Rajesh Arunachalam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rajesh Arunachalam has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
- Sumanth Venugopal
Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India
8 shared publications Preethi Palanisamy
Department of Computer Science and Engineering, Kongunadu College of Engineering and Technology, Tholurpatti, Trichy, India
4 shared publicationsKiran Bharadwaj Vedula
Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Thandalam, Chennai, India
3 shared publicationsSurendra Kumar Shukla
School of Computer Science Engineering and Technology, Bennett University, Greater Noida, India
3 shared publicationsA. Sahaya Anselin Nisha
Department Electronics and Communication Engineering, Sathyabama Institute of Science and Technology, Chennai, India
2 shared publicationsAnguraju Krishnan
Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Thandalam, Chennai, India
2 shared publications
Latest Publications
- 28 September 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Blockchain-based data storage and data sharing contract in vehicle edge computing using adaptive deep deterministic policy gradient
In the efficient growth of Vehicular Ad Hoc Networks (VANETs), the performance of data transmission and protection is crucial for improving smooth communication. Yet, it is insufficient for accurately handling a huge amount of user data to address the aforementioned issues in the training phase, and it reduces the security level of secured data; thus, it makes it more vulnerable to malicious activities and hackers for damaging the entire system. Therefore, the Vehicle Edge Computing (VEC) platform is employed in this research work, which can potentially minimize the delay of the computation tasks to ensure long-term utility of the system at time-varying communication conditions. Also, it can manage a large quantity of input data without any interference for dynamically mitigating privacy and security burdens to guarantee the data transmission performance. However, the Roadside Units (RSUs) used as automobile edge computing servers cannot be completely trusted, as they lead to privacy and protection issues. Here, a blockchain-based VEC mechanism is designed to ultimately protect the low-latency data, and it can quickly mitigate unauthorized access’s performance to make better trustworthy and efficient. VEC consists of some RSUs, and the data collected from these RSUs is stored in a blockchain. Then, Adaptive Efficient Capsnet (AE-CapsNet) is designed for the authentication process of blocks, which reduces the risk of fraud and unauthorized nodes in the network. Finally, secure VEC is done with the help of Adaptive Deep Deterministic Policy Gradient (A-DDPG), and the reliability of this designed approach is maximized by optimizing the parameters from A-DDPG by utilizing Improved Random Variable-based Fennec Fox Optimization (IRV-FFO). At last, the entire process of the designed approach is validated and compared with existing methodologies based on various metrics.
- 28 September 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Blockchain-based data storage and data sharing contract in vehicle edge computing using adaptive deep deterministic policy gradient
In the efficient growth of Vehicular Ad Hoc Networks (VANETs), the performance of data transmission and protection is crucial for improving smooth communication. Yet, it is insufficient for accurately handling a huge amount of user data to address the aforementioned issues in the training phase, and it reduces the security level of secured data; thus, it makes it more vulnerable to malicious activities and hackers for damaging the entire system. Therefore, the Vehicle Edge Computing (VEC) platform is employed in this research work, which can potentially minimize the delay of the computation tasks to ensure long-term utility of the system at time-varying communication conditions. Also, it can manage a large quantity of input data without any interference for dynamically mitigating privacy and security burdens to guarantee the data transmission performance. However, the Roadside Units (RSUs) used as automobile edge computing servers cannot be completely trusted, as they lead to privacy and protection issues. Here, a blockchain-based VEC mechanism is designed to ultimately protect the low-latency data, and it can quickly mitigate unauthorized access’s performance to make better trustworthy and efficient. VEC consists of some RSUs, and the data collected from these RSUs is stored in a blockchain. Then, Adaptive Efficient Capsnet (AE-CapsNet) is designed for the authentication process of blocks, which reduces the risk of fraud and unauthorized nodes in the network. Finally, secure VEC is done with the help of Adaptive Deep Deterministic Policy Gradient (A-DDPG), and the reliability of this designed approach is maximized by optimizing the parameters from A-DDPG by utilizing Improved Random Variable-based Fennec Fox Optimization (IRV-FFO). At last, the entire process of the designed approach is validated and compared with existing methodologies based on various metrics.
