Bhavya Goyal, Tarun Budhraja, Roheet Bhatnagar, C. Shivakumar
In order to implement Sequential Bayesian estimator using Monte carlo simulation and to get rid of limitations of Kalman filter, Particle filtering techniques plays a very crucial role for target tracking applications in state space where Importance sampling approximately distributed by posterior distribution with multimodel feature and robustness to noise. However as the particles becomes very large, the Monte Carlo representation becomes nearly equivalent to analytical description characterization for posterior distributions and has some deficiencies such as high computational cost and low sampling efficiency. Therefore, emerging computing platform, CUDA may be regarded as most appealing platform for such implementaion. Representation provided with set of samples for target distribution of state leads to increase in sampling efficiency so that graphics processing unit (GPUPU) becomes more appealing to use in Particle filter. The modification on mapping architecture are evaluated with qualitative analysis. The proposed design will be 3.5 times faster than direct design.
{"title":"Implementation of Particle Filters for Single Target Tracking Using CUDA","authors":"Bhavya Goyal, Tarun Budhraja, Roheet Bhatnagar, C. Shivakumar","doi":"10.1109/ICACC.2015.111","DOIUrl":"https://doi.org/10.1109/ICACC.2015.111","url":null,"abstract":"In order to implement Sequential Bayesian estimator using Monte carlo simulation and to get rid of limitations of Kalman filter, Particle filtering techniques plays a very crucial role for target tracking applications in state space where Importance sampling approximately distributed by posterior distribution with multimodel feature and robustness to noise. However as the particles becomes very large, the Monte Carlo representation becomes nearly equivalent to analytical description characterization for posterior distributions and has some deficiencies such as high computational cost and low sampling efficiency. Therefore, emerging computing platform, CUDA may be regarded as most appealing platform for such implementaion. Representation provided with set of samples for target distribution of state leads to increase in sampling efficiency so that graphics processing unit (GPUPU) becomes more appealing to use in Particle filter. The modification on mapping architecture are evaluated with qualitative analysis. The proposed design will be 3.5 times faster than direct design.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131194889","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}
Users in the uplink of an Orthogonal Frequency Division Multiple Access (OFDMA) system may experience different carrier frequency offset (CFO). This CFO destroy the orthogonality among subcarriers, causing inter-carrier interference and multi-user interference, which degrade the performance of system. Latest time domain schemes called "SIMUIC" and "CAMUIC" have delay in processing, since each consecutive user's CFO's are corrected with successive iteration method. Also frequency domain compensation performs better, but smaller individual CFO values only. In this paper, a hybrid multi-user interference cancellation scheme for OFDMA uplink is proposed. This employ an architecture with multiple OFDMA-demodulators to compensate the multiuser CFO's at the base station. This hybrid scheme, SPIC exploits the advantages of both time domain and frequency domain schemes. Large CFO values of each user is compensated using an efficient time domain scheme. The remaining CFOs are compensated using a Parallel Interference Cancellation in frequency domain and the CFO corrected output of each user is obtained simultaneously. Analytical and numerical evaluations show that proposed scheme achieves a significant performance gain compared to the latest schemes.
{"title":"A Hybrid Multi-user Interference Cancellation Scheme for Carrier Frequency Offset Compensation in Uplink OFDMA","authors":"P. Noufal, Ch Harish kumar","doi":"10.1109/ICACC.2015.27","DOIUrl":"https://doi.org/10.1109/ICACC.2015.27","url":null,"abstract":"Users in the uplink of an Orthogonal Frequency Division Multiple Access (OFDMA) system may experience different carrier frequency offset (CFO). This CFO destroy the orthogonality among subcarriers, causing inter-carrier interference and multi-user interference, which degrade the performance of system. Latest time domain schemes called \"SIMUIC\" and \"CAMUIC\" have delay in processing, since each consecutive user's CFO's are corrected with successive iteration method. Also frequency domain compensation performs better, but smaller individual CFO values only. In this paper, a hybrid multi-user interference cancellation scheme for OFDMA uplink is proposed. This employ an architecture with multiple OFDMA-demodulators to compensate the multiuser CFO's at the base station. This hybrid scheme, SPIC exploits the advantages of both time domain and frequency domain schemes. Large CFO values of each user is compensated using an efficient time domain scheme. The remaining CFOs are compensated using a Parallel Interference Cancellation in frequency domain and the CFO corrected output of each user is obtained simultaneously. Analytical and numerical evaluations show that proposed scheme achieves a significant performance gain compared to the latest schemes.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"11 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121006600","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}
Human detection in images is a fast growing and challenging area of research in computer vision with its main application in video surveillance, robotics, intelligent vehicle, image retrieval, defense, entertainment, behavior analysis, tracking, forensic science, medicalscience and intelligent transportation. This paper presents a robust multi-posture human detection system in images based on local feature descriptors such as HOG and BO (Block Orientation). The proposed system employs LLE method to achieve dimensionality reduction on the Hog feature descriptors and thus reduce time complexity. Performance of the proposed method is evaluated using feature and classifier based schemes with different datasets. By using classifier based schemes, fast-additive SVM outperforms other SVM classifiers. The combined feature vector can retain precision of HOG as well as improve the detection rate. The experiment results on INRIA person, SDL dataset, and TUDBrussels dataset demonstrate that combined feature vector along with LLE and fast additive SVM significantly improves the performance.
