown strong ability in generating captions from image. However, in previous LSTM-based image captioning models, the image information is input to LSTM at 0th time step, and the network gradually forgets the image information, and only uses the language model to generate a simple description, leaving the potential in generating a better description. To address this challenge, in this paper, a Long-term Recurrent Merge Network (LRMN) model is proposed to merge the image feature at each step via a language model, which not only can improve the accuracy of image captioning, but also can describe the image better. Experimental results show that the proposed LRMN model has a promising improvement in image captioning.
{"title":"Long-Term Recurrent Merge Network Model for Image Captioning","authors":"Yang Fan, Jungang Xu, Yingfei Sun, Ben He","doi":"10.1109/ICTAI.2018.00047","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00047","url":null,"abstract":"Language models based on Recurrent Neural Networks, e.g. Long Short Term Memory Network (LSTM), have shown strong ability in generating captions from image. However, in previous LSTM-based image captioning models, the image information is input to LSTM at 0th time step, and the network gradually forgets the image information, and only uses the language model to generate a simple description, leaving the potential in generating a better description. To address this challenge, in this paper, a Long-term Recurrent Merge Network (LRMN) model is proposed to merge the image feature at each step via a language model, which not only can improve the accuracy of image captioning, but also can describe the image better. Experimental results show that the proposed LRMN model has a promising improvement in image captioning.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126602974","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 : 2018-11-01DOI: 10.1109/ICTAI.2018.00087
M. Tsipouras, Dimosthenis C. Tsouros, Panagiotis N. Smyrlis, N. Giannakeas, A. Tzallas
In this paper, a novel stochastic approach for the induction of the decision trees in a tree-structured ensemble classifier is presented. The proposed algorithm is based on a stochastic process to induct each decision tree, assigning a probability for the selection of the split attribute in every tree node, designed in order to create strong and independent trees. A selection of 33 well-known classification datasets have been employed for the evaluation of the proposed algorithm, obtaining high classification results, in terms of Classification Accuracy, Average Sensitivity and Average Precision. Furthermore, a comparative study with Random Forest, Random Subspace and C4.5 is performed. The obtained results indicate the importance of the proposed algorithm, since it achieved the highest overall results in all metrics.
{"title":"Random Forests with Stochastic Induction of Decision Trees","authors":"M. Tsipouras, Dimosthenis C. Tsouros, Panagiotis N. Smyrlis, N. Giannakeas, A. Tzallas","doi":"10.1109/ICTAI.2018.00087","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00087","url":null,"abstract":"In this paper, a novel stochastic approach for the induction of the decision trees in a tree-structured ensemble classifier is presented. The proposed algorithm is based on a stochastic process to induct each decision tree, assigning a probability for the selection of the split attribute in every tree node, designed in order to create strong and independent trees. A selection of 33 well-known classification datasets have been employed for the evaluation of the proposed algorithm, obtaining high classification results, in terms of Classification Accuracy, Average Sensitivity and Average Precision. Furthermore, a comparative study with Random Forest, Random Subspace and C4.5 is performed. The obtained results indicate the importance of the proposed algorithm, since it achieved the highest overall results in all metrics.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115179575","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 : 2018-11-01DOI: 10.1109/ICTAI.2018.00131
Manish Puri, A. Varde, Xu Du, Gerard de Melo
This work focuses on the area of Smart Governance in Smart Cities, which entails transparency in government through public involvement. Specifically, it describes our research on mining urban ordinances or local laws and the public reactions to them expressed on the social media site Twitter. We mine ordinances and tweets related to each other through their mutual connection with Smart City Characteristics (SCCs) and conduct sentiment analysis of relevant tweets for analyzing opinions of the public on local laws in the given urban region. This helps assess how well that region heads towards a Smart City based on (1) how closely ordinances map to the respective SCCs and (2) the extent of public satisfaction on ordinances related to those SCCs. The mining process relies on Commonsense Knowledge (CSK), i.e., knowledge that is obvious to humans but needs to be explicitly fed into machines for automation. CSK is useful in filtering during tweet selection, conducting SCC-based ordinancetweet mapping and performing sentiment analysis of tweets. This paper presents our work in mapping ordinances to tweets through single or multiple SCCs and opinion mining of tweets along with an experimental evaluation and a discussion with useful recommendations.
