Journal of Business Intelligence and Data Analytics

Enhancing User Human computer interaction (HCI) An EDAS Method based Study

Praveen Kumar Kanumarlapudi — 2024-11-05

Human-computer interaction (HCI) is an interdisciplinary branch of research dedicated to studying the interaction between people (users) and computers, including both hardware and software equipment. Initially centered on computers, HCI has evolved to encompass various aspects of information and technology design. It focuses on the development of interfaces that allow humans to communicate effectively with computers. HCI researchers explore how people use computers and strive to create innovative solutions to enhance this interaction. A "Human-computer Interface (HCI)" serves as a vital tool enabling seamless communication between humans and computers.

Research significance: Human-Computer Interaction (HCI) is a critical aspect of human interaction, especially concerning technological design. It focuses on creating intuitive technologies and products by integrating with subscriber design, UI, and UX principles. HCI experts are dedicated to designing and implementing computer systems that prioritize user-friendliness and cater to human needs. By considering human behavior and cognitive abilities, HCI aims to optimize the user experience and ensure seamless interactions between users and technology.

Methodology: Evaluation based on Distance from Average Solution (EDAS) is a promising and effective technique in Multi-Criteria Decision Making (MCDM). It enables the ranking of alternatives by their distances from the mean solution. Generally, shorter distances from the mean are preferred, except when the distance is negative, indicating the ideal solution with the longest distance from the mean.

Alternative: Page Load Speed (ms), User Satisfaction, Task Completion Time (s), Error Rate (%), Number of Features, Memory Usage (MB)

Evaluation preference: Google Chrome, Opera, Mozilla FireFox, Microsoft Edge, Internet Explorer, Lynx

Results: From the result it is seen that Google Chrome is got the first rank where as is the Lynx is having the lowest rank

Keywords: Google Chrome, Opera, Mozilla FireFox, EDAS

Barriers to Supply Chain Management Adoption in Construction an Evaluation Using the ARAS Method

Venkata Pavan Kumar Aka — 2024-11-17

This research explores the main obstacles that impede although SCM has achieved considerable success in manufacturing, its adoption within construction remains limited, despite its potential to boost efficiency, lower costs, and enhance competitiveness. Employing the Aggregate Ratio Assessment (ARAS) method, the study evaluates and ranks five primary barriers to SCM adoption in construction. The analysis identifies "lack of resources" as the most critical barrier (Ki=0.884), followed by "lack of markets for recyclable materials" (Ki=0.795), highlighting significant issues related to resource allocation and sustainable material usage. The third-ranked barrier is the "lack of information sharing between construction firms and suppliers" (Ki=0.721), reflecting communication inefficiencies in the highly fragmented construction supply chain. "Lack of awareness regarding environmental impacts" and "limited commitment from senior management" are ranked fourth and fifth (Ki=0.484 and Ki=0.476, respectively), indicating they are less severe but still relevant challenges. Unlike manufacturing supply chains, which are designed to produce a variety of products for different clients, construction supply chains typically revolve around individual projects, necessitating a more centralized SCM approach.

The findings underscore the importance of enhancing resource availability and developing markets for recyclable materials to advance SCM practices in construction. Furthermore, improving information exchange between construction stakeholders can lead to better supply chain integration. This study enriches the existing literature on construction SCM by applying the ARAS method to quantify the relative significance of key barriers, offering practitioners and policymakers targeted insights for effective intervention. It recommends that construction firms prioritize resource management strategies, foster sustainable material markets, and enhance inter-organizational communication systems. Keywords: Supply chain management, construction industry, ARAS method, sustainability, resource optimization, information exchange

Ada Boost Regression Modelling for Real-Time Audio Signal Processing and Quality Assessment in Secondary Audio Program (SAP) Systems

