Category Archives: Uncategorized

Authors: Lavish Kumar, Mohd Aamish, Murad Aalam, Himanshu Kumar Thakur, Ashwani Dubey, Dr. Raj Kumar

Abstract: The use of artificial intelligence (AI) technology for medical image analysis has gained significant importance in contemporary health care systems. AI models assist physicians in diagnosing diseases based on medical images like x-rays, MRIs, CT scans, and ultrasound scans with great precision and fast diagnosis. Nonetheless, medical datasets involve critical and sensitive data about patients, thus raising serious concerns regarding privacy protection in the context of AI applications. The exposure or unauthorized access of medical data can result in severe ethical and legal problems [2], [9], [16]. In this paper, we present a privacy-aware medical image analysis system based on the implementation of convolutional neural networks (CNN), PyTorch framework, Streamlit toolkit, and Differential Privacy technology. CNN is used to extract the features of the medical images automatically and classify the underlying diseases. PyTorch is used for developing the proposed model efficiently, and Streamlit provides a user-friendly interface for physicians. Moreover, the training process is implemented based on differential privacy in order to maintain the privacy of the data. [4], [5]. The proposed framework can support hospitals, diagnostic centers, and telemedicine systems in secure healthcare applications [6], [20].

DOI: http://doi.org/10.5281/zenodo.21063384

Published by: vikaspatanker

Authors: Anjali Kapoor, Dr Mridula

Abstract: In order to facilitate dynamic customization in contemporary learning environments, this study introduces a Smart Autonomous System for Adaptive Student Profiling. To create constantly changing student profiles, the suggested architecture incorporates a variety of educational data sources, such as academic achievement, behavioral patterns, cognitive traits, environmental data, social interactions, and emotional indications. To handle missing data, the system uses KNN-based imputation Convolutional Neural Networks (CNNs) for emotion identification, Principal Component Analysis (PCA) for feature reduction, and XG Boost for academic risk prediction and student profile. A Deep Q-Network (DQN)-based reinforcement learning method that modifies suggestions and interventions based on learner needs enables autonomous decision-making. A hybrid recommendation engine also facilitates optimum learning paths and individualized material distribution. Real-time profiling, ongoing monitoring, proactive intervention, and adaptive feedback mechanisms are made possible by the framework's implementation within a multi-agent architecture. Learner engagement, academic achievement, and early detection of at-risk kids have all improved, according to experimental evaluation utilizing benchmark educational datasets. The findings show that the suggested approach is reliable, scalable, and successful in facilitating intelligent, customized learning environments.

DOI: https://doi.org/10.5281/zenodo.21063202

Published by: vikaspatanker

Authors: Ramanuj Singh, Assistant Professor Hariram Sahu

Abstract: Flexible pavements founded on clay subgrades are prone to premature distress because clay soils frequently combine low bearing capacity with pronounced moisture sensitivity. Expansive clays undergo cyclic swelling and shrinkage that produce heave and cracking, while non-expansive clays exhibit low shear strength and high compressibility that lead to rutting and shear failure. Conventional remedies, such as soil replacement, chemical stabilization, and cohesive non-swelling cushions, are often costly, site-sensitive, or only partially effective, and the empirical California Bearing Ratio (CBR) design framework used across India does not explicitly capture swelling behaviour or the beneficial contribution of reinforcement. This paper presents a detailed literature review of the growing body of laboratory, test-track, and field research on the use of geotextiles and geogrids to reinforce clay subgrades beneath flexible pavements. The mechanisms of tensioned-membrane action in geotextiles and lateral-restraint/reinforced-mattress action in geogrids are examined, together with reported improvements in bearing capacity, rutting resistance, and pavement service life. Findings from Indian and international studies that employ the CBR test as the principal evaluation framework are synthesized, and Indian standards and codes relevant to reinforced-pavement design are discussed. The review identifies a persistent gap between the extensive experimental evidence for the benefits of geosynthetic reinforcement and the absence of a unified, quantitative, bearing-capacity-based design procedure that differentiates between expansive and non-expansive clay subgrade conditions, and concludes with directions for future research in this area.

DOI: https://doi.org/10.5281/zenodo.21885256

Published by: vikaspatanker

Authors: Mr. Kuldeep, Associate Professor Dr. Pramod Kumar

Abstract: The Industrial Internet of Things (IIoT) has transformed industrial ecosystems by enabling real-time monitoring, automation, and data-driven decision-making. Deep learning techniques have emerged as powerful tools for predictive analytics, supporting applications such as anomaly detection, fault diagnosis, and predictive maintenance. However, centralized deep learning approaches introduce significant security and privacy risks, including data leakage, adversarial attacks, and model poisoning. This research proposes a secure hybrid deep learning framework integrating CNN-LSTM with ANFIS, along with federated learning, blockchain, and differential privacy to ensure secure, privacy-preserving, and explainable predictive analytics in IIoT environments. The framework enhances prediction accuracy while maintaining data confidentiality, robustness, and real-time performance.

