Pub Date : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569538
R. Suganya
Skin cancer is a deadly disease nowadays. So, early detection and prevention are essential. To classify the skin lesions in accurate manner an automatic Computer-Aided Diagnosis (CAD) for dermoscopy images were needed. The lesion segmentation is vital in the classification process. For segmenting the skin lesions many researchers have been developed different methods on melanocytic skin lesions (MSLs) and few methods for non-melanocytic skin lesions (NoMSLs), while the accurate segmentation for the variety of lesions are somewhat risky. In this K-means clustering is used for segmentation. After lesion is segmented extract the features such as color, text and shape. Many methods are used for classification but they focus only on melanocytic skin lesion i.e detecting melanoma only. Other lesion should also be classified for that a novel approach is used in this paper. The support vector machine (SVM) classifier was used for classification of skin lesions such as Melanoma, Basal cell carcinoma (BCC), Seborrhoeic keratosis (SK) and Nevus. The dataset collected from Dermweb. We used 100 NoMSLs and 220 MSLs set of images. Our classification method has achieved better accuracy as compared to others.
{"title":"An automated computer aided diagnosis of skin lesions detection and classification for dermoscopy images","authors":"R. Suganya","doi":"10.1109/ICRTIT.2016.7569538","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569538","url":null,"abstract":"Skin cancer is a deadly disease nowadays. So, early detection and prevention are essential. To classify the skin lesions in accurate manner an automatic Computer-Aided Diagnosis (CAD) for dermoscopy images were needed. The lesion segmentation is vital in the classification process. For segmenting the skin lesions many researchers have been developed different methods on melanocytic skin lesions (MSLs) and few methods for non-melanocytic skin lesions (NoMSLs), while the accurate segmentation for the variety of lesions are somewhat risky. In this K-means clustering is used for segmentation. After lesion is segmented extract the features such as color, text and shape. Many methods are used for classification but they focus only on melanocytic skin lesion i.e detecting melanoma only. Other lesion should also be classified for that a novel approach is used in this paper. The support vector machine (SVM) classifier was used for classification of skin lesions such as Melanoma, Basal cell carcinoma (BCC), Seborrhoeic keratosis (SK) and Nevus. The dataset collected from Dermweb. We used 100 NoMSLs and 220 MSLs set of images. Our classification method has achieved better accuracy as compared to others.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129707812","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569531
R. Anand, S. Veni, J. Aravinth
This work presents a method for identifying plant leaf disease and an approach for careful detection of diseases. The goal of proposed work is to diagnose the disease of brinjal leaf using image processing and artificial neural techniques. The diseases on the brinjal are critical issue which makes the sharp decrease in the production of brinjal. The study of interest is the leaf rather than whole brinjal plant because about 85-95 % of diseases occurred on the brinjal leaf like, Bacterial Wilt, Cercospora Leaf Spot, Tobacco mosaic virus (TMV). The methodology to detect brinjal leaf disease in this work includes K-means clustering algorithm for segmentation and Neural-network for classification. The proposed detection model based artiifical neural networks are very effective in recognizing leaf diseases.
{"title":"An application of image processing techniques for detection of diseases on brinjal leaves using k-means clustering method","authors":"R. Anand, S. Veni, J. Aravinth","doi":"10.1109/ICRTIT.2016.7569531","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569531","url":null,"abstract":"This work presents a method for identifying plant leaf disease and an approach for careful detection of diseases. The goal of proposed work is to diagnose the disease of brinjal leaf using image processing and artificial neural techniques. The diseases on the brinjal are critical issue which makes the sharp decrease in the production of brinjal. The study of interest is the leaf rather than whole brinjal plant because about 85-95 % of diseases occurred on the brinjal leaf like, Bacterial Wilt, Cercospora Leaf Spot, Tobacco mosaic virus (TMV). The methodology to detect brinjal leaf disease in this work includes K-means clustering algorithm for segmentation and Neural-network for classification. The proposed detection model based artiifical neural networks are very effective in recognizing leaf diseases.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128326411","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569513
Rapid climate change results natural calamity and severe economic impact and threats to the life. Burning fossil fuels by the medium of transportation contributes 1/3 of portion in increasing greenhouse emission and leading to raise surface temperate. Commuters in and around the developed cities faces difficulties in finding parking lot due to lack of notification process and autonomous parking systems. This causes commuters to take multiple rounds trips to get the parking slot which causes burning additional fuel and ultimately producing excessive CO2 emission. This paper describes solution to smart parking system using Internet of Things (IoT) to override parking hazards and explains how does it helps to minimize emitting greenhouse gases. IoT enables smart parking system using the system of interconnected Raspberry Pi, Distance Sensor, Pi Camera devices together. This hardware reacts to one another collects data and transmits to cloud storage.