Kiran Kumar Mandula Samuel — 2024-12-17

This research presents extensive advances in audio processing technologies and computer performance optimization methods. The study includes several innovative approaches to audio signal management, including a novel dual-function monitoring device that simultaneously records separate secondary audio program (SAP) signals through advanced switching algorithms that combine tuner modulator IF and multi-sound integrated circuits. The work extends to the design of an object-oriented database for audio data types that includes dedicated interfaces for storage, retrieval, and manipulation functions along with custom transport protocols that enable continuous streaming capabilities. In addition, the research explores personalized audio delivery systems that can simultaneously provide personalized audio experiences to multiple users through electromagnetic wave encoding and directional audio emission technologies. Performance evaluation metrics, including process parameter signal strength, response time measurements, and resolution accuracy ratings, are integrated with customer satisfaction analysis to establish comprehensive system quality frameworks. The implementation uses advanced machine learning techniques, specifically Ada Boost regression algorithms, for predictive modelling and error correction through iterative weak learning additive modelling. The results show significant improvements in audio signal processing flexibility, spatial audio quality preservation, and real-time data processing capabilities, providing the basic architectures for next-generation multimedia database systems and personalized media experiences.

Strategic Insights into Healthcare Waste Management through the DEMATEL Approach

Sridhar Kakulavaram — 2024-12-18

Proper management of healthcare waste is important for protecting public health and protecting the environment. Implementing proper disposal and treatment methods reduces health risks and helps prevent environmental pollution. Despite its importance, many healthcare facilities face challenges in implementing effective waste management strategies especially in developing regions, struggle with challenges such as weak policies, inadequate waste segregation, improper disposal techniques, and limited financial resources. Adopting sustainable waste management solutions such as steam disinfection, microwave sterilization, and chemical disinfection can improve efficiency while reducing reliance on landfill and incineration. Improving regulations, raising awareness, and promoting environmentally friendly technologies are critical to establishing A safe and sustainable system for managing healthcare waste.Research Magnificence: Healthcare management research plays a vital role in improving efficiency, improving patient care, and promoting sustainable healthcare practices. Through thorough analysis, it helps identify existing challenges, evaluate policies, and develop innovative strategies for effective healthcare management.

Methodology: Research methodology in healthcare management follows a structured approach to collecting, analyzing, and evaluating data. It combines both qualitative and quantitative techniques, including surveys, interviews, case studies, and statistical analysis, to examine healthcare policies, resource allocation, and waste management practices. Alternatives Incineration: In this study, incineration was ranked as the least preferred option due to several drawbacks. Steam sterilization: Steam sterilization was identified as the most effective approach, followed by microwave sterilization. Microwave: Currently, healthcare waste in Qazvin is disinfected using autoclave, hydrolase, and chemical devices, which are either locally produced or imported.SteamSterilization: The most suitable waste disposal methods for Qazvin include irradiation, microwave sterilization, autoclaving (steam sterilization), chemical disinfection, sanitary landfill, and incineration, which are among the most commonly used techniques.Chemical Disinfection: Waste disposal methods considered most suitable for Qazvin include Irradiation, microwave treatment, autoclaving (steam sterilization), chemical sterilization, sanitary landfill, and incineration.

Conclusion: Effective healthcare management is essential to improve service delivery and ensure safety patient well-being, and promoting environmental sustainability. This research emphasizes the importance of well-defined policies, optimal resource allocation, and innovative waste management approaches to strengthen healthcare systems. Result: The study's findings highlight both challenges and opportunities for progress in healthcare management, particularly in policy implementation, resource allocation, and waste management. The results show that healthcare facilities with well-structured management systems achieve higher efficiency, improved patient safety, and improved environmental sustainability.

Key Words: Health administration, guidelines, resource allocation, medical waste management, patient well-being, operational efficiency, environmental responsibility, compliance, medical institutions, community health.

