Nilambar Sethi - Academia.edu (original) (raw)

Papers by Nilambar Sethi

Research paper thumbnail of Summarization of Legal Texts by Using Deep Learning Approaches

CRC Press eBooks, Jun 12, 2024

Research paper thumbnail of Inclusive Review on Extractive and Abstractive Text Summarization: Taxonomy, Datasets, Techniques and Challenges

Lecture notes in networks and systems, 2023

Research paper thumbnail of MANDS: Malicious Node Detection System for Sinkhole Attack in WSN Using DRI and Cross Check Method

Research paper thumbnail of Two Phase Ensemble Learning Based Extractive Summarization for Short Documents

Research paper thumbnail of NDTRA-MAT: A Novel Technique for Evaluating the Data Transfer Rate, Reducing the False Alarm Rate, and avoiding Packet Droppings Rate against Malicious Activity in Wireless Sensor Networks

International Journal of Computer Networks and Applications

Wireless Sensor Networks (WSN) are under attack from insider packet drops. Each node will employ ... more Wireless Sensor Networks (WSN) are under attack from insider packet drops. Each node will employ a trust mechanism to assess the trustworthiness of its neighbor nodes to send packets to only the trustworthy neighbors to distinguish packets dropped by inside intruders from network faults. The false alert arises when a normal node's trust value decreases and is removed from the routing paths using trust-aware routing algorithms. Optimizing the packet delivery ratio is a critical design consideration for WSNs. WSNs have long benefited from a secure zone-based routing mechanism already in place. A new routing criterion was developed for packet transfer in multi-hop communication. The routing metric was designed to protect against message manipulation, dropping, and flooding assaults. The method used an alternative way to route a packet while avoiding dangerous zones safely and efficiently in the routing process. Despite energy conservation and greater attack resilience, congestion in the WSN has increased, and the packet delivery ratio has been reduced. Each node has computing power that serves as a transceiver for the network. A packet-dropping node is hacked and forwards any or all the packets it receives. All or some boxes are packages modified by a hacked node that is intended to deliver them. In multi-hop sensor networks, packet dropping and alteration are two popular methods that an adversary can use to interrupt communication. The proposed model NDTRA-MAT is used to avoid packet loss with reduced false alarms. It is compared with the existing models, and the performance is calculated in terms of Malicious Node Detection Accuracy Levels, Packet Loss Rate, and Packet Data rate.

Research paper thumbnail of Fuzzy Bi-GRU Based Hybrid Extractive and Abstractive Text Summarization for Long Multi-documents

Lecture notes in networks and systems, 2023

Research paper thumbnail of Analytic for Cricket Match Winner Prediction Through Major Events Quantification

Lecture notes in networks and systems, 2022

Research paper thumbnail of Non-invasive Diagnosis of Diabetes Using Chaotic Features and Genetic Learning

Lecture notes in networks and systems, 2022

Research paper thumbnail of A Survey on Detection of Malicious Nodes in Wireless Sensor Networks

2022 6th International Conference on Trends in Electronics and Informatics (ICOEI)

Research paper thumbnail of Secure Data Transmission in Wireless Sensor Networks with Secure System for Identification of Trusted Route with Node Behavior Analysis

Revue d'Intelligence Artificielle

The Wireless Sensor Network (WSN) is a novel and demanding technology that requires little proces... more The Wireless Sensor Network (WSN) is a novel and demanding technology that requires little processing and computational capabilities. In the WSN, security is a serious issue. Because of its wireless nature, it is vulnerable to a wide range of assaults and data packet loss. Secure routing is critical to avoid problems like this. When it comes to data delivery to other nodes, routing is one of the most important WSN method to provide security to the network. Based on the expected trust value, the routing process's trust mechanism prevents/includes nodes in routing. This research examines security objectives for routing the sensor networks and presents an Extreme Trust Factor for Route Identification with Prime Node (ETFRI-PN). The Prime Node (PN) examines each node's behavior throughout the delivery process, as well as computers' ability to detect malicious assaults, and assigns a trust factor to each node involved in data transmission along with Alphanumeric Inimitable La...