- Open Access
- 27 July 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 475
Ethereum blockchain and authentication-based smart contract for pest detection and smart irrigation using an adaptive deep learning model with IoT
A secure platform for exchanging and storing agricultural data is provided via a blockchain-powered framework. By integrating edge computing, blockchain technology, and the Internet of Things (IoT) the production of crops can be boosted while using fewer natural resources. In the sector of agriculture, sensors and equipment gather various data about the landscape, which can subsequently be delivered to a server in a cloud environment. Due to its extreme fragility, these data must be securely stored and guarded from unwanted access. The core aim of this work is to propose a hybrid Reconditioned Random value-based Wombat Optimization with Adaptive Multi-scale Vision Transformer-based EfficientNet (RRWO-AMViT-ENet) model integrated with Ethereum smart contracts for secure pest detection and smart irrigation in IoT environments. The gathered agricultural images are initially stored and managed using the Ethereum blockchain. Then, node authentication is performed using the Smart Contract-based Adaptive Deep Support Vector Machine (SC-ADSVM). A Reconditioned Random value-based Wombat Optimization (RRWO) is utilized to optimize the variables of the developed SC-ADSVM. In order to perform pest detection and smart irrigation, the Adaptive Multi-scale Vision Transformer-based EfficientNet (AMViT-ENet) is used. The proposed model is implemented on the IP102-Dataset, where it obtained an accuracy of 96.39% in the pest detection operation. Thus, the proposed model provides effective results for pest detection and the smart irrigation process. From the attained results, it is concluded that the recommended strategy can provide intelligent service to the farmer.
- 27 July 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 475
Open AccessEthereum blockchain and authentication-based smart contract for pest detection and smart irrigation using an adaptive deep learning model with IoT
A secure platform for exchanging and storing agricultural data is provided via a blockchain-powered framework. By integrating edge computing, blockchain technology, and the Internet of Things (IoT) the production of crops can be boosted while using fewer natural resources. In the sector of agriculture, sensors and equipment gather various data about the landscape, which can subsequently be delivered to a server in a cloud environment. Due to its extreme fragility, these data must be securely stored and guarded from unwanted access. The core aim of this work is to propose a hybrid Reconditioned Random value-based Wombat Optimization with Adaptive Multi-scale Vision Transformer-based EfficientNet (RRWO-AMViT-ENet) model integrated with Ethereum smart contracts for secure pest detection and smart irrigation in IoT environments. The gathered agricultural images are initially stored and managed using the Ethereum blockchain. Then, node authentication is performed using the Smart Contract-based Adaptive Deep Support Vector Machine (SC-ADSVM). A Reconditioned Random value-based Wombat Optimization (RRWO) is utilized to optimize the variables of the developed SC-ADSVM. In order to perform pest detection and smart irrigation, the Adaptive Multi-scale Vision Transformer-based EfficientNet (AMViT-ENet) is used. The proposed model is implemented on the IP102-Dataset, where it obtained an accuracy of 96.39% in the pest detection operation. Thus, the proposed model provides effective results for pest detection and the smart irrigation process. From the attained results, it is concluded that the recommended strategy can provide intelligent service to the farmer.
- Open Access
- 13 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
An intelligent ethereum blockchain technology for pest detection and smart irrigation in IoT using hybrid deep learning model
This research discusses the incorporation of IoT with blockchain technique to enhance the efficiency of smart farming systems, particularly focusing on plant disease classification, pest detection, and smart irrigation. The study aims to develop a secure and effective IoT-based smart farming framework using the Ethereum blockchain to store and transmit data, and a Hybrid Convolution Adaptive Recurrent MobileNet (HC-ARMNet) model for predictive analytics, optimized by the Improved Secretary Bird Optimization (ISBO) algorithm. The research employs IoT sensors to acquire real-time data, which is then stored in the Ethereum blockchain to ensure security. The HC-ARMNet model, combining 1D/2D convolutions with recurrent connections, processes this data for pest detection and irrigation management. The ISBO algorithm is leveraged to fine-tune the technique’s parameters. Datasets used: The proposed system utilizes three standard datasets for evaluation. The PlantifyDr Dataset is used for classifying plant disease, and the Pest Detection Dataset is used for recognizing pests. Also, for the smart irrigation process, the significant field images are collected manually. The accuracy, precision, and FNR rates of the ISBO-HC-ARMNet-aided plant disease classification are 94.16%, 94.2% and 5.87%. At the same time, the ISBO-HC-ARMNet-based pest detection process’s accuracy, sensitivity, and specificity are 93.78%, 93.79% and 93.76%, respectively. In addition, the ISBO-HC-ARMNet-based smart irrigation task’s MSE is 3.21, SMAPE is 0.03, and MASE is 30.23. Thus, the designed system showcases promising performance over classical approaches in terms of accuracy and error rates for plant disease classification, pest detection, and smart irrigation. The research concludes that the IoT-aided smart farming framework with blockchain and the HC-ARMNet model provides a robust solution for secure and efficient agricultural management. The system’s predictive capabilities provide accurate and timely data analysis, facilitating to the improvement of precision agriculture. Future work will focus on improving the system with advanced feature extraction strategies to reduce processing time.
