Pub Date : 2017-11-08DOI: 10.1109/FSKD.2017.8393169
Handan Zhang, B. Hu
Based on the database of public transportation network in Nanchang, this paper evaluates the accessibility of urban public transportation by using space syntax and time distance methods. Through the calculation of the space syntax index, accessibility index and the time cost of each node, the results show that the accessibility of road intensive area and urban centers is higher than other regions, the convenience of subway line is better than bus lines, and the influence of a road along the subway is more significant than that of other regions. The control value of the whole public transit network remains stable, the time cost of urban traffic has been significantly improved with the completion of the metro line 2, the average saving travel time is about 4min, and the transit time between public transportation sites is also reduced with the constructions of subway lines. The evaluations of the pubic traffic accessibility in Nanchang city have the consistent conclusions according to space syntax and time distance methods.
{"title":"Space syntax and time distance based analysis on the influences of the subways to the pubic traffic accessibility in Nanchang city","authors":"Handan Zhang, B. Hu","doi":"10.1109/FSKD.2017.8393169","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393169","url":null,"abstract":"Based on the database of public transportation network in Nanchang, this paper evaluates the accessibility of urban public transportation by using space syntax and time distance methods. Through the calculation of the space syntax index, accessibility index and the time cost of each node, the results show that the accessibility of road intensive area and urban centers is higher than other regions, the convenience of subway line is better than bus lines, and the influence of a road along the subway is more significant than that of other regions. The control value of the whole public transit network remains stable, the time cost of urban traffic has been significantly improved with the completion of the metro line 2, the average saving travel time is about 4min, and the transit time between public transportation sites is also reduced with the constructions of subway lines. The evaluations of the pubic traffic accessibility in Nanchang city have the consistent conclusions according to space syntax and time distance methods.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126330786","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 : 2017-07-30DOI: 10.1109/FSKD.2017.8393410
Tereza Parilová, E. Hladká, P. Říha
Along with the discovery of new facts and the development of new technologies and methodologies, more and more definitions and specifications emerge. The quantity of these emergences, however, can lead to paradoxical contradictions, which obscure borders. Often, we see this phenomenon of vagueness within natural language or non-exact topics. Fuzzy principles are therefore applied in wide range of (not only) scientific areas. In applied technical science, a user model based on interface and human computer cooperation meets such fuzzy borders. So, why not use it in assistive technology models? Fuzzy deals from its nature with linguistic variables and such variables are being transformed from numbers to expressions on predefined scales. Dyslexia is a neurobiological cognitive based disorder and ideal for (neuro) fuzzy computational modeling for many reasons. This paper describes the idea and process of using the fuzzy approach for obtaining information about individual problems of dyslexic users and differentiating between the type(s) of dyslexic user model he or she may belong to. Such information may serve for further clinical and psychological studies of dyslexia and linguistic based problems.
{"title":"Designing fuzzy apparatus to model dyslexic individual symptoms for clinical use","authors":"Tereza Parilová, E. Hladká, P. Říha","doi":"10.1109/FSKD.2017.8393410","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393410","url":null,"abstract":"Along with the discovery of new facts and the development of new technologies and methodologies, more and more definitions and specifications emerge. The quantity of these emergences, however, can lead to paradoxical contradictions, which obscure borders. Often, we see this phenomenon of vagueness within natural language or non-exact topics. Fuzzy principles are therefore applied in wide range of (not only) scientific areas. In applied technical science, a user model based on interface and human computer cooperation meets such fuzzy borders. So, why not use it in assistive technology models? Fuzzy deals from its nature with linguistic variables and such variables are being transformed from numbers to expressions on predefined scales. Dyslexia is a neurobiological cognitive based disorder and ideal for (neuro) fuzzy computational modeling for many reasons. This paper describes the idea and process of using the fuzzy approach for obtaining information about individual problems of dyslexic users and differentiating between the type(s) of dyslexic user model he or she may belong to. Such information may serve for further clinical and psychological studies of dyslexia and linguistic based problems.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132136605","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393043
Rong Fan, Wenxin Hu
Deep learning techniques have become the state-of-the-art approach for classification in artificial intelligence, and applied in many widespread subjects. Deep Belief Networks (DBNs) are one of the most successful models. DBNs consist of many layers of hidden factors along with a greedy layer-wise unsupervised learning algorithm. In our paper, we brought forward an approach to face recognition based on dropout DBNs, which made good performances on small training sets.
