Sheba Malarchelvi - Academia.edu (original) (raw)

Papers by Sheba Malarchelvi

Journal of critical reviews, 2020

Data mining and knowledge engineering, 2012

Data mining involves the use of sophisticated data analysis tools which discovers previously unkn... more Data mining involves the use of sophisticated data analysis tools which discovers previously unknown, valid patterns and relationships in large data sets. Educational Data Mining is concerned with developing methods for exploring the unique types of data that comes from educational scenario and using those methods to better understand students and the settings in which they learn. These days stress and depression are found to be common among students. Programming is considered to be the most essential skill for IT students in order to flourish in life. The objective of this paper is to find out the way in which stress and depression experienced by the students have impact on their programming performance. The level of stress and depression are measured by the use of questionnaires. The mark obtained by the students in the programming language is considered as a measure of programming performance. Frequent –pattern growth algorithm has been used to discover the various patterns available. Association Rule Mining has then been applied to find out the association.

Multimedia Tools and Applications, Feb 26, 2018

Long term research activities focus on the provision of fundamental understanding and easy deploy... more Long term research activities focus on the provision of fundamental understanding and easy deployment of multimedia services on the multimedia communication. The rapid growth of digital communication and electronic data exchange provides the intensive data transfer without concentrating on the security issues. Secure communication with the minimal computational and storage overhead is the challenging task with the large size members nowadays. The Group Key Management (GKM) protocols offer numerous solutions to the security issues with an efficient interaction of group members controlling them. The groups participated in secure communication belongs to open or close scenario. The participation of registered members in close group is beneficial than the open group. With the increase in number of participants, the key size and the number of key generations will increase the computational overhead. To alleviate these issues, this paper proposes the novel self-similar key generation and distribution scheme on the basis of the Elliptic Curve Diffie Hellman (ECDH) and Chinese Reminder Theorem (CRT). The assigning permission to each node to generate their own key at the specified time by the ECDH prevents the unnecessary distribution of keys that reduces the communication overhead. Then, the application of CRT theorem reduces the mathematical burden of key generation. Finally, the integration of the Elliptic Curve Cryptography (ECC) with the above mechanisms validates the number of messages transferred among the participants in both sender and receiver side. The prior key generation using ECDH and the CRT-based self-similar key generation reduces the computational and communication overhead effectively. The comparative analysis between the proposed SSKG with the existing schemes in terms of overhead, complexity assures the effectiveness of proposed schemes in secure multicast communication.

Concurrency and Computation: Practice and Experience, Oct 15, 2018

High usage levels of networking technologies has resulted in large amounts of data being generate... more High usage levels of networking technologies has resulted in large amounts of data being generated. This in-turn has lured several fraudsters, whose anomalous behaviors create undesired consequences to legitimate users. This paper proposes an Adaptive Parallelized Intrusion Detection (APID) architecture to handle the hugeness and data imbalance associated with streaming data. The architecture is composed of a feature selection strategy to reduce data size, an effective data segregation mechanism to handle data imbalance and a heterogeneous ensemble and a heuristic combiner mechanism to provide effective predictions. Adaptivity is incorporated by the reinforcement mechanism that retrains the model based on false predictions given by the model. The proposed APID architecture is generic; hence, it supports heterogeneous models and can also incorporate any number of machine learning models. Hence, it becomes flexible to adapt the model to data pertaining to any domain. Experiments were performed with KDD CUP 99, NSL-KDD, and Koyoto 2006 datasets. Comparisons performed with recent works in literature indicates anomaly detection rates between 98% to 99% exhibiting the effectiveness of the proposed model.

Network security consists of provisions and policies adopted by network administrator to prevent ... more Network security consists of provisions and policies adopted by network administrator to prevent unauthorized access of network accessible resources. Jamming can be viewed as a form of Denial-of-Service attack, whose goal is to prevent users from receiving timely and adequate information. In these attacks, the adversary is active only for a short period of time, selectively targeting messages of high importance. This paper presents a survey of the existing jamming attack prevention techniques. Selective jamming attacks can be launched by performing real-time packet classification at the physical layer. To mitigate these attacks, three schemes that prevent real-time packet classification by combining cryptographic primitives with physical-layer attributes are also presented in this paper.

