Ilavendhan Anandaraj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ilavendhan Anandaraj has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
K. Saruladha
Pondicherry Engineering College,Department of CSE,Pondicherry,India
3 shared publicationsR. Indrakumari
2 shared publicationsB. Balamurugan
1 shared publication- B. Nandhitha
Vellore Institute of Technology
1 shared publication - C. Nelson Kennedy Babu
Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences (SIMATS),Dept. of CSE,Chennai,India
1 shared publication - Calin Ovidiu Safirescu
Environment Protection Department, Faculty of Agriculture, University of Agriculture Sciences and Veterrnary Medicine Cluj-Napoca, Calea Manastur No. 3–5, 40033 Cluj-Napoca, Romania
1 shared publication
Latest Publications
- Open Access
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 66373-66392
CUNet-CLSTM: A Novel Fusion of CUNet and CLSTM for Superior Liver Cancer Detection in CT Scans
Liver cancer remains one of the main causes of mortality worldwide, requiring advancements in diagnostic systems for early detection and improved patient outcomes. Computed tomography (CT) scans are crucial in the diagnosis of liver cancer, providing detailed images for medical analysis. Despite the triumph of convolutional neural networks in medical image analysis, challenges such as overfitting, limited labeled data, and complex tumor morphology hinder accurate detection of liver cancer. This study proposes a novel architecture, the cascaded UNet convolutional long short-term model (CUNet-CLSTM), which leverages the strengths of UNet and convolutional long short-term memory to improve liver segmentation and tumor detection in CT images. The anticipated CUNet-CLSTM model evaluated on two benchmark datasets: LiTS and 3DICARDB. The experimental results show excellent performance, achieving the best DICE values of 91.3% for liver segmentation and 96.1% for tumor detection on the LiTS dataset, and 96.3% for liver segmentation and 98.3% for tumor detection on the 3DICARDB dataset. Compared to state-of-the-art models, the proposed CUNet-CLSTM not only improves segmentation accuracy, but also mitigates overfitting through sequential feature learning and optimizes computational efficiency by providing an end-to-end framework, reducing the complexity of multi-stage pipelines. This research contributes to addressing the urgent need for accurate methods for detecting liver cancer, facilitating early diagnosis, and customized treatment strategies.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 66373-66392
Open AccessCUNet-CLSTM: A Novel Fusion of CUNet and CLSTM for Superior Liver Cancer Detection in CT Scans
Liver cancer remains one of the main causes of mortality worldwide, requiring advancements in diagnostic systems for early detection and improved patient outcomes. Computed tomography (CT) scans are crucial in the diagnosis of liver cancer, providing detailed images for medical analysis. Despite the triumph of convolutional neural networks in medical image analysis, challenges such as overfitting, limited labeled data, and complex tumor morphology hinder accurate detection of liver cancer. This study proposes a novel architecture, the cascaded UNet convolutional long short-term model (CUNet-CLSTM), which leverages the strengths of UNet and convolutional long short-term memory to improve liver segmentation and tumor detection in CT images. The anticipated CUNet-CLSTM model evaluated on two benchmark datasets: LiTS and 3DICARDB. The experimental results show excellent performance, achieving the best DICE values of 91.3% for liver segmentation and 96.1% for tumor detection on the LiTS dataset, and 96.3% for liver segmentation and 98.3% for tumor detection on the 3DICARDB dataset. Compared to state-of-the-art models, the proposed CUNet-CLSTM not only improves segmentation accuracy, but also mitigates overfitting through sequential feature learning and optimizes computational efficiency by providing an end-to-end framework, reducing the complexity of multi-stage pipelines. This research contributes to addressing the urgent need for accurate methods for detecting liver cancer, facilitating early diagnosis, and customized treatment strategies.
