Pub Date : 2018-01-24DOI: 10.1109/cscita.2017.8066532
Vivian Brian Lobo, N. Ansari
Twitter, a well-liked online social networking site, facilitates millions of users on a daily basis to dispatch and orate quick 140-character notes named tweets. Nowadays, Twitter is cogitated as the fastest and popular intermediate of communication and is used to follow latest events. Tweets pertaining to a specific event can be effortlessly found using keyword matching, but there are numerous tweets that are likely to contain information that is semantically identical. Moreover, there exist many systems for recapitulating tweets related to a particular event, but they have numerous limitations and are unable to provide accurate results. This work aims to overcome the limitations of existing systems by developing a system for recapitulating tweets using graph-based clustering.
{"title":"Recapitulization of tweets using graph-based clustering","authors":"Vivian Brian Lobo, N. Ansari","doi":"10.1109/cscita.2017.8066532","DOIUrl":"https://doi.org/10.1109/cscita.2017.8066532","url":null,"abstract":"Twitter, a well-liked online social networking site, facilitates millions of users on a daily basis to dispatch and orate quick 140-character notes named tweets. Nowadays, Twitter is cogitated as the fastest and popular intermediate of communication and is used to follow latest events. Tweets pertaining to a specific event can be effortlessly found using keyword matching, but there are numerous tweets that are likely to contain information that is semantically identical. Moreover, there exist many systems for recapitulating tweets related to a particular event, but they have numerous limitations and are unable to provide accurate results. This work aims to overcome the limitations of existing systems by developing a system for recapitulating tweets using graph-based clustering.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115790022","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 : 2017-04-07DOI: 10.1109/CSCITA.2017.8066560
T. Kaewkiriya
This paper's objective is to present the performance comparison between Wi-Fi IEEE 802.11ac and Wi-Fi IEEE 802.11n by measuring the throughput and steaming rate of big data streaming. The performance test is divided into four scenarios, 1) data streaming to one device, 2) data streaming with different distances, 3) data streaming to multiple devices, and 4) live broadcast a big data streaming. The results of evaluations are as follow. In the first scenario, maximum transfer rate of IEEE 802.11ac is higher but the average transfer rate depends on the video type. In second scenario, maximum transfer rate to the first and second device of IEEE 802.11ac is significantly greater than IEEE 802.11n but IEEE 802.11ac cannot reach the third device which located on the different floor, while IEEE 802.11n can reach the third device with maximum transfer rate of 942.8 kbps. The throughput of IEEE 802.11ac is more stable than IEEE 802.11n by compare the data from the first and second device. In third scenario, the maximum transfer rate of IEEE 802.11ac is higher than IEEE 802.11n and throughput of IEEE 802.11ac is more stable than IEEE 802.11n. In fourth scenario, the maximum transfer rate and average transfer rate of IEEE 802.11ac is higher than IEEE 802.11n.