{"title":"IoT smart parking system for reducing green house gas emission","authors":"","doi":"10.1109/ICRTIT.2016.7569513","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569513","url":null,"abstract":"Rapid climate change results natural calamity and severe economic impact and threats to the life. Burning fossil fuels by the medium of transportation contributes 1/3 of portion in increasing greenhouse emission and leading to raise surface temperate. Commuters in and around the developed cities faces difficulties in finding parking lot due to lack of notification process and autonomous parking systems. This causes commuters to take multiple rounds trips to get the parking slot which causes burning additional fuel and ultimately producing excessive CO2 emission. This paper describes solution to smart parking system using Internet of Things (IoT) to override parking hazards and explains how does it helps to minimize emitting greenhouse gases. IoT enables smart parking system using the system of interconnected Raspberry Pi, Distance Sensor, Pi Camera devices together. This hardware reacts to one another collects data and transmits to cloud storage.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132221870","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569528
Shubham N. Mahalank, Keertikumar B. Malagund, R. Banakar
A complex Internet of Things infrastructure needs systematic approach in the initial stages of the design to freeze between many available design alternatives. The decisions are located at the infrastructure level, mode of data transmission and software module development level. The choices affect the several design goals indicating the alternatives to represent a multi-criteria problem to judge the quality of the new IoT design. The performance and the response time along with cost for the application in Smart Traffic Management System is the criteria. Several aspects of the design space environment are investigated to answer the question that arise at the system level integration phase, in particular the communication mode devices, software modules, design integration issue and user services are uniquely identified from this framework. The required interface units, data transfer mode and software tool suite is provided using the IoT design space exploration approach. Users preferences based on the service requirement describes an end objective design response that can be used in the solution model.
{"title":"Design space exploration for IoT based traffic density indication system","authors":"Shubham N. Mahalank, Keertikumar B. Malagund, R. Banakar","doi":"10.1109/ICRTIT.2016.7569528","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569528","url":null,"abstract":"A complex Internet of Things infrastructure needs systematic approach in the initial stages of the design to freeze between many available design alternatives. The decisions are located at the infrastructure level, mode of data transmission and software module development level. The choices affect the several design goals indicating the alternatives to represent a multi-criteria problem to judge the quality of the new IoT design. The performance and the response time along with cost for the application in Smart Traffic Management System is the criteria. Several aspects of the design space environment are investigated to answer the question that arise at the system level integration phase, in particular the communication mode devices, software modules, design integration issue and user services are uniquely identified from this framework. The required interface units, data transfer mode and software tool suite is provided using the IoT design space exploration approach. Users preferences based on the service requirement describes an end objective design response that can be used in the solution model.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115900866","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569567
S. Krishnan, S. Karthika, S. Bose
In the social world the sharing of knowledge, data's and concepts within a group is done through the network of interactions and relationships. A community is formed by a group of individuals of same interest to share common values within themselves at a higher rate than outside the community. It can be a social unit of any size. The significant chore while studying the social network is to identify the communities. Communities facilitate to determine the cluster of intermingling objects denoted as nodes and the relations within themselves. In this paper, we propose a integrated framework for community detection in social networks. To find the communities in a social network our proposed framework follows a density based approach. We implement our proposed approach for different real-time dataset and got better results. Thus the proposed framework efficiently detects the communities exist in the social network.
{"title":"Detection of communities in dynamic social networks","authors":"S. Krishnan, S. Karthika, S. Bose","doi":"10.1109/ICRTIT.2016.7569567","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569567","url":null,"abstract":"In the social world the sharing of knowledge, data's and concepts within a group is done through the network of interactions and relationships. A community is formed by a group of individuals of same interest to share common values within themselves at a higher rate than outside the community. It can be a social unit of any size. The significant chore while studying the social network is to identify the communities. Communities facilitate to determine the cluster of intermingling objects denoted as nodes and the relations within themselves. In this paper, we propose a integrated framework for community detection in social networks. To find the communities in a social network our proposed framework follows a density based approach. We implement our proposed approach for different real-time dataset and got better results. Thus the proposed framework efficiently detects the communities exist in the social network.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132659653","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569573
B. Sahoo, Prachet Bhuyan
In recent years, research has been going in the field of service composition to improvise and gain fast delivery of complex applications. These complex business processes from heterogeneous service providers are composed as services at the run time to match the requirements of the consumers. Service composition has been acknowledged as a promising approach to create composite services that are capable of supporting service user needs. Service composition addresses and resolves these business requirements raised by various end users from time to time. Service composition in SOA has various techniques to compose services dynamically based on users' requirements, considering both functional and non-functional requirements. In our work, we have proposed a framework of dynamic service composition based on the service-composition life-cycle phases. After the service discovery, the selection of potential services for composition is a challenging task. For the selection of right candidate services in the composition process, we have also considered the non-functional requirements, which are the quality of services (QoS) aspects. We have proposed a selection algorithm for obtaining a reduced set of candidate services for the service composition process.
