Pub Date : 2015-07-09DOI: 10.1109/ReTIS.2015.7232859
A. Ghosh, Tamal Das, Soumyo Chatterjee, S. Chatterjee
In this article, a comparative study between population based optimization methods with random and restricted search space definition applied in the pattern synthesis of linear antenna arrays is presented. Synthesis problem of reduced side lobe level and narrow beamwidth is considered. The design objective further considers the optimization of excitation amplitude and uniform inter element spacing using random and restricted search space definition by particle swarm optimization and differential evolution methods. As examples simulation of 12 and 21 elements have been considered. Effectiveness of the restriction in search space is proved through statistical and parametric analysis. Further comparison with published work has been carried out to prove the superiority of restricted search Particle Swarm Optimization.
{"title":"Linear array pattern synthesis using restriction in search space for evolutionary algorithms: A comparative study","authors":"A. Ghosh, Tamal Das, Soumyo Chatterjee, S. Chatterjee","doi":"10.1109/ReTIS.2015.7232859","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232859","url":null,"abstract":"In this article, a comparative study between population based optimization methods with random and restricted search space definition applied in the pattern synthesis of linear antenna arrays is presented. Synthesis problem of reduced side lobe level and narrow beamwidth is considered. The design objective further considers the optimization of excitation amplitude and uniform inter element spacing using random and restricted search space definition by particle swarm optimization and differential evolution methods. As examples simulation of 12 and 21 elements have been considered. Effectiveness of the restriction in search space is proved through statistical and parametric analysis. Further comparison with published work has been carried out to prove the superiority of restricted search Particle Swarm Optimization.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"286 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116109516","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232850
Mehr-e Munir, Ahsan Altaf, Muhammad Hasnain
A novel technique for miniaturization of microstrip patch antenna is proposed for Portable and multifunctional Communication systems. Our proposed design consists of fractal patch, H-Shape slot on fractal patch with first iteration and combination of L-Shape and U-Shape slots on the Ground plane. In this way we get smaller size antenna which is smaller than the conventional antenna. The most interesting feature of our proposed design is that we are getting multiband response in the frequency range of 1-8GHZ having Directivity in the range of 4.37dBi-5.31dBi, Gain in the range of 2.12dB-3.87dB and good impedance bandwidth for desired bands. As we have used the fractal patch with substrate in which substrate is FR4. Co-axial cable is used as a feeding method. We also employed shorting pin between fractal patch and ground plane. By the combination of all these proposed technique size of antenna is reduced 66.50% and it produces multiband response while the impedance bandwidth and gain are satisfactory for each band. We can adjust different bands by changing position of shorting pin. This type of smaller size antenna has applications in mobile phone for Wi-Fi, WALAN, Wi-Max, Bluetooth, C-band, S-band, ZigBee and also for other wireless applications.
{"title":"Miniaturization of microstrip fractal H-Shape patch antenna using stack configuration for wireless applications","authors":"Mehr-e Munir, Ahsan Altaf, Muhammad Hasnain","doi":"10.1109/ReTIS.2015.7232850","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232850","url":null,"abstract":"A novel technique for miniaturization of microstrip patch antenna is proposed for Portable and multifunctional Communication systems. Our proposed design consists of fractal patch, H-Shape slot on fractal patch with first iteration and combination of L-Shape and U-Shape slots on the Ground plane. In this way we get smaller size antenna which is smaller than the conventional antenna. The most interesting feature of our proposed design is that we are getting multiband response in the frequency range of 1-8GHZ having Directivity in the range of 4.37dBi-5.31dBi, Gain in the range of 2.12dB-3.87dB and good impedance bandwidth for desired bands. As we have used the fractal patch with substrate in which substrate is FR4. Co-axial cable is used as a feeding method. We also employed shorting pin between fractal patch and ground plane. By the combination of all these proposed technique size of antenna is reduced 66.50% and it produces multiband response while the impedance bandwidth and gain are satisfactory for each band. We can adjust different bands by changing position of shorting pin. This type of smaller size antenna has applications in mobile phone for Wi-Fi, WALAN, Wi-Max, Bluetooth, C-band, S-band, ZigBee and also for other wireless applications.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116552014","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232862
Siddharth J. Mehta, Jinkal Javia
Recommender systems attempt to predict the preference/ratings that a user would give to an item. Traditional collaborative filtering give recommendation to a user based on its similarity of ratings with the ratings of other users in the system. But they face issues such as sparsity, cold start problem, first rater problem and scalability. In the proposed framework, a user is being recommended by filtering K random users whose similarity is crossing some threshold and applying collaborative filtering only on those users. For the users/items visiting for the first time, demographic information is used. In it, demographics of users/item visiting for the first time are compared with users/item in system and discarding that user/item if a single mismatch is found. This framework has less MAE as compared to KNN or user based collaborative filtering, takes very less time to recommend as compared to above mentioned algorithms, as only K neighbors need to be considered.
