The DNA Cryptography is more efficient technique to provide security by converting the plain text into the DNA sequence. The DNA sequence consisting of four alphabets A, C, G and T. Each alphabet is related to a nucleotide. DNA can be used to store, transmit the data and used for computation of the security for the data. The existing DNA technique takes more time for generating the encryption and decryption of text. The main objective of this paper is to provide more security to the data with low time complexity. The proposed method consists of three level of security for encryption of data. In Level-1 the shift key operation and complement operations are used. In level-2 the LBP operator is applied on the output of shift key and one's complements operation. In level-3 the output of two level is converted into DNA sequence. The receiver will apply the decryption for extracting the plain text from the cipher text. This proposed DNA cryptography provides the better security than the other cryptographic techniques and also takes less time for encryption and decryption of the data and provides more security.
{"title":"Fast Three Level DNA Cryptographic Technique to Provide Better Security","authors":"C. Raju, D. P. Kumar, D. Hussenappa, V. Kulakarne","doi":"10.1145/2979779.2979792","DOIUrl":"https://doi.org/10.1145/2979779.2979792","url":null,"abstract":"The DNA Cryptography is more efficient technique to provide security by converting the plain text into the DNA sequence. The DNA sequence consisting of four alphabets A, C, G and T. Each alphabet is related to a nucleotide. DNA can be used to store, transmit the data and used for computation of the security for the data. The existing DNA technique takes more time for generating the encryption and decryption of text. The main objective of this paper is to provide more security to the data with low time complexity. The proposed method consists of three level of security for encryption of data. In Level-1 the shift key operation and complement operations are used. In level-2 the LBP operator is applied on the output of shift key and one's complements operation. In level-3 the output of two level is converted into DNA sequence. The receiver will apply the decryption for extracting the plain text from the cipher text. This proposed DNA cryptography provides the better security than the other cryptographic techniques and also takes less time for encryption and decryption of the data and provides more security.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114456246","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}
Skype is one of the most widely being used application in government sectors as well as in corporate world. Skype facilitates with several advantages. Today almost all the companies rely on Skype for all their official communication as it provides an easy to use interface for communication sitting at a single location. But, at the moment, no government organization considered preservation as a major concern. Thus, performing Digital Forensics and data preservation in case of Skype is a challenging task. This arises the requirement to store the sensitive communication the safeguard the evidences of digital communication. As per the perspective of Information Technology Act 2000/2008, to safeguard the legal admissibility of the digital records, it is mandatory to capture and preserve the digital evidences of digital data and electronic records. This paper includes the glimpse of existing mechanisms and challenges in Skype. Through this paper, implementation of proposed work for Skype will be performed that will help investigator to collect the strong data evidence.
{"title":"Proposing a method for Skype Forensic-preserving data evidences to present in front of court of law","authors":"Vijay Chauhan, D. Katre","doi":"10.1145/2979779.2979882","DOIUrl":"https://doi.org/10.1145/2979779.2979882","url":null,"abstract":"Skype is one of the most widely being used application in government sectors as well as in corporate world. Skype facilitates with several advantages. Today almost all the companies rely on Skype for all their official communication as it provides an easy to use interface for communication sitting at a single location. But, at the moment, no government organization considered preservation as a major concern. Thus, performing Digital Forensics and data preservation in case of Skype is a challenging task. This arises the requirement to store the sensitive communication the safeguard the evidences of digital communication. As per the perspective of Information Technology Act 2000/2008, to safeguard the legal admissibility of the digital records, it is mandatory to capture and preserve the digital evidences of digital data and electronic records. This paper includes the glimpse of existing mechanisms and challenges in Skype. Through this paper, implementation of proposed work for Skype will be performed that will help investigator to collect the strong data evidence.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114735963","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}
At present recommender systems (RS) are incorporating contextual and social data of the client, delivering context aware RS where it take request response approach in which the recommendations are given to the client upon his solicitation. Later on they will utilize verifiable data of the client anywhere from the Internet of Things (IoT). Currently, a proactive RS that pushes proposals to the client when the present circumstance appears proper, without unequivocal client demand has been presented in the exploration research field of RS. In this paper, an outline of a context aware RS that prescribes recommendations under the IoT worldview is proposed. We also did the empirical analysis of the Machine Learning (ML) techniques like Genetic Algorithm optimized Artificial Neural Network (GA-ANN), decision tree, ANN, bagging, boosting which will perform the reasoning of the context. All inputs are virtually derived from the IoT and its output scores are calculated based on ML techniques which will decide if to push a recommendation to the user or not. Benchmark data of the Chicago restaurant is analyzed and it was observed that for the 98% of the contexts, GA-ANN produced correct recommendations with higher accuracy and efficiency in the correct times and context.