- 13 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessAn intelligent ethereum blockchain technology for pest detection and smart irrigation in IoT using hybrid deep learning model
This research discusses the incorporation of IoT with blockchain technique to enhance the efficiency of smart farming systems, particularly focusing on plant disease classification, pest detection, and smart irrigation. The study aims to develop a secure and effective IoT-based smart farming framework using the Ethereum blockchain to store and transmit data, and a Hybrid Convolution Adaptive Recurrent MobileNet (HC-ARMNet) model for predictive analytics, optimized by the Improved Secretary Bird Optimization (ISBO) algorithm. The research employs IoT sensors to acquire real-time data, which is then stored in the Ethereum blockchain to ensure security. The HC-ARMNet model, combining 1D/2D convolutions with recurrent connections, processes this data for pest detection and irrigation management. The ISBO algorithm is leveraged to fine-tune the technique’s parameters. Datasets used: The proposed system utilizes three standard datasets for evaluation. The PlantifyDr Dataset is used for classifying plant disease, and the Pest Detection Dataset is used for recognizing pests. Also, for the smart irrigation process, the significant field images are collected manually. The accuracy, precision, and FNR rates of the ISBO-HC-ARMNet-aided plant disease classification are 94.16%, 94.2% and 5.87%. At the same time, the ISBO-HC-ARMNet-based pest detection process’s accuracy, sensitivity, and specificity are 93.78%, 93.79% and 93.76%, respectively. In addition, the ISBO-HC-ARMNet-based smart irrigation task’s MSE is 3.21, SMAPE is 0.03, and MASE is 30.23. Thus, the designed system showcases promising performance over classical approaches in terms of accuracy and error rates for plant disease classification, pest detection, and smart irrigation. The research concludes that the IoT-aided smart farming framework with blockchain and the HC-ARMNet model provides a robust solution for secure and efficient agricultural management. The system’s predictive capabilities provide accurate and timely data analysis, facilitating to the improvement of precision agriculture. Future work will focus on improving the system with advanced feature extraction strategies to reduce processing time.
- Open Access
- 25 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Adaptive deep conditional random field with blockchain for secure data sharing in software-defined wireless body area networks
Presently, blockchains are widely employed to execute the secure data transmission process among users. However, sharing the sensitive information about the patients among multiple users in the healthcare sector is difficult due to integrity and confidentiality issues. Thus, to tackle these issues in prior models, a secure data-sharing framework for Software-Defined Wireless Body Area Networks (SDWBANs) is designed. In order to ensure privacy and controlled access in SDWBANs, blockchain technology and encryption techniques are considered, which help to protect sensitive medical data. Then, the Adaptive Deep Conditional Random Field (ADCRF) is employed to perform the decision-making procedure. Further, an advanced encryption technique, Optimal Key-based Multi-Authority Attribute-Based Encryption (O-MA-ABE), is employed to ensure that authorized users can access the confidential health data. Here, the Modified Escape Search-based Piranha Foraging Optimization Algorithm (MES-PFOA) is employed to tune the Hyperparameters of ADCRF and keys of O-MA-ABE. Then, the overall performance of the developed framework is compared with classical approaches using metrics such as computational time, decryption time, and decision-making accuracy. In various validations, the developed MES-PFOA-O-MA-ABE + ADCRF-based data sharing model accomplished higher accuracy as 98.7%, precision as 98.3%, minimal encryption time as 210 (ms) and throughput as 275 (TPS) than the recent data sharing models like DTAC-TL-QM, SCCE-DS, BFL-hIoT and PPFL-ICP.