{"title":"A selection approach in service composition of SOA","authors":"B. Sahoo, Prachet Bhuyan","doi":"10.1109/ICRTIT.2016.7569573","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569573","url":null,"abstract":"In recent years, research has been going in the field of service composition to improvise and gain fast delivery of complex applications. These complex business processes from heterogeneous service providers are composed as services at the run time to match the requirements of the consumers. Service composition has been acknowledged as a promising approach to create composite services that are capable of supporting service user needs. Service composition addresses and resolves these business requirements raised by various end users from time to time. Service composition in SOA has various techniques to compose services dynamically based on users' requirements, considering both functional and non-functional requirements. In our work, we have proposed a framework of dynamic service composition based on the service-composition life-cycle phases. After the service discovery, the selection of potential services for composition is a challenging task. For the selection of right candidate services in the composition process, we have also considered the non-functional requirements, which are the quality of services (QoS) aspects. We have proposed a selection algorithm for obtaining a reduced set of candidate services for the service composition process.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131055575","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569523
G. Kumar, P. Parth, Sarthi Prabhat, Ranjan R Rajesh
This paper throws a light on the available clustering techniques and algorithms, k-means is used to cluster standard and satellite image in RGB and HSV color space. Normally satellite images comes with data and noises, in order to extract meaningful information efficiently there is a need of image clustering and performance of clustering based on pixel classification is greatly affected by the color space we selected, because image analysis in terms of Red, Green and Blue components is more difficult as compared to in terms of hue, saturation and value in context of differentiation an object. Our analysis of image clustering in two different color spaces using the k-means technique shows that clustering performance decreases with RGB color space when compared to HSV color space. CHI, DBI and SE indexes are calculated and compared.
{"title":"Performance of k-means based satellite image clustering in RGB and HSV color space","authors":"G. Kumar, P. Parth, Sarthi Prabhat, Ranjan R Rajesh","doi":"10.1109/ICRTIT.2016.7569523","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569523","url":null,"abstract":"This paper throws a light on the available clustering techniques and algorithms, k-means is used to cluster standard and satellite image in RGB and HSV color space. Normally satellite images comes with data and noises, in order to extract meaningful information efficiently there is a need of image clustering and performance of clustering based on pixel classification is greatly affected by the color space we selected, because image analysis in terms of Red, Green and Blue components is more difficult as compared to in terms of hue, saturation and value in context of differentiation an object. Our analysis of image clustering in two different color spaces using the k-means technique shows that clustering performance decreases with RGB color space when compared to HSV color space. CHI, DBI and SE indexes are calculated and compared.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132878999","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569541
D. Sudarvizhi
In image processing research field, image retrieval is extensively used in various application. Increasing need of the image retrieval, it is quiet most exciting research field. In image retrieval system, features are the most significant process used for indexing, retrieving and classifying the images. For computer systems, automatic indexing, storing and retrieving larger image collections effectively are a critical task. Nowadays several retrieval systems were implemented to overcome these issues but still there is a lack of speed and accuracy during image retrieval process. First, address the various issues on performance degradation of image retrieval then analyze and compare the methods and results in previous work. Second, discover the effective approach to be used to increase the accuracy of retrieval system significantly. This work provides a framework based on low level features extraction using Daubechies Wavelet Transform (DWT) and Zernike moments. Based on that features images are retrieved by using the distance measure. Zernike moments constitute a powerful shape descriptor due to its strength and narrative capability. Experimental results shows that our scheme provides significant improvement on retrieval accuracy compared to existing system based on the combination of both the color and edge features by using Discrete Wavelet Transform. In this paper, wang's image dataset is used for experiments.