{"title":"Performance comparison of Wi-Fi IEEE 802.11ac and Wi-Fi IEEE 802.11n","authors":"T. Kaewkiriya","doi":"10.1109/CSCITA.2017.8066560","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066560","url":null,"abstract":"This paper's objective is to present the performance comparison between Wi-Fi IEEE 802.11ac and Wi-Fi IEEE 802.11n by measuring the throughput and steaming rate of big data streaming. The performance test is divided into four scenarios, 1) data streaming to one device, 2) data streaming with different distances, 3) data streaming to multiple devices, and 4) live broadcast a big data streaming. The results of evaluations are as follow. In the first scenario, maximum transfer rate of IEEE 802.11ac is higher but the average transfer rate depends on the video type. In second scenario, maximum transfer rate to the first and second device of IEEE 802.11ac is significantly greater than IEEE 802.11n but IEEE 802.11ac cannot reach the third device which located on the different floor, while IEEE 802.11n can reach the third device with maximum transfer rate of 942.8 kbps. The throughput of IEEE 802.11ac is more stable than IEEE 802.11n by compare the data from the first and second device. In third scenario, the maximum transfer rate of IEEE 802.11ac is higher than IEEE 802.11n and throughput of IEEE 802.11ac is more stable than IEEE 802.11n. In fourth scenario, the maximum transfer rate and average transfer rate of IEEE 802.11ac is higher than IEEE 802.11n.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129180872","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 : 2017-04-07DOI: 10.1109/CSCITA.2017.8066548
S. De, Abhishek Maity, Vritti Goel, S. Shitole, A. Bhattacharya
In this paper we use a Deep Neural Network (DNN) trained on data collected from the visual media-sharing social platform Instagram account of a popular Indian lifestyle magazine to predict the popularity of future posts. This predicted popularity of the post can be used to decide advertising rates and measure performance metrics important for publishing strategy decisions. The DNN primarily uses growth rate in subscriber base, tags associated with the post, time of day when the post was made, day of the week, color descriptors of the image, time between current and previous post, popularity of previous post as features for prediction. This covers majority of the causes of variation in popularity. Mini-batch gradient descend method is used to learn the weights in DNN and the objective function is cross-entropy. The network performs acceptable for real world applications and tolerances are within acceptable limits for the application.
{"title":"Predicting the popularity of instagram posts for a lifestyle magazine using deep learning","authors":"S. De, Abhishek Maity, Vritti Goel, S. Shitole, A. Bhattacharya","doi":"10.1109/CSCITA.2017.8066548","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066548","url":null,"abstract":"In this paper we use a Deep Neural Network (DNN) trained on data collected from the visual media-sharing social platform Instagram account of a popular Indian lifestyle magazine to predict the popularity of future posts. This predicted popularity of the post can be used to decide advertising rates and measure performance metrics important for publishing strategy decisions. The DNN primarily uses growth rate in subscriber base, tags associated with the post, time of day when the post was made, day of the week, color descriptors of the image, time between current and previous post, popularity of previous post as features for prediction. This covers majority of the causes of variation in popularity. Mini-batch gradient descend method is used to learn the weights in DNN and the objective function is cross-entropy. The network performs acceptable for real world applications and tolerances are within acceptable limits for the application.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130837017","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 : 2017-04-07DOI: 10.1109/CSCITA.2017.8066527
K. Karthik, Balaji Rao Katika
Planar spoofing is a well researched problem, wherein a high quality planar photograph can be replayed in front of a still camera as a substitute for another individual's face. Most modern day face recognition systems can be fooled by this process, as the perceptual information contained in a photo-of-a-photo, is virtually the same as that of a natural photograph of an individual. Current solutions attempt to detect this form of planar-spoofing through an extrinsic training process wherein both planar samples as well as regular photos are included as separate training sets. To avoid this form of explicit discriminant model-learning, we propose a single class training procedure for establishing and quantifying the quality of natural photographs taken under different lighting conditions, in terms of their CONTRAST PROFILE. Once this distribution is learnt, a suitable threshold is set based on the mean and standard deviation to pick up outliers. In this paper, we show that with just single poses of subjects, it is possible to achieve a low Equal Error Rate (EER) of 21.56% on the CASIA dataset and a rate of 8.57% upon cross-validation with a trimmed and shortened version of the MSU dataset.
