International Conference on Global Engineering & Management Trends

Web Page Recommendation Using KNN Model and Genetic Algorithm

Authors- Phd Scholar Sumit Sharma, Dr. Pritaj Yadav Associate Professor

Abstract- – Recommender systems are very helpful on the internet that suggest things personalized just for you. They’re great because they make it easier to find what you want without being overwhelmed by too much information. This paper is all about recommending web pages by looking at how people use websites and the content on those pages. They used a smart model called K-nearest neighbors to figure out which pages you might like based on what other people with similar interests have viewed. Then, they made these suggestions even better by using a clever algorithm called the elephant herd optimization. This work tested method on real website data to see if it actually works well. Since people’s internet habits are always changing, it’s important to have a recommendation system that can keep up. The results show that approach, called Elephant Herd-based Web page Recommendation (EHWPP), really makes things work better. In simpler terms, it’s like having a smarter system that helps you find the web pages visitor want in a way that suits their interests.

Credit Card Fraud Detection In Online Transactions Using Machine Learning Algorithms

Authors- M.Tech. Scholar Ramireddy Himabindu, Asst.Prof. N Surendra, Asst.Prof. V Subhasini

Abstract- – People can use credit cards for online transactions as it provides an efficient and easy-to-use facility. With the increase in usage of credit cards, the capacity of credit card misuse has also enhanced. Credit card frauds cause significant financial losses for both credit card holders and financial companies.In this research study, the main aim is to detect such frauds, including the accessibility of public data, high-class imbalance data, the changes in fraud nature, and high rates of false alarm.Machine learning and deep learning algorithms have been used to detect frauds, but there is still a need to apply state-of-the-art deep learning algorithms to reduce fraud losses. Comparative analysis of both machine learning and deep learning algorithms was performed to find efficient outcomes. The European card benchmark dataset was used to evaluate the proposed model, which outperformed the state-of-the-art machine learning and deep learning algorithms..

Prediction of Diabetes with Web-Application using Machine Learning Algorithms

Authors- M.Tech. Student Abbareddi Anjali, Asst. Prof. R Althaf,Asst. Prof. V Subhasini

Abstract- – Manufacturing decisions inherently face uncertainties and imprecision. Fuzzy logic, and tools based on fuzzy logic, allow for the inclusion of uncertainties and imperfect information in decision making models, making them well suited for manufacturing decisions. In this study, we ﬁrst review the progression in the use of fuzzy tools in tackling different manufacturing issues during the past two decades. We then apply fuzzy linear programming to a less emphasized, but important issue in manufacturing, namely that of product mix prioritization. The proposed algorithm, based on linear programming with fuzzy constraints and integer variables, provides several advantages to existing algorithm as it carries increased ease in understanding, in use, and provides ﬂexibility in its application.

Employees Stress Detection With Facial Expressions Using Machine Learning

Authors- M.Tech. Scholar G.V.Devi, Asst.Prof. V Dakshayani, Asst.Prof V Subhasini

Abstract- – The objective of this paper is to apply machine learning and visual processing to identify overworked IT employees. Our technology is an improved version of older stress detection systems that did not include live detection or personal counseling. Stress detection methods that don’t include real-time monitoring or individual counselling are being updated in this research. A survey is used to collect data on employees’ mental stress levels in order to provide effective stress management solutions. In order to get the most out of your employees, this paper will look at stress management and how to create a healthy, spontaneous work environment.

Effects of Dietary Sodium Restriction on Blood Pressure and Cardiovascular Disease Outcome: A Review

Authors- Paradis Honarvar

Abstract- – The effect of reduction of dietary sodium intake on blood pressure has been an important topic for discussion among physicians and researchers. In the past decades, the contribution of excessive sodium intake as a risk factor for developing cardiovascular diseases has remained controversial. The objective of this manuscript was to evaluate current epidemiological studies in order to determine what effects have been observed on the blood pressure of individuals with modest reduction of dietary sodium intake and what impact this dietary modification might have on the future of cardiovascular diseases. The search strategy was based on PubMed/MEDLINE database in order to gather information on the testing hypothesis, which is that a modest reduction of dietary sodium intake has no adverse effects on health and reduces the risk of developing future cardiovascular diseases in both normotensive and hypertensive adults. The search was not limited to the country of origin, however it was limited to only peer-reviewed publications written in English. The result of this review reveals that the majority of the current studies and public guidelines support giving 5-6 g of salt/day for lowering blood pressure in both normotensive and hypertensive adults in order to lower the risk of developing non-communicable diseases, including cardiovascular disease. In conclusion, the data collected from systematic reviews, randomized control clinical trials and prospective studies all suggest that modest reduction of dietary sodium intake has a positive outcome in lowering the risk of developing cardiovascular diseases and attenuating difficulties in both normotensive and hypertensive adult population. Word Count: 250 .

