Authors: Prathibha M, Dr. Manjunath M, Dr. Evangelin Geetha D

Abstract: This study introduces an intelligent waste detection and sorting system driven by artificial intelligence and deep learning models such as YOLO and TensorFlow. It efficiently classifies waste into categories like recyclable, organic, and hazardous using real-time image analysis. A tailored model trained on waste datasets enables accurate recognition across varying environments. Developed with Python and OpenCV, the system also recommends appropriate disposal methods. Its compact design supports integration into smart bins and industrial workflows. The approach promotes automation in waste segregation, offering a sustainable and scalable solution for effective waste management.

DOI: http://doi.org/

 

Published by: vikaspatanker

Authors: Bhagwan, Assistant Professor Ashwini Sangam

Abstract: Conjunctivitis, a frequent eye illness characterized by inflammation of the conjunctiva – the delicate tissue lining the inner eyelids and covering the eye's white region, may occur from numerous causes such as bacterial or viral agents, as well as allergies. While often non-severe and self-resolving after a few of weeks, it might cause pain and hamper good vision. Harnessing the power of Convolutional Neural Networks (CNNs), a type of artificial intelligence, provides a revolutionary way to diagnose conjunctivitis in ocular pictures. CNNs excel at recognizing subtle picture patterns by learning from an enormous dataset covering both healthy and sick eyes. Trained CNN models exhibit amazing skill in detecting conjunctivitis within fresh photos with great accuracy

DOI: https://doi.org/10.5281/zenodo.15753155

Published by: vikaspatanker

Authors: Research Scholar Venugopal Burugupally, Dr Ajay Swarup

Abstract: Concrete-filled steel tubular (CFST) sections are widely used in structural applications due to their superior mechanical properties, including high axial load capacity, energy dissipation, and fire resistance. This study presents a finite element analysis (FEA) of CFST columns under axial compression using ANSYS Workbench. The numerical model incorporates nonlinear material behavior, including an elastoplastic model with strain hardening for steel and the Drucker–Prager plasticity model for concrete to account for confinement effects. A structured finite element mesh was employed, with solid elements for concrete and shell elements for steel. The analysis considered realistic boundary conditions, applying displacement-controlled axial loading with fixed base constraints. The FEM results were validated against experimental data from the literature, showing a maximum deviation of less than 5% in peak axial load prediction. Load-displacement curves confirmed that steel confinement enhances concrete performance, delaying local buckling and increasing overall strength. Stress distribution analysis indicated effective load transfer between the steel tube and concrete core, while buckling patterns demonstrated progressive load redistribution, preventing sudden failure. These findings confirm that FEM is an effective tool for optimizing CFST designs and predicting their structural response under varying load conditions.

Published by: vikaspatanker

Authors: Professor Dr. Rajendra Singh Kushwah, Ritesh Kumar

Abstract: The most popular method of forecasting SPs throughout the course of history was to make use of statistical models such as moving averages, ARIMA, and the GARCH. This was the most common strategy. It is difficult for these models to accurately predict future SPs due to the fact that financial markets are characterized by their complexity, non-linearity, and unending change. In spite of the fact that these models are able to effectively recognize particular linear trends within historical data, they often have a difficult time accurately predicting events that will occur in the future. As a result of the fact that price changes are impacted by a large variety of different factors, these models do not allow for the precise estimation of future SPs. These models are not particularly accurate as a consequence of this. In recent years, there has been an increase in interest in the topic of financial forecasting in relation to the capabilities of machine learning and deep learning approaches. This attention has brought about a number of interesting developments. The methodologies in question are able to accurately characterize not only the time-dependent patterns that are present in the data, but also the intricate and non-linear linkages that are there. In the field of time series prediction, recurrent neural networks (RNN) and long short-term memory (LSTM) networks, in addition to generalized recurrent units (GRU), have been shown to be successful tools. When it comes to capturing long-range dependencies in supply chains, it is preferable to traditional methods since it is more accurate.

