ASHA MISHRA - Academia.edu (original) (raw)

Papers by ASHA MISHRA

Research paper thumbnail of Optimizing BackPropagation using PSO _ Hill and PSO _ A *

Back propagation algorithm (BPA) have the complexity, local minima problem so we are using Partic... more Back propagation algorithm (BPA) have the complexity, local minima problem so we are using Particle Swarm optimization (PSO) algorithms to reduce and optimize BPA. In this paper, two variants of Particle Swarm Optimization (PSO) PSO_Hill and PSO_A* is used as optimization algorithm. PSO_Hill and PSO_A* algorithms are analyzed and evaluated on the basis of their advantages, applied to feed forward neural network(FNN) for back propagation algorithm(BPA) which is a gredient desent technique. where BPA is used for non_linear problems. These non_linear problems are improved by a PSO_Hill and PSO_A* algorithms.

Research paper thumbnail of Hybrid Smart Home System Automation of electrical appliances via sms and gprs on Android Platform

Technology is being on progress since the evolution and currently the main area of research is au... more Technology is being on progress since the evolution and currently the main area of research is automation technology. SMS Based Home Automation System is the earlier technology that came in existence. Each technology has several limitations. This paper emphasizes on the limitations of this technology and some advancement in automation technology to overcome those limitations. This design is presented to overcome the user non-friendly behavior limitation of SMS based automation devices and mobility of internet/gprs and embedding the two technologies. This also focuses on comparison with existing technology. The main idea of paper is to provide user friendly interface.

Research paper thumbnail of Secure key Predistribution and Mutual Node Authentication Protocol in WSN using ECC

International Journal of Computer Applications, 2014

Wireless Sensor Networks (WSNs) has foreseen big changes in data gathering, processing and dissem... more Wireless Sensor Networks (WSNs) has foreseen big changes in data gathering, processing and disseminating for monitoring specific applications such as emergency services, disaster management, and military applications etc. Since large number sensor nodes are deployed to monitor a vast field, where the operational conditions are most often harsh or even hostile so security mechanism in WSN is a greater challenge in WSN. Sensor networks pose unique challenges because of their inherent limitations in communication and computing. Sensor networks are vulnerable to security attacks due to the broadcast nature of transmission. The threats against WSN can be reduced by proper security measures. One of the commonly used methods is the use of cryptographic algorithm. This paper proposes mechanisms for Key Predistribution and mutual Authentication protocol in sensor networks using ECC with respect to constraints of WSN.

Research paper thumbnail of A Hybrid Approach for Intrusion Detection Based on Pattern Matching and Clustering using Neural Network

Network security is becoming an important issue. Due to increase in the knowledge of intruders an... more Network security is becoming an important issue. Due to increase in the knowledge of intruders and attackers different security tools fails. With the advance of technology new tools are developed and new approaches are embedded in previously developed approaches. So, Intrusion Detection System (IDS) comes into role.IDS provide second line of defense which is not in the limit of firewall and others.. In this thesis a Hybrid intrusion detection method is proposed that is based on Misuse Detection Approach and Anomaly Detection. For Misuse Detection Pattern Matching algorithm is used. Attack pattern are matched with already stored pattern. In second phase for anomaly detection approach clustering is used. But the clustering is based on Neural Network. Through the Neural Network the IDS become self-adapting in nature.

Research paper thumbnail of Introduction To Intrusion Detection System: Review

Security of a network is always an important issue. With the continuously growing network, the ba... more Security of a network is always an important issue. With the continuously growing network, the basic security such as firewall, virus scanner is easily deceived by modern attackers who are experts in using software vulnerabilities to achieve their goals. For preventing such attacks, we need even smarter security mechanism which act proactively and intelligently. Intrusion Detection System is the solution of such requirement. Many techniques have been used to implement IDS. These technique basically used in the detector part of IDS such as Neural Network, Clustering, Pattern Matching, Rule Based, Fuzzy Logic, Genetic Algorithms and many more. To improve the performance of an IDS these approaches may be used in combination to build a hybrid IDS so that benefits of two o more approaches may be combined.

Research paper thumbnail of A novel approach to capture the similarity in summarized text using embedded model

International Journal on Smart Sensing and Intelligent Systems

The presence of near duplicate textual content imposes great challenges while extracting informat... more The presence of near duplicate textual content imposes great challenges while extracting information from it. To handle these challenges, detection of near duplicates is a prime research concern. Existing research mostly uses text clustering, classification and retrieval algorithms for detection of near duplicates. Text summarization, an important tool of text mining, is not explored yet for the detection of near duplicates. Instead of using the whole document, the proposed method uses its summary as it saves both time and storage. Experimental results show that traditional similarity algorithms were able to capture similarity relatedness to a great extent even on the summarized text with a similarity score of 44.685%. Moreover, degree of similarity capture was greater (0.52%) in case of use of embedding models with better text representation as compared to traditional methods. Also, this paper highlights the research status of various similarity measures in terms of concept involve...