{"title":"Multi-posture Human Detection Based on Hybrid HOG-BO Feature","authors":"Jain B. Stoble","doi":"10.1109/ICACC.2015.99","DOIUrl":"https://doi.org/10.1109/ICACC.2015.99","url":null,"abstract":"Human detection in images is a fast growing and challenging area of research in computer vision with its main application in video surveillance, robotics, intelligent vehicle, image retrieval, defense, entertainment, behavior analysis, tracking, forensic science, medicalscience and intelligent transportation. This paper presents a robust multi-posture human detection system in images based on local feature descriptors such as HOG and BO (Block Orientation). The proposed system employs LLE method to achieve dimensionality reduction on the Hog feature descriptors and thus reduce time complexity. Performance of the proposed method is evaluated using feature and classifier based schemes with different datasets. By using classifier based schemes, fast-additive SVM outperforms other SVM classifiers. The combined feature vector can retain precision of HOG as well as improve the detection rate. The experiment results on INRIA person, SDL dataset, and TUDBrussels dataset demonstrate that combined feature vector along with LLE and fast additive SVM significantly improves the performance.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132333117","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}
Color is an evitable feature of image and its prediction is still a critical issue in computer vision and image processing. It is necessary to ensure that the perceived color of an object remains constant under varying conditions. Novelty of this paper lies in introduction of a linguistic color space using mamdani's fuzzy inference system for better color constancy and image enhancement. We define different types of membership functions with minimum number of inference rules to map RGB components to linguistic color space. Also, psychophysically measured colors are represented in terms of linguistic variables. While evaluating the algorithm, it is clear that this algorithm rivals current state of art performance without the help of training data. In addition, this method can be used for clouddetection of aerial images, thus opening further research in aerial image processing.
{"title":"A Linguistic Color Space for Image Enhancemenet","authors":"R. Chandrasekharan, M. Sasikumar","doi":"10.1109/ICACC.2015.55","DOIUrl":"https://doi.org/10.1109/ICACC.2015.55","url":null,"abstract":"Color is an evitable feature of image and its prediction is still a critical issue in computer vision and image processing. It is necessary to ensure that the perceived color of an object remains constant under varying conditions. Novelty of this paper lies in introduction of a linguistic color space using mamdani's fuzzy inference system for better color constancy and image enhancement. We define different types of membership functions with minimum number of inference rules to map RGB components to linguistic color space. Also, psychophysically measured colors are represented in terms of linguistic variables. While evaluating the algorithm, it is clear that this algorithm rivals current state of art performance without the help of training data. In addition, this method can be used for clouddetection of aerial images, thus opening further research in aerial image processing.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122761590","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}
Big-data is a popular term in the field of information and communication technology. Wireless Sensor Networks (WSN) is one of the eminent contributors of big data. WSN contains numerous sensor nodes that cooperatively monitor an environment. Each network consists of sensor node, memory, and communication device. Data generated by single sensor node is small but data generated by distributed sensor network is significantly large and it is termed as big-data. The critical issue in WSN is energy consumption and data gathering. This paper mainly focus on Expectation Maximization (EM) based clustering scheme implementation and the performance analysis of WSN using single mobile sink to eight mobile sink. From the analysis we also derived a relationship between the number of mobile sinks required for a particular network with a given number of sensor nodes. Experimental results show that the number of mobile sinks is also an important parameter to efficiently gather information in WSN.
