2018 5th International Conference on Systems and Informatics (ICSAI)最新文献_第10页

Mutation Relation Extraction and Genes Network Analysis in Colon Cancer 结肠癌突变关系提取及基因网络分析

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599412

Yinan Lu, Xiaoxin Guo, Hangyu Pan, Haowei Lin

引用次数: 1

How Does the Data set Affect CNN-based Image Classification Performance? 数据集如何影响基于cnn的图像分类性能?

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599448

Chao Luo, Xiaojie Li, Lutao Wang, Jia He, Denggao Li, Jiliu Zhou

{"title":"How Does the Data set Affect CNN-based Image Classification Performance?","authors":"Chao Luo, Xiaojie Li, Lutao Wang, Jia He, Denggao Li, Jiliu Zhou","doi":"10.1109/ICSAI.2018.8599448","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599448","url":null,"abstract":"Convolutional neural networks (ConvNets or CNNs) have been proven very effective in areas such as image recognition and classification. Especially in the field of image classification, the CNN-based method has achieved excellent performance. Performance is an important indicator for evaluating whether a CNN-based classification method is excellent, so it is important to study which factors affect performance. As we all know, image classification performance is affected by the network structure itself and the size of the data set. In particular, data set size have a significant impact on performance. While for most people, a large number of data set are difficult to obtain. Thus, we consider a question of this approach: How does the size of the data set affect performance? In order to clarify this issue, there are 35 groups experiment performed with 5 times experiment in each group (175 experiments in total). For each k-classification experiment, we do 5 groups by increasing the size of the training set. Observe changes in accuracy to analyze the effect of data set size on difference. For the same CNN-based network, experimental results of average accuracy illustrate that the larger the training set, the higher the test accuracy. However, when the training data set are insufficient, better results can be obtained. Furthermore, in each group experiment, the more categories that are classified, the more obvious the performance change. Results of this paper not only can guide us to do experiments on image classification, but also have important guiding significance for other experiments based on deep learning.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"46 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":"115855041","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}

引用次数: 34

Statistical Approach to Improve the Efficiency of Air Conditioning System Performance in Changeable Climatic Conditions 气候变化条件下提高空调系统性能效率的统计方法

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599434

E. Trushliakov, M. Radchenko, A. Radchenko, S. Kantor, Zongming Yang

{"title":"Statistical Approach to Improve the Efficiency of Air Conditioning System Performance in Changeable Climatic Conditions","authors":"E. Trushliakov, M. Radchenko, A. Radchenko, S. Kantor, Zongming Yang","doi":"10.1109/ICSAI.2018.8599434","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599434","url":null,"abstract":"A statistical approach to improve the performance of air conditioning system with taking into account the current changeable climatic conditions has been proposed. Accoding to this methodological approach the optimum designed heat load, matching current changeable climatic conditions and providing efficient performance of air conditioning system with maximum annual refrigeration effect, has been defined as a result of statistical treatment of data sets of hourly refrigeration outputs year round. According to this approach a value of optimum designed total heat load on the air conditioning system and corresponding refrigeration capacity of refrigeration machine providing the maximum annual refrigeration capacity output and a value of stable heat load (corresponding refrigeration capacity) as designed basic heat load covered with high efficiency performance of refrigeration machine in nominal mode are calculated. The values of unstable heat loads as boost loads for ambient air precooling covered with low efficiency performance of refrigeration machine in partial modes that cause energetic losses are calculated by remainder principle – as difference between optimum designed total refrigeration capacity, providing the maximum annual refrigeration output, and a value of stable heat load as designed basic heat load. The operation of refrigeration machine in partial modes needs application of energy conserving methods of air conditioning as an example with accumulation of excessive refrigeration capacity at decreased current heat loads and its using at increased current heat loads or application of expensive inventor compressors to control motor speed matching current changeable heat loads.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"151 4 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":"131077041","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}

引用次数: 17

Enhancing the Utilization of Gas Engine Module Exhaust Heat by Two-stage Chillers for Combined Electricity, Heat and Refrigeration 电、热、冷联用两级冷却器提高燃气发动机模块余热的利用