{"title":"Image quality assessment based outlier detection for face anti-spoofing","authors":"K. Karthik, Balaji Rao Katika","doi":"10.1109/CSCITA.2017.8066527","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066527","url":null,"abstract":"Planar spoofing is a well researched problem, wherein a high quality planar photograph can be replayed in front of a still camera as a substitute for another individual's face. Most modern day face recognition systems can be fooled by this process, as the perceptual information contained in a photo-of-a-photo, is virtually the same as that of a natural photograph of an individual. Current solutions attempt to detect this form of planar-spoofing through an extrinsic training process wherein both planar samples as well as regular photos are included as separate training sets. To avoid this form of explicit discriminant model-learning, we propose a single class training procedure for establishing and quantifying the quality of natural photographs taken under different lighting conditions, in terms of their CONTRAST PROFILE. Once this distribution is learnt, a suitable threshold is set based on the mean and standard deviation to pick up outliers. In this paper, we show that with just single poses of subjects, it is possible to achieve a low Equal Error Rate (EER) of 21.56% on the CASIA dataset and a rate of 8.57% upon cross-validation with a trimmed and shortened version of the MSU dataset.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125712050","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 : 2017-04-07DOI: 10.1109/CSCITA.2017.8066524
V. Vijay, M. Singh
Wireless sensor networks are very suitable for remote sensing and monitoring tasks. Sensor nodes being battery operated devices and other limited resources present many challenges for protocols in WSNs. Researches are being continuously conducted with the purpose of combating these issues. Clustering in WSNs aim to distribute the energy load of the nodes by assigning some aggregator nodes or cluster heads. This paper presents a new criteria for CH selection which uses concepts of node density and residual energy. The purpose is to have a load balance to prolong network life.
{"title":"Energy efficient cluster head selection technique for homogeneous wireless sensor networks","authors":"V. Vijay, M. Singh","doi":"10.1109/CSCITA.2017.8066524","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066524","url":null,"abstract":"Wireless sensor networks are very suitable for remote sensing and monitoring tasks. Sensor nodes being battery operated devices and other limited resources present many challenges for protocols in WSNs. Researches are being continuously conducted with the purpose of combating these issues. Clustering in WSNs aim to distribute the energy load of the nodes by assigning some aggregator nodes or cluster heads. This paper presents a new criteria for CH selection which uses concepts of node density and residual energy. The purpose is to have a load balance to prolong network life.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116447193","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}
Today Big data is one of the most widely spoken about technology that is being explored throughout the world by technology enthusiasts and academic researchers. The reason for this is the enormous data generated every second of each day. Every webpage visited, every text message sent, every post on social networking websites, check-in information, mouse clicks etc. is logged. This data needs to be stored and retrieved efficiently, moreover the data is unstructured therefore the traditional methods of strong data fail. This data needs to be stored and retrieved efficiently There is a need of an efficient, scalable and robust architecture that needs stores enormous amounts of unstructured data, which can be queried as and when required. In this paper, we come up with a novel methodology to build a data warehouse over big data technologies while specifically addressing the issues of scalability and user performance. Our emphasis is on building a data pipeline which can be used as a reference for future research on the methodologies to build a data warehouse over big data technologies for either structured or unstructured data sources. We have demonstrated the processing of data for retrieving the facts from data warehouse using two techniques, namely HiveQL and MapReduce.
{"title":"Comparing HiveQL and MapReduce methods to process fact data in a data warehouse","authors":"Haince Denis Pen, Prajyoti Dsilva, Sweedle Mascarnes","doi":"10.1109/CSCITA.2017.8066553","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066553","url":null,"abstract":"Today Big data is one of the most widely spoken about technology that is being explored throughout the world by technology enthusiasts and academic researchers. The reason for this is the enormous data generated every second of each day. Every webpage visited, every text message sent, every post on social networking websites, check-in information, mouse clicks etc. is logged. This data needs to be stored and retrieved efficiently, moreover the data is unstructured therefore the traditional methods of strong data fail. This data needs to be stored and retrieved efficiently There is a need of an efficient, scalable and robust architecture that needs stores enormous amounts of unstructured data, which can be queried as and when required. In this paper, we come up with a novel methodology to build a data warehouse over big data technologies while specifically addressing the issues of scalability and user performance. Our emphasis is on building a data pipeline which can be used as a reference for future research on the methodologies to build a data warehouse over big data technologies for either structured or unstructured data sources. We have demonstrated the processing of data for retrieving the facts from data warehouse using two techniques, namely HiveQL and MapReduce.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"310 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122774125","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 : 2017-04-01DOI: 10.1109/CSCITA.2017.8066550
Kochar Inderkumar, Sandip G. Dhende, Swapnil P. Chilap
A compact wideband quarter-wave transformer using microstrip lines is presented. The design relies on replacing a uniform microstrip line with a multi-stage equivalent circuit. The equivalent circuit is a cascade of either T or π networks. Design equations for both types of equivalent circuits have been derived. A quarter-wave transformer operating at 1 GHz is implemented. Simulation results indicate a −15 dB impedance bandwidth exceeding 64% for a 3-stage network with less than 0.25 dB of attenuation within the bandwidth. Both types of equivalent circuits provide more than 40% compaction with proper selection of components. Measured results for the fabricated unit deviate within acceptable limits. The designed quarter-wave transformer may be used to replace 90° transmission lines in various passive microwave components.