Research paper thumbnail of Forecasting Diabetes Correlated Non-alcoholic Fatty Liver Disease by Exploiting Naïve Bayes Tree

ICST Transactions on Scalable Information Systems

INTRODUCTION: In recent years, non-alcoholic fatty liver disease (NAFLD) has been identified as t... more INTRODUCTION: In recent years, non-alcoholic fatty liver disease (NAFLD) has been identified as the most vulnerable chronic disease. Fat is accumulated in the liver cells of persons with NAFLD. Diabetes is the most common ailment among people of all ages, so it is critical to recognize and prevent its adverse effects. OBJECTIVES: A relevant dataset with appropriate features was selected. Ensemble algorithms were applied for the prediction task, and finally, the method with the best performance was extracted. METHODS: In addition to Ensemble approaches namely bagging, Random forest and Ada-boost, individual classifiers Naive Bayes (NB) and C4.5 Decision tree were considered. These ML techniques were compared with the proposed NB tree algorithm, a combination of C4.5 and Naive Bayes. RESULTS: The following evaluation parameters were computed for each analyzed algorithm: accuracy, detection rate, negative predictive value (NPV), false negative rate (FNR), and false positive rate (FPR). The algorithms are then compared based on these metrics to determine the best algorithm. The NB tree was obtained to be the best method with 97.55% accuracy, 0.4853 detection rate, 0.9615 NPV, 0.0388 FNR, and 0.0099 FPR. CONCLUSION: The NB tree outperformed individual Naive bayes and C4.5 classifiers, and the other techniques studied. The developed algorithm could be applied in NAFLD-related research.

Research paper thumbnail of Rigorous assessment of data mining algorithms in gestational diabetes mellitus prediction

International Journal of Knowledge-based and Intelligent Engineering Systems, 2022

Gestational diabetes mellitus (GDM) is the type of diabetes that affects pregnant women due to hi... more Gestational diabetes mellitus (GDM) is the type of diabetes that affects pregnant women due to high blood sugar levels. The women with gestational diabetes have a chance of miscarriage during pregnancy and having chance of developing type-2 diabetes in the future. It is a general practice to take proper diabetes test like OGTT to detect GDM. This test is to be done during 24 to 28 weeks of pregnancy. In addition, the use of machine learning could be exploited for predicting gestational diabetes. The main goal of this work is to propose optimal ML algorithms for effective prediction of gestational diabetes mellitus and there by avoid it’s side effects and future complications. In this work different machine algorithms are planned to be compared for their performance in predicting GDM. Before analysing the algorithms they are implemented using 10 fold cross validation technique to obtain better performance. The algorithms implemented are Linear Discriminant Analysis, Mixture Discrimin...

Research paper thumbnail of A Comparative Study on Serial and Parallel Web Content Mining

World Wide Web (WWW) is such a repository which serves every individuals need starting with the c... more World Wide Web (WWW) is such a repository which serves every individuals need starting with the context of education to entertainment etc. But from users point of view getting relevant information with respect to one particular context is time consuming and also not so easy. It is because of the volume of data which is unstructured, distributed and dynamic in nature. There can be automation to extract relevant information with respect to one particular context, which is named as Web Content Mining. The efficiency of automation depends on validity of expected outcome as well as amount of processing time. The acceptability of outcome depends on user or user's policy. But the amount of processing time depends on the methodology of Web Content Mining. In this work a study has been carried out between Serial Web Content Mining and Parallel Web Content Mining. This work also focuses on the frame work of implementation of parallelism in Web Content Mining.

