Pub Date : 2016-06-27DOI: 10.1109/TSP.2016.7760831
S. Krile, M. Rákus, F. Schindler
This paper describes a centralized routing algorithm based on permutation of M traffic flows entering the network. The proposed approach is significantly less complex than combinatorial approach and can be used as load-balancing tool. The main advantage of such approach is that many non-perspective flow permutations could be eliminated from the calculation very early. If a new flow enters the network the algorithm offers one or more routing solutions, including the path migration for the existing flows. Of course, path migration will be performed only if it is necessary. Proposed heuristic algorithm significantly reduces the complexity, solving efficiently the problems with huge number of flows. In the sense of TE (Traffic Engineering) this routing technique looks like a very perspective load-balancing tool.
{"title":"Centralized routing algorithm based on flow permutations","authors":"S. Krile, M. Rákus, F. Schindler","doi":"10.1109/TSP.2016.7760831","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760831","url":null,"abstract":"This paper describes a centralized routing algorithm based on permutation of M traffic flows entering the network. The proposed approach is significantly less complex than combinatorial approach and can be used as load-balancing tool. The main advantage of such approach is that many non-perspective flow permutations could be eliminated from the calculation very early. If a new flow enters the network the algorithm offers one or more routing solutions, including the path migration for the existing flows. Of course, path migration will be performed only if it is necessary. Proposed heuristic algorithm significantly reduces the complexity, solving efficiently the problems with huge number of flows. In the sense of TE (Traffic Engineering) this routing technique looks like a very perspective load-balancing tool.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132201627","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760850
Tam Nguyen Kieu, L. N. Ngoc, Hung Kieu Quoc, H. H. Duy, T. D. Dinh, M. Voznák, M. Mikulec
In this paper, we consider the impact of some factors at the relay node for the amplify-and-forward and decode-and-forward modes based on the energy harvesting in full-duplex relaying networks. Specially, the closed-form expression of their outage probability and throughput is illustrated. Moreover, we appraise the systems performance in terms of the outage probability and throughput which depend on the noise at nodes as well as the distance between them.
{"title":"A performance analysis in energy harvesting full-duplex relay","authors":"Tam Nguyen Kieu, L. N. Ngoc, Hung Kieu Quoc, H. H. Duy, T. D. Dinh, M. Voznák, M. Mikulec","doi":"10.1109/TSP.2016.7760850","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760850","url":null,"abstract":"In this paper, we consider the impact of some factors at the relay node for the amplify-and-forward and decode-and-forward modes based on the energy harvesting in full-duplex relaying networks. Specially, the closed-form expression of their outage probability and throughput is illustrated. Moreover, we appraise the systems performance in terms of the outage probability and throughput which depend on the noise at nodes as well as the distance between them.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123686274","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760843
Inam Ullah, B. B. Haile, E. Mutafungwa, Jyri Hämäläinen
Relaying is one of the promising approaches for extending service coverage and improving quality of service. The self-backhauling of relays towards a serving (donor) eNode B provides cost-effective solution for deployment scenarios where conventional backhauling is either costly or unavailable. The end-to-end throughputs achievable by users served by relays are dependent on achievable throughputs on both the relay access and backhaul links. The 3GPP standardized Type 1 inband relay node (RN) employs a time-based resource partitioning between relay backhaul and access links. This resource allocation strategy coupled with sharing of eNode B (eNB) resources between the RN and users served directly by the eNB usually creates a backhaul bottleneck. The relay backhaul link performance is further degraded due to intercell interference, particularly on the cell edge where the deployment of relays are usually targeted. In this paper, the relay user's throughput enhancements by relaxation of relay backhaul bottlenecks are investigated through the use of beamforming and interference mitigation techniques. Simulation results demonstrate significant improvements in relay backhaul performance and end-to-end throughputs for relay users through the use of limited feedback beamforming and interference mitigation schemes.
