Pub Date : 2017-07-28DOI: 10.1109/CIVEMSA.2017.7995313
Ryo Oiwa, Takumi Ito, Takayuki Kawahara
The Timber Health Monitoring System, which enables constant monitoring of wooden buildings by artificial intelligence based analysis of the signals of a piezoelectric sensor attached to a piece of timber, is proposed. Basic verification was carried out by modeling timber damage and performing vibration tests. Analysis of the obtained waveform data using the k-nearest neighbor (k-NN) method and a support vector machine revealed that the proposed system has a strong classification performance. We also tried reducing the data dimensions by using principal component analysis and found that the classification rates barely decreased even if dimensional reduction was adopted. These results are promising for the realization of our proposed system.
{"title":"Timber Health Monitoring using piezoelectric sensor and machine learning","authors":"Ryo Oiwa, Takumi Ito, Takayuki Kawahara","doi":"10.1109/CIVEMSA.2017.7995313","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995313","url":null,"abstract":"The Timber Health Monitoring System, which enables constant monitoring of wooden buildings by artificial intelligence based analysis of the signals of a piezoelectric sensor attached to a piece of timber, is proposed. Basic verification was carried out by modeling timber damage and performing vibration tests. Analysis of the obtained waveform data using the k-nearest neighbor (k-NN) method and a support vector machine revealed that the proposed system has a strong classification performance. We also tried reducing the data dimensions by using principal component analysis and found that the classification rates barely decreased even if dimensional reduction was adopted. These results are promising for the realization of our proposed system.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115156349","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995296
Sumayh S. Aljameel, J. O'Shea, Keeley A. Crockett, A. Latham, M. Kaleem
This paper presents a novel Arabic Conversational Intelligent Tutoring System (CITS) that adapts the learning styles VAK for autistic children to enhance their learning. The proposed CITS architecture uses a combination of Arabic Pattern Matching and Arabic Short Text Similarity to extract the responses from the resources. The new Arabic CITS, known as LANA, is aimed at children with autism (10 to 16 years old) who have reached a basic competency with the mechanics of Arabic writing. This paper describes the architecture of LANA and its components. The experimental methodology is explained in order to conduct a pilot study in future.
{"title":"Development of an Arabic Conversational Intelligent Tutoring System for Education of children with ASD","authors":"Sumayh S. Aljameel, J. O'Shea, Keeley A. Crockett, A. Latham, M. Kaleem","doi":"10.1109/CIVEMSA.2017.7995296","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995296","url":null,"abstract":"This paper presents a novel Arabic Conversational Intelligent Tutoring System (CITS) that adapts the learning styles VAK for autistic children to enhance their learning. The proposed CITS architecture uses a combination of Arabic Pattern Matching and Arabic Short Text Similarity to extract the responses from the resources. The new Arabic CITS, known as LANA, is aimed at children with autism (10 to 16 years old) who have reached a basic competency with the mechanics of Arabic writing. This paper describes the architecture of LANA and its components. The experimental methodology is explained in order to conduct a pilot study in future.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131212936","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995339
B. Batalden, P. Leikanger, P. Wide
The main purpose to push the development towards autonomous maritime operations in shipping and offshore installations, is to increase the performance of maritime activities; by social benefits for staff or other related personal groups; by economic benefits when the ability to increase the cargo or effectuate better space allocation; by environmental benefits that's allow the ship operations to be optimized for routing, speed, etc.; and finally by an increased safety benefit in all these aspects. The increased use of artificial intelligent based benefits is expected to increase the operational performance of all the above aspects in the sense that an overall quality in logical and knowledge based will be consistent. The increased complexity of maritime activities and the offshore business requires more precise and automated solutions to achieve the expectations from staff, stakeholders, and society.
{"title":"Towards autonomous maritime operations","authors":"B. Batalden, P. Leikanger, P. Wide","doi":"10.1109/CIVEMSA.2017.7995339","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995339","url":null,"abstract":"The main purpose to push the development towards autonomous maritime operations in shipping and offshore installations, is to increase the performance of maritime activities; by social benefits for staff or other related personal groups; by economic benefits when the ability to increase the cargo or effectuate better space allocation; by environmental benefits that's allow the ship operations to be optimized for routing, speed, etc.; and finally by an increased safety benefit in all these aspects. The increased use of artificial intelligent based benefits is expected to increase the operational performance of all the above aspects in the sense that an overall quality in logical and knowledge based will be consistent. The increased complexity of maritime activities and the offshore business requires more precise and automated solutions to achieve the expectations from staff, stakeholders, and society.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"26 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126670705","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995302
Manuel R. Vargas, B. Lima, Alexandre Evsukoff
This work uses deep learning methods for intraday directional movements prediction of Standard & Poor's 500 index using financial news titles and a set of technical indicators as input. Deep learning methods can detect and analyze complex patterns and interactions in the data automatically allowing speed up the trading process. This paper focus on architectures such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), which have had good results in traditional NLP tasks. Results has shown that CNN can be better than RNN on catching semantic from texts and RNN is better on catching the context information and modeling complex temporal characteristics for stock market forecasting. The proposed method shows some improvement when compared with similar previous studies.
