International Journal of Forensic Software Engineering, 2019
Cashless economy and digital payments are one of the hot topics of research that are gaining enor... more Cashless economy and digital payments are one of the hot topics of research that are gaining enormous popularity day by day. It is primarily due to their ability to combat issues of corruption, back money, illegal transactions and counterfeit money. With the increase in number of options of digital payments, people are inclining themselves towards ease of payment. This paper focuses on two aspects: firstly, it provides an analytical study performed in the field of cashless transactions and digital payments. Secondly, it finds out the opinion of the people about cashless transactions using a hybrid approach of type 2 fuzzy logic and hesitant fuzzy sets for polarity assignment. A sentiment analysis on 'cashless economy' has been carried out using data obtained from Twitter in the form of tweets.
2019 International Conference on Advances in Computing, Communication and Control (ICAC3), 2019
For various Natural Language Processing (NLP) use cases, it is desirable to know the significance... more For various Natural Language Processing (NLP) use cases, it is desirable to know the significance of the text. Various methods based on path, corpus and knowledge measures are used to find out the similarity among words. Different word similarity approaches are analysed in this paper. The widely accepted approach is Wu and Palmer similarity measure. But it has a major disadvantage. It produces less similarity score for those pair of words which are in same hierarchy in the ontology, whereas according to the contextual meaning, these words are more connected and so should have more similarity score. This paper lists the shortcomings of Wu and Palmer formula and presents a remodelled formula to improve the scores of such pair of words. The remodelled formula uses logarithm bringing the depth of the words in the ontology under a uniform scale. wup- Wu and Palmer, LCS- Least Common Subsumer(the most clearly identified concept or word which is an ancestor of two words in the ontology), Simremodelled - Remodelled Wu and Palmer formula
Proceedings of 2nd International Conference on Communication, Computing and Networking, 2018
Uneven distribution of data between the nodes causes the data skewness problem. Due to this probl... more Uneven distribution of data between the nodes causes the data skewness problem. Due to this problem, various problems occur during the processing. So, this paper presents the brief analysis of the existing techniques related to load imbalancing with their pros and cons. Also, types of data skewness have been discussed in this paper.
This paper describes Named Entity Recognition (NER) system for Hindi language using two methodolo... more This paper describes Named Entity Recognition (NER) system for Hindi language using two methodologies. An existing BaseLine Maximum Entropy-based Named Entity (BL-MENE) model and Context Pattern-based MENE (CP-MENE) framework the one proposed in this work. BL-MENE utilizes several features for the NER task but suffers from inaccurate Named Entity (NE) boundary detection, mis-classification errors, and partial recognition of NEs due to certain missing essentials. However, CP-MENE based NER task incorporates extensive features and patterns set to overcome these problems. In fact, the CP-MENE features include right-boundary, left-boundary, part-of-speech, synonyms, gazetteers and relative pronoun features. CP-MENE formulates a kind of recursive relationship to extract high ranked NE patterns that are generated through regular expressions via python@ code. Nowadays, since the Web contents in the Hindi language are rising, especially in the health-care applications, this work is conducte...
In this paper, we propose a new scale factor in differential evolution for optimization of numeri... more In this paper, we propose a new scale factor in differential evolution for optimization of numerical data (low dimensional data) that is both seen in algebraic and exponential form in real world scenarios. With the present work we improve the optimization of DE with real world numerical data set of the Lahi crop production of Pantnagar farm, G.B. Pant University of Agriculture and Technology, Pantnagar, India; inventory demand and population of India. This study focusses on optimization of numerical data that is characterized by single dimension.
2019 4th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU), 2019
Short answer evaluation has always been an enormously popular research topic due to its large app... more Short answer evaluation has always been an enormously popular research topic due to its large application domain. In this paper, it is applied for students answer sheet evaluation. An automated method for students answer sheet evaluation may ensure that the assessment is impartial and free of any prejudices that the evaluator may have in the favor of or against the student. This paper proposes a method for students answer sheet evaluation for short answer type questions using a Fuzzy W ordNet graph based approach. The results are obtained on a synthetic dataset and as compared to the state-of-art, they seem promising.