- 25 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessAdaptive deep conditional random field with blockchain for secure data sharing in software-defined wireless body area networks
Presently, blockchains are widely employed to execute the secure data transmission process among users. However, sharing the sensitive information about the patients among multiple users in the healthcare sector is difficult due to integrity and confidentiality issues. Thus, to tackle these issues in prior models, a secure data-sharing framework for Software-Defined Wireless Body Area Networks (SDWBANs) is designed. In order to ensure privacy and controlled access in SDWBANs, blockchain technology and encryption techniques are considered, which help to protect sensitive medical data. Then, the Adaptive Deep Conditional Random Field (ADCRF) is employed to perform the decision-making procedure. Further, an advanced encryption technique, Optimal Key-based Multi-Authority Attribute-Based Encryption (O-MA-ABE), is employed to ensure that authorized users can access the confidential health data. Here, the Modified Escape Search-based Piranha Foraging Optimization Algorithm (MES-PFOA) is employed to tune the Hyperparameters of ADCRF and keys of O-MA-ABE. Then, the overall performance of the developed framework is compared with classical approaches using metrics such as computational time, decryption time, and decision-making accuracy. In various validations, the developed MES-PFOA-O-MA-ABE + ADCRF-based data sharing model accomplished higher accuracy as 98.7%, precision as 98.3%, minimal encryption time as 210 (ms) and throughput as 275 (TPS) than the recent data sharing models like DTAC-TL-QM, SCCE-DS, BFL-hIoT and PPFL-ICP.
- Open Access
- 11 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A blockchain-based secure data transmission framework in IoT using adaptive deep network with optimized cryptography mechanism
This work presents a secure data transmission process in the Internet of Things (IoT). Initially, the required data are collected and given to the Adaptive and Sparse Attention-based Dense Long Short-Term Memory (ASA-DLSTM) network for intrusion detection. The adaptive nature of the model allows for optimizing the parameters using the Sorted Fitness-based Addax Optimization Algorithm (SF-AOA). Once intrusions are detected, the data is used for the data transmission phase. It is performed using Optimal Key-based Elliptic Galois Cryptography (OK-EGC). By combining Elliptic with Galois fields and an optimal key management strategy, the proposed OK-EGC method enhances both encryption efficiency and security. Moreover, the integration of optimal key-based management using the same SF-AOA ensures that cryptographic keys are dynamically optimized based on the network’s security requirements. Then, the effectiveness of the model is compared with existing systems. The accuracy of the implemented SF-AOA-ASA-DLSTM technique is 95.97%, which is higher than the conventional techniques, such as DNN (83.77%), SVM (83.19%), 1DCNN (90.26%), and ASA-DLSTM (93.6%) for the batch size value 64. Thus, the results display that the designed model addresses the critical challenges of IoT data security by providing both robust intrusion detection and secure communication.
- 11 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA blockchain-based secure data transmission framework in IoT using adaptive deep network with optimized cryptography mechanism
This work presents a secure data transmission process in the Internet of Things (IoT). Initially, the required data are collected and given to the Adaptive and Sparse Attention-based Dense Long Short-Term Memory (ASA-DLSTM) network for intrusion detection. The adaptive nature of the model allows for optimizing the parameters using the Sorted Fitness-based Addax Optimization Algorithm (SF-AOA). Once intrusions are detected, the data is used for the data transmission phase. It is performed using Optimal Key-based Elliptic Galois Cryptography (OK-EGC). By combining Elliptic with Galois fields and an optimal key management strategy, the proposed OK-EGC method enhances both encryption efficiency and security. Moreover, the integration of optimal key-based management using the same SF-AOA ensures that cryptographic keys are dynamically optimized based on the network’s security requirements. Then, the effectiveness of the model is compared with existing systems. The accuracy of the implemented SF-AOA-ASA-DLSTM technique is 95.97%, which is higher than the conventional techniques, such as DNN (83.77%), SVM (83.19%), 1DCNN (90.26%), and ASA-DLSTM (93.6%) for the batch size value 64. Thus, the results display that the designed model addresses the critical challenges of IoT data security by providing both robust intrusion detection and secure communication.
- Open Access
- 29 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 44851
An IoT-based healthcare system using blockchain technology and multiscale stacked Residual-GRU for secure data transmission
This work resolves the crucial problem of secure data transmission in IoT-aided healthcare devices, where confidential patient data is vulnerable to breaches and cyberattacks. To resolve these complexities, this work proposes a novel secure data transmission system that combines blockchain technology, Multiobjective Weighted Restricted Boltzmann Machine (MW-RBM) for feature extraction, Magnified Feeding-based American Zebra Optimization (MFAZO) for weight optimization, and a Multiscale Stacked Residual-Gated Recurrent Unit (MSRes-GRU) for attack detection. The novelty of this work lies in combining residual GRU and blockchain for secure IoT healthcare data transmission, guaranteeing both transparency and attack detection. The improvement is displayed in weight optimization through MFAZO, which refines the feature extraction task and boosts the accuracy of the technique in attack detection. The designed approach involves gathering attack detection data, performing feature extraction utilizing MW-RBM with optimized weights and identifying IoT node attacks via the MSRes-GRU technique’s multiscale layers and the residual connections. The Homomorphic Polynomial Encryption (HPE) is further employed to secure the healthcare data during transmission. Lastly, the performance of the model is determined with conventional models. The accuracy of the designed MSRes-GRU is 96.22%, which is higher than the existing models such as DNN (85.65%), LSTM (80.71%), SVM (89.99%), and GRU (94.14%). The key results demonstrate the technique’s high detection accuracy and robust performance in recognizing the IoT-based attacks while guaranteeing effective, secure and transparent data transmission via blockchain. This research contributes to improving the secure and scalable IoT-enabled healthcare devices, providing a reliable model for trustworthy healthcare applications that preserve data integrity and privacy.