{"title":"Compact wideband quarter-wave transformer using stepped impedance microstrip lines","authors":"Kochar Inderkumar, Sandip G. Dhende, Swapnil P. Chilap","doi":"10.1109/CSCITA.2017.8066550","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066550","url":null,"abstract":"A compact wideband quarter-wave transformer using microstrip lines is presented. The design relies on replacing a uniform microstrip line with a multi-stage equivalent circuit. The equivalent circuit is a cascade of either T or π networks. Design equations for both types of equivalent circuits have been derived. A quarter-wave transformer operating at 1 GHz is implemented. Simulation results indicate a −15 dB impedance bandwidth exceeding 64% for a 3-stage network with less than 0.25 dB of attenuation within the bandwidth. Both types of equivalent circuits provide more than 40% compaction with proper selection of components. Measured results for the fabricated unit deviate within acceptable limits. The designed quarter-wave transformer may be used to replace 90° transmission lines in various passive microwave components.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128228106","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 : 2017-04-01DOI: 10.1109/CSCITA.2017.8066566
Renia Lopes, Santosh V. Chapaneri, Deepak Jayaswal
Automated musical genre classification using machine learning techniques has gained popularity for research and development of powerful tools to organize music collections available on web. Mel cepstral co-efficients (MFCC's) have been successfully used in music genre classification but they do not reflect the correlation between the adjacent co-efficients of Mel filters of a frame neither the relation between adjacent co-efficients of Mel filters of neighboring frames. This leads to loss of useful features. In this work, Hu moment based features are extracted from the spectrogram to study impact of energy concentration in the spectrogram. Under different musical genres the difference in rhythm in genres drastically changes the texture of spectrogram image. This alters the energy concentration in spectrogram. Hu moments being invariant to translation, scaling as well as rotation can capture useful features from spectrogram that are not considered by the MFCC's. Since the spectral moments are computed locally, they can assess the intensity of energy concentration at certain frequencies in spectrogram and prove as distinct features in characterizing different genres of music. Hu moment based features along with conventional music features lead to an accuracy of 83.33% for classifying 5 genres.
{"title":"Music features based on Hu moments for genre classification","authors":"Renia Lopes, Santosh V. Chapaneri, Deepak Jayaswal","doi":"10.1109/CSCITA.2017.8066566","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066566","url":null,"abstract":"Automated musical genre classification using machine learning techniques has gained popularity for research and development of powerful tools to organize music collections available on web. Mel cepstral co-efficients (MFCC's) have been successfully used in music genre classification but they do not reflect the correlation between the adjacent co-efficients of Mel filters of a frame neither the relation between adjacent co-efficients of Mel filters of neighboring frames. This leads to loss of useful features. In this work, Hu moment based features are extracted from the spectrogram to study impact of energy concentration in the spectrogram. Under different musical genres the difference in rhythm in genres drastically changes the texture of spectrogram image. This alters the energy concentration in spectrogram. Hu moments being invariant to translation, scaling as well as rotation can capture useful features from spectrogram that are not considered by the MFCC's. Since the spectral moments are computed locally, they can assess the intensity of energy concentration at certain frequencies in spectrogram and prove as distinct features in characterizing different genres of music. Hu moment based features along with conventional music features lead to an accuracy of 83.33% for classifying 5 genres.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133312422","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 : 2017-04-01DOI: 10.1109/CSCITA.2017.8066555
Tejal Carwalo, Jerin Thankappan, Vandana A. Patil
Vehicle routing problem (VRP) involves minimizing total route length while visiting each customer location exactly once. In capacitated vehicle routing problem the nodal demand of the vehicle need to be satisfied. For large scale problem use of clustering approach can improve the solution. In this paper an effective modified partition clustering approach has been proposed. The main purpose of proposed partition clustering approach is to divide the entire area into small clusters and to consider the nodal demand of each vehicle while forming the clusters; then each cluster is solved as vehicle routing problem using ant colony optimization. The proposed partition clustering approach has improved the efficiency of the solution. Experimental result shows that the proposed clustering approach is better than the previously used k-means clustering approach.
