Pub Date : 2019-02-01DOI: 10.6025/jdim/2020/18/1/33-42
Farid Ayeche, A. Alti, Abdallah Boukerram
Computing efficiency is a key in biometric identification systems for automatic facial expression recognition. It was integrated within advanced pattern recognition as an excellent paradigm while users shifted towards underlying patterns. Most existing face recognition models suffer from a low recognition rate and significant execution time. To overcome these drawbacks, we propose a new Local Gradient Neighborhood (LGN) descriptor for effective face and facial expression recognition. Firstly, the LGN components obtained by applying LGN for each block of the face image which is represented by 9-size vector. Secondly, the system concatenates features vectors of different blocks to obtain the final feature vector for the face image. Finally, it applies SVM and KNN techniques to classify the input images. Unlike other similar works, the new proposed descriptor is evaluated on two benchmarks, for face recognition and facial expression recognition respectively. The experimental results show an excellent recognition rate and fast execution time. The recognition rate for the ORL face database is 98.50% and the recognition rate for the JAFEE database is 84.28%. Subject Categories and Descriptors: [I.4.7 Feature Measurement]; [I.5 PATTERN RECOGNITION]: Neural nets General Terms: Local Gradient Neighborhood, Face Expression Recognition, Classification, SVM, Feature Extraction
{"title":"Improved Face and Facial Expression Recognition Based on a Novel Local Gradient Neighborhood","authors":"Farid Ayeche, A. Alti, Abdallah Boukerram","doi":"10.6025/jdim/2020/18/1/33-42","DOIUrl":"https://doi.org/10.6025/jdim/2020/18/1/33-42","url":null,"abstract":"Computing efficiency is a key in biometric identification systems for automatic facial expression recognition. It was integrated within advanced pattern recognition as an excellent paradigm while users shifted towards underlying patterns. Most existing face recognition models suffer from a low recognition rate and significant execution time. To overcome these drawbacks, we propose a new Local Gradient Neighborhood (LGN) descriptor for effective face and facial expression recognition. Firstly, the LGN components obtained by applying LGN for each block of the face image which is represented by 9-size vector. Secondly, the system concatenates features vectors of different blocks to obtain the final feature vector for the face image. Finally, it applies SVM and KNN techniques to classify the input images. Unlike other similar works, the new proposed descriptor is evaluated on two benchmarks, for face recognition and facial expression recognition respectively. The experimental results show an excellent recognition rate and fast execution time. The recognition rate for the ORL face database is 98.50% and the recognition rate for the JAFEE database is 84.28%. Subject Categories and Descriptors: [I.4.7 Feature Measurement]; [I.5 PATTERN RECOGNITION]: Neural nets General Terms: Local Gradient Neighborhood, Face Expression Recognition, Classification, SVM, Feature Extraction","PeriodicalId":303976,"journal":{"name":"J. Digit. Inf. Manag.","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115568563","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 : 2018-05-01DOI: 10.6025/jdim/2019/17/1/13-24
Ignacio Espinoza, Marcelo Mendoza, Pablo Ortega, Daniel Rivera, F. Weiss
Opinions in forums and social networks are released by millions of people due to the increasing number of users that use Web 2.0 platforms to opine about brands and organizations. For enterprises or government agencies it is almost impossible to track what people say producing a gap between user needs/expectations and organizations actions. To bridge this gap we create Viscovery, a platform for opinion summarization and trend tracking that is able to analyze a stream of opinions recovered from forums. To do this we use dynamic topic models, allowing to uncover the hidden structure of topics behind opinions, characterizing vocabulary dynamics. We extend dynamic topic models for incremental learning, a key aspect needed in Viscovery for model updating in near-real time. In addition, we include in Viscovery sentiment analysis, allowing to separate positive/negative words for a specific topic at different levels of granularity. Viscovery allows to visualize representative opinions and terms in each topic. At a coarse level of granularity, the dynamic of the topics can be analyzed using a 2D topic embedding, suggesting longitudinal topic merging or segmentation. In this paper we report our experience developing this platform, sharing lessons learned and opportunities that arise from the use of sentiment analysis and topic modeling in real world applications.