International Conference on Information and Communication Technologies, Aug 10, 2014

Security is a serious problem in software development which when not taken into consideration, ex... more Security is a serious problem in software development which when not taken into consideration, exploits vulnerabilities in software. Such security related problems need to be addressed as early as possible while building software. Security problems exist for many reasons. A major thing is that, software cannot resist security attacks. Software security vulnerabilities are often caused due to the flaws that might be in specification, design, implementation or testing. These flaws are unknowingly injected by the software developers during development or left unnoticed by the software testers while testing for defects in software. This requires that developers and testers use methods that consistently produce secure software, which results in a defect less product. Security must be integrated into the software development life cycle from the beginning and must persist until the product is in use. This paper brings out the security deliberation that have to be paid due attention in the various phases of software development life cycle while developing a software.

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, Nov 22, 2009

In this paper, an image adaptive, invisible digital watermarking algorithm with Orthogonal Polyno... more In this paper, an image adaptive, invisible digital watermarking algorithm with Orthogonal Polynomials based Transformation (OPT) is proposed, for copyright protection of digital images. The proposed algorithm utilizes a visual model to determine the watermarking strength necessary to invisibly embed the watermark in the mid frequency AC coefficients of the cover image, chosen with a secret key. The visual model is designed to generate a Just Noticeable Distortion mask (JND) by analyzing the low level image characteristics such as textures, edges and luminance of the cover image in the orthogonal polynomials based transformation domain. Since the secret key is required for both embedding and extraction of watermark, it is not possible for an unauthorized user to extract the embedded watermark. The proposed scheme is robust to common image processing distortions like filtering, JPEG compression and additive noise. Experimental results show that the quality of OPT domain watermarked images is better than its DCT counterpart.

Journal of Computational and Theoretical Nanoscience, Jun 1, 2017

International Journal of Web Services Research, Nov 4, 2022

The process of intrusion detection usually involves identifying complex intrusion signatures from... more The process of intrusion detection usually involves identifying complex intrusion signatures from a huge repository. This requires a complex model that can identify these signatures. This work presents a deep learning based neural network model that can perform effective intrusion detection on network transmission data. The proposed multi-layered deep learning network is composed of multiple hidden processing layers in the network that makes it a deep learning network. Detection using the deep network was observed to exhibit effective performances in detecting the intrusion signatures. Experiments were performed on standard benchmark datasets like KDD CUP 99, NSL-KDD, and Koyoto 2006+ datasets. Comparisons were performed with state-of-the-art models in literature, and the results and comparisons indicate high performances by the proposed algorithm.

Software testing, an important phase in Software Development Life Cycle (SDLC) is a time consumin... more Software testing, an important phase in Software Development Life Cycle (SDLC) is a time consuming process. Information shows that nearly 40 to 50% of software development time is spent in testing. Manual testing is labour-intensive and error-prone so there is a need for automatic testing technique. Automation brings down the time and cost involved in testing. When testing software, there are often a massive amount of possible testcases even for quite simple systems. Running each and every feasible test-case is certainly not a choice, so designing test-cases becomes a significant part of the testing process. NASA proposed Modified Condition/Decision Coverage (MC/DC) testing criterion in 1994, which is a white box testing criterion. The objective of this paper is to automate the generation of minimum number of test cases required to test a system with maximum coverage by removing the redundant test cases using MC/DC criterion. The work also gives a tool Smart Test Case Generator Tool (STCGT) that automates the minimum number of test cases required to test the source code. This will give an idea about the test cases execution for the beginners of the testing team, thereby, aids in a quality on-time product.

Image Processing and Communications, 2009

Advances in intelligent systems and computing, 2017

Internet of Things (IoT) is a backboneless network. Because of the uni-directional link and mobil... more Internet of Things (IoT) is a backboneless network. Because of the uni-directional link and mobility nature of the nodes, the network is dynamic. The nodes are self-organized and two nodes can transfer data directly when they are within the transmission range. The nodes in IoT are self-organized and dynamic so MANET routing plays a vital role. The Light weight Ad hoc On-demand Distance Vector (LOAD) is a reactive routing protocol. In LOAD, the routing involves three major processes namely route discovery, path establishment, and route maintenance. The route discovery is carried out by Route REQuest (RREQ), Route REPly (RREP), and Route ERRor (RERR) control packets. The cost of the route discovery is estimated by control packets propagation. The proposed technique Cost And Load overhead reDUction for routE discovery in LOAD ProtocoL (CALDUEL) is proposed to reduce the load overhead, by reducing the cost of route discovery.

INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT

Social interaction, conduct, and cognitive ability are all impacted by the neuro developmental il... more Social interaction, conduct, and cognitive ability are all impacted by the neuro developmental illness known as autism spectrum disorder (ASD). Even though ASD diagnosis can be difficult and time-consuming, early detection and intervention can improve long-term results. Early childhood is when autism spectrum disorder first manifests, and it eventually leads to issues with social, academic, and occupational functioning in society. Within the first year, autism signs are frequently visible in children. Some infants display autistic spectrum disorder symptoms as early as infancy, including decreased eye contact, a lack of responsiveness to their name, or a lack of interest in carers. To identify the presence of disorder at an early stage, use a deep learning system like LSTM. Self-Stimulatory Behaviours Dataset (SSBD) was used to collect the datasets, and video dataset was used to construct the system. The feature extraction algorithm is the Blaze Pose algorithm. The model file has be...

International journal of engineering research and technology, 2018

The Internet of Things (IoT), connecting a large number of communication and information devices,... more The Internet of Things (IoT), connecting a large number of communication and information devices, is the future of the scientific world. The amount of devices with Wi-Fi capabilities and built-in sensors keeps on increasing. Smart phone is at every hand and its usage is sky-rocketing. This gives way to connect anything and anybody with the internet which in turn makes secure communication and secure sharing of information critical. In this paper, the existing works are analyzed and an IoT enabled healthcare system architecture is proposed. A novel authentication scheme that supplements the security of the proposed healthcare system is also proposed. Keywords— IoT, Architecture, Enhancing Authentication, Smart Healthcare System, Security, IoT devices.

International Journal of Web Services Research

The process of intrusion detection usually involves identifying complex intrusion signatures from... more The process of intrusion detection usually involves identifying complex intrusion signatures from a huge repository. This requires a complex model that can identify these signatures. This work presents a deep learning based neural network model that can perform effective intrusion detection on network transmission data. The proposed multi-layered deep learning network is composed of multiple hidden processing layers in the network that makes it a deep learning network. Detection using the deep network was observed to exhibit effective performances in detecting the intrusion signatures. Experiments were performed on standard benchmark datasets like KDD CUP 99, NSL-KDD, and Koyoto 2006+ datasets. Comparisons were performed with state-of-the-art models in literature, and the results and comparisons indicate high performances by the proposed algorithm.

International journal of engineering research and technology, 2018

The Internet of Things (IoT), connecting a large number of communication and information devices,... more The Internet of Things (IoT), connecting a large number of communication and information devices, is the future of the scientific world. The amount of devices with Wi-Fi capabilities and built-in sensors keeps on increasing. Smart phone is at every hand and its usage is sky-rocketing. This gives way to connect anything and anybody with the internet which in turn makes secure communication and secure sharing of information critical. In this paper, the existing works are analyzed and an IoT enabled healthcare system architecture is proposed. A novel authentication scheme that supplements the security of the proposed healthcare system is also proposed. Keywords— IoT, Architecture, Enhancing Authentication, Smart Healthcare System, Security, IoT devices.

Data mining and knowledge engineering, 2012

Data mining involves the use of sophisticated data analysis tools which discovers previously unkn... more Data mining involves the use of sophisticated data analysis tools which discovers previously unknown, valid patterns and relationships in large data sets. Educational Data Mining is concerned with developing methods for exploring the unique types of data that comes from educational scenario and using those methods to better understand students and the settings in which they learn. These days stress and depression are found to be common among students. Programming is considered to be the most essential skill for IT students in order to flourish in life. The objective of this paper is to find out the way in which stress and depression experienced by the students have impact on their programming performance. The level of stress and depression are measured by the use of questionnaires. The mark obtained by the students in the programming language is considered as a measure of programming performance. Frequent –pattern growth algorithm has been used to discover the various patterns avail...

