PRPrasanna Ravichandran

Prasanna Ravichandran

*This is an algorithmically generated author record based on publicly available information.

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


Prasanna Ravichandran has a total of 39 co-authors. Here are the top co-authors by number of shared publications:

  • R. Rajesh Kanna

    Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, India

    3 shared publications
  • D. Santhakumar

    Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India

    2 shared publications
  • Vinoth Manoharan

    Department of Electronics and Communication Engineering, Saveetha School of Engineering, Saveetha University, Chennai, India

    2 shared publications
  • Alaaudeen Koolayappa Mohamed

    Department of Computer Science and Engineering, Grace College of Engineering, Thoothukudi, Tamil Nadu, India

    1 shared publication
  • Annaram K

    Avinashilingam Institute of Home Sciences: Avinashilingam Institute for Home Science and Higher Education for Women

    1 shared publication
  • Ashokkumar Mani

    Department of Electronics and Communication Engineering, Chennai Institute of Technology, Kundrathur, Chennai, India

    1 shared publication

Latest Publications

  • EFFECTIVE TIME-SERIES ANOMALY DETECTION MODEL FOR INDUSTRY CONTROL SYSTEM USING IOT AND MACHINE LEARNING TECHNIQUES

    by S.S. Subashka Ramesh, Prasanna Ravichandran, R. Lakshmi, N. Meenakshi, R. Rajesh Kanna

    Some examples of essential infrastructure that could be targeted by malicious actors include power plants, water treatment facilities, and manufacturing systems. These actions are the target of industrial control systems (ICS)-based attack detection. By exploiting control logic and communication techniques, these types of attacks can cause operational chaos. To identify instances of suspicious behavior, detection systems employ anomaly detection, machine learning, and signature-based approaches. To prevent operational failures, financial losses, and safety hazards, rapid detection is essential. Recognizing these irregularities properly is crucial to ensuring the safety and reliability of operations. In this article, a hybrid classical model is suggested by combining long short-term memory (LSTM), k-nearest neighbor (KNN), and Pelican Optimization Algorithm (POA) (LSTM-KNN-POA). This model takes the advantage of both KNN classifier and LSTM networks' capacity to learn features over time. POA enhances detection accuracy while lowering false alarms by modifying crucial KNN parameters such as number of neighbors, distance metric, and weight mechanism. To evaluate the model by comparing it to classic classifiers they include naïve Bayes, random forest, AdaBoost, CNN, standalone LSTM, and hybrid LSTM-KNN. The ICS-Anomaly Detection Dataset (ICS-ADD) is utilized for this purpose. The proposed model surpasses competitors with a 97.2% accuracy rate, 96.8% precision, 96.6% recall, 96.7% F1-score, 1.65% false alarm rate (FAR), and 0.986 area under curve (AUC). Additional tests include robustness to noisy input, accuracy during cross-validation, loss curves, and receiver-operating characteristic (ROC) curves. The LSTM-KNN-POA model is a real-world ICS application due to its high predictive accuracy, resilience to input disturbances, and wide generalizability. Findings indicate that the proposed model has the potential to serve as a solid basis for anomaly detection in smart industrial settings.

  • PERFORMANCE ANALYSIS OF EUV HOLOGRAPHIC BEAMFORMING IN VEHICULAR COMMUNICATION NETWORK

    by Alaaudeen Koolayappa Mohamed, Prasanna Ravichandran, Ganesh Kumar Natarajan, Ashokkumar Mani, Manikandan Sankarakutti Palanichamy, Rajesh Kanna Ravi