{"title":"Viscovery: Trend Tracking in Opinion Forums based on Dynamic Topic Models","authors":"Ignacio Espinoza, Marcelo Mendoza, Pablo Ortega, Daniel Rivera, F. Weiss","doi":"10.6025/jdim/2019/17/1/13-24","DOIUrl":"https://doi.org/10.6025/jdim/2019/17/1/13-24","url":null,"abstract":"Opinions in forums and social networks are released by millions of people due to the increasing number of users that use Web 2.0 platforms to opine about brands and organizations. For enterprises or government agencies it is almost impossible to track what people say producing a gap between user needs/expectations and organizations actions. To bridge this gap we create Viscovery, a platform for opinion summarization and trend tracking that is able to analyze a stream of opinions recovered from forums. To do this we use dynamic topic models, allowing to uncover the hidden structure of topics behind opinions, characterizing vocabulary dynamics. We extend dynamic topic models for incremental learning, a key aspect needed in Viscovery for model updating in near-real time. In addition, we include in Viscovery sentiment analysis, allowing to separate positive/negative words for a specific topic at different levels of granularity. Viscovery allows to visualize representative opinions and terms in each topic. At a coarse level of granularity, the dynamic of the topics can be analyzed using a 2D topic embedding, suggesting longitudinal topic merging or segmentation. In this paper we report our experience developing this platform, sharing lessons learned and opportunities that arise from the use of sentiment analysis and topic modeling in real world applications.","PeriodicalId":303976,"journal":{"name":"J. Digit. Inf. Manag.","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115446807","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 : 2013-10-01DOI: 10.11591/TELKOMNIKA.V12I6.5471
Yang Zhang, Xueling Zhu, Qiang Li, Tong Liu
The accurate modeling of micro-grid access to power system planning and design stage needs is the primary problem to solve. This paper modeled the micro grid photovoltaic power generation system ,including silicon solar cell, photovoltaic inverters, battery energy storage system, and the micro power distribution system .The use of power system analysis software (DIGSILENT) of actual power system simulation, the simulation results verify the model's correctness. In the power grid fault disturbance, the light intensity of disturbance and the load disturbances, the simulation results show that the optical storage combined with micro network has fast dynamic response characteristics, and its network of grid-connected voltage influenced by the changes of the light and load is little, while more affected by the network fault influence. DOI : http://dx.doi.org/10.11591/telkomnika.v12i6.5471 Full Text: PDF
{"title":"Modeling and Simulation of DIGSILENT-based Micro-grid System","authors":"Yang Zhang, Xueling Zhu, Qiang Li, Tong Liu","doi":"10.11591/TELKOMNIKA.V12I6.5471","DOIUrl":"https://doi.org/10.11591/TELKOMNIKA.V12I6.5471","url":null,"abstract":"The accurate modeling of micro-grid access to power system planning and design stage needs is the primary problem to solve. This paper modeled the micro grid photovoltaic power generation system ,including silicon solar cell, photovoltaic inverters, battery energy storage system, and the micro power distribution system .The use of power system analysis software (DIGSILENT) of actual power system simulation, the simulation results verify the model's correctness. In the power grid fault disturbance, the light intensity of disturbance and the load disturbances, the simulation results show that the optical storage combined with micro network has fast dynamic response characteristics, and its network of grid-connected voltage influenced by the changes of the light and load is little, while more affected by the network fault influence. DOI : http://dx.doi.org/10.11591/telkomnika.v12i6.5471 Full Text: PDF","PeriodicalId":303976,"journal":{"name":"J. Digit. Inf. Manag.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125978015","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 : 2013-02-01DOI: 10.6025/jdim/2023/21/1/1-8
Luo Xiao
Firstly, this paper gives a data aggregation algorithm based on learning automata to solve the problem that the existing data aggregation algorithm can’t solve, the uneven energy cost, and the existing algorithm can’t change the gathering path dynamically existing the overhead environment. In the proposed method, nodes can change its gathering path to adjust the overhead environment. All the nodes of WSN equipped with a learning automata. These leaning automata learn all the gathering path of the nodes. In the process of transmit information two kinds of data are transmitted, including data packet, knowledge packet .When the information of the nodes changes, according to the feedback of the nods, the learning automata gives the reward or punish to the current gathering path, which help to find the best gathering path. Secondly, this paper improved the wavelet data compression algorithm, which was brought out as the correlation between different data. The algorithm do not reduce much of the data relate to the original data. After the wavelet data compression, Huffman coding compression algorithm will improve the data compression ratio.