Journal of critical reviews, 2020

Data mining and knowledge engineering, 2012

Data mining involves the use of sophisticated data analysis tools which discovers previously unkn... more Data mining involves the use of sophisticated data analysis tools which discovers previously unknown, valid patterns and relationships in large data sets. Educational Data Mining is concerned with developing methods for exploring the unique types of data that comes from educational scenario and using those methods to better understand students and the settings in which they learn. These days stress and depression are found to be common among students. Programming is considered to be the most essential skill for IT students in order to flourish in life. The objective of this paper is to find out the way in which stress and depression experienced by the students have impact on their programming performance. The level of stress and depression are measured by the use of questionnaires. The mark obtained by the students in the programming language is considered as a measure of programming performance. Frequent –pattern growth algorithm has been used to discover the various patterns available. Association Rule Mining has then been applied to find out the association.

Multimedia Tools and Applications, Feb 26, 2018

Long term research activities focus on the provision of fundamental understanding and easy deploy... more Long term research activities focus on the provision of fundamental understanding and easy deployment of multimedia services on the multimedia communication. The rapid growth of digital communication and electronic data exchange provides the intensive data transfer without concentrating on the security issues. Secure communication with the minimal computational and storage overhead is the challenging task with the large size members nowadays. The Group Key Management (GKM) protocols offer numerous solutions to the security issues with an efficient interaction of group members controlling them. The groups participated in secure communication belongs to open or close scenario. The participation of registered members in close group is beneficial than the open group. With the increase in number of participants, the key size and the number of key generations will increase the computational overhead. To alleviate these issues, this paper proposes the novel self-similar key generation and distribution scheme on the basis of the Elliptic Curve Diffie Hellman (ECDH) and Chinese Reminder Theorem (CRT). The assigning permission to each node to generate their own key at the specified time by the ECDH prevents the unnecessary distribution of keys that reduces the communication overhead. Then, the application of CRT theorem reduces the mathematical burden of key generation. Finally, the integration of the Elliptic Curve Cryptography (ECC) with the above mechanisms validates the number of messages transferred among the participants in both sender and receiver side. The prior key generation using ECDH and the CRT-based self-similar key generation reduces the computational and communication overhead effectively. The comparative analysis between the proposed SSKG with the existing schemes in terms of overhead, complexity assures the effectiveness of proposed schemes in secure multicast communication.

Concurrency and Computation: Practice and Experience, Oct 15, 2018

High usage levels of networking technologies has resulted in large amounts of data being generate... more High usage levels of networking technologies has resulted in large amounts of data being generated. This in-turn has lured several fraudsters, whose anomalous behaviors create undesired consequences to legitimate users. This paper proposes an Adaptive Parallelized Intrusion Detection (APID) architecture to handle the hugeness and data imbalance associated with streaming data. The architecture is composed of a feature selection strategy to reduce data size, an effective data segregation mechanism to handle data imbalance and a heterogeneous ensemble and a heuristic combiner mechanism to provide effective predictions. Adaptivity is incorporated by the reinforcement mechanism that retrains the model based on false predictions given by the model. The proposed APID architecture is generic; hence, it supports heterogeneous models and can also incorporate any number of machine learning models. Hence, it becomes flexible to adapt the model to data pertaining to any domain. Experiments were performed with KDD CUP 99, NSL-KDD, and Koyoto 2006 datasets. Comparisons performed with recent works in literature indicates anomaly detection rates between 98% to 99% exhibiting the effectiveness of the proposed model.

Network security consists of provisions and policies adopted by network administrator to prevent ... more Network security consists of provisions and policies adopted by network administrator to prevent unauthorized access of network accessible resources. Jamming can be viewed as a form of Denial-of-Service attack, whose goal is to prevent users from receiving timely and adequate information. In these attacks, the adversary is active only for a short period of time, selectively targeting messages of high importance. This paper presents a survey of the existing jamming attack prevention techniques. Selective jamming attacks can be launched by performing real-time packet classification at the physical layer. To mitigate these attacks, three schemes that prevent real-time packet classification by combining cryptographic primitives with physical-layer attributes are also presented in this paper.

