Authors: Ryan Peterson, William Nelson, Joseph Baker, Victoria Adams, Chaitanya Srinivas, Sai Nishil

Abstract: Customer Relationship Management (CRM) systems have become critical platforms for managing customer interactions, business processes, and organizational knowledge in modern enterprises. However, the growing volume, variety, and complexity of customer data often create challenges in deriving meaningful insights and supporting real-time decision-making. Knowledge Graphs have emerged as a powerful technology for representing, connecting, and analyzing heterogeneous data through semantic relationships, enabling organizations to uncover hidden patterns and contextual intelligence. This paper explores the integration of Knowledge Graphs into CRM systems to enhance real-time business intelligence and insight generation. It examines how knowledge graph architectures facilitate data integration, entity resolution, relationship discovery, and semantic reasoning across diverse enterprise information sources. The study further investigates the role of advanced analytics, artificial intelligence, machine learning, and graph-based querying techniques in transforming customer data into actionable business knowledge. Additionally, the paper discusses implementation frameworks, data governance strategies, scalability considerations, security requirements, and integration challenges associated with deploying knowledge graph technologies within CRM environments. The findings indicate that knowledge graph-enabled CRM systems significantly improve customer intelligence, predictive analytics, decision support, personalization, and operational efficiency by providing a unified and context-aware view of enterprise data. The research concludes that the strategic integration of knowledge graphs into CRM ecosystems establishes a robust foundation for intelligent business operations, real-time analytics, and data-driven digital transformation initiatives.

DOI: http://doi.org/10.5281/zenodo.21187613

Published by: vikaspatanker

Authors: Jessica Allen, Nicole Green, Eric Campbell, Justin Perez, Chaitanya Srinivas, Sai Nishil

Abstract: Large Language Models (LLMs) are revolutionizing Customer Relationship Management (CRM) by enabling intelligent, context-aware, and human-like conversational interactions within enterprise platforms such as Salesforce. This research investigates the integration of LLM-driven conversational experiences into Salesforce environments to enhance customer engagement, streamline service operations, and support data-driven decision-making. By leveraging advanced natural language processing, generative AI, and real-time CRM data, conversational systems can provide personalized customer support, automate routine inquiries, assist sales and marketing teams, and improve overall customer experience. The study examines the architectural framework, implementation methodologies, and business value associated with embedding LLM capabilities into Salesforce applications. It also explores critical challenges including data privacy, security, regulatory compliance, model governance, scalability, and responsible AI deployment. Through an analysis of current enterprise practices and emerging technological trends, the research highlights how LLM-powered conversational interfaces improve operational efficiency, increase employee productivity, enhance customer satisfaction, and enable intelligent relationship management. The findings demonstrate that the adoption of generative AI within Salesforce represents a significant step toward next-generation CRM systems that deliver personalized, proactive, and highly responsive customer interactions while supporting organizational growth and digital transformation initiatives.

DOI: http://doi.org/10.5281/zenodo.21187231

Published by: vikaspatanker

Authors: Kevin Walker, Brian Scott, Steven Baker, Aaron Rivera, Chaitanya Srinivas, Sai Nishil

Abstract: The rapid growth of enterprise data assets has increased the need for intelligent data catalog systems that enable efficient data discovery, governance, quality management, and analytical decision-making. Traditional data catalogs often face challenges related to fragmented metadata, inconsistent data definitions, limited visibility across data ecosystems, and manual maintenance processes. This research explores how automated metadata integration and advanced analytics can enhance data catalog intelligence by creating a unified, dynamic, and context-aware framework for managing enterprise data assets. The study examines the role of metadata automation in capturing, classifying, enriching, and synchronizing metadata from diverse data sources, including databases, cloud platforms, data warehouses, business applications, and analytical systems. By leveraging artificial intelligence, machine learning, and metadata analytics, intelligent data catalogs can automatically identify data relationships, assess data quality, improve lineage tracking, and provide actionable insights for business users and data stewards. The research further investigates architectural components, implementation strategies, governance considerations, and scalability challenges associated with intelligent metadata-driven ecosystems. The findings demonstrate that automated metadata integration significantly improves data accessibility, operational efficiency, regulatory compliance, and decision support capabilities while reducing manual effort and governance complexity. As organizations continue to embrace data-driven transformation, intelligent data catalogs powered by automated metadata integration and analytics emerge as essential platforms for maximizing the value, usability, and strategic impact of enterprise data resources.

