Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122162
Mukta Y. Raut, S. Barve
The field of opinion mining is expanding rapidly with the widespread use of internet for e-commerce and social interaction. One of the interesting use of opinion mining is in the field of online producer-consumer industry. The primary goal of the work presented in this paper is to perform a semi-automated sentiment classification on online product reviews for product evaluation using machine learning. We also aim to induce simplicity in sentiment classification; by using a method called Dual Sentiment Analysis, we relegate the need of using complex human annotations or very high end linguistic tools to solve the polarity shift problem in opinion classification. We also propose use of a pseudo-opposites dictionary based on our training corpus which is domain consistent with the training dataset.
{"title":"A semi-automated review classification system based on supervised machine learning","authors":"Mukta Y. Raut, S. Barve","doi":"10.1109/ICISIM.2017.8122162","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122162","url":null,"abstract":"The field of opinion mining is expanding rapidly with the widespread use of internet for e-commerce and social interaction. One of the interesting use of opinion mining is in the field of online producer-consumer industry. The primary goal of the work presented in this paper is to perform a semi-automated sentiment classification on online product reviews for product evaluation using machine learning. We also aim to induce simplicity in sentiment classification; by using a method called Dual Sentiment Analysis, we relegate the need of using complex human annotations or very high end linguistic tools to solve the polarity shift problem in opinion classification. We also propose use of a pseudo-opposites dictionary based on our training corpus which is domain consistent with the training dataset.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128062351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122152
Vishakha I. Sardar, Saroj Date
Many approaches are characteristic of name opinion is based only on the review of the single-shaft, ignoring non-trivial disparities in the distribution of the word of those around Corpus different. In Proposed work a new technique introduced to determine the characteristics of the idea of the magazine online by using the difference in those statistics through two and more than two different entities, a corpus of specific domain entity and a free domain of the corpus contrasted. Then determine the inconsistency through a measurement called relevance domain (DR), which characterizes the relevance of the term for a collection of manuscripts. Compile a list of candidates for the review of the terms of the domain corpus review of a set of rules of syntax dependency. For each function extracted candidates, Then evaluate the intrinsic domain and extrinsic domain relevance, in the entities of domain-dependent and independent respectively. The candidates which are different and more specific to the domain are confirmed as the hallmark of those.
{"title":"Identifying features in opinion mining using bootstrap methodology","authors":"Vishakha I. Sardar, Saroj Date","doi":"10.1109/ICISIM.2017.8122152","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122152","url":null,"abstract":"Many approaches are characteristic of name opinion is based only on the review of the single-shaft, ignoring non-trivial disparities in the distribution of the word of those around Corpus different. In Proposed work a new technique introduced to determine the characteristics of the idea of the magazine online by using the difference in those statistics through two and more than two different entities, a corpus of specific domain entity and a free domain of the corpus contrasted. Then determine the inconsistency through a measurement called relevance domain (DR), which characterizes the relevance of the term for a collection of manuscripts. Compile a list of candidates for the review of the terms of the domain corpus review of a set of rules of syntax dependency. For each function extracted candidates, Then evaluate the intrinsic domain and extrinsic domain relevance, in the entities of domain-dependent and independent respectively. The candidates which are different and more specific to the domain are confirmed as the hallmark of those.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121638067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122189
Swapnil Manchar Shinde
Conventional traffic light control systems are based on fixed time intervals of the traffic lights. These conventional fixed traffic light controllers have limitations and are less efficient because they use a hardware, which functions according to the program that lacks the flexibility of modification and adaptation on a real time basis. Thus due to the fixed time intervals of green and red signals there is excess and unnecessary waiting time on roads and vehicles consume more fuel. This eventually adds up to the environmental pollution and creates several health issues among the people on road and residing nearby. Also these conventional traffic light control systems do not have any provisions to provide any information on traffic densities on various roads, which leads to traffic congestions. Thus, to make traffic light controlling and traffic regulation more efficient, we exploit the emergence of new technique called as Adaptive Traffic Light Control System (ATLCS). The proposed system makes the use of network of array of sensors for sensing the traffic. On categorising this sensed traffic the timing intervals of red and green lights at each crossing of roads are intelligently decided and varied so as to keep the waiting time minimum. Thus, optimization of the traffic light switching increases the road capacity, saves time for travelling and prevents traffic congestions. The system also aims at incorporating special provisions for making immediate way for the emergency vehicles. GSM cell phone interface provides traffic information to drivers on demand and also helps in efficiently regulating the traffic and alternate route taking decisions. Efficiently regulated traffic also reduces pollution. The performance of this proposed system is compared with the conventional fixed time traffic light control system. The various performance evaluation parameters are efficient operation of sensor assembly, time saved per cycle, signal switching frequency, efficient emergency mode operation and the satisfactory operation of SMS using GSM mobile. The effectiveness of this system is shown and discussed in this paper by means of simulation results and on-board display.