2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), 2018
In this paper, we have proposed a partitioning technique to handle big data. MapReduce is very se... more In this paper, we have proposed a partitioning technique to handle big data. MapReduce is very sensitive to data skewness so there is a need to develop such technique which handle the data skewness and do not affect the performance of the task. To overcome this problem we have proposed a partitioning algorithm name as PTBSH (Partition Tuning based Bagging technique to Skew Handling). It ensures the even distribution of data with the help of frequency keys and bagging. Proposed algorithm has been compared with known existing methods in terms of data skewness, data locality and runtime. Experiments have been performed on seven data sets which have been extracted from the UCI repositories.
Sarcasm detection is one of the active research area in sentimental analysis. However this paper ... more Sarcasm detection is one of the active research area in sentimental analysis. However this paper talks about one of the recent issue in sentimental analysis that us sarcasm detection. In our work, we have described different techniques used in sarcasm detection that helps a novice researcher in efficient way. This paper represent different methodologies of carrying out research in this field.
2020 International Conference on Intelligent Engineering and Management (ICIEM), 2020
Reviewer Assignment Problem (RAP) is defined as a problem of assigning the most suitable expert t... more Reviewer Assignment Problem (RAP) is defined as a problem of assigning the most suitable expert to the proposal. which is a very important task for any research organization In literature many solutions have been proposed for solving RAP but most of them do not deal with the imprecision associated with the problem. In this paper, a novel approach has been proposed for assigning proposals to legitimate experts based on their previous history and domain expertise. For the purpose, we have first extracted the most important words from the author’s submitted paper and reviewer’s published articles by constructing a fuzzy graph and applying fuzzy graph centrality measures on it. We have then created fuzzy sets for the selected keywords and their weights (for both author’s papers and reviewer’s publications). Afterwards, WordNet have been used to find the diatance beween the fuzzy sets represented for author's papers reviewers' papers. Finally, fuzzy extension principle is applied...
The problem of Word Sense Disambiguation (WSD) can be defined as the task of assigning the most a... more The problem of Word Sense Disambiguation (WSD) can be defined as the task of assigning the most appropriate sense to the polysemous word within a given context. Many supervised, unsupervised and semi-supervised approaches have been devised to deal with this problem, particularly, for the English language. However, this is not the case for Hindi language, where not much work has been done. In this paper, a new approach has been developed to perform disambiguation in Hindi language. For training the system, the text in Hindi language is converted into Hyperspace Analogue to Language (HAL) vectors, thereby, mapping each word into a high-dimensional space. We also deal with the fuzziness involved in disambiguation of words. We apply Fuzzy C-Means Clustering algorithm to form clusters denoting the various contexts in which the polysemous word may occur. The test data is then mapped into the high dimensional space created during the training phase. We test our approach on the corpus creat...
Due to the ever-evolving nature of human languages, the ambiguity in it needs to be dealt with by... more Due to the ever-evolving nature of human languages, the ambiguity in it needs to be dealt with by the researchers. Word sense disambiguation (WSD) is a classical problem of natural language processing which refers to identifying the most appropriate sense of a given word in the concerned context. WordNet graph based approaches are used by several state-of-art methods for performing WSD. This paper highlights a novel genetic algorithm based approach for performing WSD using fuzzy WordNet graph based approach. The fitness function is calculated using the fuzzy global measures of graph connectivity. For proposing this fitness function, a comparative study is performed for the global measures edge density, entropy and compactness. Also, an analytical insight is provided by presenting a visualization of the control terms for word sense disambiguation in the research papers from 2013 to 2018 present in Web of Science.
Various classical techniques such as linear regression, nearest neighbor have been used in develo... more Various classical techniques such as linear regression, nearest neighbor have been used in developing predictive models in the past. But the methodologies developed using fuzzy time series includes a wide array of work that requires special attention. The time series analysis has been of great importance to engineering and economy problems. In this paper, we present a brief summary of the various infamous methodologies available in the literature for forecasting of numerical data using fuzzy time series that includes stock prediction, temperature prediction, foreign exchange daily price estimate, crop production, educational enrollments forecasting, inventory demand and also a brief mention of the limitations of fuzzy time series.