Research paper thumbnail of Extractive Text Summarization - An effective approach to extract information from Text

2019 International Conference on contemporary Computing and Informatics (IC3I)

Research paper thumbnail of Impact of feature representation on supervised classifiers — A comparative analysis

Research paper thumbnail of Elliptic Curve Cryptography (ECC) for Security in wireless Sensor Network

This paper discusses different issues of Wireless S ensor Network (WS N) and the relevance of the... more This paper discusses different issues of Wireless S ensor Network (WS N) and the relevance of the Elliptic curve y cryptography. S ecurity in WS N is a greater challenge in WS N due to the processing limitations of sensor nodes and nature of wireless links. Extensive use of WS Ns is giving rise to different types of threats. To defend against the threats proper security schemes are required. Traditionally security is implemented through hardware or software and is generally achieved through cryptographic methods. Limited area, nature of links, limited processing, power and memory of WS Ns leads to strict constraints on the selection of cryptographic techniques. Elliptic Curve Cryptography (ECC) is the best candidate due to its smaller key size. High security despite of smaller key size results in area and power efficient crypto systems.

Research paper thumbnail of Optimizing Back-Propagation using PSO_Hill_A* and Genetic Algorithm

International Journal of Computer Applications, 2013

Back propagation(BP) is used to solve real world problems which use the concept of multilayer per... more Back propagation(BP) is used to solve real world problems which use the concept of multilayer perceptron(MLP). BP have the disadvantage of trapped in local minima, slow convergence rate and more error prone. To optimize BP Algorithm, Particle swarm optimization(PSO) and Genetic algorithm(GA) is used. Limitation of PSO_Hill and PSO_A* is overcomes when these algorithms are combined and on the basis of strength of these two algorithm we proposed a new PSO_Hill_A* algorithm which is used to optimize and enhance learning process in terms of convergence rate and accuracy. GA is a kind of method to simulate and to search the optimal solution, GA can have four operations including Encoding, selecting, crossover and Mutation. To optimize and improve BP, we proposed two architecture: 1) Use of PSO_Hill_A* before and after hidden layer. 2) Use of GA before and after hidden layer.

Research paper thumbnail of Optimizing BackPropagation using PSO _ Hill and PSO _ A *

Back propagation algorithm (BPA) have the complexity, local minima problem so we are using Partic... more Back propagation algorithm (BPA) have the complexity, local minima problem so we are using Particle Swarm optimization (PSO) algorithms to reduce and optimize BPA. In this paper, two variants of Particle Swarm Optimization (PSO) PSO_Hill and PSO_A* is used as optimization algorithm. PSO_Hill and PSO_A* algorithms are analyzed and evaluated on the basis of their advantages, applied to feed forward neural network(FNN) for back propagation algorithm(BPA) which is a gredient desent technique. where BPA is used for non_linear problems. These non_linear problems are improved by a PSO_Hill and PSO_A* algorithms.

Research paper thumbnail of Hybrid Smart Home System Automation of electrical appliances via sms and gprs on Android Platform

Technology is being on progress since the evolution and currently the main area of research is au... more Technology is being on progress since the evolution and currently the main area of research is automation technology. SMS Based Home Automation System is the earlier technology that came in existence. Each technology has several limitations. This paper emphasizes on the limitations of this technology and some advancement in automation technology to overcome those limitations. This design is presented to overcome the user non-friendly behavior limitation of SMS based automation devices and mobility of internet/gprs and embedding the two technologies. This also focuses on comparison with existing technology. The main idea of paper is to provide user friendly interface.

Research paper thumbnail of Secure key Predistribution and Mutual Node Authentication Protocol in WSN using ECC

International Journal of Computer Applications, 2014

Wireless Sensor Networks (WSNs) has foreseen big changes in data gathering, processing and dissem... more Wireless Sensor Networks (WSNs) has foreseen big changes in data gathering, processing and disseminating for monitoring specific applications such as emergency services, disaster management, and military applications etc. Since large number sensor nodes are deployed to monitor a vast field, where the operational conditions are most often harsh or even hostile so security mechanism in WSN is a greater challenge in WSN. Sensor networks pose unique challenges because of their inherent limitations in communication and computing. Sensor networks are vulnerable to security attacks due to the broadcast nature of transmission. The threats against WSN can be reduced by proper security measures. One of the commonly used methods is the use of cryptographic algorithm. This paper proposes mechanisms for Key Predistribution and mutual Authentication protocol in sensor networks using ECC with respect to constraints of WSN.

