Daily Archives: June 19, 2025

Authors: Dr.rajendra Singh HOD, Sunkara Vidya Sagar Satya Vara Prasad, Assistant professor Mr.ravi Kumar

Abstract: With the growing demand for digital transformation in recruitment, traditional methods like email-based job applications and manual screening have become inefficient. This paper proposes a secure, scalable, and role-based Job Portal Web Application that connects job seekers with employers via a modern, full-stack architecture. The system provides separate dashboards for Admin, Employer, and Job Seeker roles, enabling smooth user onboarding, job posting, resume uploads, and application tracking. Technologies used include React.js, Node.js, Express.js, MongoDB, and JWT authentication, with Cloudinary integration for secure file handling. The platform emphasizes data validation, role-based access control, and responsive UI design. Results show efficient user interaction and robust job management. The application is successfully deployed using Render and Vercel for real-time access and scalability.

Published by: vikaspatanker

Authors: Lokesh Lagudu

Abstract: The drug discovery processes necessitate an updated, sophisticated, secure, and scalable data pipeline owing to the rising scale and complexity. This framework describes a continuous, cloud-native architecture capable of comprehensive data governance throughout the entire drug discovery lifecycle. Researchers can achieve real-time, fault-tolerant, and scalable ingestion, integration, transformation, and delivery workflows using Docker, Kubernetes, Apache Kafka, as well as AWS, GCP, or Azure clouds. The framework also solves the silos and reproducibility issues alongside compliance to the industry’s rigorous security policies. It demonstrates orchestration and containerization and modular and reusable pipeline components, expediting the cooperation of computational biologists and bioinformaticians. Beyond just automation, this cloud-native approach provides observability and scalability for fluctuating workloads. In integrating these secure, orchestrated pipelines, pharmaceutical research teams can make agile, well-informed decisions which accelerates innovation in personalized medicine and data-centric therapeutic development.

Published by: vikaspatanker

Authors: B Sandeep Kumar, B Kalyani, Ch Ram Charan, Y Pooja sri, UG Student, Assistant Professor, Dept. of Electronics & Communication Engineering,

 

 

Abstract: This paper proposes an IoT-based Advanced Patients Medication Monitoring System tailored to enhance the accuracy and consistency of medication intake among patients, especially the elderly and chronically ill. The system comprises smart pillboxes embedded with sensors and controlled by microcontrollers such as Arduino or Raspberry Pi. These components are supported by wireless communication (Wi-Fi/Bluetooth) to ensure seamless data transmission to cloud platforms and mobile applications. Real-time monitoring allows caregivers and family members to track medication compliance remotely, while alerts via SMS or apps are sent in case of missed or incorrect doses. The design prioritizes patient safety, remote healthcare delivery, and ease of use.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: Gourav Jangir, Assistant Professor Ms. Neeharika Sengar, Dr. Rajendra Singh

Abstract: With the growth of online learning platforms, ensuring secure and scalable access management is essential. This paper explores the design and implementation of Role- Based Access Control (RBAC) in an EdTech platform, Study Notion, developed using the MERN (MongoDB, Express.js, React.js, Node.js) stack. We analyze how RBAC enhances data security, supports multi-user functionality, and ensures proper resource allocation among students, instructors, and admins.

Published by: vikaspatanker

Authors: Dr. Rajendra Singh, Avnish Kumar, Assistant Professor Ms. Neeharika Sengar,

 

 

Abstract: The exponential growth of online learning platforms has reshaped how coding education is delivered and accessed. This research paper presents the design and development of a scalable, user-friendly, and secure online coding education platform named "Study Notion" using the MERN stack (MongoDB, Express.js, React.js, and Node.js). The project focuses on effective UI/UX design principles, responsive design, and performance optimization to enhance learning outcomes. The platform offers features such as user role management, real-time feedback, secure authentication, course tracking, hands-on projects, and instructor evaluations. Through careful system architecture and scalable design patterns, Study Notion demonstrates how modern web technologies can support flexible and immersive educational experiences.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: Ms. Neeharika Sengar

Abstract: The rapid advancements in generative adversarial networks (GANs) have enabled the creation of highly realistic deepfake videos, posing significant risks in domains such as politics, cybersecurity, and digital media. Detecting such manipulated content has become a pressing challenge. This study investigates deepfake detection using computer vision techniques by training a convolutional neural network (CNN) model from scratch on the publicly available Face Forensics++ dataset. A systematic methodology involving data preprocessing, model training, and evaluation was adopted. The proposed CNN model achieved a detection accuracy of 92.3% on the test set. Furthermore, the model demonstrated strong generalization across various manipulation methods. The results indicate that custom-built CNN architectures, even without transfer learning, can be effective for deepfake detection when paired with rigorous training protocols. Challenges such as data imbalance and overfitting are discussed, and directions for future research are proposed.