Published by: vikaspatanker

Authors: Raymond Ashieyi-Ahorgah

Abstract: – Africa's abundant mineral resources present unprecedented opportunities for industrial transformation, yet the continent's industrial development remains constrained by inadequate energy infrastructure. This study examines the critical relationship between energy infrastructure development and mineral-based industrialization in Africa from a United States investment perspective. Drawing on recent empirical evidence and policy developments through 2025, we analyze how strategic energy investments can unlock Africa's mineral wealth while creating sustainable industrial value chains. Our analysis reveals that energy infrastructure serves as a fundamental catalyst for mineral-based industrialization, with renewable energy transitions offering particular promise for long-term sustainable development. The findings suggest that U.S. investments in Africa's energy infrastructure, particularly in renewable energy systems, can generate substantial returns while supporting the continent's industrial transformation. We recommend targeted investment strategies that leverage public-private partnerships and address key barriers including financing constraints, regulatory frameworks, and technical capacity limitations.

DOI: https://doi.org/10.5281/zenodo.17212450

 

Published by: vikaspatanker

Authors: Mr. Satish Yadav, Ashish Khandagale, Dr. Jasbir Kaur, Ms. Sandhya Thakar, MS. Ifra Kampoo

Abstract: The exponential growth of social media platforms has generated unprecedented volumes of user-generated content, creating vast repositories of public opinion and sentiment. This research investigates the application of sentiment analysis techniques to social media big data, examining methodologies for extracting, processing, and analyzing emotional insights from large-scale social media datasets. Through a comprehensive review of machine learning approaches, natural language processing techniques, and big data analytics frameworks, this study evaluates the effectiveness of various sentiment classification models when applied to Twitter, Facebook, and Instagram data. Our findings demonstrate that hybrid approaches combining lexicon-based methods with deep learning architectures achieve superior accuracy rates of 89.3% compared to traditional rule-based systems. The research also addresses critical challenges including data preprocessing, feature engineering, and scalability issues inherent in social media sentiment analysis. The implications of this work extend to business intelligence, political analysis, brand monitoring, and public health surveillance applications.

Published by: vikaspatanker

Authors: Kalpesh Desai, Komal Yadav, Jasbir Kaur, Suraj Kanal, Sandhya Thakkar

Abstract: The Internet of Things (IoT) based smart agriculture system is an emerging technology that uses sensors, gateways, cloud platforms, and mobile applications to provide real-time data on weather, soil moisture, crop growth, and livestock health to farmers. This research paper focuses on developing and implementing an IoT-based smart agriculture system. The system offers several benefits: increased efficiency, improved resource management, enhanced crop quality, better decision-making, and remote monitoring. However, potential negative impacts, such as cost, technical skills, dependence on technology, data privacy and security, and environmental impact, must be considered. Careful planning, implementation, and monitoring can help to mitigate these risks and ensure that smart agriculture systems are sustainable and effective. This research aims to give an overview of how predictive analysis and Internet of Things (IoT) devices, along with cloud management and security systems, can be used in agriculture to support multiple crops. It also takes into account the experiences of farmers and highlights the challenges and difficulties that may arise when introducing modern technology into traditional farming practices. By utilizing statistical and quantitative methods, this research seeks to bring about significant and positive changes in the current agriculture system. In simpler terms, this study explores how smart farming can enhance food production, resource management, and labor efficiency, while acknowledging the challenges and benefits of integrating modern technology into traditional farming practices.

 

 

