Pub Date : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653780
S. Mhamane, Mr. Pranav Shriram
one of the major challenges in present ticketing provision is QUEUE in buying and railway ticket checking. In this fast world people want all work is to be done within minutes with help of digitalization and usage of smartphone it is all possible. Users ticket information is stored in a database for security, which is absent in present system. Ticket checker is having admin login in application to look for user ticket with the ticket number in the database which scans in the form of QR code. Dynamic seat allocation also gives 100% utilization of seats as well proper allocation for waiting list passenger during Journey.
{"title":"Digirail- The Digital Railway System and Dynamic Seat Allocation","authors":"S. Mhamane, Mr. Pranav Shriram","doi":"10.1109/I-SMAC.2018.8653780","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653780","url":null,"abstract":"one of the major challenges in present ticketing provision is QUEUE in buying and railway ticket checking. In this fast world people want all work is to be done within minutes with help of digitalization and usage of smartphone it is all possible. Users ticket information is stored in a database for security, which is absent in present system. Ticket checker is having admin login in application to look for user ticket with the ticket number in the database which scans in the form of QR code. Dynamic seat allocation also gives 100% utilization of seats as well proper allocation for waiting list passenger during Journey.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"20 1","pages":"384-387"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90963180","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653763
A. Misra, D. S. Yadav
In this paper we have proposed a novel cluster based data sharing scheme that tries to employ the advantages of both clustering as well as proactive routing. Our clustering algorithm divides the MANET into clusters forming cluster heads, cluster gateways and cluster members during the cluster formation phase. We restrict the use of DSDV routing protocol within the cluster thereby reducing the control overhead and routing table size. Cluster maintenance and file index distribution within the cluster is done by adding extra fields in the DSDV control messages. Routing is done using the DSDV routing table. Unlike existing data lookup schemes, where a data lookup query is flooded in the entire MANET or in the cluster backbone, here it is forwarded to the nearest gateway node thereby completely eliminating flooding.
{"title":"Effective data lookup scheme for Cluster based Data Sharing in MANET","authors":"A. Misra, D. S. Yadav","doi":"10.1109/I-SMAC.2018.8653763","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653763","url":null,"abstract":"In this paper we have proposed a novel cluster based data sharing scheme that tries to employ the advantages of both clustering as well as proactive routing. Our clustering algorithm divides the MANET into clusters forming cluster heads, cluster gateways and cluster members during the cluster formation phase. We restrict the use of DSDV routing protocol within the cluster thereby reducing the control overhead and routing table size. Cluster maintenance and file index distribution within the cluster is done by adding extra fields in the DSDV control messages. Routing is done using the DSDV routing table. Unlike existing data lookup schemes, where a data lookup query is flooded in the entire MANET or in the cluster backbone, here it is forwarded to the nearest gateway node thereby completely eliminating flooding.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"51 1","pages":"367-372"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77925041","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653761
Richa Jain, Prof. Deepa Gianchandani
Detection and Recognition in traffic sign pictures or common pictures has applications in Computer vision frameworks like enlistment number plate identification, programmed movement sign location, picture recovery and help for outwardly disabled individuals. In this paper a hybrid approach based on MSER and OCR, utilizing clamor expulsion strategy, i.e. Lucy-Richardson calculation. After clamor evacuation, content district location stage begins with complexity upgraded edge improved MSER area discovery system is utilized there after morphological division is utilized to section content locale in the picture. After location stage acknowledgment stage begins in which content applicants are separated utilizing geometric filtration utilizing properties, for example, viewpoint proportion, unusualness, solidicity, and so forth. At that point Bounding box strategy is utilized to distinguish letter competitors and shape word out of them. At long last, Optical Character Recognition (OCR) instrument is utilized to concentrate message out of picture. The framework displayed beats best in class techniques on the dataset of the movement content sign information that were gotten from Jaguar Land Rover Research.