{"title":"Use of beamforming and interference mitigation techniques for relay backhaul enhancement","authors":"Inam Ullah, B. B. Haile, E. Mutafungwa, Jyri Hämäläinen","doi":"10.1109/TSP.2016.7760843","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760843","url":null,"abstract":"Relaying is one of the promising approaches for extending service coverage and improving quality of service. The self-backhauling of relays towards a serving (donor) eNode B provides cost-effective solution for deployment scenarios where conventional backhauling is either costly or unavailable. The end-to-end throughputs achievable by users served by relays are dependent on achievable throughputs on both the relay access and backhaul links. The 3GPP standardized Type 1 inband relay node (RN) employs a time-based resource partitioning between relay backhaul and access links. This resource allocation strategy coupled with sharing of eNode B (eNB) resources between the RN and users served directly by the eNB usually creates a backhaul bottleneck. The relay backhaul link performance is further degraded due to intercell interference, particularly on the cell edge where the deployment of relays are usually targeted. In this paper, the relay user's throughput enhancements by relaxation of relay backhaul bottlenecks are investigated through the use of beamforming and interference mitigation techniques. Simulation results demonstrate significant improvements in relay backhaul performance and end-to-end throughputs for relay users through the use of limited feedback beamforming and interference mitigation schemes.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"385 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122780785","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760938
Aman Pandey, Ritu Chandra, M. Dutta, Radim Burget, V. Uher, Jiri Minar
The paper proposes an automatic image processing algorithm based on shape features for the detection of red lesions. In Diabetic Retinopathy Micro-aneurysms and hemorrhages comes under the category of red lesions, which is the most common eye disease caused in diabetic patients and also leads to blindness. This paper describes an effective methodology to study any computer-aided fundus image that can be utilized as a tool for diagnosis and detection of red lesions. A Shape based extraction technique using three parameters i.e. Perimeter Area and Eccentricity is used to segment out the red lesions from rest of the image. Since the algorithm consider shape features for detection of red lesion which makes it efficient and independent of image quality. The results that are experimentally obtained by applying this algorithm has been compared with those of the ophthalmologist and the comparison of these results have been highly accurate. In addition to the accuracy of the obtained results, the proposed method is fast and having very low computational time.
{"title":"Automatic detection of red lesions in Diabetic Retinopathy using Shape based extraction technique in fundus image","authors":"Aman Pandey, Ritu Chandra, M. Dutta, Radim Burget, V. Uher, Jiri Minar","doi":"10.1109/TSP.2016.7760938","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760938","url":null,"abstract":"The paper proposes an automatic image processing algorithm based on shape features for the detection of red lesions. In Diabetic Retinopathy Micro-aneurysms and hemorrhages comes under the category of red lesions, which is the most common eye disease caused in diabetic patients and also leads to blindness. This paper describes an effective methodology to study any computer-aided fundus image that can be utilized as a tool for diagnosis and detection of red lesions. A Shape based extraction technique using three parameters i.e. Perimeter Area and Eccentricity is used to segment out the red lesions from rest of the image. Since the algorithm consider shape features for detection of red lesion which makes it efficient and independent of image quality. The results that are experimentally obtained by applying this algorithm has been compared with those of the ophthalmologist and the comparison of these results have been highly accurate. In addition to the accuracy of the obtained results, the proposed method is fast and having very low computational time.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131472583","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760923
T. Le, Mathias Ziebarth, Thomas Greiner, M. Heizmann
In our previous works, we have presented methods for optimizing wavelet filter banks, which can be used for classification of image objects. The wavelet filter banks were designed to be biorthogonal, which enables a multiscale analysis on given image data. Moreover, the filters were optimized with respect to the shape, which helps the filter banks to inherit the property of the objects. This optimization is only possible with the help of so called object filters designed to have the curve of typical objects of each class. In contrast to previous works where object filters were designed manually, a systematic and automatic design method for object filters is introduced in this paper. The new designed filters were used to optimize wavelet filter banks for classification problems. The evaluation of this method was done by comparing the results with the ones of wavelet filter banks based on the previously used object filters.
{"title":"Systematic design of object shape matched wavelet filter banks for defect detection","authors":"T. Le, Mathias Ziebarth, Thomas Greiner, M. Heizmann","doi":"10.1109/TSP.2016.7760923","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760923","url":null,"abstract":"In our previous works, we have presented methods for optimizing wavelet filter banks, which can be used for classification of image objects. The wavelet filter banks were designed to be biorthogonal, which enables a multiscale analysis on given image data. Moreover, the filters were optimized with respect to the shape, which helps the filter banks to inherit the property of the objects. This optimization is only possible with the help of so called object filters designed to have the curve of typical objects of each class. In contrast to previous works where object filters were designed manually, a systematic and automatic design method for object filters is introduced in this paper. The new designed filters were used to optimize wavelet filter banks for classification problems. The evaluation of this method was done by comparing the results with the ones of wavelet filter banks based on the previously used object filters.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115578713","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760848
Yigit Mahmutoglu, K. Türk, E. Tugcu
In this paper, we proposed particle swarm optimization (PSO) algorithm based adaptive decision feedback equalizer (DFE) for underwater acoustic communication (UWAC). In the literature, although ocean ambient noise is generally modeled as pink Gaussian noise, there is also site-specific ocean noise which can be modeled as pink Laplace noise. In this study we consider both noises. Rayleigh distributed, frequency selective fading channels (as UWAC channel) with Laplacian and Gaussian distributed, pink noise are considered. Unlike recursive least squares (RLS) and least mean squares (LMS) algorithms, PSO is independent from channel characteristics and has faster convergence. To the best of our knowledge PSO algorithm has not been used for adaptive DFE over UWAC channel. The communication performances and computational complexities of LMS, RLS and PSO based adaptive DFEs are compared. Although PSO has the highest computational complexity, our simulation results show PSO-DFE outperforms the other algorithms.