{"title":"Threshold based KNN for fast and more accurate recommendations","authors":"Siddharth J. Mehta, Jinkal Javia","doi":"10.1109/ReTIS.2015.7232862","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232862","url":null,"abstract":"Recommender systems attempt to predict the preference/ratings that a user would give to an item. Traditional collaborative filtering give recommendation to a user based on its similarity of ratings with the ratings of other users in the system. But they face issues such as sparsity, cold start problem, first rater problem and scalability. In the proposed framework, a user is being recommended by filtering K random users whose similarity is crossing some threshold and applying collaborative filtering only on those users. For the users/items visiting for the first time, demographic information is used. In it, demographics of users/item visiting for the first time are compared with users/item in system and discarding that user/item if a single mismatch is found. This framework has less MAE as compared to KNN or user based collaborative filtering, takes very less time to recommend as compared to above mentioned algorithms, as only K neighbors need to be considered.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124738359","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232904
Hossam S. Ibrahim, Sherif M. Abdou, M. Gheith
Sentiment analysis (SA) and opinion mining (OM) becomes a field of interest that fueled the attention of research during the last decade, due to the rise of the amount of internet documents (especially online reviews and comments) on the social media such as blogs and social networks. Many attempts have been conducted to build a corpus for SA, due to the consideration of importance of building such resource as a key factor in SA and OM systems. But the need of building these resources is still ongoing, especially for morphologically-Rich language (MRL) such as Arabic. In this paper, we present MIKA a multi-genre tagged corpus of modern standard Arabic (MSA) and colloquial. MIKA is manually collected and annotated at sentence level with semantic orientation (positive or negative or neutral). A number of rich set of linguistically motivated features (contextual Intensifiers, contextual Shifter and negation handling), syntactic features for conflicting phrases and others are used for the annotation process. Our data focus on MSA and Egyptian dialectal Arabic. We report the efforts of manually building and annotating our sentiment corpus using different types of data, such as tweets and Arabic microblogs (hotel reservation, product reviews, and TV program comments).
{"title":"MIKA: A tagged corpus for modern standard Arabic and colloquial sentiment analysis","authors":"Hossam S. Ibrahim, Sherif M. Abdou, M. Gheith","doi":"10.1109/ReTIS.2015.7232904","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232904","url":null,"abstract":"Sentiment analysis (SA) and opinion mining (OM) becomes a field of interest that fueled the attention of research during the last decade, due to the rise of the amount of internet documents (especially online reviews and comments) on the social media such as blogs and social networks. Many attempts have been conducted to build a corpus for SA, due to the consideration of importance of building such resource as a key factor in SA and OM systems. But the need of building these resources is still ongoing, especially for morphologically-Rich language (MRL) such as Arabic. In this paper, we present MIKA a multi-genre tagged corpus of modern standard Arabic (MSA) and colloquial. MIKA is manually collected and annotated at sentence level with semantic orientation (positive or negative or neutral). A number of rich set of linguistically motivated features (contextual Intensifiers, contextual Shifter and negation handling), syntactic features for conflicting phrases and others are used for the annotation process. Our data focus on MSA and Egyptian dialectal Arabic. We report the efforts of manually building and annotating our sentiment corpus using different types of data, such as tweets and Arabic microblogs (hotel reservation, product reviews, and TV program comments).","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124066093","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232906
Vandana Jha, N. Manjunath, P. D. Shenoy, K. Venugopal, L. Patnaik
With the increasing popularity of the Web 2.0, we are provided with more documents which express opinions on different issues. Online posting reviews has become an increasingly preferred way for people to express opinions and sentiments towards the products bought/used or services received. Analysing the large volume of online review data available, would produce useful knowledge, which could be of economic values to vendors and other interested parties. A lot of work in Opinion Mining exists for English language. In the last few years, web contents are increasing in other languages also at a faster rate and hence there is a requirement to execute opinion mining in other languages. In this paper, a Hindi Opinion Mining System (HOMS) is proposed for movie review data. It performs the task of opinion mining at the document level and classifies the documents as positive, negative and neutral using two different methods: Machine learning technique and Part-Of-Speech (POS) tagging. We have used Naive Bayes Classifier for Machine learning and in POS tagging, we have considered adjectives as opinion words. Extensive simulations conducted on a large movie data set confirms the effectiveness of the proposed approach.
