Pub Date : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860253
Muḥammad Mahdī, Nafisa Anzum, Farzanah Siddique, Md. Rashidujjaman Rifat, Kazi Shahidullah, A. İslam
Education, i.e., the backbone of a nation, encompasses a variety of role players and stakeholders among which students are, perhaps, the most important one. However, analyzing students' feedback on institutional education system from a macro level is yet to be done in the literature. To address this issue, in this paper, we conduct a study on different perspectives of institutional education based on students' feedback. Here, we mostly focus on the institutional education in Bangladesh. Our study is based on the data collected from the students through both on-line and offline surveys. We analyze the collected data to dig out various key aspects such as appropriateness of educational contents, relationship between teachers and students, and extents of malpractice in the institutional education. Additionally, we attempt for identifying different personalities who exhibit significant influence on the students. Our study reveals a number of key findings that may facilitate effective reformation and enhancement of the current educational system under focus.
{"title":"A tale of institutional education in Bangladesh: Students' perspective","authors":"Muḥammad Mahdī, Nafisa Anzum, Farzanah Siddique, Md. Rashidujjaman Rifat, Kazi Shahidullah, A. İslam","doi":"10.1109/ICCITECHN.2016.7860253","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860253","url":null,"abstract":"Education, i.e., the backbone of a nation, encompasses a variety of role players and stakeholders among which students are, perhaps, the most important one. However, analyzing students' feedback on institutional education system from a macro level is yet to be done in the literature. To address this issue, in this paper, we conduct a study on different perspectives of institutional education based on students' feedback. Here, we mostly focus on the institutional education in Bangladesh. Our study is based on the data collected from the students through both on-line and offline surveys. We analyze the collected data to dig out various key aspects such as appropriateness of educational contents, relationship between teachers and students, and extents of malpractice in the institutional education. Additionally, we attempt for identifying different personalities who exhibit significant influence on the students. Our study reveals a number of key findings that may facilitate effective reformation and enhancement of the current educational system under focus.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132152634","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860212
Md. Moinul Hoque, P. Quaresma
The current work blends the different paradigms of Question Answering systems and presents a content-aware hybrid architecture for an open-domain factoid questions. It combines a knowledge-based, information extraction-based and a web-based approach in a pipelined architecture to construct an answer to a question keeping the context and discourse of the question in view. The proposed semantic-aware hybrid architecture was compared with other QA systems designed over standard benchmark data. The work has shown enough potential in terms of accuracy and time domain complexity and can be used effectively as a semantic understanding-based QA system.
{"title":"A content-aware hybrid architecture for answering questions from open-domain texts","authors":"Md. Moinul Hoque, P. Quaresma","doi":"10.1109/ICCITECHN.2016.7860212","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860212","url":null,"abstract":"The current work blends the different paradigms of Question Answering systems and presents a content-aware hybrid architecture for an open-domain factoid questions. It combines a knowledge-based, information extraction-based and a web-based approach in a pipelined architecture to construct an answer to a question keeping the context and discourse of the question in view. The proposed semantic-aware hybrid architecture was compared with other QA systems designed over standard benchmark data. The work has shown enough potential in terms of accuracy and time domain complexity and can be used effectively as a semantic understanding-based QA system.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"378 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122992164","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860223
Protik Chandra Biswas, Mohiudding Ahmad
Support Vector Machine (SVM) is one of the most popular machine learning algorithms for pattern recognition of a specific dataset. The percentage of accuracy from a defined SVM model greatly depends on the selection of appropriate attributes for SVM model. But the most effective attributes selection for SVM algorithm is one of the most difficult tasks for any kind of data classification. A mathematical model is proposed in this paper through which effectiveness of attributes for SVM model can be calculated. The validity of this SVM model is justified by comparing the effectiveness of a SVM model with the rate of pattern recognition for corresponding SVM model. Linear, Radial Basis Function (RBF), Polynomial Kernel SVM algorithms are used for pattern recognition. The percentage of accuracy of pattern recognition increases with the effectiveness of SVM model. The range of value of effectiveness of SVM model is 0 to