{"title":"Face recognition with improved deep belief networks","authors":"Rong Fan, Wenxin Hu","doi":"10.1109/FSKD.2017.8393043","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393043","url":null,"abstract":"Deep learning techniques have become the state-of-the-art approach for classification in artificial intelligence, and applied in many widespread subjects. Deep Belief Networks (DBNs) are one of the most successful models. DBNs consist of many layers of hidden factors along with a greedy layer-wise unsupervised learning algorithm. In our paper, we brought forward an approach to face recognition based on dropout DBNs, which made good performances on small training sets.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115230804","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393111
Feng Wang, Lanfen Lin
Patent retrieval is considered as recall-oriented retrieval that aims to find all relevant patent documents for a patent query. However, current methods encounter the term mismatch problem, because of the frequent use of nonstandard technical terms in patent documents. In order to deal with this problem, we propose a new patent query expansion approach by exploiting semantic knowledge base, which can enrich the query with semantically related concepts. Concretely, to understand the query semantics, we present the WordNet and Wikipedia-based expansion algorithms enhancing the initial query. We further provide the combination strategy to execute query and obtain retrieval results. Experiments are performed based on Java environment using the CLEF-IP collection. Results show that the performance of our approach is significantly better than other state-of-the-art approaches.
{"title":"Exploiting semantic knowledge base for patent retrieval","authors":"Feng Wang, Lanfen Lin","doi":"10.1109/FSKD.2017.8393111","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393111","url":null,"abstract":"Patent retrieval is considered as recall-oriented retrieval that aims to find all relevant patent documents for a patent query. However, current methods encounter the term mismatch problem, because of the frequent use of nonstandard technical terms in patent documents. In order to deal with this problem, we propose a new patent query expansion approach by exploiting semantic knowledge base, which can enrich the query with semantically related concepts. Concretely, to understand the query semantics, we present the WordNet and Wikipedia-based expansion algorithms enhancing the initial query. We further provide the combination strategy to execute query and obtain retrieval results. Experiments are performed based on Java environment using the CLEF-IP collection. Results show that the performance of our approach is significantly better than other state-of-the-art approaches.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117138088","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}
Complex network is a kind of system structure, which widely exists in human society and nature. It can be used to capture and describe the evolution law, evolution mechanism, and dynamic behaviors. We study the model of entity growth in complex networks, achieve the single node growth model, block growth model and degree of communication difficulty based growth model, then carry out the theoretical analysis and experimental simulation, it is concluded that the entity growth model holds the characteristics of high robustness, high clustering coefficient and low average path. According to the growth model, this paper analyzes the basic idea and implementation process of the self-organizing community discovery algorithm based on information entropy, experimental results show that it is structurally reasonable and has important significance in practical application.