{"title":"Capacitated vehicle routing problem","authors":"Tejal Carwalo, Jerin Thankappan, Vandana A. Patil","doi":"10.1109/CSCITA.2017.8066555","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066555","url":null,"abstract":"Vehicle routing problem (VRP) involves minimizing total route length while visiting each customer location exactly once. In capacitated vehicle routing problem the nodal demand of the vehicle need to be satisfied. For large scale problem use of clustering approach can improve the solution. In this paper an effective modified partition clustering approach has been proposed. The main purpose of proposed partition clustering approach is to divide the entire area into small clusters and to consider the nodal demand of each vehicle while forming the clusters; then each cluster is solved as vehicle routing problem using ant colony optimization. The proposed partition clustering approach has improved the efficiency of the solution. Experimental result shows that the proposed clustering approach is better than the previously used k-means clustering approach.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132274269","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 : 2017-04-01DOI: 10.1109/CSCITA.2017.8066545
N. Hassan, K. Bijoy
Object classification in both images and videos is an important task within the field of computer vision. The process of classifying objects into predefined and semantically meaningful categories using its features is called object classification. Many researchers are working in this area to improve the accuracy of classification and to reduce the dimension of features extracted which are used for classifying the objects. In this paper, we propose Linear Predictive Coding(LPC) based signal approximation on the Tensor features which reduces the dimension of the feature by removing the redundancies in the feature set, so that the accuracy is increased with less computation time. Deep Neural Network (DNN) which is a type of artificial intelligence that could solve complex perceptual problems as fast as human brain is used in this work to classify the objects in videos and images. In the proposed method we employ the combination of Scale Invariant Feature Transform (SIFT) and Tensor features of reduced dimensions. Simulation results illustrate that the proposed model produces more accurate results than many existing methods.
{"title":"LPC based low dimensional features for object classification","authors":"N. Hassan, K. Bijoy","doi":"10.1109/CSCITA.2017.8066545","DOIUrl":"https://doi.org/10.1109/CSCITA.2017.8066545","url":null,"abstract":"Object classification in both images and videos is an important task within the field of computer vision. The process of classifying objects into predefined and semantically meaningful categories using its features is called object classification. Many researchers are working in this area to improve the accuracy of classification and to reduce the dimension of features extracted which are used for classifying the objects. In this paper, we propose Linear Predictive Coding(LPC) based signal approximation on the Tensor features which reduces the dimension of the feature by removing the redundancies in the feature set, so that the accuracy is increased with less computation time. Deep Neural Network (DNN) which is a type of artificial intelligence that could solve complex perceptual problems as fast as human brain is used in this work to classify the objects in videos and images. In the proposed method we employ the combination of Scale Invariant Feature Transform (SIFT) and Tensor features of reduced dimensions. Simulation results illustrate that the proposed model produces more accurate results than many existing methods.","PeriodicalId":299147,"journal":{"name":"2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)","volume":"296 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124242599","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：