In the current era of social media, opinion mining shows a remarkable significance in information... more In the current era of social media, opinion mining shows a remarkable significance in information retrieval and web data analysis. This new research domain becomes important as the use of social media has increased to next fold. Users here generate the content, which is in the form of emotions, comments that can be positive or negative, an individual's own view point etc. Using the social networking sites (e.g. Facebook®, twitter®), multi-media sharing sites (e.g. YouTube®, Flickr®), blogs and rich web applications as the usage of Web 2.0 increases, user can exchange or share their opinion. In this paper a detailed analysis is conducted that thoroughly discuss the domain and commonly used classification techniques to assist future research in this new emerging area. These techniques are used for Opinion Mining and Sentiment Analysis.
It is an era where there are constant advancements in the area of Information Technology. Technol... more It is an era where there are constant advancements in the area of Information Technology. Technologies such as, internet, database management system, bar code readers or information systems in nature. Information retrieval is not enough for decision making. Thus, it becomes important for us to develop automatic and intelligent tools for analyzing, interpreting develop and select strategies in the context of the application. In this paper, we provide an insight to fuzzy learning, the rules governing fuzzy logic and study the application of fuzzy forecasting. We also discuss the fu
The general perceptions about a product and the reputation of the company determine to a great ex... more The general perceptions about a product and the reputation of the company determine to a great extent how well the product sells. It is thus imperative that we make efforts to understand the public opinions and sentiments, as they can be a very good indicator of the product's future sales performance. In this paper, we explore the two most common online media which have been used by the public to express such type of subjective content: Blogs and Micro-blogs. We perform a comparative analysis of the predictive power of the two media to know which of these formats can prove to be a more useful representative of sentiments to an autonomous stock price prediction system.
Sentiment analysis or opinion mining has an extensive area in the field of research. Today we con... more Sentiment analysis or opinion mining has an extensive area in the field of research. Today we consider the huge amount of structured and unstructured data available in the web for a particular subject to get an opinion. The surplus data handling termed as big data requires some new technology to deal with. This paper considers the requirement of sentiment analysis of such huge data for fast processing. Based on Fast Fourier Transform on Temporal Intuitionistic fuzzy set generated from text, this algorithm (FFT-TIFS) expedites the sentiment classification. Fourier analysis converts a signal from its time domain to its representation in frequency domain. Such frequency domain algorithm on Temporal Intuitionistic fuzzy set is used in Sentiment analysis for the first time. This algorithm is useful for short twitter text, document level as well as sentence level binary sentiment classification. It is tested on aclImdb, Polarity, MR, Sentiment140 and CR dataset which gives an average of 80% accuracy. The proposed method shows significant improvement in required time complexity where the method achieves 17 times faster processing in comparison to sequential Fuzzy C Means(FCM) method and again it is at least 7 times faster than distributed FCM method present in literature. The method presented in this paper has a novel approach towards fastest processing time and suitability of various sizes of the text sentiment analysis.
The paper presents a scalable and generalized approach to social network analysis using fuzzy gra... more The paper presents a scalable and generalized approach to social network analysis using fuzzy graph theory. In this, we propose an intelligent sociocentric approach that calculates the degree of potential relationship of a social network of finite size, by proposing a fuzzy graph social network model. It takes into account social entity functional and relational attributes simultaneously. In this, the degree of potential relationship of a social network is computed by using two steps. In the first step, the fuzzy pairwise relationship between all social entities is computed using the proposed fuzzy node activeness index parameter with their online and offline communication relationship parameters. In the second step, all fuzzy pairwise relationships that are calculated in the first step are further employed for the calculation of the degree of potential relationship of a social network using an astute function utilizing both weighted arithmetic and geometric means. Here two weights ...