{"title":"A self-organizing community detection algorithm for complex networks","authors":"Dongming Chen, Zhaoliang Song, Cenyi Luo, Xinyu Huang","doi":"10.1109/FSKD.2017.8393291","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393291","url":null,"abstract":"Complex network is a kind of system structure, which widely exists in human society and nature. It can be used to capture and describe the evolution law, evolution mechanism, and dynamic behaviors. We study the model of entity growth in complex networks, achieve the single node growth model, block growth model and degree of communication difficulty based growth model, then carry out the theoretical analysis and experimental simulation, it is concluded that the entity growth model holds the characteristics of high robustness, high clustering coefficient and low average path. According to the growth model, this paper analyzes the basic idea and implementation process of the self-organizing community discovery algorithm based on information entropy, experimental results show that it is structurally reasonable and has important significance in practical application.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115196928","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393092
Teoh Teik Toe, Y. Nguwi, Y. Elovici, Ngai-Man Cheung, W. Ng
Hidden Markov Models (HMM) are probabilistic models that can be used for forecasting time series data. It has seen success in various domains like finance [1-5], bioinformatics [6-8], healthcare [9-11], agriculture [12-14], artificial intelligence[15-17]. However, the use of HMM in cyber security found to date is numbered. We believe the properties of HMM being predictive, probabilistic, and its ability to model different naturally occurring states form a good basis to model cyber security data. It is hence the motivation of this work to provide the initial results of our attempts to predict security attacks using HMM. A large network datasets representing cyber security attacks have been used in this work to establish an expert system. The characteristics of attacker's IP addresses can be extracted from our integrated datasets to generate statistical data. The cyber security expert provides the weight of each attribute and forms a scoring system by annotating the log history. We applied HMM to distinguish between a cyber security attack, unsure and no attack by first breaking the data into 3 cluster using Fuzzy K mean (FKM), then manually label a small data (Analyst Intuition) and finally use HMM state-based approach. By doing so, our results are very encouraging as compare to finding anomaly in a cyber security log, which generally results in creating huge amount of false detection.
{"title":"Analyst intuition based Hidden Markov Model on high speed, temporal cyber security big data","authors":"Teoh Teik Toe, Y. Nguwi, Y. Elovici, Ngai-Man Cheung, W. Ng","doi":"10.1109/FSKD.2017.8393092","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393092","url":null,"abstract":"Hidden Markov Models (HMM) are probabilistic models that can be used for forecasting time series data. It has seen success in various domains like finance [1-5], bioinformatics [6-8], healthcare [9-11], agriculture [12-14], artificial intelligence[15-17]. However, the use of HMM in cyber security found to date is numbered. We believe the properties of HMM being predictive, probabilistic, and its ability to model different naturally occurring states form a good basis to model cyber security data. It is hence the motivation of this work to provide the initial results of our attempts to predict security attacks using HMM. A large network datasets representing cyber security attacks have been used in this work to establish an expert system. The characteristics of attacker's IP addresses can be extracted from our integrated datasets to generate statistical data. The cyber security expert provides the weight of each attribute and forms a scoring system by annotating the log history. We applied HMM to distinguish between a cyber security attack, unsure and no attack by first breaking the data into 3 cluster using Fuzzy K mean (FKM), then manually label a small data (Analyst Intuition) and finally use HMM state-based approach. By doing so, our results are very encouraging as compare to finding anomaly in a cyber security log, which generally results in creating huge amount of false detection.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127007125","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393366
Szu-Yu Lin, Yu-Te Wu, W. Mao, Po-Shan Wang
Sleep is important for the restoration and renewal of the human body. Obstructive sleep apnea syndrome (OSAS), which is caused by repetitive episodes of partial or complete upper airway obstruction during sleep, is the most common type of sleep apnea. The sleep electroencephalogram (EEG) analysis has been an important tool to investigate brain activity. In this study, we used the spectral analysis and fuzzy entropy to analyze the EEG signals collected from the OSAS patients and normal control. Results obtained from the EEG power spectrum and fuzzy entropy with and without principal component analysis (PCA) process were used as the features and fed into four different classifiers, namely, linear Support Vector Machines (SVM), Liner Discriminant Analysis (LDA), subspace k-nearest neighbor (k-NN) and subspace discriminant analysis, to differentiate these two groups. Our results demonstrated that the feature resulted from power spectrum with PCA process and subspace discriminate method using 5-fold cross-validation produces the superior classification rate which is 89 ± 3.74%.