Integrating Blockchain and Cloud to Create Innovative IoT Architecture

Authors- Rishabh Rawat, Sarita, Associate Professor Dr Riya Sapra

Abstract- – The emergence of blockchain, cloud computing, and the Internet of Things (IoT) as a continuous worldview is transformational for the state-of-the-art computerized biological system. IoT systems with expanding reach are the generat massive amounts of data that appear to be properly managed if they are safe, adaptable, and skilled. Despite its versatility and abundance of resources, cloud computing frequently lacks the security that the Internet of Things demands, leaving the devices open to cyber threats. By enhancing the information intelligence, security, and dependability of IoT systems, blockchain technology, with its decentralized and impenetrable record, could close these security gaps. The goal of this research is to see how blockchain technology and cloud computing can be combined [2]. The main issues of scalability, latency, and security can be fully addressed by combining blockchain technology with cloud computing for Internet of Things applications. Blockchain’s decentralized management, transparency, and data immutability can greatly reduce the risks associated with single points of failure in centralized cloud systems. In the meantime, real-time processing of streams of Internet of Things data at scale can be made possible by cloud computing’s vast processing and storage capacity, which may exceed blockchain’s computational limits. Strong networks of IoT devices that can support vital applications in the management of supply chains, smart cities, healthcare, and other fields may result from this collaboration. In order to successfully balance cost, performance, and security, future study must concentrate on maximizing the integration of these technologies.

A Study to Observe the Use of Body Mechanic Practices among Nursing Students While Working in the Clinical Fields

Authors- Shally Sharma, Lecturer Dipak Sethi, Lecturer Jasmeet kaur

Abstract- – Mechanics is concerned with the analysis of the action of forces on object. Body mechanics is the term used to describe the efficient, coordinated and safe use of the body to move objects and carryout the activities of daily living. The major purpose of body mechanics is to facilitate the safe and efficient use of appropriate muscle groups to maintain balance, reduce the energy required, reduce fatigue and decrease the risk of injury. Good body mechanics is very much essential for the nurses. When a person moves, the balance of that person depends on the interrelationship of the centre of gravity and the base of the support. The closer the line of gravity is to the centre of base of support, the greater the person’s stability. Appropriate preparation prevents potential falls and injury and safeguards the person and equipment1.

Characterization and Antimicrobial Investigations of Silver Nanoparticles Encapsulated in Starch Produced from the Aqueous Fruit Extract of Xylopia Aethiopica

Authors: Odimgbe Ezekiel Izudike

Abstract: This research investigates the synthesis and characterization of silver nanoparticles encapsulated in starch, which are derived from the aqueous fruit extract of Xylopia aethiopica, emphasizing their antimicrobial properties. Utilizing a variety of spectroscopic, microscopic, and analytical methods, the physicochemical characteristics of the nanoparticles were clarified, revealing unique morphologies, surface chemistries, and crystalline structures. Following this, antimicrobial assays confirmed the effectiveness of the nanoparticles against several clinically significant microorganisms, such as Escherichia coli, Staphylococcus aureus, and Candida albicans. The findings suggest that the synthesized nanoparticles possess strong antimicrobial activity, with inhibitory effects noted at low concentrations. This research adds to the expanding literature on nanoparticles derived from natural products as viable alternatives to conventional antimicrobial agents, providing valuable insights into their potential uses in biomedicine and environmental health. The results of this study highlight the necessity of comprehending the physicochemical properties of nanoparticles in relation to their antimicrobial efficacy, establishing a foundation for further enhancement and development of nanoparticle-based antimicrobial therapies. Additionally, the use of natural product extracts for the synthesis of nanoparticles presents a sustainable and environmentally friendly method for producing antimicrobial agents, underscoring the potential for interdisciplinary collaboration between nanotechnology and traditional medicine.

DOI:

The Role Of Plants In Treating Diseases Caused By Microorganisms Through Natural Product-based Therapies.