{"title":"A novel approach to select most effective attributes for SVM algorithm","authors":"Protik Chandra Biswas, Mohiudding Ahmad","doi":"10.1109/ICCITECHN.2016.7860223","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860223","url":null,"abstract":"Support Vector Machine (SVM) is one of the most popular machine learning algorithms for pattern recognition of a specific dataset. The percentage of accuracy from a defined SVM model greatly depends on the selection of appropriate attributes for SVM model. But the most effective attributes selection for SVM algorithm is one of the most difficult tasks for any kind of data classification. A mathematical model is proposed in this paper through which effectiveness of attributes for SVM model can be calculated. The validity of this SVM model is justified by comparing the effectiveness of a SVM model with the rate of pattern recognition for corresponding SVM model. Linear, Radial Basis Function (RBF), Polynomial Kernel SVM algorithms are used for pattern recognition. The percentage of accuracy of pattern recognition increases with the effectiveness of SVM model. The range of value of effectiveness of SVM model is 0 to <x. We have tested our proposed algorithm for noninvasive Brain Computer Interface (BCI) system. The proposed mathematical model is applicable for any other linear or nonlinear system.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122649458","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860182
Md. Shohag Hossain, N. K. Roy, Md. Osman Ali
This work presents a Simulink-based model of a photovoltaic (PV) system using a single-diode and two-diode model of solar cell. A comparison between the two-diode and single-diode model of PV cell has been illustrated. In addition, the output of series-parallel connection of PV cells has been examined. In the model, series and shunt resistances are calculated by an efficient iteration method based on open-circuit voltage, short-circuit current and irradiance values. The PV module implemented in Simulink/MATLAB considers five parameters. The parameters are series and shunt resistance, reverse saturation current, photocurrent and ideality factor. Approximate parameters are obtained from the manufacturers datasheets. The model includes light intensity and ambient temperature as input. Power, cell temperature and voltage as well as any measurements of interests are the outputs. For the grid connection of solar cell, inverter, filter and a step-up transformer is utilized. The performance of the model is found satisfactory.
{"title":"Modeling of solar photovoltaic system using MATLAB/Simulink","authors":"Md. Shohag Hossain, N. K. Roy, Md. Osman Ali","doi":"10.1109/ICCITECHN.2016.7860182","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860182","url":null,"abstract":"This work presents a Simulink-based model of a photovoltaic (PV) system using a single-diode and two-diode model of solar cell. A comparison between the two-diode and single-diode model of PV cell has been illustrated. In addition, the output of series-parallel connection of PV cells has been examined. In the model, series and shunt resistances are calculated by an efficient iteration method based on open-circuit voltage, short-circuit current and irradiance values. The PV module implemented in Simulink/MATLAB considers five parameters. The parameters are series and shunt resistance, reverse saturation current, photocurrent and ideality factor. Approximate parameters are obtained from the manufacturers datasheets. The model includes light intensity and ambient temperature as input. Power, cell temperature and voltage as well as any measurements of interests are the outputs. For the grid connection of solar cell, inverter, filter and a step-up transformer is utilized. The performance of the model is found satisfactory.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"20 3-4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114008284","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860214
Umme Aymun Siddiqua, Tanveer Ahsan, Abu Nowshed Chy
Microblog, especially Twitter, have become an integral part of our daily life, where millions of users sharing their thoughts daily because of its short length characteristics and simple manner of expression. Monitoring and analyzing sentiments from such massive Twitter posts provide enormous opportunities for companies and other organizations to estimate the user acceptance of their products and services. But the ever-growing unstructured and informal user-generated posts in Twitter demands sentiment analysis tools that can automatically infer sentiments from Twitter posts. In this paper, we propose an approach for sentiment analysis on Twitter, where we combine a rule-based classifier with a majority voting based ensemble of supervised classifiers. We introduce a set of rules for the rule-based classifier based on the occurrences of emoticons and sentiment-bearing words. To train the supervised classifiers, we extract a set of features grouped into Twitter specific features, textual features, parts-of-speech (POS) features, lexicon based features, and bag-of-words (BoW) feature. A supervised feature selection method based on the chi-square statistics (χ2) and information gain (IG) is applied to select the best feature combination. We conducted our experiments on Stanford sentiment140 dataset. Experimental results demonstrate the effectiveness of our method over the baseline and known related work.