From Traditional to AI-Driven Risk Assessment: An SPSS-Based Statistical Investigation of Machine Learning Applications in Property and Casualty Insurance

Sudhakara Reddy Peram — 2024-12-17

The property and casualty (P&C) insurance industry is undergoing a transformative shift from traditional rigid risk assessment methods to AI-driven predictive models. This study examines the integration of artificial intelligence and machine learning technologies in insurance risk management, moving beyond conventional actuarial models that are often linear, paper-based, and time-consuming. The research focuses on how AI can facilitate continuous, real-time risk assessment and monitoring, particularly in healthcare, where personalized care and precision medicine are gaining importance. Key variables analysed include AI integration levels, insurance types, data sources, regional variations, regulatory readiness, customer demographics, risk prediction accuracy, claims fraud detection capabilities, cost reduction potential, customer trust factors, and compliance levels. The method uses SPSS statistical analysis to explore these multifaceted relationships across different insurance sectors and geographies. The findings indicate that AI-powered systems significantly improve the effectiveness of risk management approaches by providing immediate alerts to anomalies and emerging threats, while improving fairness and transparency by reducing human biases associated with traditional methods. This technological advancement represents not just an operational improvement, but also a strategic paradigm shift in how insurers perceive, access and manage risk in today’s rapidly evolving digital world.

Algorithmic Framework for Retail Media Optimization and Consumer Engagement Enhancement

Divya Soundarapandian — 2024-12-17

Abstract: This study explores the growing impact of marketing technology and retail media platforms on modern business strategies. It highlights how data analytics, automation, and digital advertising tools are empowering brands to deliver personalized, scalable, and effective marketing campaigns. Retail media platforms are leveraging first-party data to create new revenue streams and strengthen brand-retailer collaboration. Together, these innovations are transforming customer engagement, improving marketing effectiveness, and shaping the future of digital commerce through better, data-driven decision-making and targeted consumer experiences.

Research Significance: The focus of this research is on understanding how marketing technology and retail media platforms are reshaping digital marketing and consumer engagement. By exploring their integration, the study provides insights into data usage, personalization, and improving advertising performance. It highlights how these platforms are helping businesses achieve higher ROI, improve brand visibility, and build customer loyalty. These findings contribute to strategic decision-making for marketers, helping companies navigate the evolving digital landscape and leverage technology for sustainable competitive advantage.

Methodology: The research adopts a mixed-methods approach that combines qualitative and quantitative analysis to examine the impact of marketing technology and retail media platforms. Secondary data from academic journals, industry reports, and case studies are analyzed to understand trends and best practices. Additionally, surveys and interviews with marketing professionals and retailers provide insights into real-world applications, challenges, and outcomes. This comprehensive methodology ensures a balanced assessment of technology integration, effectiveness, and its impact on consumer engagement and business performance.

Alternative: Input Parameters: Ad Spend USD, Impressions Millions, Click Through Rate (%)

Evaluation Parameter: Output Parameter: Sales Revenue USD Result: Hash Table is getting first place of the table and Graph is getting last place of the table

Keywords: Ad Spend USD, Impressions Millions, Click Through Rate (%), Sales Revenue USD

Performance Optimization in Large-Scale Database Migration A Multi-Algorithm Assessment

Tirumala Gundala — 2024-12-06

Database migration is a critical process for organizations transitioning to modern computing systems and cloud infrastructures. This study analyzes performance factors influencing migration outcomes using data from 200 migration projects. The research examines the impact of data size (14.35–4,897.32 GB), migration complexity (1–50 steps), and team expertise on overall success rates. Correlation analysis reveals migration complexity has a strong negative relationship with success rates (-0.65), team expertise has a positive effect (0.51), and data size shows a weaker negative impact (-0.36). Random Forest Regression demonstrated the best performance on training data (R² = 0.9767, MSE = 3.7261), followed by Support Vector Regression (R² = 0.8791, MSE = 19.3033) and Linear Regression (R² = 0.8634, MSE = 21.8080). Test results were consistent, with R² values ranging from 0.7590 to 0.8077, confirming model reliability. Findings highlight team expertise as the most influential factor, enabling mitigation of challenges posed by large data volumes and complex migration processes. Migration complexity remains the primary obstacle, underscoring the need for streamlined strategies. These insights provide practical guidance for organizations, emphasizing skilled teams and simplified architectures to optimize success in cloud migration projects.