International Conference on Information and Communication Technologies, Aug 10, 2014

Security is a serious problem in software development which when not taken into consideration, ex... more Security is a serious problem in software development which when not taken into consideration, exploits vulnerabilities in software. Such security related problems need to be addressed as early as possible while building software. Security problems exist for many reasons. A major thing is that, software cannot resist security attacks. Software security vulnerabilities are often caused due to the flaws that might be in specification, design, implementation or testing. These flaws are unknowingly injected by the software developers during development or left unnoticed by the software testers while testing for defects in software. This requires that developers and testers use methods that consistently produce secure software, which results in a defect less product. Security must be integrated into the software development life cycle from the beginning and must persist until the product is in use. This paper brings out the security deliberation that have to be paid due attention in the various phases of software development life cycle while developing a software.

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, Nov 22, 2009

In this paper, an image adaptive, invisible digital watermarking algorithm with Orthogonal Polyno... more In this paper, an image adaptive, invisible digital watermarking algorithm with Orthogonal Polynomials based Transformation (OPT) is proposed, for copyright protection of digital images. The proposed algorithm utilizes a visual model to determine the watermarking strength necessary to invisibly embed the watermark in the mid frequency AC coefficients of the cover image, chosen with a secret key. The visual model is designed to generate a Just Noticeable Distortion mask (JND) by analyzing the low level image characteristics such as textures, edges and luminance of the cover image in the orthogonal polynomials based transformation domain. Since the secret key is required for both embedding and extraction of watermark, it is not possible for an unauthorized user to extract the embedded watermark. The proposed scheme is robust to common image processing distortions like filtering, JPEG compression and additive noise. Experimental results show that the quality of OPT domain watermarked images is better than its DCT counterpart.

Journal of Computational and Theoretical Nanoscience, Jun 1, 2017

International Journal of Web Services Research, Nov 4, 2022

The process of intrusion detection usually involves identifying complex intrusion signatures from... more The process of intrusion detection usually involves identifying complex intrusion signatures from a huge repository. This requires a complex model that can identify these signatures. This work presents a deep learning based neural network model that can perform effective intrusion detection on network transmission data. The proposed multi-layered deep learning network is composed of multiple hidden processing layers in the network that makes it a deep learning network. Detection using the deep network was observed to exhibit effective performances in detecting the intrusion signatures. Experiments were performed on standard benchmark datasets like KDD CUP 99, NSL-KDD, and Koyoto 2006+ datasets. Comparisons were performed with state-of-the-art models in literature, and the results and comparisons indicate high performances by the proposed algorithm.

Software testing, an important phase in Software Development Life Cycle (SDLC) is a time consumin... more Software testing, an important phase in Software Development Life Cycle (SDLC) is a time consuming process. Information shows that nearly 40 to 50% of software development time is spent in testing. Manual testing is labour-intensive and error-prone so there is a need for automatic testing technique. Automation brings down the time and cost involved in testing. When testing software, there are often a massive amount of possible testcases even for quite simple systems. Running each and every feasible test-case is certainly not a choice, so designing test-cases becomes a significant part of the testing process. NASA proposed Modified Condition/Decision Coverage (MC/DC) testing criterion in 1994, which is a white box testing criterion. The objective of this paper is to automate the generation of minimum number of test cases required to test a system with maximum coverage by removing the redundant test cases using MC/DC criterion. The work also gives a tool Smart Test Case Generator Tool (STCGT) that automates the minimum number of test cases required to test the source code. This will give an idea about the test cases execution for the beginners of the testing team, thereby, aids in a quality on-time product.

Image Processing and Communications, 2009

Advances in intelligent systems and computing, 2017

Internet of Things (IoT) is a backboneless network. Because of the uni-directional link and mobil... more Internet of Things (IoT) is a backboneless network. Because of the uni-directional link and mobility nature of the nodes, the network is dynamic. The nodes are self-organized and two nodes can transfer data directly when they are within the transmission range. The nodes in IoT are self-organized and dynamic so MANET routing plays a vital role. The Light weight Ad hoc On-demand Distance Vector (LOAD) is a reactive routing protocol. In LOAD, the routing involves three major processes namely route discovery, path establishment, and route maintenance. The route discovery is carried out by Route REQuest (RREQ), Route REPly (RREP), and Route ERRor (RERR) control packets. The cost of the route discovery is estimated by control packets propagation. The proposed technique Cost And Load overhead reDUction for routE discovery in LOAD ProtocoL (CALDUEL) is proposed to reduce the load overhead, by reducing the cost of route discovery.

INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT

Social interaction, conduct, and cognitive ability are all impacted by the neuro developmental il... more Social interaction, conduct, and cognitive ability are all impacted by the neuro developmental illness known as autism spectrum disorder (ASD). Even though ASD diagnosis can be difficult and time-consuming, early detection and intervention can improve long-term results. Early childhood is when autism spectrum disorder first manifests, and it eventually leads to issues with social, academic, and occupational functioning in society. Within the first year, autism signs are frequently visible in children. Some infants display autistic spectrum disorder symptoms as early as infancy, including decreased eye contact, a lack of responsiveness to their name, or a lack of interest in carers. To identify the presence of disorder at an early stage, use a deep learning system like LSTM. Self-Stimulatory Behaviours Dataset (SSBD) was used to collect the datasets, and video dataset was used to construct the system. The feature extraction algorithm is the Blaze Pose algorithm. The model file has be...

International journal of engineering research and technology, 2018

The Internet of Things (IoT), connecting a large number of communication and information devices,... more The Internet of Things (IoT), connecting a large number of communication and information devices, is the future of the scientific world. The amount of devices with Wi-Fi capabilities and built-in sensors keeps on increasing. Smart phone is at every hand and its usage is sky-rocketing. This gives way to connect anything and anybody with the internet which in turn makes secure communication and secure sharing of information critical. In this paper, the existing works are analyzed and an IoT enabled healthcare system architecture is proposed. A novel authentication scheme that supplements the security of the proposed healthcare system is also proposed. Keywords— IoT, Architecture, Enhancing Authentication, Smart Healthcare System, Security, IoT devices.

International Journal of Web Services Research

The process of intrusion detection usually involves identifying complex intrusion signatures from... more The process of intrusion detection usually involves identifying complex intrusion signatures from a huge repository. This requires a complex model that can identify these signatures. This work presents a deep learning based neural network model that can perform effective intrusion detection on network transmission data. The proposed multi-layered deep learning network is composed of multiple hidden processing layers in the network that makes it a deep learning network. Detection using the deep network was observed to exhibit effective performances in detecting the intrusion signatures. Experiments were performed on standard benchmark datasets like KDD CUP 99, NSL-KDD, and Koyoto 2006+ datasets. Comparisons were performed with state-of-the-art models in literature, and the results and comparisons indicate high performances by the proposed algorithm.

International journal of engineering research and technology, 2018

The Internet of Things (IoT), connecting a large number of communication and information devices,... more The Internet of Things (IoT), connecting a large number of communication and information devices, is the future of the scientific world. The amount of devices with Wi-Fi capabilities and built-in sensors keeps on increasing. Smart phone is at every hand and its usage is sky-rocketing. This gives way to connect anything and anybody with the internet which in turn makes secure communication and secure sharing of information critical. In this paper, the existing works are analyzed and an IoT enabled healthcare system architecture is proposed. A novel authentication scheme that supplements the security of the proposed healthcare system is also proposed. Keywords— IoT, Architecture, Enhancing Authentication, Smart Healthcare System, Security, IoT devices.

Data mining and knowledge engineering, 2012

Data mining involves the use of sophisticated data analysis tools which discovers previously unkn... more Data mining involves the use of sophisticated data analysis tools which discovers previously unknown, valid patterns and relationships in large data sets. Educational Data Mining is concerned with developing methods for exploring the unique types of data that comes from educational scenario and using those methods to better understand students and the settings in which they learn. These days stress and depression are found to be common among students. Programming is considered to be the most essential skill for IT students in order to flourish in life. The objective of this paper is to find out the way in which stress and depression experienced by the students have impact on their programming performance. The level of stress and depression are measured by the use of questionnaires. The mark obtained by the students in the programming language is considered as a measure of programming performance. Frequent –pattern growth algorithm has been used to discover the various patterns avail...