Research paper thumbnail of Generic model for automated player selection for cricket teams using recurrent neural networks

Evolutionary Intelligence, 2020

In this paper, an optimized model has been proposed exclusively for the game of cricket whereby a... more In this paper, an optimized model has been proposed exclusively for the game of cricket whereby a team of fifteen members can be chosen in an unbiased strategy. The proposed method involves a hybrid technique that uses the concept of genetic algorithm (GA) and recurrent neural networks (RNN) for selecting efficient players. Suitable preprocessing is applied to the individual players historical statistics and an initial feature matrix is generated for a player. This feature matrix is fed to the proposed mathematical function used in GA. The GA utilizes a novel fitness function for the minimization of loss-factor. This results in a refined feature matrix. This refined feature matrix is further subjected to RNN to assess a final score for the individual player. Finally, the proposed model comes up with a concurrent rank table that can be referred by the team selectors for an easy and efficient player selection for the upcoming match. It may be essentially considered that the proposed model provides results for the upcoming match or tournament only. Three different authentic datasets have been referred for the purpose of experimental evaluation of the proposed model. The results are compared with the recent match performances of each players. Surprisingly, almost equivalent results are obtained which supports the robustness of the scheme. In cases, the proposed scheme outperforms the manual team selection in terms of performance, that indicates that a slight better team could have been created in certain cases. The overall rate of accuracy in terms of predicted list of players for each match vis-a-vis the manually selected players comes out to be satisfactorily 98.5%.

Research paper thumbnail of Inductive Learning of Complex Fuzzy Relation

International Journal of Computer Science, Engineering and Information Technology, 2011

The objective of this paper to investigate the notion of complex fuzzy set in general view. In co... more The objective of this paper to investigate the notion of complex fuzzy set in general view. In constraint to a traditional fuzzy set, the membership function of the complex fuzzy set, the range from [0.1] extended to a unit circle in the complex plane. In this article the comprehensive mathematical operations on the complex fuzzy set are presented. The basic operation of complex fuzzy set such as union, intersection, complement of complex fuzzy set and complex fuzzy relation are studied. Also vector aggregation and fuzzy relation over the complex fuzzy set are discussed. Two novel operations of complement and projection for complex fuzzy relation are introduced.

Research paper thumbnail of Web Information Retrieval: Applications of Soft Computing

Research paper thumbnail of Probabilistic Interpretation of Complex Fuzzy Set

International Journal of Computer Science, Engineering and Information Technology, 2012

Research paper thumbnail of Intelligent stuttering speech recognition: A succinct review

Multimedia Tools and Applications, 2022

Research paper thumbnail of A Review of Data Analytic Schemes for Prediction of Vivid Aspects in International Cricket Matches

2019 5th International Conference On Computing, Communication, Control And Automation (ICCUBEA), 2019

Cricket is among the most popular game of the planet. It has all the potential to grab the attent... more Cricket is among the most popular game of the planet. It has all the potential to grab the attention of sports-persons, spectators, financial institutions, and thus ultimately the researchers. Data mining approaches, being the backbone, several prediction schemes and analytics have been presented related to cricket. In this paper, we intend to present a vivid review of several important data mining schemes specifically meant for analytics related to cricket matches that are reported in the literature. The review is made in three distinct approaches based on the format of cricket matches played around the world. These are the one-day matches, T-20 matches, and test matches. Finally, comparative analysis have also been made and are presented separately for all the three formats among the available schemes. Suitable discussion is presented at the end of the paper that may be utilized in the direction of future works.

Research paper thumbnail of Finite State Machine as a Designing Tool for Web Based Transactional Systems

Web based systems are highly useful for extending business as well as information sharing. Many p... more Web based systems are highly useful for extending business as well as information sharing. Many platforms and technologies available for development of Web based systems. For a successful Web based system the design plays a vital role where the business logic is to be realised. Many traditional design approaches available, among which choosing the appropriate one is a challenge. Many Web based systems are developed in a hit and trail manner to meet the business objective. But having a proper design helps in future enhancement and systematic understanding of the system. In this paper Finite Automaton has been chosen as a design approach for Web based transactional systems which are functionally different than Web based informative systems. Finite automaton is an oldest and efficient mechanism for modelling any mathematical problem. Software development or Web based development can be visualized as s mathematical problem hence finite automaton can be used as a design approach for deve...