{"title":"EEG signal analysis of patients with obstructive sleep apnea syndrome (OSAS) using power spectrum and fuzzy entropy","authors":"Szu-Yu Lin, Yu-Te Wu, W. Mao, Po-Shan Wang","doi":"10.1109/FSKD.2017.8393366","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393366","url":null,"abstract":"Sleep is important for the restoration and renewal of the human body. Obstructive sleep apnea syndrome (OSAS), which is caused by repetitive episodes of partial or complete upper airway obstruction during sleep, is the most common type of sleep apnea. The sleep electroencephalogram (EEG) analysis has been an important tool to investigate brain activity. In this study, we used the spectral analysis and fuzzy entropy to analyze the EEG signals collected from the OSAS patients and normal control. Results obtained from the EEG power spectrum and fuzzy entropy with and without principal component analysis (PCA) process were used as the features and fed into four different classifiers, namely, linear Support Vector Machines (SVM), Liner Discriminant Analysis (LDA), subspace k-nearest neighbor (k-NN) and subspace discriminant analysis, to differentiate these two groups. Our results demonstrated that the feature resulted from power spectrum with PCA process and subspace discriminate method using 5-fold cross-validation produces the superior classification rate which is 89 ± 3.74%.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123395874","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393030
Hua Yang, Jipu Gao, Changbao Xu, Zheng Long, Weigang Feng, S. Xiong, Shuaiwei Liu, Shan Tan
Early detection of equipment faults plays a crucial role in power system, and automatic change detection of working status of an equipment is an efficient tool for this purpose. In this study, we proposed a novel method to automatically detect temperature change in local region of a substation equipment in power system using bi-temporal infrared images. We considered the change detection as two-class classification problem, and a supervised machine learning algorithm — Random Forest (RF) — was used for forecasting change trend. Various features were extracted from two temporal images for change detection. The features we extracted include gray-level, weighted intensity mean, RGB, LBP, gray-level histogram, and texture originating from the grayscale images and color images of the bi-temporal infrared images of the substation equipment. Cross validation was used to evaluate the robustness of these extracted features. Due to the existence of environmental noise, there are isolated detection points in the change detection results. In order to remove these isolated noise points and improve detection accuracy, we performed a morphological filtering on the detection results. Evaluation indexes such as Dice Similarity Index (DSI), kappa coefficient were used to evaluate the detection performance. Four classical change detection methods i.e. Image Differencing, Image Ratioing, Change vector analysis (CVA) and Principal Component Analysis (PCA) were tested for comparison purpose. Experimental results demonstrated that the proposed algorithm outperformed significantly these classical methods.
早期发现设备故障在电力系统中起着至关重要的作用，而设备工作状态变化自动检测是实现这一目标的有效工具。在这项研究中，我们提出了一种利用双时相红外图像自动检测电力系统中变电站设备局部温度变化的新方法。我们将变化检测视为两类分类问题，并使用有监督机器学习算法随机森林(Random Forest, RF)来预测变化趋势。从两幅时间图像中提取各种特征进行变化检测。从变电站设备双时相红外图像的灰度图像和彩色图像中提取的特征包括灰度、加权强度均值、RGB、LBP、灰度直方图和纹理。交叉验证用于评估这些提取特征的鲁棒性。由于环境噪声的存在，变化检测结果中存在孤立的检测点。为了去除这些孤立的噪声点，提高检测精度，我们对检测结果进行了形态学滤波。采用Dice Similarity Index (DSI)、kappa系数等评价指标对检测性能进行评价。对四种经典的变化检测方法即图像差分、图像比例、变化向量分析(CVA)和主成分分析(PCA)进行了比较。实验结果表明，该算法明显优于这些经典方法。
{"title":"Infrared image change detection of substation equipment in power system using random forest","authors":"Hua Yang, Jipu Gao, Changbao Xu, Zheng Long, Weigang Feng, S. Xiong, Shuaiwei Liu, Shan Tan","doi":"10.1109/FSKD.2017.8393030","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393030","url":null,"abstract":"Early detection of equipment faults plays a crucial role in power system, and automatic change detection of working status of an equipment is an efficient tool for this purpose. In this study, we proposed a novel method to automatically detect temperature change in local region of a substation equipment in power system using bi-temporal infrared images. We considered the change detection as two-class classification problem, and a supervised machine learning algorithm — Random Forest (RF) — was used for forecasting change trend. Various features were extracted