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599492

M. Radchenko, R. Radchenko, O. Ostapenko, A. Zubarev, Artem Hrych

{"title":"Enhancing the Utilization of Gas Engine Module Exhaust Heat by Two-stage Chillers for Combined Electricity, Heat and Refrigeration","authors":"M. Radchenko, R. Radchenko, O. Ostapenko, A. Zubarev, Artem Hrych","doi":"10.1109/ICSAI.2018.8599492","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599492","url":null,"abstract":"The efficiency of utilization of cogeneration gas engine module exhaust heat into the cold by the absorption Li-Br chiller was analyzed. The presence of significant heat losses caused by contradictory conditions of joint performance of absorption Li-Br chiller and cogenerative gas engine module on the temperature of return heat fluid (heating water) at the outlet of absorption Li-Br chiller and its temperature at the inlet of cooling system of cogenerative gas engine was revealed. The twostage chillers with absorption Li-Br chiller as a high-temperature stage and adsorption chiller or refrigerant ejector chiller as a low-temperature stage of heat utilization (according to the temperature of heating water) was considered. The application of an adsorption chiller to transform the heat of return heating water after the absorption Li-Br chiller was proposed. The possibility of applying a refrigerant ejector chiller to transform a low potential heat of return heating water after the absorption Li-Br chiller is considered. A two-stage transformation of the heat by refrigerant ejector chiller as the first stage and absorption chiller as the second stage was proposed.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","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":"131270410","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}

引用次数: 24

Entity Grammar Systems and Knowledge Engineering in the Background of Big Data 大数据背景下的实体语法系统与知识工程

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599433

R. Zheng, Yun Wang

引用次数: 0

A rapid face detection method based on skin color model and local binary gradient feature 基于肤色模型和局部二值梯度特征的快速人脸检测方法

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599306

Zhiyong Peng, Jun Wu, Guoliang Fan

引用次数: 0

Video Stream Relocalization With Deep Learning 基于深度学习的视频流重新定位

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599392

Tingting Hu, Hanxu Sun

引用次数: 1

Application on Information Island with Information Visualization and Software Engineering 信息可视化与软件工程在信息孤岛中的应用

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599364

Jiahui Lv, Kaimin Shen, S. Johnson, Fan Chen, Guorui Li

{"title":"Application on Information Island with Information Visualization and Software Engineering","authors":"Jiahui Lv, Kaimin Shen, S. Johnson, Fan Chen, Guorui Li","doi":"10.1109/ICSAI.2018.8599364","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599364","url":null,"abstract":"The problem of “information islands” has become a bottleneck that restricts information construction and resource sharing in universities. Information islands cause waste of information resources. The data that has been used is only used in digital displays and cannot be used for management and decision-making. Students cannot absorb in-depth and the information obtained is not comprehensive. As a result, the information can only be used within the school. It can neither share with others nor use the resources of others to update and add to their information. A large number of established education networks are unable to function. Even the more networks are built, the greater waste are existed. Through the visualization of the data network under the campus environment, the free flow of data and information is an important way to solve information islands. This paper proposes an algorithmic theory of data structure visualization and provides an information flow project under the Python scene. It attempts to solve the problems of information islands in the campus environment and helps students to better obtain information and digest information.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"13 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":"123157115","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}

引用次数: 4

Design of Multi-PMU Real-time Communication Test Software Based on MFC 基于MFC的多pmu实时通信测试软件设计

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599351

Weiqing Tao, Tuan Zhang, Lin Li, Dachao Xu

引用次数: 0

Functional Test for Phasor Data Concentrator in Distribution Network 配电网相量数据集中器的功能测试

2018 5th International Conference on Systems and Informatics (ICSAI) Pub Date : 2018-11-01 DOI: 10.1109/ICSAI.2018.8599487

Weiqing Tao, Xinhua Zhu, Tuan Zhang, Jinsong Liu, Ping Ling

引用次数: 0