    This paper presents an analysis of the capacity and bit error rate (BER) in a vehicular communication network that utilizes holographic beamforming at the transmitter. The network operates in urban areas and connects vehicles to the internet through infrastructure. The holographic beamforming technique employed is known as passive electronically steered array (PESA) or phased array, which enables antenna movement control without discrete phase shifters. In optical holography, the reference wave is the traveling wave that transforms into the desired beam, referred to as the object wave. The hologram acts as the structure that transfers energy from the reference wave to the object wave. The pattern of element coupling, which converts guided excitation into a free space wave, is represented by the hologram. In this study, we propose the use of an extreme ultraviolet (EUV) hologram to enhance the system’s performance, particularly in meeting terabyte-level bandwidth requirements. Each base station in the network consists of a large number of antennas. The EUV holographic beamformer serves as a passive system, enabling both reception and transmission using the hologram without the need for antenna-level switching. This eliminates the requirement for separate amplifiers and baseband components at the antenna level because they can be contained within the radio unit. The paper derives closed-form expressions for the capacity and BER of the proposed EUV hologram-based vehicle communication network, considering both base station and access point setups.

  • Multiband reconfigurable MIMO antenna using fractal geometry and PIN diode switches for next generation wireless networks

    by Vinoth M, R Prasanna, Maharajan M S, Rajesh Kanna R

    This study presents the design and analysis of a unique reconfigurable multiband antenna that utilizes reciprocity theory and fractal geometry, with the PIN diode serving as the driving mechanism for compact, advanced wireless communication systems. The proposed antenna design system comprises architectural structures known as Ohmic (Antenna 1) and Sigma (Antenna 2). The simulation of the suggested method was conducted using the HFSS software in Ansys. The analysis and presentation of the simulated and measured findings are conducted. The presented antenna system is designed to radiate at a center frequency of 4 GHz–5 GHz. The findings suggest that the antenna system suggested in this study provides the capability for multi-frequency operation, which is regulated by the ON and OFF states of the PIN diode. Ohmic antenna radiates from 2.3 GHz to 6.8 GHz, achieving 4 frequency bands of operation during the ON state of the diode and covers from 2.5 GHz to 6.85 GHz in the OFF state, enabling three frequency bands of operation. Reciprocally, the Sigma antenna radiates from 2.3 GHz to 6.4 GHz, covering 3 frequency bands of operation during the ON state and achieves 4 frequency bands of operation covering from 2.6 GHz to 6.2 GHz during the OFF state. Furthermore, the separate functionality of the scheme’s antennas is also showcased. The empirical examination of the antenna constructed using a FR4 substrate provided empirical support for the concurrence observed in the simulation outcomes.


  • PATIENT DIABETIC RETINOPATHY DIAGNOSIS AND CLASSIFICATION MODEL USING INTERNET OF THINGS WITH CLOUD COMPUTING

    by T. Ragupathi, R. Prasanna, Rengarajan Chitra

    Recent developments in the healthcare sector allow the Internet of Things (IoT) to connect numerous medical gadgets, sensors, and healthcare professionals, offering quality medical services in remote areas. The use of IoT in healthcare increases patient safety, reduces healthcare costs, boosts the accessibility of healthcare services, and enhances operational efficiency in the healthcare industry. This paper introduces a novel disease diagnosis and prediction model, leveraging IoT and cloud technologies, named TLBO-KELM. This model employs the teaching and learning-based 0ptimization (TLBO) algorithm in conjunction with the kkernel extreme learning machine (KELM). Initially, the model conducts data collection from diverse sources including IoT devices, data repositories, and medicinal records. Subsequently, TLBO-KELM is implemented to identify and envisage diseases using patient data. The TLBO algorithm within KELM aids in parameter tuning-enhancing classification performance. Evaluation against a benchmark diabetic retinopathy (DR) dataset demonstrates superior performance compared to previous models, validating the efficacy of TLBO-KELM.


  • Enhanced Early Brain Tumor Detection Crossing Blood-Brain Barrier through MRI Images Using Berkeley Wavelet-Transformation-Based Segmentation

    by D. Santhakumar, R. Prasanna, M. Sivakumar, S. Aswath, P. S. Arthy, R. Rajesh Kanna

    Brain tumor is one of the reasons for several mortality cases in hospitals. Early detection and diagnosis of brain tumors are necessary to cure the disease early. The extraction of the tumor from the brain's magnetic resonance image (MRI) is considered to be a difficult task when done by clinical experts, and it is also pretty time-consuming. These drawbacks can be overcome by using computer vision-based technologies. The proposed method detects brain tumor crossing the blood-brain barrier (BBB) through MRI images by using Berkeley wavelet transformation (BWT) for segmenting the affected areas. Support vector machine (SVM) is used for classification purpose by which the classification process is divided into two different categories namely, the tumor affected and tumor non-affected parts. Initially, the acquired image is converted to a greyscale from RGB. Then, image segmentation is done. During the image segmentation, morphological operations are carried out. Two morphological operations have been used in the proposed system. They are erosion and dilation. Both these techniques are used for edge detection. In erosion, the pixels are removed from the edges of the tumor image. In dilation, pixels are added at the edges of the tumor images. After the morphological operation, feature extraction is carried out. The features like homogeneity, contrast of the image and the energy might be determined. Then, the image is classified using the SVM classification algorithm. The experimental results have been tabulated and depicted using graphical representations. Comparing to the existing approaches the proposed method is proved to be better in accuracy and efficiency.


  • SMART DRIVING LICENSING SYSTEM AND AUTHORIZATION OF AUTONOMOUS VEHICLE INTEGRATING WIRELESS SENSOR NETWORKS AND IoT

    by D. Santhakumar, M. B. Sudhan, R. Prasanna, S. P. Manikandan, Banu Priya Prathaban, R. Rajesh Kanna, G. Saravanan

    The advent of autonomous vehicles has revolutionized the automotive industry, offering promising advancements in safety, efficiency, and mobility. To integrate these autonomous vehicles into our society seamlessly, it is imperative to establish a robust licensing system that ensures the safe operation of automated vehicles on public roads. This article presents an effective smart Driving Licensing System (SDLS), a digital framework designed to regulate the existing licensing system and authorize licensing for autonomous vehicles. Through a comprehensive assessment process, the system assesses the drivers and the autonomous vehicle’s ability to navigate various road conditions, respond to dynamic environments, and prioritize safety for passengers and other road users. SDLS integrates high-level security through facial and fingerprint verification for identity verification to preserve licensing data. Hacking and unauthorized access to autonomous vehicles is prevented by robust cybersecurity protocols. The key benefits of SDLS include automated data collection, integration of wireless sensor networks (WSN) and Internet of Things (IoT), smart application processing, real-time license checks, cybersecurity measures, automated testing, and digital certification. The proposed system offers a comprehensive approach to safely integrating autonomous vehicles into our transportation ecosystem. The autonomous vehicles are integrated with antennas at rooftops or into bumpers, depending upon the vehicle design which can be connected with the SDLS for signal communication. Furthermore, the SDLS establishes a framework for continuous monitoring and updates, enabling ongoing assessments to keep pace with evolving technology and safety standards.


  • Open Access

    Multi-Band Flexible UWB Antenna for Flexible Electronics and Biomedical Applications

    by Prasanna R, Thamarai Selvi G, Annaram K, Venkatalakshmi K

    This article, proposes a flexible ultra-wide band (UWB) antenna for wearable electronics and biomedical applications. The antenna presented for this work is fabricated on kapton polyimide substrate and the operating frequency band ranges from 2.4GHz to 7.1GHz. The proposed antenna has elliptical radiating element and achieves improved impedance matching characteristics through coplanar waveguide (CPW) fed. A detailed study on choice of substrate is performed and the kapton substrate make the antenna less susceptible for degradation in antenna performance that arises due to bending effects. The measurement and simulated results of the fabricated antenna shows good degree of agreement. The return loss performance of the proposed antenna is greater than − 10dB in all the operating bands with improved gain and directivity. The flexible nature with multiple frequency band of operation and good bending performance makes the proposed antenna appropriate for wearable electronic and biomedical applications.