{"title":"Empirical analysis of Machine Learning Techniques for context aware Recommender Systems in the environment of IoT","authors":"Nitin Sachdeva, R. Dhir, Akshi Kumar","doi":"10.1145/2979779.2979818","DOIUrl":"https://doi.org/10.1145/2979779.2979818","url":null,"abstract":"At present recommender systems (RS) are incorporating contextual and social data of the client, delivering context aware RS where it take request response approach in which the recommendations are given to the client upon his solicitation. Later on they will utilize verifiable data of the client anywhere from the Internet of Things (IoT). Currently, a proactive RS that pushes proposals to the client when the present circumstance appears proper, without unequivocal client demand has been presented in the exploration research field of RS. In this paper, an outline of a context aware RS that prescribes recommendations under the IoT worldview is proposed. We also did the empirical analysis of the Machine Learning (ML) techniques like Genetic Algorithm optimized Artificial Neural Network (GA-ANN), decision tree, ANN, bagging, boosting which will perform the reasoning of the context. All inputs are virtually derived from the IoT and its output scores are calculated based on ML techniques which will decide if to push a recommendation to the user or not. Benchmark data of the Chicago restaurant is analyzed and it was observed that for the 98% of the contexts, GA-ANN produced correct recommendations with higher accuracy and efficiency in the correct times and context.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125791367","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}
The cloud platforms are gaining more popularity every year and adding up more customers to their portals. The cloud platforms are being flooded with the millions of user queries every second, which are becoming a major challenge to process them in the shortest possible time. The existing solutions do not evaluate the individual load on the virtual machines, while scheduling the tasks on the cloud platforms. In this paper, the new task scheduling model has been proposed, which utilizes the ant colony optimization for the load based VM allocation for each task loaded in the list for processing. The proposed model has been designed to calculate the load on the list of available VMs. The available list of the VM's is evaluated against the process cost, which checks the ability of VM in focus to process the given task. The VMs, who are eligible to process the given task, are shortlisted and the given task is assigned to the VM with the least load. The experimental results have manifested the effectiveness of the proposed model in comparison with the existing models to take the accurate offloading decisions.
{"title":"Cost Aware Load Balanced Task Scheduling with Active VM Load Evaluation","authors":"A. Kaur, Bikrampal Kaur","doi":"10.1145/2979779.2979861","DOIUrl":"https://doi.org/10.1145/2979779.2979861","url":null,"abstract":"The cloud platforms are gaining more popularity every year and adding up more customers to their portals. The cloud platforms are being flooded with the millions of user queries every second, which are becoming a major challenge to process them in the shortest possible time. The existing solutions do not evaluate the individual load on the virtual machines, while scheduling the tasks on the cloud platforms. In this paper, the new task scheduling model has been proposed, which utilizes the ant colony optimization for the load based VM allocation for each task loaded in the list for processing. The proposed model has been designed to calculate the load on the list of available VMs. The available list of the VM's is evaluated against the process cost, which checks the ability of VM in focus to process the given task. The VMs, who are eligible to process the given task, are shortlisted and the given task is assigned to the VM with the least load. The experimental results have manifested the effectiveness of the proposed model in comparison with the existing models to take the accurate offloading decisions.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127373127","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}
The performance of CSMA MAC degrades significantly due to hidden terminal problem as carrier sensing cannot avoid collision, this problem is faced by many CSMA MAC based systems hence it is one of the important issue which needs tobe solved in wireless communications. Idle listening of sensor nodes is a major source of energy waste during reprogramming and must be minimized. Although CSMA MAC is in the TinyOS release & the majority reprogramming systems use CSMA, the proposed work replaces existing CSMA with more efficient MAC i.e. a T-MAC. It uses TMAC unlike CSMA MAC in Deluge & most of the dissemination protocols to make the protocol more energy efficient, proper coordination & time synchronization between the node, proper bandwidth utilization & to carry appropriate MAC layer management functions like periodic wake up and sleep, neighbor's knowledge etc. TMAC uses the simple policy with fixed frames with variable active period & time-out interval which add many benefits like decreasing idle listening by duty cycle, collisions etc. hence improving the performance of designed protocol, making it better than the other protocols as it is more capable & adaptive as T-MAC prevents the packet collisions & ultimately solves the hidden terminal problem.