{"title":"Particle swarm optimization algorithm based decision feedback equalizer for underwater acoustic communication","authors":"Yigit Mahmutoglu, K. Türk, E. Tugcu","doi":"10.1109/TSP.2016.7760848","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760848","url":null,"abstract":"In this paper, we proposed particle swarm optimization (PSO) algorithm based adaptive decision feedback equalizer (DFE) for underwater acoustic communication (UWAC). In the literature, although ocean ambient noise is generally modeled as pink Gaussian noise, there is also site-specific ocean noise which can be modeled as pink Laplace noise. In this study we consider both noises. Rayleigh distributed, frequency selective fading channels (as UWAC channel) with Laplacian and Gaussian distributed, pink noise are considered. Unlike recursive least squares (RLS) and least mean squares (LMS) algorithms, PSO is independent from channel characteristics and has faster convergence. To the best of our knowledge PSO algorithm has not been used for adaptive DFE over UWAC channel. The communication performances and computational complexities of LMS, RLS and PSO based adaptive DFEs are compared. Although PSO has the highest computational complexity, our simulation results show PSO-DFE outperforms the other algorithms.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122901793","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760893
M. Kołodziej, A. Majkowski, L. Oskwarek, R. Rak
This study was carried out to select EEG signal preprocessing methods to effectively detect and classify Steady State Visually Evoked Potentials (SSVEP). Algorithms, such as: Common Average Reference, Independent Component Analysis (in the task of electrooculography artifacts removing and SSVEP enhancement) and combinations of them were implemented and tested. The best classification accuracy improvement was obtained for CAR and ICA-SSVEP preprocessing methods. Experiments showed high usefulness of these methods in the context of SSVEP detection.
{"title":"Comparison of EEG signal preprocessing methods for SSVEP recognition","authors":"M. Kołodziej, A. Majkowski, L. Oskwarek, R. Rak","doi":"10.1109/TSP.2016.7760893","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760893","url":null,"abstract":"This study was carried out to select EEG signal preprocessing methods to effectively detect and classify Steady State Visually Evoked Potentials (SSVEP). Algorithms, such as: Common Average Reference, Independent Component Analysis (in the task of electrooculography artifacts removing and SSVEP enhancement) and combinations of them were implemented and tested. The best classification accuracy improvement was obtained for CAR and ICA-SSVEP preprocessing methods. Experiments showed high usefulness of these methods in the context of SSVEP detection.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128285868","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760820
L. Malina, J. Hajny, Zdenek Martinasek
The paper deals with using modern smart handheld and wearable devices such as smartphones, smartwatches and microcomputers in privacy-preserving authentication and access control systems. Authentication and access control systems usually employ chip cards and smart cards as users' authentication devices. Nevertheless, current privacy-preserving authentication schemes often require more powerful devices such as smartphones and smartwatches. This paper provides the performance assessment of cryptographic and math methods on the smart devices. Further, a privacy-preserving authentication scheme is implemented in order to investigate its performance on these smart devices. Finally, the benefits and limits of deploying the smart devices in privacy preserving authentication systems are discussed.