这项工作的重点是智慧城市的智慧治理领域，这需要通过公众参与实现政府的透明度。具体来说，它描述了我们对采矿城市条例或地方法律的研究以及公众在社交媒体网站Twitter上表达的反应。我们通过与智慧城市特征(Smart City Characteristics, SCCs)的相互联系来挖掘彼此相关的法令和推文，并对相关推文进行情感分析，以分析公众对特定城市区域当地法律的意见。这有助于评估该地区向智慧城市迈进的程度，其依据是(1)各条例与相应的标准和准则的紧密程度，以及(2)公众对与这些标准和准则相关的条例的满意程度。挖掘过程依赖于常识知识(Commonsense Knowledge, CSK)，即对人类来说显而易见的知识，但需要明确地输入机器以实现自动化。CSK在tweet选择过程中的过滤，进行基于scc的条例tweet映射和对tweet进行情感分析方面非常有用。本文介绍了我们通过单个或多个scc和推文的意见挖掘将条例映射到推文方面的工作，并进行了实验评估和讨论，提出了有用的建议。
{"title":"Smart Governance Through Opinion Mining of Public Reactions on Ordinances","authors":"Manish Puri, A. Varde, Xu Du, Gerard de Melo","doi":"10.1109/ICTAI.2018.00131","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00131","url":null,"abstract":"This work focuses on the area of Smart Governance in Smart Cities, which entails transparency in government through public involvement. Specifically, it describes our research on mining urban ordinances or local laws and the public reactions to them expressed on the social media site Twitter. We mine ordinances and tweets related to each other through their mutual connection with Smart City Characteristics (SCCs) and conduct sentiment analysis of relevant tweets for analyzing opinions of the public on local laws in the given urban region. This helps assess how well that region heads towards a Smart City based on (1) how closely ordinances map to the respective SCCs and (2) the extent of public satisfaction on ordinances related to those SCCs. The mining process relies on Commonsense Knowledge (CSK), i.e., knowledge that is obvious to humans but needs to be explicitly fed into machines for automation. CSK is useful in filtering during tweet selection, conducting SCC-based ordinancetweet mapping and performing sentiment analysis of tweets. This paper presents our work in mapping ordinances to tweets through single or multiple SCCs and opinion mining of tweets along with an experimental evaluation and a discussion with useful recommendations.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122170538","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 : 2018-11-01DOI: 10.1109/ICTAI.2018.00147
Stefan Blumer, M. Eichelberger, Roger Wattenhofer
This paper presents an efficient traffic scheduling algorithm for vehicles such as cars, trains or ships. We provide guarantees for deadlock and starvation freedom, therefore ensuring progress for each vehicle in the system. Our method tolerates vehicles which do not disappear from the traffic network once they reach their destination, but rather continue towards subsequent destinations. Therefore, vehicles can run indefinitely. We introduce the concept of "safe spots", which are locations where a vehicle can stop without ever blocking another vehicle. Using such safe spots, we divide routes into short segments, which reduces the number of routing alternatives exponentially, thus allowing real-time traffic allocation.
{"title":"Efficient Traffic Routing with Progress Guarantees","authors":"Stefan Blumer, M. Eichelberger, Roger Wattenhofer","doi":"10.1109/ICTAI.2018.00147","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00147","url":null,"abstract":"This paper presents an efficient traffic scheduling algorithm for vehicles such as cars, trains or ships. We provide guarantees for deadlock and starvation freedom, therefore ensuring progress for each vehicle in the system. Our method tolerates vehicles which do not disappear from the traffic network once they reach their destination, but rather continue towards subsequent destinations. Therefore, vehicles can run indefinitely. We introduce the concept of \"safe spots\", which are locations where a vehicle can stop without ever blocking another vehicle. Using such safe spots, we divide routes into short segments, which reduces the number of routing alternatives exponentially, thus allowing real-time traffic allocation.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117251937","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 : 2018-11-01DOI: 10.1109/ictai.2018.00005
{"title":"Message from the ICTAI General Chairs","authors":"","doi":"10.1109/ictai.2018.00005","DOIUrl":"https://doi.org/10.1109/ictai.2018.00005","url":null,"abstract":"","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1994 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128636815","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 : 2018-11-01DOI: 10.1109/ICTAI.2018.00067
Jian Xu, Y. Wu, Ning Zheng, Liming Tu, Ming Luo
Business districts serve as basic structures for understanding the organization of real-world economic network. Discovering these business districts in cities establish new types of valuable applications that can benefit end users: Business investors can better identify the proximity of existing business districts and hence, can contribute a better future planning for investing. In this paper, we propose improved affinity propagation clustering for business districts mining. Given check-in data, whose geography information represents business venues' location, we introduce a affinity propagation clustering algorithm(AP), a basic solution, to cluster venues. This strategy requires that real-valued messages are exchanged among business venues until a set of centers and corresponding business districts gradually emerges. However, the computational complexity of AP is affected by the scale of input. And it's not adaptive for random distribution of venues when mining business districts. To conduct business districts mining efficiently, we introduce a pruning method, termed as PAP. And then present merging based mine approach, termed as MAP. We conduct experiments from Yelp data, and experimental results show that our proposed method outperforms the basic solutions and resolves the problem well.