Research paper thumbnail of Summarization of Legal Texts by Using Deep Learning Approaches

CRC Press eBooks, Jun 12, 2024

Research paper thumbnail of Inclusive Review on Extractive and Abstractive Text Summarization: Taxonomy, Datasets, Techniques and Challenges

Lecture notes in networks and systems, 2023

Research paper thumbnail of MANDS: Malicious Node Detection System for Sinkhole Attack in WSN Using DRI and Cross Check Method

Research paper thumbnail of Two Phase Ensemble Learning Based Extractive Summarization for Short Documents

Research paper thumbnail of NDTRA-MAT: A Novel Technique for Evaluating the Data Transfer Rate, Reducing the False Alarm Rate, and avoiding Packet Droppings Rate against Malicious Activity in Wireless Sensor Networks

International Journal of Computer Networks and Applications

Wireless Sensor Networks (WSN) are under attack from insider packet drops. Each node will employ ... more Wireless Sensor Networks (WSN) are under attack from insider packet drops. Each node will employ a trust mechanism to assess the trustworthiness of its neighbor nodes to send packets to only the trustworthy neighbors to distinguish packets dropped by inside intruders from network faults. The false alert arises when a normal node's trust value decreases and is removed from the routing paths using trust-aware routing algorithms. Optimizing the packet delivery ratio is a critical design consideration for WSNs. WSNs have long benefited from a secure zone-based routing mechanism already in place. A new routing criterion was developed for packet transfer in multi-hop communication. The routing metric was designed to protect against message manipulation, dropping, and flooding assaults. The method used an alternative way to route a packet while avoiding dangerous zones safely and efficiently in the routing process. Despite energy conservation and greater attack resilience, congestion in the WSN has increased, and the packet delivery ratio has been reduced. Each node has computing power that serves as a transceiver for the network. A packet-dropping node is hacked and forwards any or all the packets it receives. All or some boxes are packages modified by a hacked node that is intended to deliver them. In multi-hop sensor networks, packet dropping and alteration are two popular methods that an adversary can use to interrupt communication. The proposed model NDTRA-MAT is used to avoid packet loss with reduced false alarms. It is compared with the existing models, and the performance is calculated in terms of Malicious Node Detection Accuracy Levels, Packet Loss Rate, and Packet Data rate.

Research paper thumbnail of Fuzzy Bi-GRU Based Hybrid Extractive and Abstractive Text Summarization for Long Multi-documents

Lecture notes in networks and systems, 2023

Research paper thumbnail of Analytic for Cricket Match Winner Prediction Through Major Events Quantification

Lecture notes in networks and systems, 2022

Research paper thumbnail of Non-invasive Diagnosis of Diabetes Using Chaotic Features and Genetic Learning

Lecture notes in networks and systems, 2022

Research paper thumbnail of A Survey on Detection of Malicious Nodes in Wireless Sensor Networks

2022 6th International Conference on Trends in Electronics and Informatics (ICOEI)

Research paper thumbnail of Secure Data Transmission in Wireless Sensor Networks with Secure System for Identification of Trusted Route with Node Behavior Analysis

Revue d'Intelligence Artificielle

The Wireless Sensor Network (WSN) is a novel and demanding technology that requires little proces... more The Wireless Sensor Network (WSN) is a novel and demanding technology that requires little processing and computational capabilities. In the WSN, security is a serious issue. Because of its wireless nature, it is vulnerable to a wide range of assaults and data packet loss. Secure routing is critical to avoid problems like this. When it comes to data delivery to other nodes, routing is one of the most important WSN method to provide security to the network. Based on the expected trust value, the routing process's trust mechanism prevents/includes nodes in routing. This research examines security objectives for routing the sensor networks and presents an Extreme Trust Factor for Route Identification with Prime Node (ETFRI-PN). The Prime Node (PN) examines each node's behavior throughout the delivery process, as well as computers' ability to detect malicious assaults, and assigns a trust factor to each node involved in data transmission along with Alphanumeric Inimitable La...