{"title":"Deep learning for stock market prediction from financial news articles","authors":"Manuel R. Vargas, B. Lima, Alexandre Evsukoff","doi":"10.1109/CIVEMSA.2017.7995302","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995302","url":null,"abstract":"This work uses deep learning methods for intraday directional movements prediction of Standard & Poor's 500 index using financial news titles and a set of technical indicators as input. Deep learning methods can detect and analyze complex patterns and interactions in the data automatically allowing speed up the trading process. This paper focus on architectures such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), which have had good results in traditional NLP tasks. Results has shown that CNN can be better than RNN on catching semantic from texts and RNN is better on catching the context information and modeling complex temporal characteristics for stock market forecasting. The proposed method shows some improvement when compared with similar previous studies.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128310470","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995298
B. Duthil, A. Imoussaten, J. Montmain
Nowadays, ecology and sustainable development are priority government's actions. In Europe, and more specifically in France, sustainable development (SD) is generally broken down into several distinct evaluation criteria. Each criterion is a requirement imposed by the government and corresponds to strategic stakes. When SD improvement actions are financed in an economic region or a city of the French territory by the government, a set of measures is usually set up to assess and control the impact of these actions. More precisely, these measures are used to check whether the region or the city has efficiently invested its budget in respect to the SD strategy of the government. This assessment process is a complex task for the government. Indeed, evaluations are only based on reports provided by the financed regions. These very numerous reports are written in natural language and thus, it is a thorny and time-consuming task for the government to efficiently identify the meaningful information in a plethora of reports and then objectively assess all the expected priorities. This project aims at automating the assessment process from the huge corpus of documents. Text-mining and segmentation techniques are introduced to automatically quantify the attention the region or the city pays to a given criterion. Obviously, this quantification can only be imprecisely determined. Then, the possibility theory is used to merge the information related to each criterion prioritization from all the documents. Finally, an application on the 265 largest cities in France shows the potential of the approach.
{"title":"A text-mining and possibility theory based model using public reports to highlight the sustainable development strategy of a city","authors":"B. Duthil, A. Imoussaten, J. Montmain","doi":"10.1109/CIVEMSA.2017.7995298","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995298","url":null,"abstract":"Nowadays, ecology and sustainable development are priority government's actions. In Europe, and more specifically in France, sustainable development (SD) is generally broken down into several distinct evaluation criteria. Each criterion is a requirement imposed by the government and corresponds to strategic stakes. When SD improvement actions are financed in an economic region or a city of the French territory by the government, a set of measures is usually set up to assess and control the impact of these actions. More precisely, these measures are used to check whether the region or the city has efficiently invested its budget in respect to the SD strategy of the government. This assessment process is a complex task for the government. Indeed, evaluations are only based on reports provided by the financed regions. These very numerous reports are written in natural language and thus, it is a thorny and time-consuming task for the government to efficiently identify the meaningful information in a plethora of reports and then objectively assess all the expected priorities. This project aims at automating the assessment process from the huge corpus of documents. Text-mining and segmentation techniques are introduced to automatically quantify the attention the region or the city pays to a given criterion. Obviously, this quantification can only be imprecisely determined. Then, the possibility theory is used to merge the information related to each criterion prioritization from all the documents. Finally, an application on the 265 largest cities in France shows the potential of the approach.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127965234","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995292
S. Maleki, C. Bingham
A new Cluster-based methodology for real-time Novelty Detection and Isolation (NDI) in sensor networks, is presented. The proposed algorithm enables uniform clustering across time-frames to indicate the presence of a “healthy” network. In the event of novelty, the associated sensor is seen to be clustered in a non-uniform manner with respect other sensors in the network, thereby facilitating fault isolation. Moreover, a statistical approach is proposed to determine a noise tolerance level for reducing false alarms. Performance of the proposed algorithm is examined using datasets obtained from a number of industrial case studies, and the significance for fault detection for such systems is demonstrated. Specifically, it is shown that through a correct selection of the noise tolerance level, an emerging failure is successfully isolated in presence of other abrupt changes that visually might be perceived as indication of a failure.