Published by: vikaspatanker

Authors: Mayank Sharma, Assistant Professor Ms. Neeharika Sengar, Dr. Rajendra Singh

Abstract: This paper presents 'Study Notion,' a full-stack EdTech web platform developed using the MERN stack (MongoDB, Express.js, React.js, Node.js). It addresses core challenges in online education such as access, personalization, and engagement. The platform offers role-based dashboards, secure payments, instructor analytics, and adaptive learning components. Designed for scalability, the solution empowers learners and educators with an intuitive and effective digital learning space.

Published by: vikaspatanker

Authors: Rajesh Chaurasiya, Vishal Sharma

Abstract: With the rapid growth of artificial intelligence (AI), deep learning models are becoming more complex and require significant computing power, memory, and energy. This makes it difficult to deploy them on devices with limited resources, such as smartphones, embedded systems, and edge devices. To address this challenge, model compression techniques have emerged as a key solution. These methods reduce the size and computational cost of AI models while keeping their performance close to that of the original models. This paper explores four widely used model compression techniques: pruning, quantization, knowledge distillation, and low-rank factorization. Each technique is explained in terms of how it works, its advantages, and the trade-offs it brings. A special focus is placed on pure compression strategies, which avoid external indexing or lookup tables and are better suited for simple and energy-efficient systems. A case study using a convolutional neural network (CNN) shows that combining pruning and quantization can reduce model size by more than 80% and speed up inference time by 30% with only a small loss in accuracy. The study also highlights key metrics for evaluating compressed models, including memory usage, speed, and accuracy. Finally, the paper discusses real-world applications in mobile devices, healthcare, and autonomous systems, along with future directions such as automated compression tools and energy-aware training. Overall, this research supports the development of more accessible, scalable, and eco-friendly AI by making models lighter and more efficient.

DOI: http://doi.org/10.5281/zenodo.15718659

 

Published by: vikaspatanker

Authors: Mohammed Muzaffar, Mohammed Saif, Abdul Baser

Abstract: Nowadays, people pay more attention in artificial intelligence (AI) research, and they try to make Al smarter. The machine learning became a popular subject, especially in object recognition area. Aiming at providing a faster and more accurate plant species recognition program, the author introduced the deep learning and convolution neural network (CNN), and decided to build a CNN project with pycharm, anaconda, kera to find the best way to improve recognition program accuracy and recognition speed. The author tried to change the learning epoch time and learning data set capacity to found the best solution. After tests were finished, the result of output plots analyze is that both adding learning epochs time and extend training image set are all helpful to improve recognition accuracy and speed. As for the effect of increase learning time, it is more obvious in improving accuracy while extend training set size, which is a better method to reduce recognition time. The end of the thesis contained the experiment result, the deficiency of this essay and the future prospect forecast of the machine learning applied in plant area.

Published by: vikaspatanker

Authors: Shashanth. N, Naveen Kumar, Dr Sanjay Dutta

Abstract: Graph isomorphism the problem of finding out whether two graphs are structurally identical or same is one of the most fundamental in various fields such as computer science, chemistry, and biology specifically mathematics and so on .This breakdown deals into several algorithms which are designed to address or evaluate graph isomorphism, some of the algorithms are been studied in this paper those are, is_isomorphic, could_be_isomorphic, fast_could_be_isomorphic, and faster_could_be_isomorphic .Each algorithm preforms using different strategies to evaluate graph similarity, from strict structural comparison to quick preliminary checks based on graph properties. While is_isomorphic uses the VF2 algorithm for precise matching, could_be_isomorphic functions offer faster assessments by evaluating global and local graph properties. However these algorithms possess limitations such as potential false positives and scalability issues for large datasets. The provided flowcharts illustrate the step by step processes involved in each algorithm, which helps in understanding their functionalities. By developing graph isomorphism algorithms researchers can find out new opportunities for applications in network analysis, pattern recognition, and beyond.

Published by: vikaspatanker