DOI: http://doi.org/10.5281/zenodo.21186870

Published by: vikaspatanker

Authors: Alexandra Price, Natalie Simmons, Gregory Foster, Stephanie Cook, Chaitanya Srinivas, Sai Nishil

Abstract: The growing complexity of customer interactions and the increasing demand for personalized services have accelerated the adoption of Artificial Intelligence (AI) in Customer Relationship Management (CRM) systems. This research explores the development of AI agent-driven context-aware recommendation systems designed to enhance intelligent customer relationship management through real-time personalization, predictive analytics, and automated decision support. By leveraging advanced AI agents, machine learning algorithms, natural language processing, and contextual data analysis, modern CRM platforms can generate highly relevant recommendations tailored to individual customer preferences, behaviors, purchase histories, and engagement patterns. Context-aware recommendation systems continuously analyze customer interactions across multiple channels to deliver personalized product suggestions, marketing content, service solutions, and engagement strategies that improve customer satisfaction and business performance. The study examines the architectural framework, operational mechanisms, and implementation strategies of AI-powered recommendation systems while addressing critical challenges related to data privacy, scalability, model accuracy, transparency, and ethical AI governance. Furthermore, the research highlights the role of autonomous AI agents in automating customer engagement processes, enhancing decision intelligence, and supporting proactive relationship management. The findings demonstrate that integrating context-aware AI recommendation capabilities into CRM environments significantly improves customer experience, operational efficiency, customer retention, and revenue generation, positioning intelligent recommendation systems as a key component of next-generation digital CRM ecosystems.

DOI: http://doi.org/10.5281/zenodo.21186715

Published by: vikaspatanker

Authors: Divya Krishnan Maniyeri, Professor (Dr) Parshuram Dhaked

Abstract: This bibliographic analytical paper systematically evaluates the theoretical and empirical literature surrounding the integration of Information and Communication Technology (ICT) in secondary school systems, with specific reference to the Indian classroom context. Positioned within the scholarly mandates of the National Education Policy (NEP) 2020 and institutional research criteria at Sabarmati University, this analysis explores the structural mechanisms through which technological treatments influence cognitive academic outcomes and learner dispositions. Historically, educational technology research has been limited by a reliance on un-moderated, direct-effect correlational models, leaving an empirical gap regarding the unique, conditional variables that determine localized instructional success. This paper traces the evolution of educational technology literature from early psychological frameworks to contemporary digital-age learning models, culminating in a thematic assessment of the "no significant difference phenomenon." By synthesizing global meta-analyses alongside domestic quasi-experimental trials, this paper maps the research gaps that justify an experimental investigation into the moderating role of student attitudes within an Aptitude-Treatment Interaction (ATI) framework. The analysis concludes that sustainable technology implementation requires moving past simple device provisioning to prioritize the psychological readiness and attitudinal architecture of the individual learner.

Published by: vikaspatanker

Authors: OM Kute, Yuvraj Narwade, T.B. Faruki

Abstract: Denial of Service (DoS) attacks are one of the most common cyber threats that disrupt network services by overwhelming systems with malicious traffic. Traditional cloud-based detection methods often experience higher latency and increased bandwidth usage, making them less effective for real-time protection. The DoS Attack Detection System Using Edge Machine Learning introduces an intelligent approach that detects malicious network traffic directly at edge devices before it reaches the central server. By leveraging Edge Computing, Machine Learning, and real-time traffic analysis, the system identifies abnormal network behavior with low latency and improved accuracy. This approach reduces server overload, enhances network security, and ensures continuous availability of services while providing a scalable and efficient solution for modern IoT and edge-enabled environments.

