2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)最新文献

{"title":"Approach to Virtual Production System Modelling","authors":"Yu. V. Ostrovsky","doi":"10.1109/ISCSIC54682.2021.00078","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00078","url":null,"abstract":"Modern production is characterized by constantly occurring changes in the composition of the produced products, caused both by market and objective reasons. Virtual production is one way of building working manufacturing in this conditions. For the evaluate virtual production characteristic, an adequate and non-complex model is required. Here is presented a morphological model of the production system, taking into account the production approach and the need for similarity of all components of the model. As a unit cell of the model, it is proposed to use the triad, which combines the following components, as producer, product and gene of productive heredity. The last component of the triad displays the relationship between the product and the producer in content and meaning, due to the presence of common attributes, and also defines a characteristic of common properties, such as their capacity. To work with a lot of data in uncertainty and limited information on the early stages of design, it is possible to use information relationship analysis methods, such as triadic formal concepts analysis. Context analysis will simplify the task of forming a model of a virtual production system, based on the selection of elements close to the specified property of the future production system. Further studies of selected triclasteriszation algorithms are proposed to improve the accuracy of the simulation.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115986974","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}

{"title":"Electromechanical Platform with Removable Overlay for Exploring, Tuning and Evaluating Reinforcement Learning Algorithms","authors":"Thye Lye Kelvin Tan","doi":"10.1109/ISCSIC54682.2021.00029","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00029","url":null,"abstract":"Presented a physical electromechanical movable maze platform for evaluating reinforcement learning (RL) algorithms. The use of embedded hall sensors in the platform for detecting the spherical magnetic ball provides benefits over top mounted camera systems. The process of adapting RL algorithms like Q-table, SARSA and Neural Network to function with the platform was discussed. A comparative evaluation of the performance against baseline was presented. The electromechanical platform provides unique features, benefits, and challenges. The platform serves as a tool in RL algorithm tuning and validation. The platform also serves as a pedagogical tool, especially in providing learners a means to visualize the RL algorithms in action.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"10 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120984698","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}

{"title":"Demographic Market Segmentation on Short Banking Movement Descriptions Applying Natural Language Processing","authors":"Silvia García-Méndez, Francisco de Arriba Pérez, Óscar Barba Seara, Milagros Fernández Gavilanes, F. González-Castaño","doi":"10.1109/ISCSIC54682.2021.00035","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00035","url":null,"abstract":"Banking movement descriptions can be a valuable type of short texts for knowledge extraction with application in finance and social studies. Conventional research on text mining has mostly been applied to medium-sized documents. Knowledge extraction from banking movement descriptions is challenging due to the lack of meaningful textual data and their ad-hoc terminology. In this work we present a clustering analysis on short banking movement descriptions based on Natural Language Processing techniques. We exploit the knowledge in an experimental data set composed of almost 20,000 real banking transactions that have been anonymised as required by European data protection regulations. At the end, we were able to extract five distinctive user clusters with similar demographics. Our approach has potential applications in Personal Finance Management.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127848300","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}

{"title":"A Novel Method for Multi-UAV Cooperative Reconnaissance Mission Planning in Denied Environment","authors":"Jingyu Liu, Yanfei Liu, Mingzhi Cong, Zhong Wang, Jieling Wang","doi":"10.1109/ISCSIC54682.2021.00012","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00012","url":null,"abstract":"The traditional swarm intelligence algorithm to solve the path planning in single combat style of unmanned aerial vehicle (UAV) can no longer meet the requirements of multi-UAV cooperative reconnaissance mission planning (MUCRMP) problem in denied environment for its slow convergence rate, ignorance of complex constraints and guidance to local optimization. A novel method for multi-UAV cooperative reconnaissance mission planning in denied environment (MUCRMP-DE) based on an improved synthetic heuristic algorithm is proposed to tackle these. In this paper, a hierarchical model is established with the global optimization goal of UAV's minimum radar detection time at first, including the planning of reconnaissance sequence between and within target groups, as well as relative position to targets. Then an improved synthetic heuristic algorithm is proposed to solve the model, which obtains valuable reconnaissance mission plan. For an application example of reconnaissance mission involving 68 targets, the simulation results show that the improved synthetic heuristic algorithm can suit the needs of the mission, particularly in effectively evading the detection of multiple radars. While it can also give better anti-radar attributes to the UA V and efficiently improved the convergence speed in the specific reconnaissance mission.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129063598","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}

{"title":"Forecasting Daily MRT Passenger Flow in Taipei Based on Google Search Queries","authors":"Haoran Jie, Hetai Zou, Qinneng Xu","doi":"10.1109/ISCSIC54682.2021.00020","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00020","url":null,"abstract":"In recent decades, the advancement of the transportation system raises people's reliance on public transportation. Taipei metro is one of the most often-used modern transportation in Taiwan with around 2 million ridership per day. Forecasting passenger flow has been a critical topic in transportation research, with the purpose to facilitate traffic control. Accurate prediction on passenger flow would be essential for the efficiency in terms of operation and management of urban metro systems. In this paper, we focus on forecasting the daily Taipei metro passenger flow with various external covariates including Google search quires, calendar variables, and disaster variables to examine their forecasting power. Four existing methods such as linear regression, least absolute shrinkage, selection operator (LASSO), random forest, and autoregressive integrated moving average (ARIMA) are employed. The result suggests that random forest appears to yield the most competitive result among models and including Google search queries as covariates can in fact improve the accuracy of prediction.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117206308","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}