Research paper thumbnail of A Hybrid Approach for Intrusion Detection Based on Pattern Matching and Clustering using Neural Network

Network security is becoming an important issue. Due to increase in the knowledge of intruders an... more Network security is becoming an important issue. Due to increase in the knowledge of intruders and attackers different security tools fails. With the advance of technology new tools are developed and new approaches are embedded in previously developed approaches. So, Intrusion Detection System (IDS) comes into role.IDS provide second line of defense which is not in the limit of firewall and others.. In this thesis a Hybrid intrusion detection method is proposed that is based on Misuse Detection Approach and Anomaly Detection. For Misuse Detection Pattern Matching algorithm is used. Attack pattern are matched with already stored pattern. In second phase for anomaly detection approach clustering is used. But the clustering is based on Neural Network. Through the Neural Network the IDS become self-adapting in nature.

Research paper thumbnail of Introduction To Intrusion Detection System: Review

Security of a network is always an important issue. With the continuously growing network, the ba... more Security of a network is always an important issue. With the continuously growing network, the basic security such as firewall, virus scanner is easily deceived by modern attackers who are experts in using software vulnerabilities to achieve their goals. For preventing such attacks, we need even smarter security mechanism which act proactively and intelligently. Intrusion Detection System is the solution of such requirement. Many techniques have been used to implement IDS. These technique basically used in the detector part of IDS such as Neural Network, Clustering, Pattern Matching, Rule Based, Fuzzy Logic, Genetic Algorithms and many more. To improve the performance of an IDS these approaches may be used in combination to build a hybrid IDS so that benefits of two o more approaches may be combined.

Research paper thumbnail of A novel approach to capture the similarity in summarized text using embedded model

International Journal on Smart Sensing and Intelligent Systems

The presence of near duplicate textual content imposes great challenges while extracting informat... more The presence of near duplicate textual content imposes great challenges while extracting information from it. To handle these challenges, detection of near duplicates is a prime research concern. Existing research mostly uses text clustering, classification and retrieval algorithms for detection of near duplicates. Text summarization, an important tool of text mining, is not explored yet for the detection of near duplicates. Instead of using the whole document, the proposed method uses its summary as it saves both time and storage. Experimental results show that traditional similarity algorithms were able to capture similarity relatedness to a great extent even on the summarized text with a similarity score of 44.685%. Moreover, degree of similarity capture was greater (0.52%) in case of use of embedding models with better text representation as compared to traditional methods. Also, this paper highlights the research status of various similarity measures in terms of concept involve...

Research paper thumbnail of Extractive Text Summarization - An effective approach to extract information from Text

2019 International Conference on contemporary Computing and Informatics (IC3I)

Research paper thumbnail of Impact of feature representation on supervised classifiers — A comparative analysis

Research paper thumbnail of Elliptic Curve Cryptography (ECC) for Security in wireless Sensor Network

This paper discusses different issues of Wireless S ensor Network (WS N) and the relevance of the... more This paper discusses different issues of Wireless S ensor Network (WS N) and the relevance of the Elliptic curve y cryptography. S ecurity in WS N is a greater challenge in WS N due to the processing limitations of sensor nodes and nature of wireless links. Extensive use of WS Ns is giving rise to different types of threats. To defend against the threats proper security schemes are required. Traditionally security is implemented through hardware or software and is generally achieved through cryptographic methods. Limited area, nature of links, limited processing, power and memory of WS Ns leads to strict constraints on the selection of cryptographic techniques. Elliptic Curve Cryptography (ECC) is the best candidate due to its smaller key size. High security despite of smaller key size results in area and power efficient crypto systems.

Research paper thumbnail of Optimizing Back-Propagation using PSO_Hill_A* and Genetic Algorithm

International Journal of Computer Applications, 2013

Back propagation(BP) is used to solve real world problems which use the concept of multilayer per... more Back propagation(BP) is used to solve real world problems which use the concept of multilayer perceptron(MLP). BP have the disadvantage of trapped in local minima, slow convergence rate and more error prone. To optimize BP Algorithm, Particle swarm optimization(PSO) and Genetic algorithm(GA) is used. Limitation of PSO_Hill and PSO_A* is overcomes when these algorithms are combined and on the basis of strength of these two algorithm we proposed a new PSO_Hill_A* algorithm which is used to optimize and enhance learning process in terms of convergence rate and accuracy. GA is a kind of method to simulate and to search the optimal solution, GA can have four operations including Encoding, selecting, crossover and Mutation. To optimize and improve BP, we proposed two architecture: 1) Use of PSO_Hill_A* before and after hidden layer. 2) Use of GA before and after hidden layer.