DOI: https://doi.org/10.5281/zenodo.21060033

Published by: vikaspatanker

Authors: Sk Samsul Hoda, Professor Dr Vipin kumar

Abstract: Bending and focusing magnets, both normal- or super-conducting, are crucial elements for the performance of any particle accelerator. Their design require-ments are always more tighten regarding components’ misalignment and mag-netic properties. This dissertation proposes new solutions for characterizing mag-netic materials and monitoring solenoids’ magnetic axis misalignments. A superconducting permeameter is designed to characterize the new-generation superconducting magnet yokes at their operational temperature and saturation level. As proof of principle, the magnetic characterization of ARMCO®Pure Iron was performed at the cryogenic temperature of 4.2 K and a saturation level of nearly 3 T. A case study based on the new HL-LHC superconducting magnets quantifies the impact of the magnetic properties of the yoke on the performances of the superconducting magnets. A flux-metric based method is proposed to identify the relative magnetic perme-ability of weakly magnetic materials. As proof of principle, the magnetic prop-erties of the ITER TF coils quench detection stainless steel are analyzed. This method is not suitable to test materials with a relative permeability lower than 1.1. Hence, a measurement system based on a new magneto-metric method is conceived and validated employing a standard reference sample. The methods proposed in this thesis are currently employed at CERN’s magnetic laboratory to face an increasing number of requests concerning not only the magnetic charac-terization of materials for magnets but also for shielding systems and compatibil-ity of various components with high magnetic fields. In this thesis, the results of the evaluation of ARMCO®Pure Iron as the yoke of the new LHC superconducting magnets and CRYOPHY as the magnetic shield for the cryomodule prototypes of HL-LHC Crab Cavities are reported. Finally, a new Hall-sensor method is conceived and implemented for monitor-ing the coils alignment in multi-coil magnets, directly during their operation in particle accelerators. The proposed method is suitable even for those cases when almost the whole magnet aperture is not accessible. Requiring only a few mea-surements of the magnetic field at fixed positions inside the magnet aperture, the method overcomes the main drawback of the other Hall sensor-based methods which is having to deal with sturdy mechanics of the moving stages. The method is validated numerically on a challenging case study related to the Solenoid B of the project ELI-NP.

DOI: https://doi.org/10.5281/zenodo.21058750

Published by: vikaspatanker

Authors: Ruchi Gandhi

Abstract: Religious tourism is one of the most important and significant sectors of the Indian tourism industry. It plays a major role in contributing to economic growth, employment generation, infrastructure development, cultural preservation, and regional development. Gujarat is the one of the states from India which has rich religious heritage and some of them are known worldwide such as Somnath, Dwarka, Ambaji, Dakor and Palitana. However, some other religious destinations are underdevelopment though they have tourism potential. One such destination is Kameshwar Mahadev Temple, situated on the bank of the Ambika River in Gadat village, Navsari District, Gujarat. The main purpose of this research is to investigate the potential for sustainable development of Kameshwar Mahadev Temple as a regional religious tourism destination. The study evaluates the temple’s historical significance, geographical setting, tourism resources, visitor characteristics, existing infrastructure, environmental attributes, and socio-economic context. Furthermore, it examines opportunities and constraints associated with tourism development through SWOT analysis and sustainable tourism assessment frameworks. The research uses the mixed-method approach which is based on secondary data, demographic analysis, tourism statistics, infrastructure assessment, policy review, and qualitative evaluation. Findings indicate that Kameshwar Mahadev Temple possesses significant strengths including religious importance, strategic accessibility, natural landscapes, cultural heritage, and an established visitor base. Nevertheless, deficiencies in tourism infrastructure, accommodation facilities, sanitation, destination marketing, and community participation continue to constrain its development potential. This study introduces a master plan for tourism that combines better roads and facilities, environmental protection, community involvement, smart marketing, and teamwork among local authorities. The findings show that focusing on sustainable tourism can turn the Kameshwar Mahadev Temple into a major regional pilgrimage site. This development will boost the local economy and create jobs for residents while fully protecting the surrounding natural resources.