{"title":"Combining a rule-based classifier with ensemble of feature sets and machine learning techniques for sentiment analysis on microblog","authors":"Umme Aymun Siddiqua, Tanveer Ahsan, Abu Nowshed Chy","doi":"10.1109/ICCITECHN.2016.7860214","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860214","url":null,"abstract":"Microblog, especially Twitter, have become an integral part of our daily life, where millions of users sharing their thoughts daily because of its short length characteristics and simple manner of expression. Monitoring and analyzing sentiments from such massive Twitter posts provide enormous opportunities for companies and other organizations to estimate the user acceptance of their products and services. But the ever-growing unstructured and informal user-generated posts in Twitter demands sentiment analysis tools that can automatically infer sentiments from Twitter posts. In this paper, we propose an approach for sentiment analysis on Twitter, where we combine a rule-based classifier with a majority voting based ensemble of supervised classifiers. We introduce a set of rules for the rule-based classifier based on the occurrences of emoticons and sentiment-bearing words. To train the supervised classifiers, we extract a set of features grouped into Twitter specific features, textual features, parts-of-speech (POS) features, lexicon based features, and bag-of-words (BoW) feature. A supervised feature selection method based on the chi-square statistics (χ2) and information gain (IG) is applied to select the best feature combination. We conducted our experiments on Stanford sentiment140 dataset. Experimental results demonstrate the effectiveness of our method over the baseline and known related work.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"50 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122697626","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860242
Sudipta Paul, Nurani Saoda, S M Mahbubur Rahman, D. Hatzinakos
Automatic prediction of continuous level emotional state requires selection of suitable affective features to develop a regression system based on supervised machine learning. This paper investigates the performance of low-level dynamic features for predicting two common dimensions of emotional state, namely, valence and arousal instantaneously. Low-complexity features are extracted from audio and visual modalities independently and fused in the feature level. Features with minimum redundancy and maximum relevancy are chosen by using the mutual information-based selection process. The performance of frame-by-frame prediction of emotional state using the moderate length features as proposed in this paper is evaluated on spontaneous and naturalistic human-human conversation of SEMAINE database. Experimental results show that the proposed features selected by mutual information can be used for instantaneous prediction of emotional state with an accuracy higher than traditional audio or visual features that are used for affective computation.
{"title":"Mutual information-based selection of audiovisual affective features to predict instantaneous emotional state","authors":"Sudipta Paul, Nurani Saoda, S M Mahbubur Rahman, D. Hatzinakos","doi":"10.1109/ICCITECHN.2016.7860242","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860242","url":null,"abstract":"Automatic prediction of continuous level emotional state requires selection of suitable affective features to develop a regression system based on supervised machine learning. This paper investigates the performance of low-level dynamic features for predicting two common dimensions of emotional state, namely, valence and arousal instantaneously. Low-complexity features are extracted from audio and visual modalities independently and fused in the feature level. Features with minimum redundancy and maximum relevancy are chosen by using the mutual information-based selection process. The performance of frame-by-frame prediction of emotional state using the moderate length features as proposed in this paper is evaluated on spontaneous and naturalistic human-human conversation of SEMAINE database. Experimental results show that the proposed features selected by mutual information can be used for instantaneous prediction of emotional state with an accuracy higher than traditional audio or visual features that are used for affective computation.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264660","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860203
Biswabandhu Jana, S. Mitra, K. Oswal, G. Saha, S. Banerjee
Ultrasound (US) Doppler spectrograms have been widely used for diagnosing vascular obstructions. This paper presents an Android smartphone based new approach for detecting the blood flow condition based on the US Doppler spectrogram images. A set of 59 spectrograms acquired from a US Doppler system is processed to extract features, and these non-redundant features are fed into a supervised classifier to determine the normal and abnormal blood flow. The classification is performed using the k-nearest neighbors (k-NN), Support vector machine (SVM), Naive Bayes (NB) and Multilayer perception (MLP) based classifiers. The SVM based classifier has shown superior performance, having an accuracy of 86.4 %, with a sensitivity and specificity of 96.4 % and 77.4 % respectively. The complete technique is implemented as an Android application and the results show the efficacy of the presented approach for the automated diagnosis of arterial diseases.