International Journal of Forensic Software Engineering, 2019
Cashless economy and digital payments are one of the hot topics of research that are gaining enor... more Cashless economy and digital payments are one of the hot topics of research that are gaining enormous popularity day by day. It is primarily due to their ability to combat issues of corruption, back money, illegal transactions and counterfeit money. With the increase in number of options of digital payments, people are inclining themselves towards ease of payment. This paper focuses on two aspects: firstly, it provides an analytical study performed in the field of cashless transactions and digital payments. Secondly, it finds out the opinion of the people about cashless transactions using a hybrid approach of type 2 fuzzy logic and hesitant fuzzy sets for polarity assignment. A sentiment analysis on 'cashless economy' has been carried out using data obtained from Twitter in the form of tweets.
2019 International Conference on Advances in Computing, Communication and Control (ICAC3), 2019
For various Natural Language Processing (NLP) use cases, it is desirable to know the significance... more For various Natural Language Processing (NLP) use cases, it is desirable to know the significance of the text. Various methods based on path, corpus and knowledge measures are used to find out the similarity among words. Different word similarity approaches are analysed in this paper. The widely accepted approach is Wu and Palmer similarity measure. But it has a major disadvantage. It produces less similarity score for those pair of words which are in same hierarchy in the ontology, whereas according to the contextual meaning, these words are more connected and so should have more similarity score. This paper lists the shortcomings of Wu and Palmer formula and presents a remodelled formula to improve the scores of such pair of words. The remodelled formula uses logarithm bringing the depth of the words in the ontology under a uniform scale. wup- Wu and Palmer, LCS- Least Common Subsumer(the most clearly identified concept or word which is an ancestor of two words in the ontology), Simremodelled - Remodelled Wu and Palmer formula
Proceedings of 2nd International Conference on Communication, Computing and Networking, 2018
Uneven distribution of data between the nodes causes the data skewness problem. Due to this probl... more Uneven distribution of data between the nodes causes the data skewness problem. Due to this problem, various problems occur during the processing. So, this paper presents the brief analysis of the existing techniques related to load imbalancing with their pros and cons. Also, types of data skewness have been discussed in this paper.
This paper describes Named Entity Recognition (NER) system for Hindi language using two methodolo... more This paper describes Named Entity Recognition (NER) system for Hindi language using two methodologies. An existing BaseLine Maximum Entropy-based Named Entity (BL-MENE) model and Context Pattern-based MENE (CP-MENE) framework the one proposed in this work. BL-MENE utilizes several features for the NER task but suffers from inaccurate Named Entity (NE) boundary detection, mis-classification errors, and partial recognition of NEs due to certain missing essentials. However, CP-MENE based NER task incorporates extensive features and patterns set to overcome these problems. In fact, the CP-MENE features include right-boundary, left-boundary, part-of-speech, synonyms, gazetteers and relative pronoun features. CP-MENE formulates a kind of recursive relationship to extract high ranked NE patterns that are generated through regular expressions via python@ code. Nowadays, since the Web contents in the Hindi language are rising, especially in the health-care applications, this work is conducte...
In this paper, we propose a new scale factor in differential evolution for optimization of numeri... more In this paper, we propose a new scale factor in differential evolution for optimization of numerical data (low dimensional data) that is both seen in algebraic and exponential form in real world scenarios. With the present work we improve the optimization of DE with real world numerical data set of the Lahi crop production of Pantnagar farm, G.B. Pant University of Agriculture and Technology, Pantnagar, India; inventory demand and population of India. This study focusses on optimization of numerical data that is characterized by single dimension.
2019 4th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU), 2019
Short answer evaluation has always been an enormously popular research topic due to its large app... more Short answer evaluation has always been an enormously popular research topic due to its large application domain. In this paper, it is applied for students answer sheet evaluation. An automated method for students answer sheet evaluation may ensure that the assessment is impartial and free of any prejudices that the evaluator may have in the favor of or against the student. This paper proposes a method for students answer sheet evaluation for short answer type questions using a Fuzzy W ordNet graph based approach. The results are obtained on a synthetic dataset and as compared to the state-of-art, they seem promising.