{"title":"Reliable Approach to Address Broadcast Storm & Hidden Terminal Problem in Multihop Wireless Sensor Network for Image Dissemination","authors":"V. Gulhane, L. Malik","doi":"10.1145/2979779.2979820","DOIUrl":"https://doi.org/10.1145/2979779.2979820","url":null,"abstract":"The performance of CSMA MAC degrades significantly due to hidden terminal problem as carrier sensing cannot avoid collision, this problem is faced by many CSMA MAC based systems hence it is one of the important issue which needs tobe solved in wireless communications. Idle listening of sensor nodes is a major source of energy waste during reprogramming and must be minimized. Although CSMA MAC is in the TinyOS release & the majority reprogramming systems use CSMA, the proposed work replaces existing CSMA with more efficient MAC i.e. a T-MAC. It uses TMAC unlike CSMA MAC in Deluge & most of the dissemination protocols to make the protocol more energy efficient, proper coordination & time synchronization between the node, proper bandwidth utilization & to carry appropriate MAC layer management functions like periodic wake up and sleep, neighbor's knowledge etc. TMAC uses the simple policy with fixed frames with variable active period & time-out interval which add many benefits like decreasing idle listening by duty cycle, collisions etc. hence improving the performance of designed protocol, making it better than the other protocols as it is more capable & adaptive as T-MAC prevents the packet collisions & ultimately solves the hidden terminal problem.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121714799","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}
E-Learning has become an essential element in everyday life. This method of teaching is being used to teach the students who are at remote location. This method has many advantages over the traditional method of teaching but there are several limitations in this method. One of those limitations is what if a student has a query? Probably, the answer seeking student will shoot an e-mail to the teacher along with his query and the teacher will reply with appropriate answer. The problem arises when many students ask the same query and the teacher has to reply each of them. There should be some kind of automation that can find that this query has been already answered and the system should reply with the appropriate answer. In this paper, we proposed an approach for an automatic email response system based on semantic similarity between queries and comparing between semantic similarity and semantic relatedness and find out which one is best for finding correct sense in query and finding score on the basis of sense match. System will be able to respond the email queries provided response will be available in the database.
{"title":"Automatic Email Response System in E-learning","authors":"Ankita Mittal, A. Ramamurthy","doi":"10.1145/2979779.2979868","DOIUrl":"https://doi.org/10.1145/2979779.2979868","url":null,"abstract":"E-Learning has become an essential element in everyday life. This method of teaching is being used to teach the students who are at remote location. This method has many advantages over the traditional method of teaching but there are several limitations in this method. One of those limitations is what if a student has a query? Probably, the answer seeking student will shoot an e-mail to the teacher along with his query and the teacher will reply with appropriate answer. The problem arises when many students ask the same query and the teacher has to reply each of them. There should be some kind of automation that can find that this query has been already answered and the system should reply with the appropriate answer. In this paper, we proposed an approach for an automatic email response system based on semantic similarity between queries and comparing between semantic similarity and semantic relatedness and find out which one is best for finding correct sense in query and finding score on the basis of sense match. System will be able to respond the email queries provided response will be available in the database.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122726141","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}
Ternary logic has been evolved from binary logic due to its many advantages as it is energy efficient, less complex and faster speed for serial transfer. Due to these technological advancements ternary circuits have attracted many researchers to implement ternary circuits. In digital system, NOT, NOR and NAND are of importance as they are the main building blocks of many complex arithmetic and logic circuits. In this paper, we discuss the basic ternary gates and some circuits implemented by using FinFET. An extensive simulation is performed for all the gates and circuits using Tspice Simulator. FinFET is being adapted instead of traditional MOSFET because of its captivity over the drawbacks occurred during narrowing to nanometer scale. Results obtained have expected functionality of each gate and circuits, additionally there is enhancement in performance parameters.