{"title":"Smartphone based blood flow feature extraction and classification from Doppler spectrum images","authors":"Biswabandhu Jana, S. Mitra, K. Oswal, G. Saha, S. Banerjee","doi":"10.1109/ICCITECHN.2016.7860203","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860203","url":null,"abstract":"Ultrasound (US) Doppler spectrograms have been widely used for diagnosing vascular obstructions. This paper presents an Android smartphone based new approach for detecting the blood flow condition based on the US Doppler spectrogram images. A set of 59 spectrograms acquired from a US Doppler system is processed to extract features, and these non-redundant features are fed into a supervised classifier to determine the normal and abnormal blood flow. The classification is performed using the k-nearest neighbors (k-NN), Support vector machine (SVM), Naive Bayes (NB) and Multilayer perception (MLP) based classifiers. The SVM based classifier has shown superior performance, having an accuracy of 86.4 %, with a sensitivity and specificity of 96.4 % and 77.4 % respectively. The complete technique is implemented as an Android application and the results show the efficacy of the presented approach for the automated diagnosis of arterial diseases.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129560790","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860200
S. Sabab, Md. Hamjajul Ashmafee
In the real world, books and documents are the sources of knowledge. But this knowledge is only bounded to people with clear vision. Our society includes a group of people who does not have a clear vision or people who are blind. For this group, world is like a black illusion. The shape and structure's information of an object is unavailable to them let alone reading a document. For blind acquiring knowledge by reading documents is cumbersome. Braille is one of the methods which is used to read a book or document. In this method, any document has to be converted to braille format to become understandable to a blind. The problem arises due to the fact that, this is an expensive procedure and many times not available. The solution is rather simple, introduce a smart device with a multimodal system that can convert any document to the interpreted form to a blind. A blind can read document only by tapping words which is then audibly presented through text to speech engine. “Blind Reader” — developed for touch devices which is user friendly and effective interactive system for visionless or low vision people.
{"title":"Blind Reader: An intelligent assistant for blind","authors":"S. Sabab, Md. Hamjajul Ashmafee","doi":"10.1109/ICCITECHN.2016.7860200","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860200","url":null,"abstract":"In the real world, books and documents are the sources of knowledge. But this knowledge is only bounded to people with clear vision. Our society includes a group of people who does not have a clear vision or people who are blind. For this group, world is like a black illusion. The shape and structure's information of an object is unavailable to them let alone reading a document. For blind acquiring knowledge by reading documents is cumbersome. Braille is one of the methods which is used to read a book or document. In this method, any document has to be converted to braille format to become understandable to a blind. The problem arises due to the fact that, this is an expensive procedure and many times not available. The solution is rather simple, introduce a smart device with a multimodal system that can convert any document to the interpreted form to a blind. A blind can read document only by tapping words which is then audibly presented through text to speech engine. “Blind Reader” — developed for touch devices which is user friendly and effective interactive system for visionless or low vision people.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"517 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116334941","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860237
A. Chowdhury, M. S. Rahman
This work attempts to find the most optimal setting for a convolutional neural network (CNN) for Bengali digit dataset classification. Recognition of handwritten Bengali numerals has recently gained much interest among researchers due to the significant performance gain found in the recognition of English numerals using neural network based architecture. In this work, a new dataset of 70,000 samples were created first by taking handwriting of 1750 persons where 982 persons were male and the rests were female. These individual image samples are then converted to grayscale, normalized, inverted and pickled to complete the data preprocessing step. Later this dataset was recognized using several convolutional neural network settings where the most optimal setting being found to be two convolution layer with Tanh activation, one hidden layer with Tanh activation and one output layer with softmax activation. The proposed optimal number of feature maps is (35, 45). The minimum validation error has been found to be 1.22% which is the current best result compared to all other methods in the literature.