- 28 November 2024
- Published by Springer Nature
- p. 191-201
Enhancing Network Security: A Study on Phishing Threats and Countermeasures
- 28 November 2024
- Published by Springer Nature
- p. 191-201
Enhancing Network Security: A Study on Phishing Threats and Countermeasures
- 28 November 2024
- Published by Springer Nature
- p. 157-175
Empowering Cyber Defenses: Shielding Against Man-in-the-Middle Attacks with Public Key Infrastructure (PKI)
- 28 November 2024
- Published by Springer Nature
- p. 157-175
Empowering Cyber Defenses: Shielding Against Man-in-the-Middle Attacks with Public Key Infrastructure (PKI)
- 28 November 2024
- Published by Springer Nature
- p. 323-340
Enhancing Education Through Technology: A Critical Review of Computer-Assisted Learning
- 28 November 2024
- Published by Springer Nature
- p. 323-340
Enhancing Education Through Technology: A Critical Review of Computer-Assisted Learning
- 23 October 2024
- Published by Springer Nature
- p. 417-432
Proof of Computational Power: An Innovative Consensus Algorithm for Blockchain Systems
- 23 October 2024
- Published by Springer Nature
- p. 417-432
Proof of Computational Power: An Innovative Consensus Algorithm for Blockchain Systems
- 8 May 2024
- Published by Taylor & Francis
- p. 173-184
Enhancing Cardiovascular Health Diagnosis through Predictive Analysis of Electronic Health Records
In the past few years, heart disease or cardiovascular disease became a life-threatening disease and the basis for many deaths across the world. The early prediction of heart disease can save many people’s life. This chapter proposed a deep learning-based framework for diagnosing heart disease. The proposed framework uses the long short-term memory for diagnosing heart disease based on the medical history of the patient. The hyperparameters of the LSTM based prediction model are further optimized using a genetic algorithm (GA). The experiments show that the proposed DL framework achieves remarkable results on the benchmark heart disease datasets, namely UCI Heart Disease Data and Kaggle Heart Disease Data. The results of the proposed LSTM model with GA based hyperparameter optimization methods got better accuracy than other existing state-of-the-art methods.
- 8 May 2024
- Published by Taylor & Francis
- p. 173-184
Enhancing Cardiovascular Health Diagnosis through Predictive Analysis of Electronic Health Records
In the past few years, heart disease or cardiovascular disease became a life-threatening disease and the basis for many deaths across the world. The early prediction of heart disease can save many people’s life. This chapter proposed a deep learning-based framework for diagnosing heart disease. The proposed framework uses the long short-term memory for diagnosing heart disease based on the medical history of the patient. The hyperparameters of the LSTM based prediction model are further optimized using a genetic algorithm (GA). The experiments show that the proposed DL framework achieves remarkable results on the benchmark heart disease datasets, namely UCI Heart Disease Data and Kaggle Heart Disease Data. The results of the proposed LSTM model with GA based hyperparameter optimization methods got better accuracy than other existing state-of-the-art methods.
- Open Access
Clustering Based Optimal Cluster Head Selection Using Bio-Inspired Neural Network in Energy Optimization of 6LowPAN
The goal of today’s technological era is to make every item smart. Internet of Things (IoT) is a model shift that gives a whole new dimension to the common items and things. Wireless sensor networks, particularly Low-Power and Lossy Networks (LLNs), are essential components of IoT that has a significant influence on daily living. Routing Protocol for Low Power and Lossy Networks (RPL) has become the standard protocol for IoT and LLNs. It is not only used widely but also researched by various groups of people. The extensive use of RPL and its customization has led to demanding research and improvements. There are certain issues in the current RPL mechanism, such as an energy hole, which is a huge issue in the context of IoT. By the initiation of Grid formation across the sensor nodes, which can simplify the cluster formation, the Cluster Head (CH) selection is accomplished using fish swarm optimization (FSO). The performance of the Graph-Grid-based Convolution clustered neural network with fish swarm optimization (GG-Conv_Clus-FSO) in energy optimization of the network is compared with existing state-of-the-art protocols, and GG-Conv_Clus-FSO outperforms the existing approaches, whereby the packet delivery ratio (PDR) is enhanced by 95.14%.