Published by: vikaspatanker

Authors: Rishav Bairagya, Barshan Kundu, Arghya Biswas, Nikhilesh Sil

Abstract: Artificial intelligence (AI)-based emergency response systems provide emerging as key enablers of smart infrastructure safety, improved real-time decision-making, risk assessment, and catastrophe mitigation tactics across multiple domains. The combination of machine learning (ML), deep learning (DL), computer vision, IoT-enabled predictive analytics, and AI-powered robotics in optimising emergency response mechanisms is examined in this systematic literature review, which includes more than 100 eligible papers. In addition to offering a thorough evaluation of technological developments and adoption bar-riers, the study thoroughly investigates AI applications in disaster management, real-time incident detection, healthcare emergency response, industrial hazard prevention, cybersecurity frameworks, and intelligent traffic control. According to the findings, artificial intelligence (AI) has greatly increased automated hazard detection, predictive accuracy, and emergency resource optimisation. These improvements have sped up reaction times, reduced human error, and improved situational awareness in crisis management. Early warning systems for earth-quakes, floods, and wildfires have been made possible by AI-driven predictive analytics models, promoting proactive risk mitigation and catastrophe prepar-edness. Artificial intelligence (AI)-driven computer vision and sensor-based surveillance technologies have enhanced incident detection in real-time emergency response, cutting down on intervention delays and guaranteeing more effective use of emergency resources. Triage automation, geospatial analytics for ambulance dispatch, and AI-enhanced diagnostic technologies have simplified medical crisis management in the healthcare industry, increasing survival rates and cutting down on treatment delays. Furthermore, cybersecurity intelligence systems, robotic automation, and AI-integrated industrial safety frameworks have improved workplace hazard prevention and cyber threat identification. In an emergency, an AI-powered drone-based system facilitates communication between firefighters via light, sound, and a graphical user interface. AI-driven technology solves problems based on situational awareness (SA). Emergency response systems powered by AI improve the security of smart infrastructure. Real-time emergency response optimisation, automated hazard detection, and enhanced risk assessment are all made possible by AI technologies. Real-time fire scenarios are identified using an AI-powered smart firefighting system. During disasters, artificial intelligence (AI) can improve the efficiency of emergency response.AI's role as a crucial enabler of intelligent, data-driven emergency response frameworks, fire fighting, and emergency response will be further reinforced as AI technologies continue to advance and are incorporated into emergency management strategies. This will improve crisis preparedness, real-time intervention capabilities, and global disaster resilience. // This review offers a thorough synthesis of AI's revolutionary role in contemporary emergency management, including insights into technological advancements, constraints, and policy considerations.

 

Published by: vikaspatanker

Authors: Ramlah Ampatuan Duge,, Taya Panigel Adam, Salahudin D. Solaiman

Abstract: – This research determined the level of cooperative learning strategies in group activities, group games, peer mentoring, and problem-solving activities; the students' level of learning outcomes on the 2nd and 3rd quarter of the S.Y. 2023-2024; and the relationship of demographic profile to cooperative learning strategies on students' learning outcomes. Additionally, this study determined the relationship between cooperative learning strategies and learning outcomes; and the significant influence of cooperative learning strategies on students' learning outcomes. Descriptive-correlation research design was utilized to analyze the gathered data from the respondents who were identified using stratified sampling with proportional allocation and complete enumeration. Mean and the spearman's rho with correlation coefficient were used to describe the results and to test the hypotheses of the study correspondingly.Results of the statistical analyses revealed that the majority of the respondents strongly agreed on their cooperative learning strategies in peer mentoring and problem-solving activities. Subsequently, most of the respondents strongly agreed that there are learning outcomes in their subjects such as English, Mathematics, and Science. Findings revealed that cooperative learning strategies have a significant relationship with the learning outcomes in English, Mathematics and Science subjects. Moreover, cooperative learning strategies have a significant influence on learning outcomes in the same subjects.

DOI: https://doi.org/10.5281/zenodo.15738047

 

Published by: vikaspatanker

Authors: Ms. Tanvi Parab, Ms.Saloni Pawar, Dr. Jasbir Kaur, Assistant Professor Ms. Sandhya Thakkar

Abstract: The field of drug discovery has undergone a remarkable transformation with the integration of artificial intelligence (AI) techniques. AI-driven approaches have the potential to significantly accelerate and enhance the drug discovery pipeline by streamlining key stages such as target identification, compound screening, lead optimization, and preclinical prediction. This paper provides a comprehensive overview of the various AI methodologies employed in drug discovery, including machine learning, deep learning, reinforcement learning, and natural language processing. We explore how these technologies are being utilized to analyze complex biological data, predict molecular interactions, and identify promising drug candidates with greater efficiency and accuracy. Furthermore, the paper examines the challenges and limitations associated with data quality, model interpretability, and regulatory acceptance. We also highlight recent advancements and successful case studies demonstrating real-world applications of AI in pharmaceutical research. Ethical implications, data privacy concerns, and the evolving role of human expertise in AI- assisted workflows are critically discussed. Finally, the paper outlines future prospects, emphasizing the potential of AI to revolutionize personalized medicine and accelerate the development of novel therapeutics in a cost-effective and time- efficient manner.

Published by: vikaspatanker