Authors: Etus Patrick Chimuanya, Erienu Kennedy Obruche

Abstract: The increasing resistance of micro-organisms to conventional antibiotics has become a significant global health concern, driving the exploration of alternative antimicrobial agents, particularly plant-based natural products. This study aimed to investigate the potential role of selected medicinal plants in the treatment of infections caused by micro-organisms, with a primary focus on assessing their antimicrobial effectiveness. To achieve this, an experimental research design was employed. Plant materials were carefully collected, processed, and subjected to detailed phytochemical screening to identify the presence of bioactive compounds. Standard laboratory procedures were used to prepare plant extracts, which were subsequently tested against a range of selected pathogenic micro-organisms using the agar well diffusion method. The zones of inhibition formed around the wells were measured, and the results were analyzed statistically to evaluate the antimicrobial activity of each extract. Findings revealed that the selected plant extracts exhibited varying degrees of antimicrobial activity. Significant zones of inhibition were observed against the bacterial isolates, which suggested the presence of active phytochemical constituents, including alkaloids, flavonoids, tannins, and saponins. These results also indicated that some plant extracts exhibited antimicrobial properties comparable to those of standard antibiotics. In conclusion, the study confirms that medicinal plants possess considerable antimicrobial potential, offering promising alternatives for the management of infections caused by resistant micro-organisms. The study recommends further research to isolate, purify, and identify the active compounds responsible for these effects, with the goal of developing them into pharmaceutical products.

DOI: https://doi.org/10.5281/zenodo.18885288

Conceptualizing Decentralized School Governance: Theoretical Models For Community-Led Management In Cooch Behar’s Borderland Elementary Institutions

Authors: Manik Ghosh, Dr. Neeraj Tiwari

Abstract: Decentralized school governance has emerged as a critical response to the limitations of centralized educational systems in diverse, marginalized regions. This conceptual paper explores theoretical models for community-led management in Cooch Behar's elementary institutions, a borderland district in West Bengal marked by historical princely legacies, Rajbanshi indigenous influences, and geopolitical vulnerabilities. The research problem addresses how top-down governance overlooks local agency, exacerbating inequities in border contexts. Drawing on theories of participatory democracy and postcolonial administration, the paper proposes a hybrid framework integrating community councils with indigenous decision-making practices. Key arguments emphasize adaptability to border dynamics, such as migration and cultural hybridity. Contributions include a novel model for decolonizing education management, with implications for India's National Education Policy 2020. This work advances conceptual discourse on equitable governance, highlighting the potential of localized theories to empower borderland communities.

DOI: https://doi.org/10.5281/zenodo.18887146

Integrated Multimodal Artificial Intelligence Using Large Language Models

Authors: Chintu Kodanda Ramu, Dr.Pankaj Khairnar

Abstract: Artificial Intelligence (AI) has advanced rapidly with the development of transformer-based large language models capable of understanding and generating human language. However, traditional language models mainly process textual information and fail to integrate other forms of data such as images and speech. Human communication naturally combines multiple modalities including text, visual perception, and sound. This limitation has encouraged the development of Multimodal Large Language Models (MLLMs), which integrate text, image, and speech understanding within a unified framework. This paper examines multimodal learning approaches, transformer architectures, and multimodal fusion strategies used in modern AI systems. The study highlights how multimodal systems improve contextual understanding, emotion recognition, and human-computer interaction compared to unimodal systems. Experimental observations show that transformer-based multimodal architectures provide improved accuracy and adaptability. The paper also discusses key challenges including computational complexity, data alignment, and scalability. The findings indicate that multimodal large language models represent a major step toward building intelligent systems capable of human-like understanding.

DOI: https://doi.org/10.5281/zenodo.20095914

Privacy-Aware Federated Learning For Distributed Cyber Defense

Authors: Sunil Chandolu, Dr.Pankaj Khairnar

Abstract: The increasing use of cloud computing, Internet of Things (IoT) systems, and distributed enterprise networks has significantly increased cybersecurity risks in modern digital environments. Traditional intrusion detection systems often depend on centralized architectures and signature-based approaches that fail to identify evolving cyber threats effectively. Machine learning techniques have improved threat detection capabilities by enabling automated analysis of network traffic and anomaly detection. However, centralized machine learning models require the collection of sensitive data into a single server, creating concerns related to privacy, scalability, and security. Federated learning has emerged as a decentralized solution that allows collaborative model training without sharing raw data. This paper proposes a federated machine learning framework for privacy-preserving cyber threat detection in distributed network environments. The framework integrates privacy-preserving mechanisms, secure aggregation, and scalable deep learning models to improve intrusion detection performance while maintaining data confidentiality. Experimental analysis demonstrates that the proposed federated approach achieves high detection accuracy, reduced communication overhead, and enhanced privacy compared to centralized learning systems.