{"title":"Social Media Named Entity Recognition Based On Graph Attention Network","authors":"Wei Zhang, J. Luo, Kehua Yang","doi":"10.1109/ISCSIC54682.2021.00033","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00033","url":null,"abstract":"Named entity recognition is a basic task of natural language processing. With the development of the Internet, social media has become the main way of information transmission and sharing with friends, but social media texts are often short and informal, resulting in low entity recognition accuracy. In this paper, we use the Graph Attention Network (GAT) for the first time in the task of Chinese social media named entity recognition to generate the representation of the nodes in the sentence selection parsing tree, and capture the information of the sentence itself through the self-attention layer. In order to reduce the impact of Chinese word segmentation errors, we use a combination of character vectors and word vectors, and incorporate part of speech information for training. We integrate the above two points into the classic named entity recognition model BiLSTM-CRF model to form a new model to conduct research on named entity recognition of Chinese social media text. Experimental results show that our model achieves competitive results.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132181851","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}

{"title":"[Title page]","authors":"","doi":"10.1109/iscsic54682.2021.00002","DOIUrl":"https://doi.org/10.1109/iscsic54682.2021.00002","url":null,"abstract":"","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127649188","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}

{"title":"Automatic Steering Angle and Direction Prediction for Autonomous Driving Using Deep Learning","authors":"Nosherwan Ijaz, Yuehua Wang","doi":"10.1109/ISCSIC54682.2021.00058","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00058","url":null,"abstract":"In this paper, we first examine the literature of steering angle and direction analysis and prediction using deep learning under diverse hazardous conditions or adverse weather conditions. We present our insights learned and propose a new deep neural network to automate steering angle and direction prediction based on real-world environmental perceptions and dynamic driving representation. We systematically explore the proposed deep neural network and its neurons using DeepTest comparing Rambo and Chauffeur models. There are two sets of data that we have used to test our network and trained driving models. One is the dataset from the Udacity self-driving challenge and the other is the dataset collected when we are driving in and around Commerce, Texas with the goal of ensuring the robustness of the proposed deep neural network against hazardous and adverse driving conditions. We then experimentally evaluate our network and models compared to the state-of-the-art on two datasets. The evaluation provides clear evidence and meaningful scientific insights to address grand challenges for safe autonomous driving.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116833328","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}

{"title":"Baggage Routing with Scheduled Departures using Deep Reinforcement Learning","authors":"René Arendt Sørensen, Jens Rosenberg, H. Karstoft","doi":"10.1109/ISCSIC54682.2021.00014","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00014","url":null,"abstract":"As the number of travellers in airports increase, the load on the Baggage Handling Systems naturally gets higher. To accommodate this, airports can either expand or optimize their Baggage Handling System. Therefore, capacity is a common parameter to evaluate Baggage Handling Systems, and methods that can increase the capacity are highly valued within the airport industry. Previous work has shown that Deep Reinforcement Learning methods can be applied to increase the system capacity when a high load is constantly applied. It is, however, still not clear, how well such Deep Reinforcement Learning agents perform when the load of the system can change according to distributed flight schedules and realistic distributions of incoming baggage. In this work, we apply Deep Reinforcement Learning to a simulated Baggage Handling System with flight schedules and a distribution of incoming baggage generalized from data from a real airport. As opposed to previous work, we allow empty baggage totes to be stored at the entry point until new baggage arrives. The centralized Deep Reinforcement Learning agent must learn to balance the number of baggage totes in the entry queue, while also learning optimal routing strategies, ensuring that all bags meet their scheduled departure times. The performance is measured by the average number of delivered bags and the average number of rush bags that occurred in the example environment. We find that by using Deep Reinforcement Learning in this type of congested system with scheduled departures, we can reduce the number of rush bags, compared to a dynamic shortest path method with deadlock avoidance, resulting in a higher number of delivered bags in the system.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116406474","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}

{"title":"Dynamic Workforce Scheduling and Routing in a Smart City Using Temporal Batch Decomposition","authors":"Hunabad Tejdeep Reddy, Rishabh Ranjan, Kujirai Toshihiro","doi":"10.1109/ISCSIC54682.2021.00056","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00056","url":null,"abstract":"A major challenge for the service providers in smart cities operating in domains such as health, security, maintenance, etc. is to provide efficient assignments of personnel to handle the incidents related to their services. These incidents could be divided into two categories. The first category is called scheduled events like regular maintenance operations, whose information is available in prior. The second category is called dynamic events and consists of emergency events that occur unpredictably at any time which we call dynamic events. The goal is to assign a common set of personnel efficiently to both the categories simultaneously, to reduce average service time of each event. Typically, in large scenarios, heuristics like greedy algorithms are used to obtain solutions in real time to facilitate immediate handling of dynamic events. However, they are myopic and cannot deliver optimized solutions across a large horizon. We propose a method for large scenarios in real time that are more globally optimized as compared to greedy algorithms. The proposed method involves a) A newly developed Mixed Integer Linear Program formulation, which considers multiple independent events that need to be handled parallelly, and b) Decomposition of the large scenario into a queue of smaller batches of events based on their occurrence/requested time. This method handles dynamically occurring events immediately without having to recompute the schedule for the entire time horizon but instead do batchwise assignment. Proposed method was validated by comparing it with the baseline greedy method and a modified version of the baseline called Priority greedy method. The assignment of personnel by the proposed method resulted in a reduction in average service time of events for large scenarios compared to that of the other two methods and was able to provide solution in a reasonable time. The proposed method increases the efficiency of providing services by reducing the associated risk.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124317241","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}