{"title":"A Hybrid Approach for Detection and Recognition of Traffic Text Sign using MSER and OCR","authors":"Richa Jain, Prof. Deepa Gianchandani","doi":"10.1109/I-SMAC.2018.8653761","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653761","url":null,"abstract":"Detection and Recognition in traffic sign pictures or common pictures has applications in Computer vision frameworks like enlistment number plate identification, programmed movement sign location, picture recovery and help for outwardly disabled individuals. In this paper a hybrid approach based on MSER and OCR, utilizing clamor expulsion strategy, i.e. Lucy-Richardson calculation. After clamor evacuation, content district location stage begins with complexity upgraded edge improved MSER area discovery system is utilized there after morphological division is utilized to section content locale in the picture. After location stage acknowledgment stage begins in which content applicants are separated utilizing geometric filtration utilizing properties, for example, viewpoint proportion, unusualness, solidicity, and so forth. At that point Bounding box strategy is utilized to distinguish letter competitors and shape word out of them. At long last, Optical Character Recognition (OCR) instrument is utilized to concentrate message out of picture. The framework displayed beats best in class techniques on the dataset of the movement content sign information that were gotten from Jaguar Land Rover Research.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"24 1","pages":"775-778"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78217691","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653748
S. Priya, Dr. R. Manavalan
Weighted Extreme Learning Machine (WELM) is one among the machine learning algorithms with extremely learning and good generalization capabilities. WELM handles the imbalanced dataset efficiently for assigning less weight to majority class and more weight to minority class. In general, the classification performance of WELM extremely depends on the parameters such as the input weight matrix, the value of bias and the number of hidden neurons and the weights associated with majority and minority classes. The arbitrary selection of hidden biases and the input weight, WELM produces inconsistent result. In this paper, hybridization of WELM with Invasive Weed optimization and WELM with BAT algorithm are proposed to tune the parameters for WELM such as initial weight and hidden bias values. The proposed methodologies are called as WELM- IWO and WELM-BAT. The proposed methods are evaluated over three real world medical diagnosis problems such as Hepatitis, Diabetes and Thyroid diseases. The experimental results proved that one of the proposed methods WELM-IWO outperforms well on all three datasets.
{"title":"Tuning the Parameters of Weighted ELM using IWO and BAT Algorithm to Improve the Classification Performance","authors":"S. Priya, Dr. R. Manavalan","doi":"10.1109/I-SMAC.2018.8653748","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653748","url":null,"abstract":"Weighted Extreme Learning Machine (WELM) is one among the machine learning algorithms with extremely learning and good generalization capabilities. WELM handles the imbalanced dataset efficiently for assigning less weight to majority class and more weight to minority class. In general, the classification performance of WELM extremely depends on the parameters such as the input weight matrix, the value of bias and the number of hidden neurons and the weights associated with majority and minority classes. The arbitrary selection of hidden biases and the input weight, WELM produces inconsistent result. In this paper, hybridization of WELM with Invasive Weed optimization and WELM with BAT algorithm are proposed to tune the parameters for WELM such as initial weight and hidden bias values. The proposed methodologies are called as WELM- IWO and WELM-BAT. The proposed methods are evaluated over three real world medical diagnosis problems such as Hepatitis, Diabetes and Thyroid diseases. The experimental results proved that one of the proposed methods WELM-IWO outperforms well on all three datasets.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"35 1","pages":"547-552"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78078402","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653722
P. M. Salunke, Vishal. V. Mahale
In this paper we proposed a novel technique to store the data authentically in the cloud. Since because of elastic property from the point of view of storage space cloud is most popular to store data. Cloud is inquiring about stores data on it. Therefore, security is must for store data for preserving it from malicious attackers as well as there may be leakage in stored data security. Many times there is necessary condition for hiding the user or data owner identity from cloud. A technique use in this paper shows anonymous authentication for stored data on cloud. This system preserves the identity of the users before storing it on cloud. The main aim of this paper is only valid user have ability to encrypt stored data with help of accessing its control features. The basic idea behind this scenario is to prevent stored data of cloud as well as its creation, modification etc. In this approach, cloud is familiar with access policies of every stored data also several KDCs are used for key management. Expensive operations are carried out easily in decentralized cloud system than centralized cloud system approach. The proposed system is implemented and tested in java with mysql database.
{"title":"Secure Data sharing in Distributed Cloud Environment","authors":"P. M. Salunke, Vishal. V. Mahale","doi":"10.1109/I-SMAC.2018.8653722","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653722","url":null,"abstract":"In this paper we proposed a novel technique to store the data authentically in the cloud. Since because of elastic property from the point of view of storage space cloud is most popular to store data. Cloud is inquiring about stores data on it. Therefore, security is must for store data for preserving it from malicious attackers as well as there may be leakage in stored data security. Many times there is necessary condition for hiding the user or data owner identity from cloud. A technique use in this paper shows anonymous authentication for stored data on cloud. This system preserves the identity of the users before storing it on cloud. The main aim of this paper is only valid user have ability to encrypt stored data with help of accessing its control features. The basic idea behind this scenario is to prevent stored data of cloud as well as its creation, modification etc. In this approach, cloud is familiar with access policies of every stored data also several KDCs are used for key management. Expensive operations are carried out easily in decentralized cloud system than centralized cloud system approach. The proposed system is implemented and tested in java with mysql database.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"119 1","pages":"262-266"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/I-SMAC.2018.8653722","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72522988","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653756
Vaishali Malpe, Prathamesh S. Tugaonkar
Machine Learning is ruling the world due to its accuracy and timely predictions for the given set of problems. Machine Learning is highly used for health monitoring to reduce the mortality rate and enhance the life expectancy. Organs such as kidneys, pancreas are highly affected in the run of life. Cancers like breast cancer has shown increase in the count since last decade. This leads to invent new techniques in the field of medical sciences which can give accurate and timely predictions to reduce the mortality rate. This paper presents comparative study of the current research using various machine learning algorithms and big data techniques to handle huge volume of data.