{"title":"A one-class Clustering technique for Novelty Detection and Isolation in sensor networks","authors":"S. Maleki, C. Bingham","doi":"10.1109/CIVEMSA.2017.7995292","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995292","url":null,"abstract":"A new Cluster-based methodology for real-time Novelty Detection and Isolation (NDI) in sensor networks, is presented. The proposed algorithm enables uniform clustering across time-frames to indicate the presence of a “healthy” network. In the event of novelty, the associated sensor is seen to be clustered in a non-uniform manner with respect other sensors in the network, thereby facilitating fault isolation. Moreover, a statistical approach is proposed to determine a noise tolerance level for reducing false alarms. Performance of the proposed algorithm is examined using datasets obtained from a number of industrial case studies, and the significance for fault detection for such systems is demonstrated. Specifically, it is shown that through a correct selection of the noise tolerance level, an emerging failure is successfully isolated in presence of other abrupt changes that visually might be perceived as indication of a failure.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125918027","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995294
H. Chafouk, L. Gliga
A real time fire and explosion detection system is presented in this paper, using data acquired from a Wireless Sensor Network inside a room. First it is filtered to remove the noise. Then, the stochastic process is modelled in real time. The model is also used to predict the future temperature. The outputs of the model are used to detect sensor faults, this way assuring the reliability of the data. Fires are detected using a change detection method three being proposed in this paper, but just one being recommended. Finally, explosions are identified using the predicted data.
{"title":"Detection of faulty sensors of fire and explosions","authors":"H. Chafouk, L. Gliga","doi":"10.1109/CIVEMSA.2017.7995294","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995294","url":null,"abstract":"A real time fire and explosion detection system is presented in this paper, using data acquired from a Wireless Sensor Network inside a room. First it is filtered to remove the noise. Then, the stochastic process is modelled in real time. The model is also used to predict the future temperature. The outputs of the model are used to detect sensor faults, this way assuring the reliability of the data. Fires are detected using a change detection method three being proposed in this paper, but just one being recommended. Finally, explosions are identified using the predicted data.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114880455","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995303
C. Belhadj, W. Hamanah, M. Kassas
This paper presents and discusses the performance evaluation, monitoring and analysis of a Heating, Ventilation and Air Conditioning (HVAC) system in a residence in Saudi Arabia. The installed air conditioning (A/C) system operates in extreme and severe weather conditions. The local area is characterized by a high level of ambient temperature, high irradiation, high humidity and frequent dust storms. The Laboratory Virtual Instrument Engineering Workbench (LabVIEW) interface capabilities achieved several objectives such as system parameters measurements and performance evaluation of the A/C unit. The constructed LabVIEW engine displays the environmental parameters and the electrical variables such as in-house air temperature at several points, air flow, pressure humidity, out-side temperature, irradiation, wind speed, voltage, current and power on the front panel windows of the interface continuously. LabVIEW has shown good performance in communicating with several devices simultaneously and capability of displaying several variables behavior in real time manner. The designed virtual instrument (VI) filters executed different tasks on a priority basis. The online data display in multi-scale window frame is informative and educative. The online efficiency evaluation is useful for system operation and analysis. The developed system provided good support for research and educational purposes.
{"title":"LabVIEW based real time Monitoring of HVAC System for Residential Load","authors":"C. Belhadj, W. Hamanah, M. Kassas","doi":"10.1109/CIVEMSA.2017.7995303","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995303","url":null,"abstract":"This paper presents and discusses the performance evaluation, monitoring and analysis of a Heating, Ventilation and Air Conditioning (HVAC) system in a residence in Saudi Arabia. The installed air conditioning (A/C) system operates in extreme and severe weather conditions. The local area is characterized by a high level of ambient temperature, high irradiation, high humidity and frequent dust storms. The Laboratory Virtual Instrument Engineering Workbench (LabVIEW) interface capabilities achieved several objectives such as system parameters measurements and performance evaluation of the A/C unit. The constructed LabVIEW engine displays the environmental parameters and the electrical variables such as in-house air temperature at several points, air flow, pressure humidity, out-side temperature, irradiation, wind speed, voltage, current and power on the front panel windows of the interface continuously. LabVIEW has shown good performance in communicating with several devices simultaneously and capability of displaying several variables behavior in real time manner. The designed virtual instrument (VI) filters executed different tasks on a priority basis. The online data display in multi-scale window frame is informative and educative. The online efficiency evaluation is useful for system operation and analysis. The developed system provided good support for research and educational purposes.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127542500","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995309
Ghazal Rouhafzay, A. Crétu
A possible solution to ensure real-time interaction with virtual environments, while not visibly degrading the quality of object models is to construct selectively-densified meshes, that preserve a higher density around the regions that characterize the most the object's shape and properties. The purpose of such an approach is to aim at improving the perceived quality of the models in those areas subjected to increased observation by users. In this paper, a classical computational visual attention model is employed on images collected from multiple viewpoints over the surface of an object to identify regions that attract visual attention. A novel approach is then proposed to allow the use of this model for the detection of salient points on the surface of 3D objects, including: an iterative technique to extract salient points from the saliency map, a procedure for the selection of viewpoints for saliency computation based on the best viewpoint for an object, and a projection algorithm to find the coordinates of the identified salient points in images on the surface of the 3D object. The areas around the identified salient points are constrained at maximum resolution in a selectively-densified mesh obtained using the QSlim simplification algorithm. The results are compared with existing solutions from the literature to demonstrate the superiority of the proposed approach.