{"title":"An Approach to Ternary Logic gates using FinFET","authors":"K. Jyoti, S. Narkhede","doi":"10.1145/2979779.2979838","DOIUrl":"https://doi.org/10.1145/2979779.2979838","url":null,"abstract":"Ternary logic has been evolved from binary logic due to its many advantages as it is energy efficient, less complex and faster speed for serial transfer. Due to these technological advancements ternary circuits have attracted many researchers to implement ternary circuits. In digital system, NOT, NOR and NAND are of importance as they are the main building blocks of many complex arithmetic and logic circuits. In this paper, we discuss the basic ternary gates and some circuits implemented by using FinFET. An extensive simulation is performed for all the gates and circuits using Tspice Simulator. FinFET is being adapted instead of traditional MOSFET because of its captivity over the drawbacks occurred during narrowing to nanometer scale. Results obtained have expected functionality of each gate and circuits, additionally there is enhancement in performance parameters.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126336684","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}
Cryptographically generated address (CGA) is a prime inherent element of SEND protocol introduced in IPv6.CGA works without relying on any trusted third party authority or Public Key Infrastructure (PKI).CGA find their application in proving address ownership and prevent spoofing or theft of IPv6 addresses by binding senders public key with the generated address. Though CGA is a promising technique and offers substantial amount of security, it does possess some limitations and performance bottlenecks. CGA is computationally intensive determined by the security parameter 'sec' and bandwidth gobbling due to use of RSA keys. For a higher value of 'sec', there is no guarantee on termination of brute force search for modifier. This paper evaluates the performance and discusses possible techniques that can be used in optimizing the use of IPv6 CGA. The techniques discussed are the possible modifications to the standard RFC 3972.These include reducing the granularity factor of sec from 16 to 8, replacing RSA with ECC and ECSDSA, using SHA-256 hash function instead of SHA-1 and including subnet prefix in the calculation of CGA. The paper also compares the modified CGA with standard CGA and advocates the reasons for incorporating these changes so that enhanced hybrid version of CGA can be obtained.
{"title":"IPv6 Cryptographically Generated Address: Analysis and Optimization","authors":"Junaid Latief Shah, J. Parvez","doi":"10.1145/2979779.2979781","DOIUrl":"https://doi.org/10.1145/2979779.2979781","url":null,"abstract":"Cryptographically generated address (CGA) is a prime inherent element of SEND protocol introduced in IPv6.CGA works without relying on any trusted third party authority or Public Key Infrastructure (PKI).CGA find their application in proving address ownership and prevent spoofing or theft of IPv6 addresses by binding senders public key with the generated address. Though CGA is a promising technique and offers substantial amount of security, it does possess some limitations and performance bottlenecks. CGA is computationally intensive determined by the security parameter 'sec' and bandwidth gobbling due to use of RSA keys. For a higher value of 'sec', there is no guarantee on termination of brute force search for modifier. This paper evaluates the performance and discusses possible techniques that can be used in optimizing the use of IPv6 CGA. The techniques discussed are the possible modifications to the standard RFC 3972.These include reducing the granularity factor of sec from 16 to 8, replacing RSA with ECC and ECSDSA, using SHA-256 hash function instead of SHA-1 and including subnet prefix in the calculation of CGA. The paper also compares the modified CGA with standard CGA and advocates the reasons for incorporating these changes so that enhanced hybrid version of CGA can be obtained.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131711133","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}
In content based image retrieval(CBIR), the searching and retrieving of similar kinds of digital images from an image database are realized on the visual features of a given query image. The efficiency and accuracy of any CBIR scheme depends on the extracted significant visual features of the digital images. This paper considered a CBIR scheme based on the proficient combination of extracted color and texture visual features. The visual features are extracted from the enhanced HSV color image after enhancing the RGB color image using Laplacian filter. In the presented work, the color feature is extracted from the quantized histograms of Hue (H) and Saturation (S) components while texture feature is extracted from computed gray level co- occurrence matrices (GLCMs) of each sub image of discrete wavelet transform (DWT) of Value (V) component of HSV color image. The extracted color and texture visual features are combined together after normalizing them individually. The proposed CBIR scheme is evaluated on standard Corel image database and observed that the combined feature vector produces the satisfactory results in terms of performance evaluation metrics i.e. precision, recall and F-score. The experimental results are also showed that the proposed CBIR scheme outperforms as compare to the some other existing schemes.