DOI: http://doi.org/10.5281/zenodo.21033316

Published by: vikaspatanker

Authors: Kester Nwinuazor Neemana, Victor Dugbor

Abstract: The interaction between soil and structure (SSI) is a key factor in determination of the dynamic response of foundation systems under cyclic and impact loading. However, most of the previous studies concentrated on the conventional concrete foundations and the effects of other sustainable materials are rarely studied under complex loading condition. Further, few research has focused on the interaction between cyclic and impact loading in a nonlinear-SSI model. The aim of this study is to overcome these shortcomings by developing an advanced nonlinear numerical model for comparing the SSI performance of geopolymer and conventional foundations under combined cyclic and impact loading. The model incorporated soil stiffness degradation, damping characteristics of the soil materials and introduces a novel Damage Accumulation Index (DAI) to quantify progressive deterioration. Using MATLAB simulation approach, transient and steady state dynamic responses were captured in time domain analysis. The results shows that geopolymer foundations outperform the conventional foundations in all the important parameters. In particular, the peak displacement was reduced by ~4.69% while the reduction in velocity and acceleration responses was ~7.62% and the stiffness degradation was ~6.54%, respectively. Moreover, geopolymer foundations have energy dissipation capacity of about 7.35% higher. The proposed DAI model also shows that the cumulative damage was reduced by ~27.33%. These results verify a better damping and better stiffness retention capacity and a better resistance to dynamic loading effects of geopolymer foundations. The study confirms that geopolymer foundation offers a promising sustainable alternative for infrastructure subjected to cyclic, impact, and seismic loading conditions.

DOI: https://doi.org/10.5281/zenodo.21032123

Published by: vikaspatanker

Authors: Rushikesh Falke, Vishal Bagal, Pranav Bartakke

Abstract: Choosing the right career path is a critical decision for students and often requires personalized guidance based on their interests, skills, and abilities. This paper proposes an Intelligent Questionnaire-Based Career Path Recommendation System that utilizes the Random Forest machine learning algorithm to recommend suitable career options. The system collects user responses through a structured questionnaire covering personality traits, technical skills, academic interests, aptitude, and career preferences. The collected data are processed and analyzed using a trained Random Forest model to predict the most appropriate career path. In addition to career recommendations, the system provides guidance on relevant skills and learning resources to enhance career readiness. A web-based interface enables users to complete the assessment and receive recommendations instantly. The proposed approach improves the accuracy and personalization of career guidance compared with traditional counseling methods. The experimental results demonstrate that the system provides reliable recommendations and supports students in making informed career decisions. The proposed framework is scalable and can be extended with real-time job market data and advanced AI techniques in future work.

DOI: https://doi.org/10.5281/zenodo.21031283

Published by: vikaspatanker

Authors: Shivam Namdev, Bhanu Pratap Singh

Abstract: The rapid increase in urbanization, public security challenges, and criminal activities has accelerated the development of intelligent surveillance systems for real-time violence detection and criminal activity identification. Traditional surveillance systems often depend heavily on manual monitoring, which limits detection efficiency, increases response time, and reduces reliability in complex environments. Recent advancements in deep learning, machine learning, computer vision, sensor networks, and predictive analytics have significantly improved automated surveillance capabilities for public safety management. This review presents an intelligent deep learning framework for violence detection and criminal activity identification in smart surveillance systems by analyzing recent developments in convolutional neural networks (CNNs), 3D-CNNs, ConvLSTM architectures, transfer learning, optimization techniques, and sensor-based monitoring systems. The framework integrates video analytics, spatiotemporal feature extraction, facial recognition, object detection, anomaly detection, and predictive threat analysis into a unified intelligent surveillance ecosystem. Furthermore, the study highlights the role of real-time monitoring, smart city technologies, and intelligent decision-support systems in improving public security operations. The review indicates that deep learning-based surveillance frameworks significantly improve violence detection accuracy, reduce false alarms, enhance predictive threat identification, and support automated emergency response systems in modern smart environments.

Published by: vikaspatanker

Authors: Prakash Gahora, Bhanu Pratap Singh

Abstract: The rapid growth of digital communication, cloud computing, Internet of Things (IoT), and smart infrastructures has significantly increased cybersecurity threats and network vulnerabilities. Traditional intrusion detection systems (IDS) often struggle to detect sophisticated and evolving cyber-attacks due to their dependence on static rule-based mechanisms. To address these limitations, Machine Learning (ML) and Explainable Artificial Intelligence (XAI) have emerged as promising solutions for intelligent and adaptive intrusion detection. This research explores the integration of ML and XAI techniques in intrusion detection systems to improve attack detection accuracy, transparency, and real-time threat response. The study reviews various machine learning approaches, including supervised learning, deep learning, reinforcement learning, and federated learning methods used in modern IDS frameworks. Additionally, the role of explainable AI in enhancing trust, interpretability, and decision-making within cybersecurity systems is examined. The proposed approach emphasizes intelligent threat detection, reduced false alarm rates, and improved adaptability in IoT, industrial, and distributed computing environments. The findings indicate that AI-driven IDS frameworks provide efficient and scalable cybersecurity solutions capable of addressing emerging cyber threats while ensuring transparency and reliability in security operations.

Published by: vikaspatanker