Open AccessClustering Based Optimal Cluster Head Selection Using Bio-Inspired Neural Network in Energy Optimization of 6LowPAN
The goal of today’s technological era is to make every item smart. Internet of Things (IoT) is a model shift that gives a whole new dimension to the common items and things. Wireless sensor networks, particularly Low-Power and Lossy Networks (LLNs), are essential components of IoT that has a significant influence on daily living. Routing Protocol for Low Power and Lossy Networks (RPL) has become the standard protocol for IoT and LLNs. It is not only used widely but also researched by various groups of people. The extensive use of RPL and its customization has led to demanding research and improvements. There are certain issues in the current RPL mechanism, such as an energy hole, which is a huge issue in the context of IoT. By the initiation of Grid formation across the sensor nodes, which can simplify the cluster formation, the Cluster Head (CH) selection is accomplished using fish swarm optimization (FSO). The performance of the Graph-Grid-based Convolution clustered neural network with fish swarm optimization (GG-Conv_Clus-FSO) in energy optimization of the network is compared with existing state-of-the-art protocols, and GG-Conv_Clus-FSO outperforms the existing approaches, whereby the packet delivery ratio (PDR) is enhanced by 95.14%.
- 5 October 2021
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (6) , 6489-6496
Stackelberg security game to mitigate the DoS attack in vehicular ad-hoc networks
- 5 October 2021
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (6) , 6489-6496
Stackelberg security game to mitigate the DoS attack in vehicular ad-hoc networks
- 1 May 2021
- Published by Taylor & Francis
- p. 39-54
Blockchain Performance
Blockchain technology is the next big thing in the applied science. It is a cryptography-based distributed digital ledger with a chain of information blocks identified using cryptographic signature. In general, a blockchain is a new version of database that allows many participants to concurrently share the database with a provision to alter it in a securable manner. Blockchain facilitates the most reliable transaction among unreliable contributors in the network, and hence, has raised noteworthy attention among scientists, developers and research scholars. The blocks of non-editable information are back linked, and to access a particular block, it is mandatory to refer to the previous block signature, which can be traced all the way back to the very first block created. The designing pattern of blockchain requires a solid cryptography, which includes a prior hashing to validate the existing transaction as well as the cumulative transaction along with consensus algorithm for contributor to consent a particular transaction to the global tamper-resistant ledger. If an invader makes an attempt to alter a block, they have to alter all blocks that are included afterwards the most recent block, which makes the attack impossible. The components of blockchain are cryptography, peer-to-peer network, consensus mechanism, ledger and a set of protocols. Based on the application, the blockchain is considered as public and private. In public, the details of the contributors are not known and the transaction is carried out with the help of mathematical proof. In contrast to this, in private blockchain, the contributors know the identity of each other and trust mutually by definition. The Bank of Japan and the European Central Bank have conducted a joint research project on blockchain, called Stella, in the year 2007 in the financial market infrastructure and announced that the blockchain technology is the ideal solution that satisfies the performance needs in a real-time gross settlement system. It is estimated that the global cost of financial fraud is 20 billion USD annually. Blockchain technology identifies the fraud immediately in the network with the help of real-time audit trail. With its security characteristics, blockchain is influencing the global currency market by evading Denial Of Service and Ransomware while holding historic immutability, which attracts the industries not restricted to logistics, pharmaceuticals, banking, cyber security and smart contracts with incomparable performance. The United States Defence Advanced Research Projects Agency (DARPA) requested to enforce blockchain technology to develop a ‘Secure Messaging Platform’ to exchange messages through a decentralized protocol. This proves the efficiency of blockchain-based system. In this chapter, the performance of blockchain-based system is discussed and evaluated for various applications.