{"title":"A Content Based Image Retrieval using Color and Texture Features","authors":"Naushad Varish, Arup Kumar Pal","doi":"10.1145/2979779.2979787","DOIUrl":"https://doi.org/10.1145/2979779.2979787","url":null,"abstract":"In content based image retrieval(CBIR), the searching and retrieving of similar kinds of digital images from an image database are realized on the visual features of a given query image. The efficiency and accuracy of any CBIR scheme depends on the extracted significant visual features of the digital images. This paper considered a CBIR scheme based on the proficient combination of extracted color and texture visual features. The visual features are extracted from the enhanced HSV color image after enhancing the RGB color image using Laplacian filter. In the presented work, the color feature is extracted from the quantized histograms of Hue (H) and Saturation (S) components while texture feature is extracted from computed gray level co- occurrence matrices (GLCMs) of each sub image of discrete wavelet transform (DWT) of Value (V) component of HSV color image. The extracted color and texture visual features are combined together after normalizing them individually. The proposed CBIR scheme is evaluated on standard Corel image database and observed that the combined feature vector produces the satisfactory results in terms of performance evaluation metrics i.e. precision, recall and F-score. The experimental results are also showed that the proposed CBIR scheme outperforms as compare to the some other existing schemes.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123129809","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}
B. G. Deshmukh, Premkumar S. Jain, Manasi S. Patwardhan, Viraj Kulkarni
These days the most crucial and commercially valuable information is becoming increasingly available on the World Wide Web. Companies which provide financial services are also making their products available on the web. As there are various types of web financial information sources, such as News Blogs, News Articles, Financial websites and Social Media, a lot of work is being carried out in the Stock Market domain using Data Analytics. This paper tries to find out if twitter sentiments and commodity prices help in predicting actual stock prices for top 50 companies listed on NIFTY at NSE, India, by using Natural Language Processing, Sentiment Analysis and Machine Learning techniques. The results show that, Twitter sentiment gives 70% accuracy while predicting the actual stock prices and the accuracy is improved by 15% when integrated with commodity prices for making company-wise predictions. Furthermore, we check if analyst's recommendations have more impact on stock market price movements for all companies listed on NSE as compared to tweeter public sentiments. The results show that, analyst's recommendations contribute more with 9% of the increase in prediction accuracy.
{"title":"Spin-offs in Indian Stock Market owing to Twitter Sentiments, Commodity Prices and Analyst Recommendations","authors":"B. G. Deshmukh, Premkumar S. Jain, Manasi S. Patwardhan, Viraj Kulkarni","doi":"10.1145/2979779.2979856","DOIUrl":"https://doi.org/10.1145/2979779.2979856","url":null,"abstract":"These days the most crucial and commercially valuable information is becoming increasingly available on the World Wide Web. Companies which provide financial services are also making their products available on the web. As there are various types of web financial information sources, such as News Blogs, News Articles, Financial websites and Social Media, a lot of work is being carried out in the Stock Market domain using Data Analytics. This paper tries to find out if twitter sentiments and commodity prices help in predicting actual stock prices for top 50 companies listed on NIFTY at NSE, India, by using Natural Language Processing, Sentiment Analysis and Machine Learning techniques. The results show that, Twitter sentiment gives 70% accuracy while predicting the actual stock prices and the accuracy is improved by 15% when integrated with commodity prices for making company-wise predictions. Furthermore, we check if analyst's recommendations have more impact on stock market price movements for all companies listed on NSE as compared to tweeter public sentiments. The results show that, analyst's recommendations contribute more with 9% of the increase in prediction accuracy.","PeriodicalId":298730,"journal":{"name":"Proceedings of the International Conference on Advances in Information Communication Technology & Computing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114986684","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：