Daily Archives: May 13, 2026

Authors: Ms. Sanika Sachin Jadhav

Abstract: The growing use of algorithmic management systems in pharmaceutical organisations has changed how employees are supervised, evaluated, and directed. Instead of relying on human managers, these systems use automated data collection and continuous monitoring to govern how employees work. This study looks at both sides of this shift, the operational benefits it produces and the psychological harm it causes. A cross sectional survey was conducted with 250 pharmaceutical professionals, comprising 125 Sales Representatives and 125 Quality Control Analysts. The study measured technostress, psychological contract breach, and perceived algorithmic opacity. Results showed that AI supervision increased output by 18.4% but also led to a 22% rise in technostress scores and a 128% jump in turnover intention among algorithmically managed workers. A strong negative correlation of r = 0.74 (p < 0.01) between algorithmic opacity and organisational trust confirms that lack of transparency is a key mechanism through which algorithmic management damages the employee organisation relationship. Based on these findings, this paper proposes a Human Centric Algorithmic Framework that incorporates Human in the Loop design as a practical governance solution.

Published by: vikaspatanker

Authors: Nishant Singh, Sudhanshu Kumar, Shushant Mani Tripathi, Manisha Pundir

Abstract: With the rapid growth of digital streaming platforms, users are exposed to a vast amount of movie content, making it difficult to identify relevant choices. This paper presents a Content-Based Movie Recommendation System that suggests movies based on their inherent features such as genre, cast, and keywords. The proposed system utilizes Machine Learning techniques, including TF-IDF (Term Frequency–Inverse Document Frequency) or Count Vectorization for feature extraction and Cosine Similarity for measuring similarity between movies. Unlike collaborative filtering methods, the system does not rely on user interaction data, thereby effectively addressing the cold start problem for new users. The model processes a structured movie dataset, converts textual data into numerical vectors, and generates recommendations based on similarity scores. The system is implemented using Python and deployed using Streamlit, providing an interactive and user-friendly interface. Experimental results demonstrate that the proposed system can efficiently generate accurate and relevant movie recommendations in real time. This approach highlights the effectiveness of content-based filtering techniques in enhancing user experience and improving content discovery in modern digital platforms.

Published by: vikaspatanker

Authors: Gaikwad Komal Vitthal, Shaikh Javed Ahmad, Shaikh Aslam Amir

Abstract: The detection and Classification of military aircraft play a crucial role in modern defence and surveillance systems. Traditional radar based approaches are often limited by high cost, environmental constraint, and reduced effectiveness against stealth aircraft. This paper presents a deep learning based approach for automatic military aircraft detection using the YOLOv5 object detection framework. The model is trained on publicly available framework. Experimental results demonstrate that the proposed system successfully detects aircraft such as F-35 and F-16 with confidence score of 0.94 and 0.80, respectively, while achieving an inference speed of approximately 6ms per image. The system provides high accuracy,robustness, and real time capability, Making it suitable for defence surveillance applications.

DOI: https://doi.org/10.5281/zenodo.20155776

Published by: vikaspatanker

Authors: Pragnesh L Thakkar, H C Patel

Abstract: An endeavor has been made to check and investigate the impact of surface roughness on the characteristics of squeeze film between porous annular discs is bestowed in presence of magnetic fluid. The involved Reynolds equation is solved with suitable boundary conditions and expressions for pressure and load carrying capacity are obtained. The expressions are obtained numerically and results are bestowed graphically. It is found that the load carrying capacity increase with increasing magnetization. The impact becomes more sharp when mean (-ve) is involved. In addition, standard deviation and aspect ratio decrease the load carrying capacity this negative effect is going to be minimized by the magnetic fluid lubricant in the case of negatively skewed roughness. Moreover, the investigation makes it clear that a performance of a bearing system is going to be enhanced by choosing suitable values of magnetization parameter and aspect ratio.

DOI: http://doi.org/10.5281/zenodo.20153697

Published by: vikaspatanker

Authors: Harshith S, Nikhilesh G, Raghunandan S, Shashank D S, Mrs. Shwetha S K

Abstract: Crop illnesses remain one of the major sources of farm losses worldwide, and identifying them at an early stage can greatly improve yield protection. Many farmers still depend on manually walking across their fields and inspecting each plant, a process that consumes significant time and can be inconsistent. This study presents a low-cost detection system we developed using an ESP32-CAM to capture images of leaves and transmit them wirelessly to a cloud-based machine learning model. The system analyses each image to determine if the leaf is healthy or affected by a particular disease, and the outcome appears immediately on a web interface accessible to farmers via their phones. Our aim was to design an affordable and easy-to-use solution so that even smallholder farmers without technical expertise can operate it with ease and confidence in their daily farming activities without needing additional support.

DOI: http://doi.org/10.5281/zenodo.20153156

Published by: vikaspatanker

Authors: Keshav Sharma

Abstract: Artificial Intelligence (AI) has become a groundbreaking phenomenon in the modern healthcare system as it allows conducting sophisticated data analysis, predictive modeling, and intelligent decision support. The world is gradually moving towards the adoption of AI technologies in all healthcare facilities to improve the precision of diagnosis, the ease of treatment regimen, the efficiency of work, and the price of healthcare. The methods of diagnosis and treatment of diseases in the healthcare sector are changing with AI-based systems, beginning with the interpretation of medical images up to personalized medicine and robotic surgery. Nevertheless, even though it may have some advantages, the introduction of AI into the health care industry also creates strong doubts regarding the privacy of its data, algorithm bias, transparency, and ethical accountability. This research paper will discuss the use of artificial intelligence in the modern healthcare system through the analysis of its use, advantages, drawbacks, and ethical concerns. The paper discusses the role of machine learning algorithms and deep learning models in detecting disease, patient monitoring, and management in healthcare. Additionally, the paper also critically assesses the issues like data reliability, non-interpretability of AI models, and regulatory issues. The results have underscored that although AI can achieve great success in enhancing healthcare delivery, its use should be supported by effective governance policies and ethical considerations to achieve safe and fair use. The study ends with the recommendation that healthcare authorities, computer scientists, and policy makers need to engage in interdisciplinary collaboration to optimize the advantages of AI and reduce the risks, which may arise.

Published by: vikaspatanker