{"title":"Improved Affinity Propagation Clustering for Business Districts Mining","authors":"Jian Xu, Y. Wu, Ning Zheng, Liming Tu, Ming Luo","doi":"10.1109/ICTAI.2018.00067","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00067","url":null,"abstract":"Business districts serve as basic structures for understanding the organization of real-world economic network. Discovering these business districts in cities establish new types of valuable applications that can benefit end users: Business investors can better identify the proximity of existing business districts and hence, can contribute a better future planning for investing. In this paper, we propose improved affinity propagation clustering for business districts mining. Given check-in data, whose geography information represents business venues' location, we introduce a affinity propagation clustering algorithm(AP), a basic solution, to cluster venues. This strategy requires that real-valued messages are exchanged among business venues until a set of centers and corresponding business districts gradually emerges. However, the computational complexity of AP is affected by the scale of input. And it's not adaptive for random distribution of venues when mining business districts. To conduct business districts mining efficiently, we introduce a pruning method, termed as PAP. And then present merging based mine approach, termed as MAP. We conduct experiments from Yelp data, and experimental results show that our proposed method outperforms the basic solutions and resolves the problem well.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127018572","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 : 2018-11-01DOI: 10.1109/ICTAI.2018.00073
Mehdi Othmani-Guibourg, A. E. Seghrouchni, J. Farges
We propose a conceptually simple new decentralised and non-communicating strategy for the multi-agent patrolling based on the LSTM architecture. The recurrent neural networks and more specifically the LSTM architecture, as machines to learn temporal series, are well adapted to the multi-agent patrol problem to the extent that they can be viewed as a decision problem over the time. For a given scenario, a LSTM neural network is first trained from data generated in simulation for that configuration, then embedded in agents that shall use it to navigate through the area to patrol choosing the next place to visit by feeding it with their current node. Finally, this new LSTM-based strategy is evaluated in simulation and compared with two representative strategies, a cognitive and centralised one, and a reactive and decentralised one. Preliminary results indicate that the proposed strategy is globally not better than the representative strategies for the aggregating criterion of average idleness, but better than the decentralised representative for the evaluation criteria of mean interval and quadratic mean interval.
{"title":"Path Generation with LSTM Recurrent Neural Networks in the Context of the Multi-Agent Patrolling","authors":"Mehdi Othmani-Guibourg, A. E. Seghrouchni, J. Farges","doi":"10.1109/ICTAI.2018.00073","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00073","url":null,"abstract":"We propose a conceptually simple new decentralised and non-communicating strategy for the multi-agent patrolling based on the LSTM architecture. The recurrent neural networks and more specifically the LSTM architecture, as machines to learn temporal series, are well adapted to the multi-agent patrol problem to the extent that they can be viewed as a decision problem over the time. For a given scenario, a LSTM neural network is first trained from data generated in simulation for that configuration, then embedded in agents that shall use it to navigate through the area to patrol choosing the next place to visit by feeding it with their current node. Finally, this new LSTM-based strategy is evaluated in simulation and compared with two representative strategies, a cognitive and centralised one, and a reactive and decentralised one. Preliminary results indicate that the proposed strategy is globally not better than the representative strategies for the aggregating criterion of average idleness, but better than the decentralised representative for the evaluation criteria of mean interval and quadratic mean interval.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123629862","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：