DOI: https://doi.org/10.5281/zenodo.20096028

Artificial Intelligence Approaches For Multimodal Emotion Understanding

Authors: Udaya Kumar Nanubala, Dr.Pankaj Khairnar

Abstract: Emotion recognition has become an important research area in artificial intelligence and affective computing. Human emotions are expressed through different modalities such as text, speech, and facial expressions, making multimodal learning essential for accurate emotion detection. This research paper examines transformer-based deep learning models for multimodal emotion recognition and highlights their advantages over traditional machine learning and recurrent neural network approaches. The proposed framework integrates textual, speech, and image data using attention-based fusion strategies to improve contextual understanding and long-range dependency learning. Benchmark datasets such as IEMOCAP, MELD, and CMU-MOSEI are discussed to evaluate the effectiveness of multimodal systems. Experimental analysis indicates that transformer-based architectures outperform conventional CNN and RNN models in terms of recognition accuracy, robustness, and adaptability. The findings suggest that attention mechanisms and multimodal fusion significantly improve emotion recognition performance in real-world applications such as healthcare, education, virtual assistants, and human-computer interaction.

DOI: https://doi.org/10.5281/zenodo.20096085

An Efficient Multimodal Affective Computing Framework For Real-Time Applications

Authors: Preetham Narote, Dr.Pankaj Khairnar

Abstract: Emotion recognition has become an important area of research in artificial intelligence and affective computing because emotions play a major role in human communication and decision-making. Traditional emotion recognition systems mainly depend on a single type of data such as facial expressions, speech, or text. These unimodal approaches often fail to capture the complexity of human emotions and perform poorly in real-world situations. The present study proposes an optimized and adaptive deep learning framework for real-time multimodal emotion recognition using visual, audio, and textual data. The framework integrates Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), transformer architectures, and attention-based multimodal fusion techniques to improve emotion classification accuracy and contextual understanding. Optimization methods such as model pruning, lightweight architectures, and adaptive learning mechanisms are incorporated to reduce computational complexity and support real-time processing. The study also integrates cultural emotion frameworks such as Rasa Theory to improve contextual and cross-cultural emotional understanding. Experimental observations indicate that multimodal systems outperform unimodal systems in emotion recognition tasks by improving robustness, adaptability, and reliability. The proposed framework contributes to affective computing, healthcare systems, intelligent virtual assistants, and human-computer interaction by providing efficient and scalable real-time emotion recognition solutions.

DOI: https://doi.org/10.5281/zenodo.20096182

Biodiversity And Seasonal Distribution Of Zooplankton In Freshwater Systems

Authors: Thumane Anil, Dr.Uttam Chand Gupta

Abstract: Freshwater ecosystems play an important role in maintaining ecological balance, supporting biodiversity, and providing essential resources for human activities. Zooplankton are microscopic aquatic organisms that occupy a central position in freshwater food chains and serve as reliable indicators of water quality and ecosystem health. The present study investigates the seasonal variation of zooplankton diversity and its relationship with physicochemical parameters in the Sathnala Project reservoir located in Adilabad district, Telangana. The study focuses on four major zooplankton groups namely Rotifera, Cladocera, Copepoda, and Ostracoda. Seasonal sampling was conducted during summer, monsoon, and winter periods to analyze species diversity, abundance, and distribution patterns. Physicochemical parameters such as temperature, pH, dissolved oxygen, turbidity, and nutrient concentration were also evaluated. The findings indicate that seasonal variations significantly influence zooplankton communities and water quality characteristics. Higher zooplankton abundance was observed during summer due to increased nutrient concentration and phytoplankton growth, whereas monsoon conditions resulted in reduced diversity because of dilution and increased turbidity. Winter showed moderate abundance with relatively stable ecological conditions. The study confirms that zooplankton communities are effective bioindicators for freshwater ecosystem assessment and water quality monitoring. The research contributes important baseline data for ecological studies and sustainable management of freshwater resources in Telangana.

DOI: https://doi.org/10.5281/zenodo.20096245