Browsing by Author "Surendran R."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Deep learning based intelligent industrial fault diagnosis model(Tech Science Press, 2022) Surendran R.; Khalaf, Osamah Ibrahim; Tavera Romero, Carlos AndresIn the present industrial revolution era, the industrial mechanical system becomes incessantly highly intelligent and composite. So, it is necessary to develop data-driven and monitoring approaches for achieving quick, trustable, and high-quality analysis in an automated way. Fault diagnosis is an essential process to verify the safety and reliability operations of rotating machinery. The advent of deep learning (DL) methods employed to diagnose faults in rotating machinery by extracting a set of feature vectors from the vibration signals. This paper presents an Intelligent Industrial Fault Diagnosis using Sailfish Optimized Inception with Residual Network (IIFD-SOIR) Model. The proposed model operates on three major processes namely signal representation, feature extraction, and classification. The proposed model uses a Continuous Wavelet Transform (CWT) is for preprocessed representation of the original vibration signal. In addition, Inception with ResNet v2 based feature extraction model is applied to generate high-level features. Besides, the parameter tuning of Inception with the ResNet v2 model is carried out using a sailfish optimizer. Finally, a multilayer perceptron (MLP) is applied as a classification technique to diagnose the faults proficiently. Extensive experimentation takes place to ensure the outcome of the presented model on the gearbox dataset and a motor bearing dataset. The experimental outcome indicated that the IIFD-SOIR model has reached a higher average accuracy of 99.6% and 99.64% on the applied gearbox dataset and bearing dataset. The simulation outcome ensured that the proposed model has attained maximum performance over the compared methods.Item Encryption with User Authentication Model for Internet of Medical Things Environment(Tech Science Press, 2023) Riya K.S.; Surendran R.; Romero, Carlos Andrés Tavera; Sendil, M. SadishInternet of Medical Things (IoMT) enabled e-healthcare has the potential to greately improve conventional healthcare services significantly. However, security and privacy become major issues of IoMT because of the restricted processing abilities, storage, and energy constraints of the sensors. Therefore, it leads to infeasibility of developing traditional cryptographic solutions to the IoMT sensors. In order to ensure security on sensitive medical data, effective encryption and authentication techniques need to be designed to assure security of the patients and healthcare service providers. In this view, this study designs an effective metaheuristic optimization based encryption with user authentication (EMOE-UA) technique for IoMT environment. This work proposes an EMOE-UA technique aims to accomplish mutual authentication for addressing the security issues and reducing the computational complexity. Moreover, the EMOE-UA technique employs optimal multikey homomorphic encryption (OMKHE) technique to encrypt the IoMT data. Furthermore, the improved social spider optimization algorithm (ISSOA) was employed for the optimal multikey generation of the MKHE technique. The experimental result analysis of the EMOE-UA technique takes place using benchmark data and the results are examined under various aspects. The simulation results reported the considerably better performance of the EMOE-UA technique over the existing techniques.Item Privacy Preserving Reliable Data Transmission in Cluster Based Vehicular Adhoc Networks(Tech Science Press, 2022) Tamilvizhi T.; Surendran R.; Tavera Romero, Carlos Andres; Sendil, M. SadishVANETs are a subclass of mobile ad hoc networks (MANETs) that enable efficient data transmission between vehicles and other vehicles, road side units (RSUs), and infrastructure. The purpose of VANET is to enhance security, road traffic management, and traveler services. Due to the nature of real-time issues such as reliability and privacy, messages transmitted via the VANET must be secret and confidential. As a result, this study provides a method for privacy-preserving reliable data transmission in a cluster-based VANET employing Fog Computing (PPRDA-FC). The PPRDA-FC technique suggested here seeks to ensure reliable message transmission by utilising FC and an optimal set of cluster heads (CH). The proposed PPRDA-FC technique utilizes a moth flame optimization with levy flight based clustering (MFO-LFC) process to identify and form clusters from a suitable set of CHs. The CHs are responsible for monitoring each vehicle in their respective clusters. Simultaneously, the CHs provide the most efficient and secure pathways for message transmission. Finally, a deep neural network (DNN) is used as a classification tool to distinguish between attacker-controlled and real-world automobiles. To evaluate the suggested PPRDA-FC technique’s increased performance, a series of simulations were run and the results analyzed using a variety of metrics. The acquired experimental findings illustrate the suggested PPRDA-FC technique’s superiority to recent state-of-the-art procedures.