Research paper thumbnail of Forecasting Diabetes Correlated Non-alcoholic Fatty Liver Disease by Exploiting Naïve Bayes Tree

ICST Transactions on Scalable Information Systems

INTRODUCTION: In recent years, non-alcoholic fatty liver disease (NAFLD) has been identified as t... more INTRODUCTION: In recent years, non-alcoholic fatty liver disease (NAFLD) has been identified as the most vulnerable chronic disease. Fat is accumulated in the liver cells of persons with NAFLD. Diabetes is the most common ailment among people of all ages, so it is critical to recognize and prevent its adverse effects. OBJECTIVES: A relevant dataset with appropriate features was selected. Ensemble algorithms were applied for the prediction task, and finally, the method with the best performance was extracted. METHODS: In addition to Ensemble approaches namely bagging, Random forest and Ada-boost, individual classifiers Naive Bayes (NB) and C4.5 Decision tree were considered. These ML techniques were compared with the proposed NB tree algorithm, a combination of C4.5 and Naive Bayes. RESULTS: The following evaluation parameters were computed for each analyzed algorithm: accuracy, detection rate, negative predictive value (NPV), false negative rate (FNR), and false positive rate (FPR). The algorithms are then compared based on these metrics to determine the best algorithm. The NB tree was obtained to be the best method with 97.55% accuracy, 0.4853 detection rate, 0.9615 NPV, 0.0388 FNR, and 0.0099 FPR. CONCLUSION: The NB tree outperformed individual Naive bayes and C4.5 classifiers, and the other techniques studied. The developed algorithm could be applied in NAFLD-related research.

Research paper thumbnail of Rigorous assessment of data mining algorithms in gestational diabetes mellitus prediction

International Journal of Knowledge-based and Intelligent Engineering Systems, 2022

Gestational diabetes mellitus (GDM) is the type of diabetes that affects pregnant women due to hi... more Gestational diabetes mellitus (GDM) is the type of diabetes that affects pregnant women due to high blood sugar levels. The women with gestational diabetes have a chance of miscarriage during pregnancy and having chance of developing type-2 diabetes in the future. It is a general practice to take proper diabetes test like OGTT to detect GDM. This test is to be done during 24 to 28 weeks of pregnancy. In addition, the use of machine learning could be exploited for predicting gestational diabetes. The main goal of this work is to propose optimal ML algorithms for effective prediction of gestational diabetes mellitus and there by avoid it’s side effects and future complications. In this work different machine algorithms are planned to be compared for their performance in predicting GDM. Before analysing the algorithms they are implemented using 10 fold cross validation technique to obtain better performance. The algorithms implemented are Linear Discriminant Analysis, Mixture Discrimin...

Research paper thumbnail of A Comparative Study on Serial and Parallel Web Content Mining

World Wide Web (WWW) is such a repository which serves every individuals need starting with the c... more World Wide Web (WWW) is such a repository which serves every individuals need starting with the context of education to entertainment etc. But from users point of view getting relevant information with respect to one particular context is time consuming and also not so easy. It is because of the volume of data which is unstructured, distributed and dynamic in nature. There can be automation to extract relevant information with respect to one particular context, which is named as Web Content Mining. The efficiency of automation depends on validity of expected outcome as well as amount of processing time. The acceptability of outcome depends on user or user's policy. But the amount of processing time depends on the methodology of Web Content Mining. In this work a study has been carried out between Serial Web Content Mining and Parallel Web Content Mining. This work also focuses on the frame work of implementation of parallelism in Web Content Mining.

