COA-SSD: A novel chaotic optimization algorithm for enhancement of real-time video surveillance images using single shot detector with MobileNetV2 Vivek Pandiya Raj, K. Radha, S. Harihara Gopalan, C. Venkataramanan, R. Dhanapal, A. Manikandan Systems and Soft Computing, 2025 Video surveillance involves the deployment of cameras to observe and record activities for security and monitoring purposes. This is vital for crime prevention, public safety, and improving operational efficiency across various environments. The rising demand for real-time security and threat detection has increased interest in sophisticated video surveillance systems. However, challenges persist in achieving an accurate automated analysis under diverse environmental and situational conditions. This paper presents an optimization strategy for video surveillance system deployment using a deep-learning algorithm. This strategy combines the base image with information about the behavioral events depicted in the frame sequence and then uses a Sobel filter to detect boundaries. The present study employs a rapid feature point identification algorithm known as the local-peak scale-invariant feature transform (LP-SIFT), which is based on multi-scale local peak features that are invariant to scale and represent multi-scale fluid turbulence. Traditional segmentation methods in video surveillance often lack contextual understanding and temporal consistency, which Modulated Memory Networks aim to address using adaptive memory-driven feature modulation. Next, we used an (SSD) with MobileNet V2 to classify fragments. SSDs can bypass the region proposal network and reduce latency. SSDs incorporate several optimizations such as multiple cooperative functions and base boxes to compensate for the loss of accuracy. To optimize and enhance the accuracy and efficiency of the video surveillance classification, the model parameters were fine-tuned. The Coati Optimization Algorithm (COA) is a metaheuristic algorithm inspired by coati behaviors: their cooperative strategy when attacking iguanas, and their anti-predator and avoidance behavior strategies. To evaluate the LP-SIFT algorithm, we considered datasets with varying scenes, pixel sizes, and distortion levels, across different lighting conditions and environments.
Intelligent Classification System for Thyroid Disease Diagnosis using Medical Imaging Data with Extreme Learning Machine Dency Flora G, C Venkataramanan Proceedings of 8th International Conference on Computing Methodologies and Communication Iccmc 2025, 2025 Thyroid disease, encompassing conditions such as hyperthyroidism and hypothyroidism, it demands an prompt diagnosis to ensure proper detection and treatment. The research develops a deep learning-based framework for detecting thyroid diseases using image datasets. The evaluation of the model was conducted using benchmark datasets from Kaggle and newly curated thyroid ultrasound image datasets from the UCI repository, specifically targeting hyperthyroid and hypothyroid conditions. To enhance image quality and reduce noise, Wiener filtering was applied during the preprocessing stage. For classification, because of its high generalizability and lightning-fast learning speed, the Extreme Learning Machine (ELM) method was chosen. Furthermore, the model’s hyper parameters were fine-tuned using a Hybrid Dragonfly Optimization Algorithm (HDFOA), combining exploration and exploitation capabilities to boost detection accuracy. Showing promise for rapid and dependable thyroid illness detection in clinical settings. The proposed model outperformed the current leading models and achieved a higher accuracy of 97.2% based on evaluation metrics such as accuracy, precision, recall, and F1-score.
Design of a M-shaped microstrip patch antenna for ISM band of applications Loganayaki K, Mohana Priya J, Naveen E, Prathaksana S, Venkataramanan C 2025 IEEE International Students Conference on Electrical Electronics and Computer Science Sceecs 2025, 2025 A micro-strip patch antenna (MPA) is widely applied in the field of wireless communication, due to its smaller size and frequency of operation. An M-shaped MPA is proposed in this paper which operates in the band of 2.4GHz. The rectangular MPA has many slot shapes or strips, such as M-Strip, Zigzag pattern, and multiple circles, to enhance properties like VSWR, return loss(RL), gain, and frequency bandwidth. Microstrip patch antennas are becoming more and more popular because of their small, flat shape. These antennas can be readily applied in spacecraft, airplanes or portable communication devices. This antenna design's VSWR and return loss at 2.4GHz are measured to be 1.06 and -42.463 dB, respectively. The suggested antenna accomplishes downsizing without sacrificing return loss, VSWR, or resonant frequency by using microstrip line feeding.
Graphene Based Solar Photonic Battery for Aircraft-A Finite Element Based 2D Analysis Geetha P, R Sudarmani, Venkataramanan c, Satyam Satyam, Sudarson Nagarajan SAE Technical Papers, 2025 <div class="section abstract"><div class="htmlview paragraph">Over the past decade, significant progress in nano science and nanotechnology has opened new avenues for the development of high-performance photovoltaic cells. At present, a variety of nanostructure-based designs—comprising metals, polymers, and semiconductors—are being explored for photovoltaic applications. Advancements in the understanding of optical and electrical mechanisms governing photovoltaic conversion have been supported by theoretical analyses and modeling studies. Nevertheless, the high fabrication cost and relatively low efficiency of conventional solar photovoltaic cells remain major barriers to their large-scale deployment. One-dimensional (1D) nano materials, in particular, have introduced promising prospects for enhancing photovoltaic performance owing to their unique structural and electronic characteristics. Nanowires, nano rods, and nanotubes exemplify such 1D nanostructures, offering substantial potential to improve photon absorption, electron transport, and charge collection within photovoltaic devices. Graphene, a two-dimensional (2D) atomically thin lattice of carbon arranged in a hexagonal configuration, has emerged as a material of exceptional scientific interest. Its superior mechanical properties are attributed to the sp<sup>2</sup>-hybridized covalent bonds formed by three of the four valence electrons of each carbon atom with neighboring atoms. The remaining delocalized electron contributes to the remarkable optoelectronic properties of graphene, including its exceptionally high carrier mobility, which surpasses that of many conventional conductive materials. Furthermore, graphene thin films can be fabricated through a range of solution-based processing techniques, such as spin-coating, thereby enabling cost-effective, scalable, and versatile production. In the present study, a graphene-based two-dimensional solar cell is modeled and analyzed using the finite element method (FEM) to investigate its photovoltaic behavior and performance characteristics. It is found that the cell potential is 3.85V, VoC is 4.05V, Load cycle current is 4.25V with the surface temperature as 319K. The battery gets saturated at 1500s with graphene. Meanwhile, lithium battery produces cell potential as 3.05V, VoC is 3.05V, Load cycle current is 3.25V. Thus, grapene shows an improvement of 8% in cell potential, 25% in load current value. Lithium battery used for cell phones has the Qn=3500mAh capacity. In graphene, it is 3958mAh with an improvement of 13%.</div></div>
Novel Framework Design of MIMO Antenna for 5G Applications P. Kabilamani, K. P. Porkodi, C Kanmani Pappa, P. Nagarajan, N. Ashokkumar, C Venkataramanan Proceedings of the 5th International Conference on Smart Electronics and Communication Icosec 2024, 2024