{"title":"An Algorithm of Wavelet Data Compression Based on Wireless Sensor Network","authors":"Luo Xiao","doi":"10.6025/jdim/2023/21/1/1-8","DOIUrl":"https://doi.org/10.6025/jdim/2023/21/1/1-8","url":null,"abstract":"Firstly, this paper gives a data aggregation algorithm based on learning automata to solve the problem that the existing data aggregation algorithm can’t solve, the uneven energy cost, and the existing algorithm can’t change the gathering path dynamically existing the overhead environment. In the proposed method, nodes can change its gathering path to adjust the overhead environment. All the nodes of WSN equipped with a learning automata. These leaning automata learn all the gathering path of the nodes. In the process of transmit information two kinds of data are transmitted, including data packet, knowledge packet .When the information of the nodes changes, according to the feedback of the nods, the learning automata gives the reward or punish to the current gathering path, which help to find the best gathering path. Secondly, this paper improved the wavelet data compression algorithm, which was brought out as the correlation between different data. The algorithm do not reduce much of the data relate to the original data. After the wavelet data compression, Huffman coding compression algorithm will improve the data compression ratio.","PeriodicalId":303976,"journal":{"name":"J. Digit. Inf. Manag.","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121055579","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 : 2013-02-01DOI: 10.4156/jcit.vol8.issue8.50
Wei Chen, J. Shen, Jiabin Xue
This paper studies a low-cost computerbased 3D laser radar collection system. First, the control of actuator is realized by serial communication and the 2D image is captured from lines to surface, then denoise processing calibration is carried out by using Open CV. By using Irrlicht3D engine, the point cloud data is to be rendered to convert the 2D images to the 3D effect. Robot’s collection on external image is achieved through the study of Open CV learning that combined with VC2008.
{"title":"Study on a Robot 3D Laser Radar Information Collection System","authors":"Wei Chen, J. Shen, Jiabin Xue","doi":"10.4156/jcit.vol8.issue8.50","DOIUrl":"https://doi.org/10.4156/jcit.vol8.issue8.50","url":null,"abstract":"This paper studies a low-cost computerbased 3D laser radar collection system. First, the control of actuator is realized by serial communication and the 2D image is captured from lines to surface, then denoise processing calibration is carried out by using Open CV. By using Irrlicht3D engine, the point cloud data is to be rendered to convert the 2D images to the 3D effect. Robot’s collection on external image is achieved through the study of Open CV learning that combined with VC2008.","PeriodicalId":303976,"journal":{"name":"J. Digit. Inf. Manag.","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124974391","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}
This paper presents fuzzy clustering algorithms to establish a grassroots ontology – a machine-generated weak ontology – based on folksonomies. Furthermore, it describes a search engine for vaguely associated terms and aggregates them into several meaningful cluster categories, based on the introduced weak grassroots ontology. A potential application of this ontology, weblog extraction, is illustrated using a simple example. Added value and possible future studies are discussed in the conclusion.
{"title":"A Fuzzy Grassroots Ontology for improving Weblog Extraction","authors":"Edy Portmann, Andreas Meier","doi":"10.7892/BORIS.45584","DOIUrl":"https://doi.org/10.7892/BORIS.45584","url":null,"abstract":"This paper presents fuzzy clustering algorithms to establish a grassroots ontology – a machine-generated weak ontology – based on folksonomies. Furthermore, it describes a search engine for vaguely associated terms and aggregates them into several meaningful cluster categories, based on the introduced weak grassroots ontology. A potential application of this ontology, weblog extraction, is illustrated using a simple example. Added value and possible future studies are discussed in the conclusion.","PeriodicalId":303976,"journal":{"name":"J. Digit. Inf. Manag.","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122136554","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 : 2010-07-07DOI: 10.1007/978-3-642-14306-9_17
Mohammad Hassan, Yaser A. Al-Lahham
{"title":"Locality Preserving Scheme of Text Databases Representative in Distributed Information Retrieval Systems","authors":"Mohammad Hassan, Yaser A. Al-Lahham","doi":"10.1007/978-3-642-14306-9_17","DOIUrl":"https://doi.org/10.1007/978-3-642-14306-9_17","url":null,"abstract":"","PeriodicalId":303976,"journal":{"name":"J. Digit. Inf. Manag.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129474872","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：