{"title":"Machine LearningTrends in Medical Sciences","authors":"Vaishali Malpe, Prathamesh S. Tugaonkar","doi":"10.1109/I-SMAC.2018.8653756","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653756","url":null,"abstract":"Machine Learning is ruling the world due to its accuracy and timely predictions for the given set of problems. Machine Learning is highly used for health monitoring to reduce the mortality rate and enhance the life expectancy. Organs such as kidneys, pancreas are highly affected in the run of life. Cancers like breast cancer has shown increase in the count since last decade. This leads to invent new techniques in the field of medical sciences which can give accurate and timely predictions to reduce the mortality rate. This paper presents comparative study of the current research using various machine learning algorithms and big data techniques to handle huge volume of data.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"39 1","pages":"495-499"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75320123","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653782
K. Kumar, K. Krishna, K. Raghavendra, K. Harish
This paper presents the design and implementation of a 4-b Flash Analog to Digital Converter (ADC) in 180nm digital CMOS technology. The proposed flash ADC utilizes resistive ladder logic network, high speed comparators and a encoder logic to convert the given continuous input signal into output binary code. The flash ADC utilizes a novel encoder realized using pseudo dynamic CMOS logic which has been implemented with fewer transistors compared to the previous other techniques. Without the need of time interleaving technique, the proposed ADC is capable of operating at its full sampling rate. The designed flash ADC consumes 0.686mW when operated from a power supply voltage of 1.8V. The operating speed of this circuit is 10GHz and the simulated integral non-linearity error (INL) and differential non-linearity error (DNL) are between 0.1/-0.02LSB and 0.33/-0.12LSB respectively. It occupies an effective area of 0.32mm2.
{"title":"A High Speed Flash Analog to Digital Converter","authors":"K. Kumar, K. Krishna, K. Raghavendra, K. Harish","doi":"10.1109/I-SMAC.2018.8653782","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653782","url":null,"abstract":"This paper presents the design and implementation of a 4-b Flash Analog to Digital Converter (ADC) in 180nm digital CMOS technology. The proposed flash ADC utilizes resistive ladder logic network, high speed comparators and a encoder logic to convert the given continuous input signal into output binary code. The flash ADC utilizes a novel encoder realized using pseudo dynamic CMOS logic which has been implemented with fewer transistors compared to the previous other techniques. Without the need of time interleaving technique, the proposed ADC is capable of operating at its full sampling rate. The designed flash ADC consumes 0.686mW when operated from a power supply voltage of 1.8V. The operating speed of this circuit is 10GHz and the simulated integral non-linearity error (INL) and differential non-linearity error (DNL) are between 0.1/-0.02LSB and 0.33/-0.12LSB respectively. It occupies an effective area of 0.32mm2.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"49 1","pages":"283-288"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74986381","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653752
Aniket Kodre, Komal Tikone, Mansi Sonawane, Pratik Jare, P. Shinde
India was the fourth largest motor vehicle/car manufacturer in the world in 2016. The growth rate of car ownership is raising big time in India. Presently, the average level of ownership stands at 13 per 1,000 populations and this is expected to increase exponentially. Car owners and Car users sometimes face problems related to their vehicles like remembering the renewal date of PUC, Routine check-ups, maintenance and accordingly periodical expenditure of the vehicle related things. Also trapping in a car or overheating of car causes suffocation kind of problems, where immediate communication is very much needed. So there is a need of a system that will support car users in maintaining vehicle related issues in easy way.This project work, proposed a system that helps car user to manage car related things. An android application is developed to provide the features like reminders for PUC renewal, Routine check-ups and maintenance, which will reduce the efforts of the car users. It provides necessary help to the car user by giving information whenever required. User can explore new cities around him/her very easily. Misplaced objects in the car are detected through the system. Based on traveling pattern future destinations are predicted.Thus, the project work resulted into development of a system which assists the car user by providing the necessary support.