{"title":"HOMS: Hindi opinion mining system","authors":"Vandana Jha, N. Manjunath, P. D. Shenoy, K. Venugopal, L. Patnaik","doi":"10.1109/ReTIS.2015.7232906","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232906","url":null,"abstract":"With the increasing popularity of the Web 2.0, we are provided with more documents which express opinions on different issues. Online posting reviews has become an increasingly preferred way for people to express opinions and sentiments towards the products bought/used or services received. Analysing the large volume of online review data available, would produce useful knowledge, which could be of economic values to vendors and other interested parties. A lot of work in Opinion Mining exists for English language. In the last few years, web contents are increasing in other languages also at a faster rate and hence there is a requirement to execute opinion mining in other languages. In this paper, a Hindi Opinion Mining System (HOMS) is proposed for movie review data. It performs the task of opinion mining at the document level and classifies the documents as positive, negative and neutral using two different methods: Machine learning technique and Part-Of-Speech (POS) tagging. We have used Naive Bayes Classifier for Machine learning and in POS tagging, we have considered adjectives as opinion words. Extensive simulations conducted on a large movie data set confirms the effectiveness of the proposed approach.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"os-38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127777709","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232894
Ujjwal Manikya Nath, S. Datta, C. Dey
Multiple interconnected tanks supplied by more than one pump is a MIMO process which is quite common for industrial applications. Presently, Internal Model Control (IMC) technique is widely used in controlling industrial MIMO processes due to its sole tuning parameter. But, as the IMC technique is entirely based on the process model hence in case of any uncertainty in modeling, nonlinear interacting behavior as well as time varying features of the process parameters impose limitations on the performance of IMC controllers. To overcome such limitations, in the proposed work, a simple auto-tuning scheme is incorporated in the conventional IMC based Proportional Integral controller (IMC-PI). In the proposed auto-tuner, the only tuning parameter i.e., the close-loop time constant is continuously varied depending on the instantaneous process error. Performance of the proposed auto-tuned IMC-PI controller (IMC-API) along with conventional IMC-PI controller are verified on a miniaturized industrial coupled tank process which is a well known interacting MIMO process. Here, control task is aimed towards maintaining the water levels at the respective desired values under both the set point change and load disturbance. Controlling MIMO processes inherently includes uncertainties which have to be taken care through adequate control design. Therefore, stability study of a close-loop system along with robustness of controller has to be ensured against process model perturbation. Experimental results substantiate the performance superiority along with its robustness of the proposed IMC-API compared to conventional IMC-PI controllers.