- 29 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 44851
Open AccessAn IoT-based healthcare system using blockchain technology and multiscale stacked Residual-GRU for secure data transmission
This work resolves the crucial problem of secure data transmission in IoT-aided healthcare devices, where confidential patient data is vulnerable to breaches and cyberattacks. To resolve these complexities, this work proposes a novel secure data transmission system that combines blockchain technology, Multiobjective Weighted Restricted Boltzmann Machine (MW-RBM) for feature extraction, Magnified Feeding-based American Zebra Optimization (MFAZO) for weight optimization, and a Multiscale Stacked Residual-Gated Recurrent Unit (MSRes-GRU) for attack detection. The novelty of this work lies in combining residual GRU and blockchain for secure IoT healthcare data transmission, guaranteeing both transparency and attack detection. The improvement is displayed in weight optimization through MFAZO, which refines the feature extraction task and boosts the accuracy of the technique in attack detection. The designed approach involves gathering attack detection data, performing feature extraction utilizing MW-RBM with optimized weights and identifying IoT node attacks via the MSRes-GRU technique’s multiscale layers and the residual connections. The Homomorphic Polynomial Encryption (HPE) is further employed to secure the healthcare data during transmission. Lastly, the performance of the model is determined with conventional models. The accuracy of the designed MSRes-GRU is 96.22%, which is higher than the existing models such as DNN (85.65%), LSTM (80.71%), SVM (89.99%), and GRU (94.14%). The key results demonstrate the technique’s high detection accuracy and robust performance in recognizing the IoT-based attacks while guaranteeing effective, secure and transparent data transmission via blockchain. This research contributes to improving the secure and scalable IoT-enabled healthcare devices, providing a reliable model for trustworthy healthcare applications that preserve data integrity and privacy.
- Open Access
- 16 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 43912
Blockchain-based secure MEC model for VANETs using hybrid networks
Vehicular Ad-hoc Networks (VANETs) are a type of mobile ad-hoc network that enables vehicles to interact with one another and roadside infrastructure. Multi-Access Edge Computing (MEC) provides a promising solution by positioning storage and computation resources closer to the network edge. This helps to reduce the latency and improve performance. The combination of MEC and blockchain enhances data processing and security. This integration improves privacy safeguards, prevents fraud, and supports trusted communication within VANETs. Consequently, this proposed model aims to develop an innovative approach that leverages these technologies. The main objective of the implemented technique is to create a blockchain architecture powered by deep learning, which ensures the safety of VANETs. The network architecture consists of three layers: perception, edge computing, and services. The main goal of the initial layer is to protect the privacy of VANET data through blockchain activities. The perception layer processes data using edge computing and cloud services. The service layer ensures data protection by through the blockchain technology and storing information in a public cloud. The last layer focuses on addressing user demands for throughput and Quality of Service (QoS). The proposed framework is good for assessing the dependability of vehicle nodes stored on the blockchain. To accomplish node authentication, an Adaptive and Dilated Hybrid Network (ADHyNet) is used. In this approach, the Residual Long Short-Term Memory (Res-LSTM) with Gated Recurrent Unit (GRU) forms the ADHyNet, where the Random Number Updated Skill Optimization Algorithm (RNU-SOA) is used to optimize the hyperparameters. Finally, the encryption process is carried out using Homomorphic Encryption combined with Elliptic Curve Cryptography (HECC) to secure data. This process ensures that confidential user information is protected against unauthorized access. The functionality of the system is thoroughly assessed and simulated. The suggested technique outperforms well than other approaches in terms of data security in VANET.