{"title":"Smart and Efficient Personal Car Assistant System","authors":"Aniket Kodre, Komal Tikone, Mansi Sonawane, Pratik Jare, P. Shinde","doi":"10.1109/I-SMAC.2018.8653752","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653752","url":null,"abstract":"India was the fourth largest motor vehicle/car manufacturer in the world in 2016. The growth rate of car ownership is raising big time in India. Presently, the average level of ownership stands at 13 per 1,000 populations and this is expected to increase exponentially. Car owners and Car users sometimes face problems related to their vehicles like remembering the renewal date of PUC, Routine check-ups, maintenance and accordingly periodical expenditure of the vehicle related things. Also trapping in a car or overheating of car causes suffocation kind of problems, where immediate communication is very much needed. So there is a need of a system that will support car users in maintaining vehicle related issues in easy way.This project work, proposed a system that helps car user to manage car related things. An android application is developed to provide the features like reminders for PUC renewal, Routine check-ups and maintenance, which will reduce the efforts of the car users. It provides necessary help to the car user by giving information whenever required. User can explore new cities around him/her very easily. Misplaced objects in the car are detected through the system. Based on traveling pattern future destinations are predicted.Thus, the project work resulted into development of a system which assists the car user by providing the necessary support.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"32 1","pages":"12-17"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88642481","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653603
R. Preethi, M. Sughasiny
In MANET, when a mobile node needs to communicate with a remote destination, it relies on the other nodes to relay the packets. This multi-hop packet transmission can extend the network coverage area using limited power and improve area spectral efficiency. Since the mobile nodes are battery driven and one of the major sources of energy consumption is radio transmission, selfish nodes are unwilling to lose their battery energy in relaying other users’ packets. To tackle this problem, this paper proposed a novel price based game theory routing (PBGTR) algorithm in MANET. Using this routing algorithm, a source node finds Minimum Cost Routing Path (MCRP) within destination node, then forward packet to destination via this MCRP. After the successful transmission, a source node pays the payment to each participated nodes. The simulation results shows that the proposed PBGTR routing algorithm is more efficient than other existing routing protocols. Furthermore, it consumes minimum cost for routing.
{"title":"PBGTR: PRICE BASED GAME THEORY ROUTING FOR MINIMUM COST ROUTING PATH IN MANET","authors":"R. Preethi, M. Sughasiny","doi":"10.1109/I-SMAC.2018.8653603","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653603","url":null,"abstract":"In MANET, when a mobile node needs to communicate with a remote destination, it relies on the other nodes to relay the packets. This multi-hop packet transmission can extend the network coverage area using limited power and improve area spectral efficiency. Since the mobile nodes are battery driven and one of the major sources of energy consumption is radio transmission, selfish nodes are unwilling to lose their battery energy in relaying other users’ packets. To tackle this problem, this paper proposed a novel price based game theory routing (PBGTR) algorithm in MANET. Using this routing algorithm, a source node finds Minimum Cost Routing Path (MCRP) within destination node, then forward packet to destination via this MCRP. After the successful transmission, a source node pays the payment to each participated nodes. The simulation results shows that the proposed PBGTR routing algorithm is more efficient than other existing routing protocols. Furthermore, it consumes minimum cost for routing.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"4 1","pages":"469-474"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78440576","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 : 2018-08-01DOI: 10.1109/I-SMAC.2018.8653709
N. Sivaramakrishnan, V. Subramaniyaswamy
Collaborative filtering is one among the top most preferred techniques when implementing recommendation systems. In recent times, more interest has turned towards parallel GPU-based implementation of collaborative filtering algorithms. Concurrent way of solving any problem is more preferable by everyone nowadays. The objective of GPU-based collaborative filtering recommender system is to produce recommendations in parallel and choosing the best among all. We have proposed three different methods namely Parallel Item Average Computation (PIAC), Parallel User Based Collaborative Filtering (PUBCF) and Parallel Item Based Collaborative Filtering (PIBCF).We have evaluated all these methods with standard evaluation metrics. As a result of task parallelism, the PIBCF method produces optimum choice for providing better recommendation results.
{"title":"GPU-based Collaborative Filtering Recommendation System using Task parallelism approach","authors":"N. Sivaramakrishnan, V. Subramaniyaswamy","doi":"10.1109/I-SMAC.2018.8653709","DOIUrl":"https://doi.org/10.1109/I-SMAC.2018.8653709","url":null,"abstract":"Collaborative filtering is one among the top most preferred techniques when implementing recommendation systems. In recent times, more interest has turned towards parallel GPU-based implementation of collaborative filtering algorithms. Concurrent way of solving any problem is more preferable by everyone nowadays. The objective of GPU-based collaborative filtering recommender system is to produce recommendations in parallel and choosing the best among all. We have proposed three different methods namely Parallel Item Average Computation (PIAC), Parallel User Based Collaborative Filtering (PUBCF) and Parallel Item Based Collaborative Filtering (PIBCF).We have evaluated all these methods with standard evaluation metrics. As a result of task parallelism, the PIBCF method produces optimum choice for providing better recommendation results.","PeriodicalId":53631,"journal":{"name":"Koomesh","volume":"17 1","pages":"111-116"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72858480","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：