{"title":"Privacy-preserving authentication systems using smart devices","authors":"L. Malina, J. Hajny, Zdenek Martinasek","doi":"10.1109/TSP.2016.7760820","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760820","url":null,"abstract":"The paper deals with using modern smart handheld and wearable devices such as smartphones, smartwatches and microcomputers in privacy-preserving authentication and access control systems. Authentication and access control systems usually employ chip cards and smart cards as users' authentication devices. Nevertheless, current privacy-preserving authentication schemes often require more powerful devices such as smartphones and smartwatches. This paper provides the performance assessment of cryptographic and math methods on the smart devices. Further, a privacy-preserving authentication scheme is implemented in order to investigate its performance on these smart devices. Finally, the benefits and limits of deploying the smart devices in privacy preserving authentication systems are discussed.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130494413","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760973
C. Yilmaz, C. Köse
Human Computer Interaction (HCI) has become an important focus of both computer science researches and industrial applications. And, on-screen gaze estimation is one of the hottest topics in this rapidly growing field. Eye-gaze direction estimation is a sub-research area of on-screen gaze estimation and the number of studies that focused on the estimation of on-screen gaze direction is limited. Due to this, various appearance-based video-oculography methods are investigated in this work. Firstly, a new dataset is created via user images taken from daylight censored cameras located at computer screen. Then, Local Binary Pattern Histogram (LBPH), which is used in this work for the first time to obtain on-screen gaze direction information, and Principal Component Analysis (PCA) methods are employed to extract image features. And, parameter optimized Support Vector Machine (SVM), Artificial Neural Networks (ANNs) and k-Nearest Neighbor (k-NN) learning methods are adopted in order to estimate on-screen gaze direction. Finally, these methods' abilities to correctly estimate the on-screen gaze direction are compared using the resulting classification accuracies of applied methods and previous works. The best classification accuracy of 96.67% is obtained when using LBPH and SVM method pair which is better than previous works. The results also show that appearance based methods are pretty applicable for estimating on-screen gaze direction.
{"title":"Local Binary Pattern Histogram features for on-screen eye-gaze direction estimation and a comparison of appearance based methods","authors":"C. Yilmaz, C. Köse","doi":"10.1109/TSP.2016.7760973","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760973","url":null,"abstract":"Human Computer Interaction (HCI) has become an important focus of both computer science researches and industrial applications. And, on-screen gaze estimation is one of the hottest topics in this rapidly growing field. Eye-gaze direction estimation is a sub-research area of on-screen gaze estimation and the number of studies that focused on the estimation of on-screen gaze direction is limited. Due to this, various appearance-based video-oculography methods are investigated in this work. Firstly, a new dataset is created via user images taken from daylight censored cameras located at computer screen. Then, Local Binary Pattern Histogram (LBPH), which is used in this work for the first time to obtain on-screen gaze direction information, and Principal Component Analysis (PCA) methods are employed to extract image features. And, parameter optimized Support Vector Machine (SVM), Artificial Neural Networks (ANNs) and k-Nearest Neighbor (k-NN) learning methods are adopted in order to estimate on-screen gaze direction. Finally, these methods' abilities to correctly estimate the on-screen gaze direction are compared using the resulting classification accuracies of applied methods and previous works. The best classification accuracy of 96.67% is obtained when using LBPH and SVM method pair which is better than previous works. The results also show that appearance based methods are pretty applicable for estimating on-screen gaze direction.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132310498","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 : 2016-06-27DOI: 10.1109/TSP.2016.7760939
Lukas Povoda, Radim Burget, M. Dutta
This paper deals with sentiment analysis in text documents, especially text valence detection. The proposed solution is based on Support Vector Machines classifier. This classifier was trained with huge amount of data and complex word combinations were analysed. For this purpose distributed learning on 112 processors was used. Datasets used for training and testing were automatically obtained from real user feedback on products from different web pages (and different product segments). The proposed solution has been evaluated with different languages - English, German, Czech and Spanish. This paper improves accuracy achieved with the Big Data approach about 11%. The best accuracy achieved in this work was 95.31% for recognition of positive and negative text valence. The described learning is fully automatic, can be applied to any language and no complicated preprocessing is needed.
{"title":"Sentiment analysis based on Support Vector Machine and Big Data","authors":"Lukas Povoda, Radim Burget, M. Dutta","doi":"10.1109/TSP.2016.7760939","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760939","url":null,"abstract":"This paper deals with sentiment analysis in text documents, especially text valence detection. The proposed solution is based on Support Vector Machines classifier. This classifier was trained with huge amount of data and complex word combinations were analysed. For this purpose distributed learning on 112 processors was used. Datasets used for training and testing were automatically obtained from real user feedback on products from different web pages (and different product segments). The proposed solution has been evaluated with different languages - English, German, Czech and Spanish. This paper improves accuracy achieved with the Big Data approach about 11%. The best accuracy achieved in this work was 95.31% for recognition of positive and negative text valence. The described learning is fully automatic, can be applied to any language and no complicated preprocessing is needed.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116967226","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：