Published by: vikaspatanker

Authors: Sneha Kanawade, Dr. Suvarna Patil, Siddhi Kadu, Aniruddha Ojha, Aryan Sahu, Indra Pratap Singh Rajawat

Abstract: Synthetic Aperture Radar is vital remote sensing technology, offering all-weather, day-and- night imaging ca-pabilities. However, its inherent grayscale nature, along with speckle noise, presents significant challenges for interpretation by non-specialists. This review addresses recent advancements in applying deep learning to SAR colorization, a technique aimed at enhancing visual interpretability of these images while preserving unique radiometric properties. The primary motivation is to bridge the gap between complex radar data, intuitive visual analysis, thereby broadening its application in fields like disaster management, environmental monitoring. Major themes covered include critical distinction between grayscale colorization, SAR-tooptical translation, evolution of methodologies from tradi-tional regression to advanced deep learning models, lack of standardized evaluation protocols that has hindered progress. Existing technologies often involve convolutional neural networks, Generative Adversarial Networks (GANs). This review high-lights a proposed methodology centered on conditional GAN within a complete benchmarking protocol utilizing synthetically generated ground truth via intensity-high saturation (IHS) fusion. Key features of this approach include an end-to-end supervised learning framework, use of domain-specific evaluation metrics (Q4, NRMSE, SAM). This advancement holds significant impli-cations for real-time disaster response, contributes to Sustainable Development Goals (SDGs) such as ”Sustainable Cities and Com-munities”, ”Climate Action” by making critical environmental data more accessible, actionable.

Published by: vikaspatanker

Authors: Manjesh Kumar, Assistant Professor Jaya Shukla, Professor Rajnish Bhasker

Abstract: Short-term electric price prediction is important in deregulated power markets and operations as well as planning processes as it aids in the bidding process, risk management and demand response programs. The growing infiltration of renewable energy sources, as well as switching variability of the loads, and market uncertainties, has brought about high nonlinearity and volatility in the electricity price dynamics, which restrain the applicability of traditional forecasting techniques. In solving such challenges, this paper suggests a hybrid deep learning forecasting structure combined with efficient feature selection mechanism to predict short-term price of electricity. The advanced feature selection methods are used in the proposed approach to determine the most informative market, demand, and generation-related variables and to lower the dimensions, as well as to remove redundant information. A hybrid deep learning model, which is a combination of the positive attributes of sequential and nonlinear learning structures, is subsequently trained exploiting the chosen features to absorb intricate temporal variations and price surges. An evaluation of the model by real-world data of the electricity market and a comparison with the traditional statistical methods and individual machine learning are conducted. The simulation outcomes prove that the suggested hybrid structure is more accurate in predictions, more robust, and converges faster, which is indicated by the lower error indicators like MAE, RMSE, and MAPE. In addition, the feature selection step will increase the interpretability and the computational efficiency of models without affecting prediction accuracy. The results attest to the fact that the suggested approach is highly applicable when it comes to short-term electricity price prediction in highly volatile and renewable-based power markets.

Published by: vikaspatanker

Authors: Professor B. R. Shaalini

Abstract: Background: Chronic cigarette smoking induces systemic pathophysiological changes, leading to respiratory muscle deconditioning, impaired pulmonary ventilation, and peripheral muscle fatigue. While Inspiratory Muscle Training (IMT) targets central ventilatory drive, progressive resistance training addresses systemic deconditioning. Aim: To evaluate the combined effectiveness of Inspiratory Muscle Training and DeLorme progressive resistance exercise on respiratory muscle strength, pulmonary function, and functional capacity in active smokers. Methods: This pre-post experimental study enrolled 30 active young adult smokers (aged 20–40 years; mean smoking history: 5.4 ± 1.8 pack-years). Participants underwent a structured 6-week intervention consisting of targeted IMT using a threshold resistance device (40–60% of Maximal Inspiratory Pressure [MIP], 20 min/day, 5 days/week) and DeLorme progressive resistance exercise focused on the bilateral quadriceps femoris muscle groups (3 sets of 10 repetitions at 50%, 75%, and 100% of 10-Repetition Maximum [10RM], 5 days/week). Outcome measures included MIP, spirometric parameters (FEV1, FVC, MVV), functional capacity via the Six-Minute Walk Test (6MWT), and exertional dyspnea via the Borg CR10 Scale. