Daily Archives: November 3, 2025

Authors: T. Sekar, A. Sangeetha

Abstract: The increased number of road accidents associated with violating two-wheeler helmet usage is very alarming and this situation demands the introduction of smart surveillance systems to maintain safety of the people. In this paper, we present the idea of a new system of helmet detection using deep learning algorithms and image processing to detect whether a person is not wearing a helmet automatically or not. The publicly available Kaggle Helmet Detection dataset that includes 7,500 images having annotations of bounding-boxes of helmet head, and person is used by the system. We transform the annotations to a binary classification task – Helmet and No Helmet and use the YOLOv5 object detection model because of its speed and accuracy of the inference. This was done by training the model using transfer learning and optimizing the model with data augmentation techniques to achieve cross generalization under different kinds of light and environmental conditions. Our system is tenable based on the results of experiments because it took into consideration a real-world scenario. The model based on the YOLOv5 had a generally high accuracy of 95.64%, precision of 94.32%, recall of 91.23% and an F1-score of 92.75. Real-time inference can also be done with the system as it can perform 24.56 ms/frame. This will fit it to be used in surveillance systems in a city environment. Also, Deep SORT tracking has been integrated to provide effective tracking without redundancy. This project will be useful in the development of intelligent traffic systems to automate the process of identifying non-helmets with high precision making it useful to law enforcement and citizen and driver safety on the road. It may be extended in the future to have modules of number plate recognition and fine imposing modules to be able to implement all the traffic rules.

Published by: vikaspatanker

Authors: Pushkar Chaudhari, Vaibhav Thakre, Tushar Chaudhari, Tanaya Bhaute, Dr.Rais Khan

Abstract: Port scanning is an essential technique in the arsenal of network security professionals, enabling the identification of active services and potential vulnerabilities on target systems. Despite advances in the field, traditional tools like Nmap and Masscan face limitations in usability, scan speed, resource efficiency, and integration capabilities. This paper presents the development and robust evaluation of an advanced port scanning tool built with Python, applying multi-threading and asynchronous techniques. Through comparative assessments, the proposed tool demonstrates compelling advantages in speed, resource efficiency, and cross-platform support, contributing to both practical and academic applications in cybersecurity.

Published by: vikaspatanker

Authors: M. Anbarasan, Dr. P. Guhan

Abstract: Fruit quality inspection plays a critical role in reducing post-harvest losses and ensuring consumer safety in the agricultural supply chain. Conventional manual inspection techniques are time-consuming, manual and ineffective on larger scales. To address these constraints, the paper introduces a model of identifying fruit quality using deep learning techniques that employ methods of digital image processing. The model exploits two-stage and evaluation procedure including classification and detection operation. We used pre-trained DenseNet networks with transfer learning to divide the fruits into three quality levels of Fresh, Overripe, and Spoiled quality. The method of image preprocessing normalization, filtering, and augmentation were used to increase the model robustness. The DenseNet model had an evaluation accuracy of 97.82%, which was higher as compared to SVM (89.53%) and Random Forest (90.21%) which are the conventional classifiers. Parallel to it, we also tested object detection models such as YOLOv8 to recognize and bound fruits with bounding boxes and label quality. YOLOv8 was revealed to be very fast with an average precision (mAP) of 96.1% and intersection over union (IoU) of 87.3%. It was also calculated that precision, recall, F1-score, and the time of inference were taken across 10 models. Findings confirm the efficiency of deep learning in automating the process of fruit quality determination to consequently deploy real-time applications in separating systems. The presented model is very flexible to other types of agricultural products and compatible with smart farming and automation processes that include retailing. Generally, this work fills the nexus between manual inspection and smart visual systems by making the fruit quality monitoring scalable, consistent, and efficient.

Published by: vikaspatanker

Authors: Kalaji L K, Thyagarajan K

Abstract: This paper presents a MATLAB/Simulink model of Photo Voltaic (PV) using Maximum Power Point Tracking (MPPT) technique and a converter. This model provide 200 V output from a 24 V input. The development of PV model, the integration of the MPPT with an average model of power electronics and the MATLAB implementation are described. The converter section consists of an isolated coupled inductor DC-DC converter. It has high gain. It consist of a dual-voltage doubler circuit. In addition, the energy in the coupled inductor leakage inductance can be recycled via a nondissipative snubber on the primary side. Thus, the system efficiency is improved. It completes the simulation of a PV energy conversion system.

DOI: https://doi.org/10.5281/zenodo.17510805

 

Published by: vikaspatanker

Authors: Mr. Ghanshyam Gajanan Lihankar, Prof. Snehal. V. Raut

Abstract: This research presents the design and development of a cybersecurity framework for AI-based personal assistants. These assistants, such as Alexa, Siri, and Google Assistant, are widely used for daily tasks but face growing risks from cyber threats and data breaches. The proposed system focuses on improving the security, privacy, and trust of AI assistants by identifying potential vulnerabilities and applying defense mechanisms. The paper explains the architecture, which includes threat detection, secure communication, user authentication, and data protection layers. This model ensures safe interaction, protects user information, and defends against unauthorized access or manipulation using advanced security techniques.

Published by: vikaspatanker

Authors: 1Mr. Rushi A. Jadhao, Prof. S. V. Athawale, Prof. S. V. Raut

Abstract: Brain-Computer Interfaces (BCIs) are fundamentally reshaping the landscape of human-machine interaction, rapidly emerging as an advanced generation of Natural User Interfaces (NUIs) that enable direct, non-muscular communication between the human brain and external apparatus. This paper systematically integrates BCI technology with established NUI principles, demonstrating how sophisticated neural control systems facilitate intuitive and natural data interaction within complex digital environments. The analysis encompasses recent technological milestones and practical uses, particularly within healthcare, communication restoration, and advanced assistive technologies, while simultaneously providing a critical evaluation of persistent operational, economic, and ethical challenges. A systemic review of contemporary technological trajectories, especially those anticipated for the 2024–2025 period, strongly suggests that BCIs are poised to become the quintessential example of an NUI, leveraging raw neural signals to permit effortless, volitional control over devices. Consequently, this study positions BCIs as potent, evolving technologies capable of enriching human functions and addressing neurological pathologies, a potential underpinned by stellar advancements in high-fidelity non-invasive EEG systems, Artificial Intelligence (AI)-enhanced signal processing, and integrated multimodal interfaces.

Published by: vikaspatanker