{"title":"Feature based image retrieval system using Zernike moments and Daubechies Wavelet Transform","authors":"D. Sudarvizhi","doi":"10.1109/ICRTIT.2016.7569541","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569541","url":null,"abstract":"In image processing research field, image retrieval is extensively used in various application. Increasing need of the image retrieval, it is quiet most exciting research field. In image retrieval system, features are the most significant process used for indexing, retrieving and classifying the images. For computer systems, automatic indexing, storing and retrieving larger image collections effectively are a critical task. Nowadays several retrieval systems were implemented to overcome these issues but still there is a lack of speed and accuracy during image retrieval process. First, address the various issues on performance degradation of image retrieval then analyze and compare the methods and results in previous work. Second, discover the effective approach to be used to increase the accuracy of retrieval system significantly. This work provides a framework based on low level features extraction using Daubechies Wavelet Transform (DWT) and Zernike moments. Based on that features images are retrieved by using the distance measure. Zernike moments constitute a powerful shape descriptor due to its strength and narrative capability. Experimental results shows that our scheme provides significant improvement on retrieval accuracy compared to existing system based on the combination of both the color and edge features by using Discrete Wavelet Transform. In this paper, wang's image dataset is used for experiments.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132543070","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569600
R. Giridharan, E. K. Vellingiriraj, P. Balasubramanie
The aim of this paper is to develop a system that involves character recognition and information retrieval of Brahmi, Vattezhuthu and Grantha letters from temple epigraphy and their conversion to the present Tamil digital text format. Though many researchers have implemented various algorithms and techniques for character recognition in different languages, Ancient letter conversion still poses a big challenge. Because Image recognition technology has reached near-perfection when it comes to scanning English and other language text. But optical character recognition (OCR) software capable of digitizing printed Tamil text with high levels of accuracy is still elusive. Only a few people are familiar with the ancient characters and make attempts to convert them into written documents manually. If this continues, all the precious information given by our forefathers will not be known to the future generations. The proposed system overcomes such a situation by converting all the ancient characters from inscriptions and palm manuscripts into Tamil digital text format. After converting into the Tamil digital text, the words will not be correct spelling. Because the ancient words are Etymological word, the meaning is not known. So this modal approach is to solve these types of problem and convert the Tamil digital text with meaning.
{"title":"Identification of Tamil ancient characters and information retrieval from temple epigraphy using image zoning","authors":"R. Giridharan, E. K. Vellingiriraj, P. Balasubramanie","doi":"10.1109/ICRTIT.2016.7569600","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569600","url":null,"abstract":"The aim of this paper is to develop a system that involves character recognition and information retrieval of Brahmi, Vattezhuthu and Grantha letters from temple epigraphy and their conversion to the present Tamil digital text format. Though many researchers have implemented various algorithms and techniques for character recognition in different languages, Ancient letter conversion still poses a big challenge. Because Image recognition technology has reached near-perfection when it comes to scanning English and other language text. But optical character recognition (OCR) software capable of digitizing printed Tamil text with high levels of accuracy is still elusive. Only a few people are familiar with the ancient characters and make attempts to convert them into written documents manually. If this continues, all the precious information given by our forefathers will not be known to the future generations. The proposed system overcomes such a situation by converting all the ancient characters from inscriptions and palm manuscripts into Tamil digital text format. After converting into the Tamil digital text, the words will not be correct spelling. Because the ancient words are Etymological word, the meaning is not known. So this modal approach is to solve these types of problem and convert the Tamil digital text with meaning.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125480412","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 : 2016-04-08DOI: 10.1109/ICRTIT.2016.7569532
R. Reshma, G. Ambikesh, P. S. Thilagam
Recommender systems are used to find preferences of people or to predict the ratings with the help of information available from other users. The most widely used collaborative filtering recommender system by the e-commerce sites suffers from both the sparsity and cold-start problem due to insufficient data. Most of the existing systems consider only the ratings of the similar users and they do not give any preferences to the social behavior of users which shall aid the recommendations made to the user to a great extent. In this paper, instead of finding similarity from rating information, we propose a new approach which predicts the ratings of items by considering directed and transitive trust with timestamps and profile similarity from the social network along with the user-rated information. In cases where the trust and the rating details of users from the system is absent, we still make use of the social data of the users like the products liked by the user, user's social profile-education status, location etc. to make recommendation. Experimental analysis proves that our approach can improve the user recommendations at the extreme levels of sparsity in user-rating data. We also show that our approach works considerably well for cold-start users under the circumstances where collaborative filtering approach fails.
{"title":"Alleviating data sparsity and cold start in recommender systems using social behaviour","authors":"R. Reshma, G. Ambikesh, P. S. Thilagam","doi":"10.1109/ICRTIT.2016.7569532","DOIUrl":"https://doi.org/10.1109/ICRTIT.2016.7569532","url":null,"abstract":"Recommender systems are used to find preferences of people or to predict the ratings with the help of information available from other users. The most widely used collaborative filtering recommender system by the e-commerce sites suffers from both the sparsity and cold-start problem due to insufficient data. Most of the existing systems consider only the ratings of the similar users and they do not give any preferences to the social behavior of users which shall aid the recommendations made to the user to a great extent. In this paper, instead of finding similarity from rating information, we propose a new approach which predicts the ratings of items by considering directed and transitive trust with timestamps and profile similarity from the social network along with the user-rated information. In cases where the trust and the rating details of users from the system is absent, we still make use of the social data of the users like the products liked by the user, user's social profile-education status, location etc. to make recommendation. Experimental analysis proves that our approach can improve the user recommendations at the extreme levels of sparsity in user-rating data. We also show that our approach works considerably well for cold-start users under the circumstances where collaborative filtering approach fails.","PeriodicalId":351133,"journal":{"name":"2016 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124293399","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：