{"title":"Centralized auto-tuned IMC-PI controllers for industrial coupled tank process with stability analysis","authors":"Ujjwal Manikya Nath, S. Datta, C. Dey","doi":"10.1109/ReTIS.2015.7232894","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232894","url":null,"abstract":"Multiple interconnected tanks supplied by more than one pump is a MIMO process which is quite common for industrial applications. Presently, Internal Model Control (IMC) technique is widely used in controlling industrial MIMO processes due to its sole tuning parameter. But, as the IMC technique is entirely based on the process model hence in case of any uncertainty in modeling, nonlinear interacting behavior as well as time varying features of the process parameters impose limitations on the performance of IMC controllers. To overcome such limitations, in the proposed work, a simple auto-tuning scheme is incorporated in the conventional IMC based Proportional Integral controller (IMC-PI). In the proposed auto-tuner, the only tuning parameter i.e., the close-loop time constant is continuously varied depending on the instantaneous process error. Performance of the proposed auto-tuned IMC-PI controller (IMC-API) along with conventional IMC-PI controller are verified on a miniaturized industrial coupled tank process which is a well known interacting MIMO process. Here, control task is aimed towards maintaining the water levels at the respective desired values under both the set point change and load disturbance. Controlling MIMO processes inherently includes uncertainties which have to be taken care through adequate control design. Therefore, stability study of a close-loop system along with robustness of controller has to be ensured against process model perturbation. Experimental results substantiate the performance superiority along with its robustness of the proposed IMC-API compared to conventional IMC-PI controllers.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129709032","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232849
Upasana Talukdar, R. Baruah, S. Hazarika
Learning patterns from spatio-temporal data streams is an important problem within Artificial Intelligence. Knowledge is important for recognition of patterns. Representation of large and diverse knowledge requires formal basis. Description Logics (DLs) constitute a family of knowledge representation formalism which provide object-oriented representation with formal semantics. Qualitative spatial and temporal reasoning (QSTR) encompass efforts devoted to providing useful and well-grounded models to be used as high level qualitative descriptions of spatio-temporal change. In this paper we combine DL with QSTR and put forward a formal, explicit knowledge representation formalism for representation of motion patterns. Reasoning services of the DL system is used for recognizing motion patterns from spatio-temporal data.
{"title":"A description logic based QSTR framework for recognizing motion patterns from spatio-temporal data","authors":"Upasana Talukdar, R. Baruah, S. Hazarika","doi":"10.1109/ReTIS.2015.7232849","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232849","url":null,"abstract":"Learning patterns from spatio-temporal data streams is an important problem within Artificial Intelligence. Knowledge is important for recognition of patterns. Representation of large and diverse knowledge requires formal basis. Description Logics (DLs) constitute a family of knowledge representation formalism which provide object-oriented representation with formal semantics. Qualitative spatial and temporal reasoning (QSTR) encompass efforts devoted to providing useful and well-grounded models to be used as high level qualitative descriptions of spatio-temporal change. In this paper we combine DL with QSTR and put forward a formal, explicit knowledge representation formalism for representation of motion patterns. Reasoning services of the DL system is used for recognizing motion patterns from spatio-temporal data.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126387025","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232895
S. Mukherjee, Sivaji Bandyopadhyay
A tree model is constructed for the econometric problem domain and for topic modeling of news reports using a clustering approach. Here segments are represented as discretized intervals defined on econometric variables for speeding up the construction of regression tree. This discretization is achieved from variances defined on variables with predictability for that generated for calculating category utility values defined on correlated variables where the discretization method proposed has the aim to satisfy a constraint of minimum entropy distribution of values of the predictor variable among the categories. An algorithm is proposed for tree merging which is used for incrementally incorporating information for new time intervals with the existing model to generate updated tree model for maintaining logical consistency. The tree merging algorithm has been shown to be suitable for applying to news report documents or econometric information. This is accomplished with a proposed Pruning procedure for maintaining logical consistency in the merged tree which is applied together with existing approaches for limiting pruning and access costs for reducing misclassification error.
{"title":"Clustering to determine predictive model for news reports analysis and econometric modeling","authors":"S. Mukherjee, Sivaji Bandyopadhyay","doi":"10.1109/ReTIS.2015.7232895","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232895","url":null,"abstract":"A tree model is constructed for the econometric problem domain and for topic modeling of news reports using a clustering approach. Here segments are represented as discretized intervals defined on econometric variables for speeding up the construction of regression tree. This discretization is achieved from variances defined on variables with predictability for that generated for calculating category utility values defined on correlated variables where the discretization method proposed has the aim to satisfy a constraint of minimum entropy distribution of values of the predictor variable among the categories. An algorithm is proposed for tree merging which is used for incrementally incorporating information for new time intervals with the existing model to generate updated tree model for maintaining logical consistency. The tree merging algorithm has been shown to be suitable for applying to news report documents or econometric information. This is accomplished with a proposed Pruning procedure for maintaining logical consistency in the merged tree which is applied together with existing approaches for limiting pruning and access costs for reducing misclassification error.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131745673","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232907
Amiya Samantaray, K. Mahapatra, Bibek Kabi, A. Routray
Speech emotion recognition is one of the recent challenges in speech processing and Human Computer Interaction (HCI) in order to address various operational needs for the real world applications. Besides human facial expressions, speech has been proven to be one of the most precious modalities for automatic recognition of human emotions. Speech is a spontaneous medium of perceiving emotions which provides in-depth information related to different cognitive states of a human being. In this context, a novel approach is being introduces using a combination of prosody features (i.e. pitch, energy, Zero crossing rate), quality features (i.e. Formant Frequencies, Spectral features etc.), derived features (i.e. Mel-Frequency Cepstral Coefficient (MFCC), Linear Predictive Coding Coefficients (LPCC)) and dynamic feature (Mel-Energy spectrum dynamic Coefficients (MEDC)) for robust automatic recognition of speaker's state of emotion. Multilevel SVM classifier is used for identification of seven discrete emotional states namely anger, disgust, fear, happy, neutral, sad and surprise in `Five native Assamese Languages'. The overall results of the conducted experiments revealed that the approach of using the combination of features achieved an average accuracy rate of 82.26% for speaker independent cases.