{"title":"Adaptive traffic light control system","authors":"Swapnil Manchar Shinde","doi":"10.1109/ICISIM.2017.8122189","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122189","url":null,"abstract":"Conventional traffic light control systems are based on fixed time intervals of the traffic lights. These conventional fixed traffic light controllers have limitations and are less efficient because they use a hardware, which functions according to the program that lacks the flexibility of modification and adaptation on a real time basis. Thus due to the fixed time intervals of green and red signals there is excess and unnecessary waiting time on roads and vehicles consume more fuel. This eventually adds up to the environmental pollution and creates several health issues among the people on road and residing nearby. Also these conventional traffic light control systems do not have any provisions to provide any information on traffic densities on various roads, which leads to traffic congestions. Thus, to make traffic light controlling and traffic regulation more efficient, we exploit the emergence of new technique called as Adaptive Traffic Light Control System (ATLCS). The proposed system makes the use of network of array of sensors for sensing the traffic. On categorising this sensed traffic the timing intervals of red and green lights at each crossing of roads are intelligently decided and varied so as to keep the waiting time minimum. Thus, optimization of the traffic light switching increases the road capacity, saves time for travelling and prevents traffic congestions. The system also aims at incorporating special provisions for making immediate way for the emergency vehicles. GSM cell phone interface provides traffic information to drivers on demand and also helps in efficiently regulating the traffic and alternate route taking decisions. Efficiently regulated traffic also reduces pollution. The performance of this proposed system is compared with the conventional fixed time traffic light control system. The various performance evaluation parameters are efficient operation of sensor assembly, time saved per cycle, signal switching frequency, efficient emergency mode operation and the satisfactory operation of SMS using GSM mobile. The effectiveness of this system is shown and discussed in this paper by means of simulation results and on-board display.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117160891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122157
Swati D. Patil, P. S. Sanjekar
Musical instruments are consist of wide variety of domain so manual classification of these instruments is difficult and challenging task. To make the process of classifying musical instrument easy and less dependent on human supervision given system is designed. There are some algorithm are available for classification tsk from which we uses SVM, MLP and AdaBoost for better result. This system mainly designed for automatic classification of musical instrument using SVM, MLP and AdaBoost classifiers. Formal Concept Analysis technique is also applied to show relationship between musical instruments and their attributes. This system is evaluated with SVM, MLP and AdaBoost classifiers which show that AdaBoost gives better result than SVM and MLP.