- 16 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 43912
Open AccessBlockchain-based secure MEC model for VANETs using hybrid networks
Vehicular Ad-hoc Networks (VANETs) are a type of mobile ad-hoc network that enables vehicles to interact with one another and roadside infrastructure. Multi-Access Edge Computing (MEC) provides a promising solution by positioning storage and computation resources closer to the network edge. This helps to reduce the latency and improve performance. The combination of MEC and blockchain enhances data processing and security. This integration improves privacy safeguards, prevents fraud, and supports trusted communication within VANETs. Consequently, this proposed model aims to develop an innovative approach that leverages these technologies. The main objective of the implemented technique is to create a blockchain architecture powered by deep learning, which ensures the safety of VANETs. The network architecture consists of three layers: perception, edge computing, and services. The main goal of the initial layer is to protect the privacy of VANET data through blockchain activities. The perception layer processes data using edge computing and cloud services. The service layer ensures data protection by through the blockchain technology and storing information in a public cloud. The last layer focuses on addressing user demands for throughput and Quality of Service (QoS). The proposed framework is good for assessing the dependability of vehicle nodes stored on the blockchain. To accomplish node authentication, an Adaptive and Dilated Hybrid Network (ADHyNet) is used. In this approach, the Residual Long Short-Term Memory (Res-LSTM) with Gated Recurrent Unit (GRU) forms the ADHyNet, where the Random Number Updated Skill Optimization Algorithm (RNU-SOA) is used to optimize the hyperparameters. Finally, the encryption process is carried out using Homomorphic Encryption combined with Elliptic Curve Cryptography (HECC) to secure data. This process ensures that confidential user information is protected against unauthorized access. The functionality of the system is thoroughly assessed and simulated. The suggested technique outperforms well than other approaches in terms of data security in VANET.
- Open Access
- 29 November 2025
- Published by Springer Nature in Journal on Wireless Communications and Networking
- Vol. 2026 (1)
Fuzzy computation on ensemble deep network for the performance of vampire attack detection model in WSN
Context: Wireless sensor network (WSN) is susceptible to vampire attacks. It is a type of denial of service (DoS) attack that drains sensor nodes’ energy, leading to network failure. The study addresses the challenge by detecting these attacks to conserve energy and maintain network functionality. Objective: The research aims to develop a fuzzy ranking-based ensemble deep network (EDN) for vampire attack detection in WSN, thereby extending the network’s lifespan and improving security. Methods: The proposed model involves three phases: data collection, feature selection using the enhanced piranha foraging optimization algorithm (E-PFOA), and attack detection using EDN, which combines long short-term memory (LSTM), recurrent neural network (RNN), gated recurrent unit (GRU), and temporal convolution network (TCN). The final detection outcome is determined through fuzzy ranking. Results: The sensitivity, specificity, and F1-score of the implemented vampire attack detection model were attained with 96.85%, 95.56%, and 96.10% for the k-fold value of 5, and these values are significantly higher than those of conventional approaches. The ROC curve and confusion matrix further validated the model’s effectiveness. Conclusion: The study successfully implemented a fuzzy ranking-based vampire attack detection model that outperforms traditional methods, offering a promising solution for securing WSN against vampire attacks and ensuring the network’s lifetime.
- 29 November 2025
- Published by Springer Nature in Journal on Wireless Communications and Networking
- Vol. 2026 (1)
Open AccessFuzzy computation on ensemble deep network for the performance of vampire attack detection model in WSN
Context: Wireless sensor network (WSN) is susceptible to vampire attacks. It is a type of denial of service (DoS) attack that drains sensor nodes’ energy, leading to network failure. The study addresses the challenge by detecting these attacks to conserve energy and maintain network functionality. Objective: The research aims to develop a fuzzy ranking-based ensemble deep network (EDN) for vampire attack detection in WSN, thereby extending the network’s lifespan and improving security. Methods: The proposed model involves three phases: data collection, feature selection using the enhanced piranha foraging optimization algorithm (E-PFOA), and attack detection using EDN, which combines long short-term memory (LSTM), recurrent neural network (RNN), gated recurrent unit (GRU), and temporal convolution network (TCN). The final detection outcome is determined through fuzzy ranking. Results: The sensitivity, specificity, and F1-score of the implemented vampire attack detection model were attained with 96.85%, 95.56%, and 96.10% for the k-fold value of 5, and these values are significantly higher than those of conventional approaches. The ROC curve and confusion matrix further validated the model’s effectiveness. Conclusion: The study successfully implemented a fuzzy ranking-based vampire attack detection model that outperforms traditional methods, offering a promising solution for securing WSN against vampire attacks and ensuring the network’s lifetime.