{"title":"A novel approach of speech emotion recognition with prosody, quality and derived features using SVM classifier for a class of North-Eastern Languages","authors":"Amiya Samantaray, K. Mahapatra, Bibek Kabi, A. Routray","doi":"10.1109/ReTIS.2015.7232907","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232907","url":null,"abstract":"Speech emotion recognition is one of the recent challenges in speech processing and Human Computer Interaction (HCI) in order to address various operational needs for the real world applications. Besides human facial expressions, speech has been proven to be one of the most precious modalities for automatic recognition of human emotions. Speech is a spontaneous medium of perceiving emotions which provides in-depth information related to different cognitive states of a human being. In this context, a novel approach is being introduces using a combination of prosody features (i.e. pitch, energy, Zero crossing rate), quality features (i.e. Formant Frequencies, Spectral features etc.), derived features (i.e. Mel-Frequency Cepstral Coefficient (MFCC), Linear Predictive Coding Coefficients (LPCC)) and dynamic feature (Mel-Energy spectrum dynamic Coefficients (MEDC)) for robust automatic recognition of speaker's state of emotion. Multilevel SVM classifier is used for identification of seven discrete emotional states namely anger, disgust, fear, happy, neutral, sad and surprise in `Five native Assamese Languages'. The overall results of the conducted experiments revealed that the approach of using the combination of features achieved an average accuracy rate of 82.26% for speaker independent cases.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130710591","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 : 2015-07-09DOI: 10.1109/ReTIS.2015.7232893
S. Mohanty, A. Mishra, D. C. Panda
Progress in the field of Information and Communication Technology (ICT) has benefited the e-Governance solutions with higher efficiency and better accountability. In this paper we have identified a domain of government which focuses on welfare schemes for the weaker sections of the society. For the better acceptability of the schemes, information sharing and analysis of the scheme related information is crucial. Bearing this in mind, we propose an e-Governance model, named as Intelligent Government Scheme Advisor (IGoSA), to facilitate as a decision support system with scheme based analysis for the citizens and government agencies. The main goal is to use the available information and experience present with government agencies and feedback from public to build more successful schemes by taking the help of machine learning techniques and emerging data management solutions.
{"title":"IGoSA — A novel framework for analysis of and facilitating government schemes","authors":"S. Mohanty, A. Mishra, D. C. Panda","doi":"10.1109/ReTIS.2015.7232893","DOIUrl":"https://doi.org/10.1109/ReTIS.2015.7232893","url":null,"abstract":"Progress in the field of Information and Communication Technology (ICT) has benefited the e-Governance solutions with higher efficiency and better accountability. In this paper we have identified a domain of government which focuses on welfare schemes for the weaker sections of the society. For the better acceptability of the schemes, information sharing and analysis of the scheme related information is crucial. Bearing this in mind, we propose an e-Governance model, named as Intelligent Government Scheme Advisor (IGoSA), to facilitate as a decision support system with scheme based analysis for the citizens and government agencies. The main goal is to use the available information and experience present with government agencies and feedback from public to build more successful schemes by taking the help of machine learning techniques and emerging data management solutions.","PeriodicalId":161306,"journal":{"name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122556879","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：