Research paper thumbnail of Generic model for automated player selection for cricket teams using recurrent neural networks

Evolutionary Intelligence, 2020

In this paper, an optimized model has been proposed exclusively for the game of cricket whereby a... more In this paper, an optimized model has been proposed exclusively for the game of cricket whereby a team of fifteen members can be chosen in an unbiased strategy. The proposed method involves a hybrid technique that uses the concept of genetic algorithm (GA) and recurrent neural networks (RNN) for selecting efficient players. Suitable preprocessing is applied to the individual players historical statistics and an initial feature matrix is generated for a player. This feature matrix is fed to the proposed mathematical function used in GA. The GA utilizes a novel fitness function for the minimization of loss-factor. This results in a refined feature matrix. This refined feature matrix is further subjected to RNN to assess a final score for the individual player. Finally, the proposed model comes up with a concurrent rank table that can be referred by the team selectors for an easy and efficient player selection for the upcoming match. It may be essentially considered that the proposed model provides results for the upcoming match or tournament only. Three different authentic datasets have been referred for the purpose of experimental evaluation of the proposed model. The results are compared with the recent match performances of each players. Surprisingly, almost equivalent results are obtained which supports the robustness of the scheme. In cases, the proposed scheme outperforms the manual team selection in terms of performance, that indicates that a slight better team could have been created in certain cases. The overall rate of accuracy in terms of predicted list of players for each match vis-a-vis the manually selected players comes out to be satisfactorily 98.5%.

Research paper thumbnail of Inductive Learning of Complex Fuzzy Relation

International Journal of Computer Science, Engineering and Information Technology, 2011

The objective of this paper to investigate the notion of complex fuzzy set in general view. In co... more The objective of this paper to investigate the notion of complex fuzzy set in general view. In constraint to a traditional fuzzy set, the membership function of the complex fuzzy set, the range from [0.1] extended to a unit circle in the complex plane. In this article the comprehensive mathematical operations on the complex fuzzy set are presented. The basic operation of complex fuzzy set such as union, intersection, complement of complex fuzzy set and complex fuzzy relation are studied. Also vector aggregation and fuzzy relation over the complex fuzzy set are discussed. Two novel operations of complement and projection for complex fuzzy relation are introduced.

Research paper thumbnail of Web Information Retrieval: Applications of Soft Computing

Research paper thumbnail of Probabilistic Interpretation of Complex Fuzzy Set

International Journal of Computer Science, Engineering and Information Technology, 2012

Research paper thumbnail of Intelligent stuttering speech recognition: A succinct review

Multimedia Tools and Applications, 2022

Research paper thumbnail of A Review of Data Analytic Schemes for Prediction of Vivid Aspects in International Cricket Matches

2019 5th International Conference On Computing, Communication, Control And Automation (ICCUBEA), 2019

Cricket is among the most popular game of the planet. It has all the potential to grab the attent... more Cricket is among the most popular game of the planet. It has all the potential to grab the attention of sports-persons, spectators, financial institutions, and thus ultimately the researchers. Data mining approaches, being the backbone, several prediction schemes and analytics have been presented related to cricket. In this paper, we intend to present a vivid review of several important data mining schemes specifically meant for analytics related to cricket matches that are reported in the literature. The review is made in three distinct approaches based on the format of cricket matches played around the world. These are the one-day matches, T-20 matches, and test matches. Finally, comparative analysis have also been made and are presented separately for all the three formats among the available schemes. Suitable discussion is presented at the end of the paper that may be utilized in the direction of future works.

Research paper thumbnail of Finite State Machine as a Designing Tool for Web Based Transactional Systems

Web based systems are highly useful for extending business as well as information sharing. Many p... more Web based systems are highly useful for extending business as well as information sharing. Many platforms and technologies available for development of Web based systems. For a successful Web based system the design plays a vital role where the business logic is to be realised. Many traditional design approaches available, among which choosing the appropriate one is a challenge. Many Web based systems are developed in a hit and trail manner to meet the business objective. But having a proper design helps in future enhancement and systematic understanding of the system. In this paper Finite Automaton has been chosen as a design approach for Web based transactional systems which are functionally different than Web based informative systems. Finite automaton is an oldest and efficient mechanism for modelling any mathematical problem. Software development or Web based development can be visualized as s mathematical problem hence finite automaton can be used as a design approach for deve...