2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), 2018
In this paper, we have proposed a partitioning technique to handle big data. MapReduce is very se... more In this paper, we have proposed a partitioning technique to handle big data. MapReduce is very sensitive to data skewness so there is a need to develop such technique which handle the data skewness and do not affect the performance of the task. To overcome this problem we have proposed a partitioning algorithm name as PTBSH (Partition Tuning based Bagging technique to Skew Handling). It ensures the even distribution of data with the help of frequency keys and bagging. Proposed algorithm has been compared with known existing methods in terms of data skewness, data locality and runtime. Experiments have been performed on seven data sets which have been extracted from the UCI repositories.
Sarcasm detection is one of the active research area in sentimental analysis. However this paper ... more Sarcasm detection is one of the active research area in sentimental analysis. However this paper talks about one of the recent issue in sentimental analysis that us sarcasm detection. In our work, we have described different techniques used in sarcasm detection that helps a novice researcher in efficient way. This paper represent different methodologies of carrying out research in this field.
2020 International Conference on Intelligent Engineering and Management (ICIEM), 2020
Reviewer Assignment Problem (RAP) is defined as a problem of assigning the most suitable expert t... more Reviewer Assignment Problem (RAP) is defined as a problem of assigning the most suitable expert to the proposal. which is a very important task for any research organization In literature many solutions have been proposed for solving RAP but most of them do not deal with the imprecision associated with the problem. In this paper, a novel approach has been proposed for assigning proposals to legitimate experts based on their previous history and domain expertise. For the purpose, we have first extracted the most important words from the author’s submitted paper and reviewer’s published articles by constructing a fuzzy graph and applying fuzzy graph centrality measures on it. We have then created fuzzy sets for the selected keywords and their weights (for both author’s papers and reviewer’s publications). Afterwards, WordNet have been used to find the diatance beween the fuzzy sets represented for author's papers reviewers' papers. Finally, fuzzy extension principle is applied...
The problem of Word Sense Disambiguation (WSD) can be defined as the task of assigning the most a... more The problem of Word Sense Disambiguation (WSD) can be defined as the task of assigning the most appropriate sense to the polysemous word within a given context. Many supervised, unsupervised and semi-supervised approaches have been devised to deal with this problem, particularly, for the English language. However, this is not the case for Hindi language, where not much work has been done. In this paper, a new approach has been developed to perform disambiguation in Hindi language. For training the system, the text in Hindi language is converted into Hyperspace Analogue to Language (HAL) vectors, thereby, mapping each word into a high-dimensional space. We also deal with the fuzziness involved in disambiguation of words. We apply Fuzzy C-Means Clustering algorithm to form clusters denoting the various contexts in which the polysemous word may occur. The test data is then mapped into the high dimensional space created during the training phase. We test our approach on the corpus creat...
Due to the ever-evolving nature of human languages, the ambiguity in it needs to be dealt with by... more Due to the ever-evolving nature of human languages, the ambiguity in it needs to be dealt with by the researchers. Word sense disambiguation (WSD) is a classical problem of natural language processing which refers to identifying the most appropriate sense of a given word in the concerned context. WordNet graph based approaches are used by several state-of-art methods for performing WSD. This paper highlights a novel genetic algorithm based approach for performing WSD using fuzzy WordNet graph based approach. The fitness function is calculated using the fuzzy global measures of graph connectivity. For proposing this fitness function, a comparative study is performed for the global measures edge density, entropy and compactness. Also, an analytical insight is provided by presenting a visualization of the control terms for word sense disambiguation in the research papers from 2013 to 2018 present in Web of Science.
Various classical techniques such as linear regression, nearest neighbor have been used in develo... more Various classical techniques such as linear regression, nearest neighbor have been used in developing predictive models in the past. But the methodologies developed using fuzzy time series includes a wide array of work that requires special attention. The time series analysis has been of great importance to engineering and economy problems. In this paper, we present a brief summary of the various infamous methodologies available in the literature for forecasting of numerical data using fuzzy time series that includes stock prediction, temperature prediction, foreign exchange daily price estimate, crop production, educational enrollments forecasting, inventory demand and also a brief mention of the limitations of fuzzy time series.