from two temporal images for change detection. The features we extracted include gray-level, weighted intensity mean, RGB, LBP, gray-level histogram, and texture originating from the grayscale images and color images of the bi-temporal infrared images of the substation equipment. Cross validation was used to evaluate the robustness of these extracted features. Due to the existence of environmental noise, there are isolated detection points in the change detection results. In order to remove these isolated noise points and improve detection accuracy, we performed a morphological filtering on the detection results. Evaluation indexes such as Dice Similarity Index (DSI), kappa coefficient were used to evaluate the detection performance. Four classical change detection methods i.e. Image Differencing, Image Ratioing, Change vector analysis (CVA) and Principal Component Analysis (PCA) were tested for comparison purpose. Experimental results demonstrated that the proposed algorithm outperformed significantly these classical methods.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121230077","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393051
A. Diveev, G. Balandina, S. Konstantinov
The paper describes a novel numerical symbolic regression method. It's called complete binary variational genetic programming. We use it for synthesis of optimal control. This method performs better than genetic programming at crossover, reduces the search area and speeds up search algorithm by using small variations. The efficiency of the new method is proven on the given example of control system synthesis for mobile robot.
{"title":"Binary variational genetic programming for the problem of synthesis of control system","authors":"A. Diveev, G. Balandina, S. Konstantinov","doi":"10.1109/FSKD.2017.8393051","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393051","url":null,"abstract":"The paper describes a novel numerical symbolic regression method. It's called complete binary variational genetic programming. We use it for synthesis of optimal control. This method performs better than genetic programming at crossover, reduces the search area and speeds up search algorithm by using small variations. The efficiency of the new method is proven on the given example of control system synthesis for mobile robot.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128125119","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393379
Zhao Pei, Hai-Dong Shang, Yi Su, Miao Ma, Yali Peng
Conventionally, students attendance records are taken manually by teachers through roll calling in the class. It is time-consuming and prone to errors. Moreover, records of attendance are difficult to handle and preserve for the long-term. In this paper, we propose a more conveniently method of attendance statistics, which achieved through the Convolutional Neural Network (CNN). The traditional method of face recognition, such as Eigenface, is sensitive to lighting, noise, gestures, expressions and etc. Hence, we utilize CNN to implement face recognition, in order to reduce the effect of environmental change on experimental results. In addition, CNN is a method which needs lots of data for training. To resolve the problem, we design a new method to collect face data which can get lots of face data quickly and conveniently.
{"title":"Convolutional neural networks for class attendance","authors":"Zhao Pei, Hai-Dong Shang, Yi Su, Miao Ma, Yali Peng","doi":"10.1109/FSKD.2017.8393379","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393379","url":null,"abstract":"Conventionally, students attendance records are taken manually by teachers through roll calling in the class. It is time-consuming and prone to errors. Moreover, records of attendance are difficult to handle and preserve for the long-term. In this paper, we propose a more conveniently method of attendance statistics, which achieved through the Convolutional Neural Network (CNN). The traditional method of face recognition, such as Eigenface, is sensitive to lighting, noise, gestures, expressions and etc. Hence, we utilize CNN to implement face recognition, in order to reduce the effect of environmental change on experimental results. In addition, CNN is a method which needs lots of data for training. To resolve the problem, we design a new method to collect face data which can get lots of face data quickly and conveniently.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125493298","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：