{"title":"Performance Analysis of Big Data Gathering in Wireless Sensor Network Using an EM Based Clustering Scheme","authors":"K. Remesh Babu, G. Suja, P. Samuel, S. Jos","doi":"10.1109/ICACC.2015.48","DOIUrl":"https://doi.org/10.1109/ICACC.2015.48","url":null,"abstract":"Big-data is a popular term in the field of information and communication technology. Wireless Sensor Networks (WSN) is one of the eminent contributors of big data. WSN contains numerous sensor nodes that cooperatively monitor an environment. Each network consists of sensor node, memory, and communication device. Data generated by single sensor node is small but data generated by distributed sensor network is significantly large and it is termed as big-data. The critical issue in WSN is energy consumption and data gathering. This paper mainly focus on Expectation Maximization (EM) based clustering scheme implementation and the performance analysis of WSN using single mobile sink to eight mobile sink. From the analysis we also derived a relationship between the number of mobile sinks required for a particular network with a given number of sensor nodes. Experimental results show that the number of mobile sinks is also an important parameter to efficiently gather information in WSN.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115667697","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}
Heterogeneous Network consists of wired and wireless network. In these networks, congestion control and quality of service is major issue. Due to this issues, delay and jitter are increased which decreases the performance of network. For reducing this issues there are various queue management techniques which are classified as Active Queue Management and Passive Queue Management. AQM consists of access routers which are used to detect congestion. Working principle of AQM is very effective for congestion control. AQM such as Random Early Detection (RED), has various types such as Adaptive-RED (ARED), Refined-ARED (RE-ARED), Combination of ARED, RE-ARED is Cautious Adaptive RED (CARED). In this paper, CARED is designed for Heterogeneous network. CARED has dynamically changing maximum drop probability (maxp) depends upon level of traffic load. FUZZY-CARED is designed to improve CARED in which maxp cautiously increases and decreases after detecting congestion in the network. The proposed work aims to keep average queue length (newavg) around required target range by cautiously selecting increase maxp on current traffic load. The simulation results shows comparison of ARED, CARED and FUZZY-CARED in which FUZZY-CARED gives better results than ARED, CARED.
{"title":"Fuzzy Cautious Adaptive Random Early Detection for Heterogeneous Network","authors":"S. Ravindra, Ashwini B. Patil","doi":"10.1109/ICACC.2015.106","DOIUrl":"https://doi.org/10.1109/ICACC.2015.106","url":null,"abstract":"Heterogeneous Network consists of wired and wireless network. In these networks, congestion control and quality of service is major issue. Due to this issues, delay and jitter are increased which decreases the performance of network. For reducing this issues there are various queue management techniques which are classified as Active Queue Management and Passive Queue Management. AQM consists of access routers which are used to detect congestion. Working principle of AQM is very effective for congestion control. AQM such as Random Early Detection (RED), has various types such as Adaptive-RED (ARED), Refined-ARED (RE-ARED), Combination of ARED, RE-ARED is Cautious Adaptive RED (CARED). In this paper, CARED is designed for Heterogeneous network. CARED has dynamically changing maximum drop probability (maxp) depends upon level of traffic load. FUZZY-CARED is designed to improve CARED in which maxp cautiously increases and decreases after detecting congestion in the network. The proposed work aims to keep average queue length (newavg) around required target range by cautiously selecting increase maxp on current traffic load. The simulation results shows comparison of ARED, CARED and FUZZY-CARED in which FUZZY-CARED gives better results than ARED, CARED.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114669124","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}
A metasurface (MS) antenna that allows polarization reconfigurability is proposed. The MS antenna is formed by a MS and source antenna, separated by a small air gap. The MS consists of 16 identical unit cells on a substrate, where each unit cell used is a corner truncated square patch. A microstrip fed slot antenna (MFSA) is used as the source antenna. The MS converts the linearly polarized (LP) signal generated by the MFSA into a circularly polarized (CP) signal with wider return loss bandwidth(RLBW). By rotating the MS relative to the MFSA, different polarizations could be achieved. For verification of simulation results, the MS antennas are fabricated and measured. Simulated and measured results show good agreements. The MS antenna has an operating frequency of 2.4 GHz, suitable for WLAN applications.
{"title":"A 2.4 GHz Polarization Reconfigurable Metasurface Antenna","authors":"Najla Mohammed Sali, B. Paul","doi":"10.1109/ICACC.2015.69","DOIUrl":"https://doi.org/10.1109/ICACC.2015.69","url":null,"abstract":"A metasurface (MS) antenna that allows polarization reconfigurability is proposed. The MS antenna is formed by a MS and source antenna, separated by a small air gap. The MS consists of 16 identical unit cells on a substrate, where each unit cell used is a corner truncated square patch. A microstrip fed slot antenna (MFSA) is used as the source antenna. The MS converts the linearly polarized (LP) signal generated by the MFSA into a circularly polarized (CP) signal with wider return loss bandwidth(RLBW). By rotating the MS relative to the MFSA, different polarizations could be achieved. For verification of simulation results, the MS antennas are fabricated and measured. Simulated and measured results show good agreements. The MS antenna has an operating frequency of 2.4 GHz, suitable for WLAN applications.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126292429","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}
Jerin Jose, T. Mathew, A. Thomas, N. Haripriya, Mahima Cherian, D. D. Krishna
This paper presents a hybrid-log periodic dipole antenna (H-LPDA) which is a cost effective alternative to the regular planar-log periodic dipole antenna (PLPDA) . In case of a PLPDA, required substrate dimensions increases with bandwidth as we have to accommodate dipoles of shortest dimensions to the longest. In order to make the antenna more cost effective in terms of the high frequency substrates used, a 3D structure is incorporated with the PLPDA while keeping the overall dimension as well as the performance same as the original PLPDA. In this paper, a PLPDA designed to operate over 700MHz - 4.5GHz is replaced by the proposed H-LPDA design. The design is simulated, fabricated and measured. The antenna is found to have performance similar to that of the original PLPDA antenna with good impedance matching (VSWR<;2) and a stable radiation pattern with a gain of 6.5dB over the desired operating band.