{"title":"Selectively-densified mesh construction for virtual environments using salient points derived from a computational model of visual attention","authors":"Ghazal Rouhafzay, A. Crétu","doi":"10.1109/CIVEMSA.2017.7995309","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995309","url":null,"abstract":"A possible solution to ensure real-time interaction with virtual environments, while not visibly degrading the quality of object models is to construct selectively-densified meshes, that preserve a higher density around the regions that characterize the most the object's shape and properties. The purpose of such an approach is to aim at improving the perceived quality of the models in those areas subjected to increased observation by users. In this paper, a classical computational visual attention model is employed on images collected from multiple viewpoints over the surface of an object to identify regions that attract visual attention. A novel approach is then proposed to allow the use of this model for the detection of salient points on the surface of 3D objects, including: an iterative technique to extract salient points from the saliency map, a procedure for the selection of viewpoints for saliency computation based on the best viewpoint for an object, and a projection algorithm to find the coordinates of the identified salient points in images on the surface of the 3D object. The areas around the identified salient points are constrained at maximum resolution in a selectively-densified mesh obtained using the QSlim simplification algorithm. The results are compared with existing solutions from the literature to demonstrate the superiority of the proposed approach.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129380660","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 : 2017-06-26DOI: 10.1109/CIVEMSA.2017.7995297
A. Anand, R. D. Labati, M. Hanmandlu, V. Piuri, F. Scotti
Biometric systems are enabling technologies for a wide set of applications in Ambient Intelligence (AmI) environments. In this context, speaker recognition techniques are of paramount importance due to their high user acceptance and low required cooperation. Typical applications of biometric recognition in AmI environments are identification techniques designed to recognize individuals in small datasets. Biometric recognition methods are frequently deployed on embedded hardware and therefore need to be optimized in terms of computational time as well as used memory. This paper presents a text-independent speaker recognition method particularly suitable for identification in AmI environments. The proposed method first computes the Mel Frequency Cepstral Coefficients (MFCC) and then creates Information Set Features (ISF) by applying a fuzzy logic approach. Finally, it estimates the user's identity by using a hierarchical classification technique based on computational intelligence. We evaluated the performance of the speaker recognition method using signals belonging to the NIST-2003 switchboard speaker database. The achieved results showed that the proposed method reduced the size of the template with respect to traditional approaches based on Gaussian Mixture Models (GMM) and achieved better identification accuracy.
{"title":"Text-independent speaker recognition for Ambient Intelligence applications by using Information Set Features","authors":"A. Anand, R. D. Labati, M. Hanmandlu, V. Piuri, F. Scotti","doi":"10.1109/CIVEMSA.2017.7995297","DOIUrl":"https://doi.org/10.1109/CIVEMSA.2017.7995297","url":null,"abstract":"Biometric systems are enabling technologies for a wide set of applications in Ambient Intelligence (AmI) environments. In this context, speaker recognition techniques are of paramount importance due to their high user acceptance and low required cooperation. Typical applications of biometric recognition in AmI environments are identification techniques designed to recognize individuals in small datasets. Biometric recognition methods are frequently deployed on embedded hardware and therefore need to be optimized in terms of computational time as well as used memory. This paper presents a text-independent speaker recognition method particularly suitable for identification in AmI environments. The proposed method first computes the Mel Frequency Cepstral Coefficients (MFCC) and then creates Information Set Features (ISF) by applying a fuzzy logic approach. Finally, it estimates the user's identity by using a hierarchical classification technique based on computational intelligence. We evaluated the performance of the speaker recognition method using signals belonging to the NIST-2003 switchboard speaker database. The achieved results showed that the proposed method reduced the size of the template with respect to traditional approaches based on Gaussian Mixture Models (GMM) and achieved better identification accuracy.","PeriodicalId":123360,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134289625","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：