{"title":"Musical instrument identification using SVM, MLP& AdaBoost with formal concept analysis","authors":"Swati D. Patil, P. S. Sanjekar","doi":"10.1109/ICISIM.2017.8122157","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122157","url":null,"abstract":"Musical instruments are consist of wide variety of domain so manual classification of these instruments is difficult and challenging task. To make the process of classifying musical instrument easy and less dependent on human supervision given system is designed. There are some algorithm are available for classification tsk from which we uses SVM, MLP and AdaBoost for better result. This system mainly designed for automatic classification of musical instrument using SVM, MLP and AdaBoost classifiers. Formal Concept Analysis technique is also applied to show relationship between musical instruments and their attributes. This system is evaluated with SVM, MLP and AdaBoost classifiers which show that AdaBoost gives better result than SVM and MLP.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129580857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122170
Tejashri A. Patil, S. Pandey, A. T. Bhole
In cloud computing environment various forms of services allows users to store the information at remote location. But, there are many drawbacks as well because of the remote storage. However, it is plagued by security issues despite its numerous advantages. The paper presents a review of the current security issues in cloud computing environment like lack of control of data, lack of trust and multi-tenancy. Ensuring cloud data integrity is to be the big issue. To overcome unauthorized access of data users by Cloud Service Provider, integrity verification is done through Trusted Third Party Auditor. The proposed algorithm handles encrypted data and performs auditing without decrypting data. The algorithm performs auditing over encrypted data. As data is not decrypted by auditors during auditing process, proposed algorithm becomes more secure than existing algorithm. Third party auditing process removes auditing overhead of data owner.
{"title":"A review on contemporary security issues of cloud computing","authors":"Tejashri A. Patil, S. Pandey, A. T. Bhole","doi":"10.1109/ICISIM.2017.8122170","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122170","url":null,"abstract":"In cloud computing environment various forms of services allows users to store the information at remote location. But, there are many drawbacks as well because of the remote storage. However, it is plagued by security issues despite its numerous advantages. The paper presents a review of the current security issues in cloud computing environment like lack of control of data, lack of trust and multi-tenancy. Ensuring cloud data integrity is to be the big issue. To overcome unauthorized access of data users by Cloud Service Provider, integrity verification is done through Trusted Third Party Auditor. The proposed algorithm handles encrypted data and performs auditing without decrypting data. The algorithm performs auditing over encrypted data. As data is not decrypted by auditors during auditing process, proposed algorithm becomes more secure than existing algorithm. Third party auditing process removes auditing overhead of data owner.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127585590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122179
Sunil Dilip Jain
With the development of cloud computing, storage of whole world started shifting to the cloud. Management and security of such a large data was very difficult, to lower the security issues, Tokenization was developed, but for maintaining the security and safety of the Tokenization servers, there was need of a strong encryption algorithm. This paper presents Next Generation Encryption Algorithm, a strong encryption and authentication mechanism for maintaining the confidentiality and integrity of the data which leverages the security and privacy provided by Tokenization mechanism.
{"title":"Enhancing security in Tokenization using NGE for storage as a service","authors":"Sunil Dilip Jain","doi":"10.1109/ICISIM.2017.8122179","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122179","url":null,"abstract":"With the development of cloud computing, storage of whole world started shifting to the cloud. Management and security of such a large data was very difficult, to lower the security issues, Tokenization was developed, but for maintaining the security and safety of the Tokenization servers, there was need of a strong encryption algorithm. This paper presents Next Generation Encryption Algorithm, a strong encryption and authentication mechanism for maintaining the confidentiality and integrity of the data which leverages the security and privacy provided by Tokenization mechanism.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128037887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122177
Jayashri Patil, S. Barve
Due to increasing volume of data in information technology, saving storage space and providing security to data has acquired more attention and popularity. In data processing and data mining, duplicates can effect severely. Data deduplication is a technique that eliminates duplicate data and store only one copy, promoting single instance storage. The main challenges are to identify maximum duplicate segment and selecting the storage nodes for distributing fragments of files. In this paper we proposed, Duplicate Detection and Fragment Placement (DDFP) a deduplication system that effectively eliminates duplicate data and fragments placement that allocates unique instances of a data file on storage nodes. For repeated data, reference pointer is used and only unique data is stored on the storage node. This increases the percentage of duplicate data detection. A fragment placement algorithm is used for placing fragments on different storage nodes. To select nodes T-coloring is used, Set T is used, which restricts the nodes that are at distance T from one another. DDFP considerably achieves duplicate elimination and obtain the high level of security on data fragments by storing fragments of the data file using T-coloring. This Selects the nodes that are not adjacent which prevent unauthorized access to data from other users.