{"title":"A Cost Effective Hybrid-Log Periodic Dipole Antenna (H-LPDA)","authors":"Jerin Jose, T. Mathew, A. Thomas, N. Haripriya, Mahima Cherian, D. D. Krishna","doi":"10.1109/ICACC.2015.54","DOIUrl":"https://doi.org/10.1109/ICACC.2015.54","url":null,"abstract":"This paper presents a hybrid-log periodic dipole antenna (H-LPDA) which is a cost effective alternative to the regular planar-log periodic dipole antenna (PLPDA) . In case of a PLPDA, required substrate dimensions increases with bandwidth as we have to accommodate dipoles of shortest dimensions to the longest. In order to make the antenna more cost effective in terms of the high frequency substrates used, a 3D structure is incorporated with the PLPDA while keeping the overall dimension as well as the performance same as the original PLPDA. In this paper, a PLPDA designed to operate over 700MHz - 4.5GHz is replaced by the proposed H-LPDA design. The design is simulated, fabricated and measured. The antenna is found to have performance similar to that of the original PLPDA antenna with good impedance matching (VSWR<;2) and a stable radiation pattern with a gain of 6.5dB over the desired operating band.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130570888","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}
A. Deshmukh, Shafin Nagarbowdi, A. Desai, S. Shaikh, K. Lele, K. Ray
Broadband 90° isosceles triangular microstrip antenna derived from equivalent equilateral triangular microstrip antenna, is proposed. The parametric study for variation in isosceles angle from 50° to 90° is presented. The increasing angle tunes the spacing between TM10 and TM11 modes of the triangular patch to realize broadband response. The simulated and measured bandwidth of more than 600 MHz (> 45%) is obtained. This is more than the bandwidth realized in equilateral triangular microstrip antenna. The proposed 90° isosceles patch yields broadside radiation pattern with gain of more than 6 dBi over entire bandwidth.
{"title":"Broadband 90° Isosceles Triangular Microstrip Antenna","authors":"A. Deshmukh, Shafin Nagarbowdi, A. Desai, S. Shaikh, K. Lele, K. Ray","doi":"10.1109/ICACC.2015.39","DOIUrl":"https://doi.org/10.1109/ICACC.2015.39","url":null,"abstract":"Broadband 90° isosceles triangular microstrip antenna derived from equivalent equilateral triangular microstrip antenna, is proposed. The parametric study for variation in isosceles angle from 50° to 90° is presented. The increasing angle tunes the spacing between TM10 and TM11 modes of the triangular patch to realize broadband response. The simulated and measured bandwidth of more than 600 MHz (> 45%) is obtained. This is more than the bandwidth realized in equilateral triangular microstrip antenna. The proposed 90° isosceles patch yields broadside radiation pattern with gain of more than 6 dBi over entire bandwidth.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122301928","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}
K. Raju, T. Sreerekha, P. Vidya, Rajeev R R, P. C. Reghu Raj
Transliteration forms an essential part of transcription which converts text from one writing system to another. The need for translating data has become larger than before as the world is getting together through social media. Machine transliteration has emerged as a part of information retrieval and machine translation projects to translate named entities, that are not registered in the dictionary, based on phonemes and graphemes. This paper proposes a machine learning technique that performs transliteration from Tamil to Malayalam, two languages that belong to Dravidian family. Transliteration can be used to supplement machine translation process by handling the issues that can happen due to the presence of named entities.
{"title":"Tamil to Malayalam Transliteration","authors":"K. Raju, T. Sreerekha, P. Vidya, Rajeev R R, P. C. Reghu Raj","doi":"10.1109/ICACC.2015.86","DOIUrl":"https://doi.org/10.1109/ICACC.2015.86","url":null,"abstract":"Transliteration forms an essential part of transcription which converts text from one writing system to another. The need for translating data has become larger than before as the world is getting together through social media. Machine transliteration has emerged as a part of information retrieval and machine translation projects to translate named entities, that are not registered in the dictionary, based on phonemes and graphemes. This paper proposes a machine learning technique that performs transliteration from Tamil to Malayalam, two languages that belong to Dravidian family. Transliteration can be used to supplement machine translation process by handling the issues that can happen due to the presence of named entities.","PeriodicalId":368544,"journal":{"name":"2015 Fifth International Conference on Advances in Computing and Communications (ICACC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130897211","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：