In the current era of social media, opinion mining shows a remarkable significance in information... more In the current era of social media, opinion mining shows a remarkable significance in information retrieval and web data analysis. This new research domain becomes important as the use of social media has increased to next fold. Users here generate the content, which is in the form of emotions, comments that can be positive or negative, an individual's own view point etc. Using the social networking sites (e.g. Facebook®, twitter®), multi-media sharing sites (e.g. YouTube®, Flickr®), blogs and rich web applications as the usage of Web 2.0 increases, user can exchange or share their opinion. In this paper a detailed analysis is conducted that thoroughly discuss the domain and commonly used classification techniques to assist future research in this new emerging area. These techniques are used for Opinion Mining and Sentiment Analysis.
It is an era where there are constant advancements in the area of Information Technology. Technol... more It is an era where there are constant advancements in the area of Information Technology. Technologies such as, internet, database management system, bar code readers or information systems in nature. Information retrieval is not enough for decision making. Thus, it becomes important for us to develop automatic and intelligent tools for analyzing, interpreting develop and select strategies in the context of the application. In this paper, we provide an insight to fuzzy learning, the rules governing fuzzy logic and study the application of fuzzy forecasting. We also discuss the fu
The general perceptions about a product and the reputation of the company determine to a great ex... more The general perceptions about a product and the reputation of the company determine to a great extent how well the product sells. It is thus imperative that we make efforts to understand the public opinions and sentiments, as they can be a very good indicator of the product's future sales performance. In this paper, we explore the two most common online media which have been used by the public to express such type of subjective content: Blogs and Micro-blogs. We perform a comparative analysis of the predictive power of the two media to know which of these formats can prove to be a more useful representative of sentiments to an autonomous stock price prediction system.
Sentiment analysis or opinion mining has an extensive area in the field of research. Today we con... more Sentiment analysis or opinion mining has an extensive area in the field of research. Today we consider the huge amount of structured and unstructured data available in the web for a particular subject to get an opinion. The surplus data handling termed as big data requires some new technology to deal with. This paper considers the requirement of sentiment analysis of such huge data for fast processing. Based on Fast Fourier Transform on Temporal Intuitionistic fuzzy set generated from text, this algorithm (FFT-TIFS) expedites the sentiment classification. Fourier analysis converts a signal from its time domain to its representation in frequency domain. Such frequency domain algorithm on Temporal Intuitionistic fuzzy set is used in Sentiment analysis for the first time. This algorithm is useful for short twitter text, document level as well as sentence level binary sentiment classification. It is tested on aclImdb, Polarity, MR, Sentiment140 and CR dataset which gives an average of 80% accuracy. The proposed method shows significant improvement in required time complexity where the method achieves 17 times faster processing in comparison to sequential Fuzzy C Means(FCM) method and again it is at least 7 times faster than distributed FCM method present in literature. The method presented in this paper has a novel approach towards fastest processing time and suitability of various sizes of the text sentiment analysis.
The paper presents a scalable and generalized approach to social network analysis using fuzzy gra... more The paper presents a scalable and generalized approach to social network analysis using fuzzy graph theory. In this, we propose an intelligent sociocentric approach that calculates the degree of potential relationship of a social network of finite size, by proposing a fuzzy graph social network model. It takes into account social entity functional and relational attributes simultaneously. In this, the degree of potential relationship of a social network is computed by using two steps. In the first step, the fuzzy pairwise relationship between all social entities is computed using the proposed fuzzy node activeness index parameter with their online and offline communication relationship parameters. In the second step, all fuzzy pairwise relationships that are calculated in the first step are further employed for the calculation of the degree of potential relationship of a social network using an astute function utilizing both weighted arithmetic and geometric means. Here two weights ...
Uploads
Papers by Devendra Tayal