{"title":"DDFP: Duplicate detection and fragment placement in deduplication system for security and storage space","authors":"Jayashri Patil, S. Barve","doi":"10.1109/ICISIM.2017.8122177","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122177","url":null,"abstract":"Due to increasing volume of data in information technology, saving storage space and providing security to data has acquired more attention and popularity. In data processing and data mining, duplicates can effect severely. Data deduplication is a technique that eliminates duplicate data and store only one copy, promoting single instance storage. The main challenges are to identify maximum duplicate segment and selecting the storage nodes for distributing fragments of files. In this paper we proposed, Duplicate Detection and Fragment Placement (DDFP) a deduplication system that effectively eliminates duplicate data and fragments placement that allocates unique instances of a data file on storage nodes. For repeated data, reference pointer is used and only unique data is stored on the storage node. This increases the percentage of duplicate data detection. A fragment placement algorithm is used for placing fragments on different storage nodes. To select nodes T-coloring is used, Set T is used, which restricts the nodes that are at distance T from one another. DDFP considerably achieves duplicate elimination and obtain the high level of security on data fragments by storing fragments of the data file using T-coloring. This Selects the nodes that are not adjacent which prevent unauthorized access to data from other users.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134526087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122182
Rekha Sugandhi, A. Mahajan
This paper discusses the semantic network approach to identify affects in natural language input and focusses on representing spatio-temporal affect information. It has been observed that this approach performs better in analysis of affect information that can be effectively utilized for the prognosis of human cognitive behavior. The research work in this paper describes a new approach towards simple representation of multi-dimensional affect data that facilitates the provision of emotions or affects with varying granularity. The analysis algorithm thus executed on the semantic representation generates temporally significant behavior patterns. The analysis of the semantic network generates temporally significant behavior patterns. The framework has been designed to be extensible over a wide variety of applications in cognitive computing.
{"title":"A semantic network approach to affect analysis: A case study on depression","authors":"Rekha Sugandhi, A. Mahajan","doi":"10.1109/ICISIM.2017.8122182","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122182","url":null,"abstract":"This paper discusses the semantic network approach to identify affects in natural language input and focusses on representing spatio-temporal affect information. It has been observed that this approach performs better in analysis of affect information that can be effectively utilized for the prognosis of human cognitive behavior. The research work in this paper describes a new approach towards simple representation of multi-dimensional affect data that facilitates the provision of emotions or affects with varying granularity. The analysis algorithm thus executed on the semantic representation generates temporally significant behavior patterns. The analysis of the semantic network generates temporally significant behavior patterns. The framework has been designed to be extensible over a wide variety of applications in cognitive computing.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125376716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122141
M. Hilal, P. Yannawar, A. Gaikwad
Today there are various types of image editing tools which make totally changes in image with free of cost, Image has performed a significant role in Human life but image has easily fiddle using image processing software. Fiddle image has difficult to detect that it is original or not for this reasons the image forgery detection topic is active research work nowadays. The proposed of this paper to detect image inconsistency using Histogram of Orientated Gradient (HOG) method which help us to determining which block has manipulation of an images. The paper conducting with many stages namely acquisition, preprocessing, and feature extraction and matching the performance of this system are based on false accepted rate (FAR) and false reject rate (FRR)
{"title":"Image inconsistency detection using histogram of orientated gradient (HOG)","authors":"M. Hilal, P. Yannawar, A. Gaikwad","doi":"10.1109/ICISIM.2017.8122141","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122141","url":null,"abstract":"Today there are various types of image editing tools which make totally changes in image with free of cost, Image has performed a significant role in Human life but image has easily fiddle using image processing software. Fiddle image has difficult to detect that it is original or not for this reasons the image forgery detection topic is active research work nowadays. The proposed of this paper to detect image inconsistency using Histogram of Orientated Gradient (HOG) method which help us to determining which block has manipulation of an images. The paper conducting with many stages namely acquisition, preprocessing, and feature extraction and matching the performance of this system are based on false accepted rate (FAR) and false reject rate (FRR)","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"3 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116810485","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：