- 1 May 2021
- Published by Taylor & Francis
- p. 39-54
Blockchain Performance
Blockchain technology is the next big thing in the applied science. It is a cryptography-based distributed digital ledger with a chain of information blocks identified using cryptographic signature. In general, a blockchain is a new version of database that allows many participants to concurrently share the database with a provision to alter it in a securable manner. Blockchain facilitates the most reliable transaction among unreliable contributors in the network, and hence, has raised noteworthy attention among scientists, developers and research scholars. The blocks of non-editable information are back linked, and to access a particular block, it is mandatory to refer to the previous block signature, which can be traced all the way back to the very first block created. The designing pattern of blockchain requires a solid cryptography, which includes a prior hashing to validate the existing transaction as well as the cumulative transaction along with consensus algorithm for contributor to consent a particular transaction to the global tamper-resistant ledger. If an invader makes an attempt to alter a block, they have to alter all blocks that are included afterwards the most recent block, which makes the attack impossible. The components of blockchain are cryptography, peer-to-peer network, consensus mechanism, ledger and a set of protocols. Based on the application, the blockchain is considered as public and private. In public, the details of the contributors are not known and the transaction is carried out with the help of mathematical proof. In contrast to this, in private blockchain, the contributors know the identity of each other and trust mutually by definition. The Bank of Japan and the European Central Bank have conducted a joint research project on blockchain, called Stella, in the year 2007 in the financial market infrastructure and announced that the blockchain technology is the ideal solution that satisfies the performance needs in a real-time gross settlement system. It is estimated that the global cost of financial fraud is 20 billion USD annually. Blockchain technology identifies the fraud immediately in the network with the help of real-time audit trail. With its security characteristics, blockchain is influencing the global currency market by evading Denial Of Service and Ransomware while holding historic immutability, which attracts the industries not restricted to logistics, pharmaceuticals, banking, cyber security and smart contracts with incomparable performance. The United States Defence Advanced Research Projects Agency (DARPA) requested to enforce blockchain technology to develop a ‘Secure Messaging Platform’ to exchange messages through a decentralized protocol. This proves the efficiency of blockchain-based system. In this chapter, the performance of blockchain-based system is discussed and evaluated for various applications.
- 9 March 2021
- Published by Bentham Science Publishers Ltd. in Recent Patents on Engineering
- Vol. 15 (2) , 150-160
Bayesian Game Approach to Mitigate DoS Attack in Vehicular Ad-Hoc Networks
Background: Trustful message transmission within the Vehicular ad-hoc Networks is needed as traffic related safety applications needs successful and reliable delivery of messages. The biggest issue is how only the trustworthy parties can be retained and the misbehaved are revoked. From the background analysis, it gives a detailed view of various vulnerabilities in these networks and the techniques used by the researchers to identify and mitigate the attack. Based on the drawbacks observed in the literature the proposed Bayesian Game Mechanism has been designed. Objective: The major objective of this manuscript is to identify the Denial of Service Attack in Vehicular Ad-hoc Networks as it depletes availability of the resources. This attack is identified using Bayesian Game approach. Methods: The Bayesian game approach is used to identify the attack. It analyzes the behavior of vehicles and classifies them into trustworthy or malicious. Results: The simulation is conducted using Network simulator 2.34 and the traffic model is designed using by considering 100 nodes. From the results it is inferred that Packet drop ratio has been improved by 9.82 % and the delay and throughput has been minimized, when the proposed mechanism is used in the presence of attackers. Conclusion: This paper identifies Denial of Service attack as the most vulnerable attack in this network and has designed game theoretic approach namely Bayesian approach for preventing this attack. The proposed method has minimized the delay and packet drop and improved the throughput when compared against the bench mark.
- 9 March 2021
- Published by Bentham Science Publishers Ltd. in Recent Patents on Engineering
- Vol. 15 (2) , 150-160
Bayesian Game Approach to Mitigate DoS Attack in Vehicular Ad-Hoc Networks
Background: Trustful message transmission within the Vehicular ad-hoc Networks is needed as traffic related safety applications needs successful and reliable delivery of messages. The biggest issue is how only the trustworthy parties can be retained and the misbehaved are revoked. From the background analysis, it gives a detailed view of various vulnerabilities in these networks and the techniques used by the researchers to identify and mitigate the attack. Based on the drawbacks observed in the literature the proposed Bayesian Game Mechanism has been designed. Objective: The major objective of this manuscript is to identify the Denial of Service Attack in Vehicular Ad-hoc Networks as it depletes availability of the resources. This attack is identified using Bayesian Game approach. Methods: The Bayesian game approach is used to identify the attack. It analyzes the behavior of vehicles and classifies them into trustworthy or malicious. Results: The simulation is conducted using Network simulator 2.34 and the traffic model is designed using by considering 100 nodes. From the results it is inferred that Packet drop ratio has been improved by 9.82 % and the delay and throughput has been minimized, when the proposed mechanism is used in the presence of attackers. Conclusion: This paper identifies Denial of Service attack as the most vulnerable attack in this network and has designed game theoretic approach namely Bayesian approach for preventing this attack. The proposed method has minimized the delay and packet drop and improved the throughput when compared against the bench mark.