{"title":"Towards optimal convolutional neural network parameters for bengali handwritten numerals recognition","authors":"A. Chowdhury, M. S. Rahman","doi":"10.1109/ICCITECHN.2016.7860237","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860237","url":null,"abstract":"This work attempts to find the most optimal setting for a convolutional neural network (CNN) for Bengali digit dataset classification. Recognition of handwritten Bengali numerals has recently gained much interest among researchers due to the significant performance gain found in the recognition of English numerals using neural network based architecture. In this work, a new dataset of 70,000 samples were created first by taking handwriting of 1750 persons where 982 persons were male and the rests were female. These individual image samples are then converted to grayscale, normalized, inverted and pickled to complete the data preprocessing step. Later this dataset was recognized using several convolutional neural network settings where the most optimal setting being found to be two convolution layer with Tanh activation, one hidden layer with Tanh activation and one output layer with softmax activation. The proposed optimal number of feature maps is (35, 45). The minimum validation error has been found to be 1.22% which is the current best result compared to all other methods in the literature.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124236981","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 : 2016-12-01DOI: 10.1109/ICCITECHN.2016.7860193
Rim Afdhal, R. Ejbali, M. Zaied
The emotion recognition has become a hot research topic in different domains: Human-Machine-Interaction, Natural Language processing etc. Recent research in the domain of Human Computer Interaction aims at recognizing the user's emotional state to give a smooth interface between humans and computers and to improve their interaction. In this paper we propose an emotion recognition system based on the analysis of the shapes of the wrinkles. The system contains four steps. The first one is detection of face's elements which is realized by the Viola and Jones detector. The second is localization of the wrinkles which is achieved automatically. Then, the information extraction. Finally, the classification using the wavelet network.
情感识别已成为人机交互、自然语言处理等领域的研究热点。人机交互领域的最新研究旨在识别用户的情感状态，为人机交互提供一个流畅的界面，从而改善人机交互。本文提出了一种基于皱纹形状分析的情绪识别系统。该系统包含四个步骤。首先是人脸元素的检测，由Viola and Jones检测器实现。二是自动定位皱纹。然后，进行信息提取。最后，利用小波网络进行分类。
{"title":"Emotion recognition using the shapes of the wrinkles","authors":"Rim Afdhal, R. Ejbali, M. Zaied","doi":"10.1109/ICCITECHN.2016.7860193","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2016.7860193","url":null,"abstract":"The emotion recognition has become a hot research topic in different domains: Human-Machine-Interaction, Natural Language processing etc. Recent research in the domain of Human Computer Interaction aims at recognizing the user's emotional state to give a smooth interface between humans and computers and to improve their interaction. In this paper we propose an emotion recognition system based on the analysis of the shapes of the wrinkles. The system contains four steps. The first one is detection of face's elements which is realized by the Viola and Jones detector. The second is localization of the wrinkles which is achieved automatically. Then, the information extraction. Finally, the classification using the wavelet network.","PeriodicalId":287635,"journal":{"name":"2016 19th International Conference on Computer and Information Technology (ICCIT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126491972","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：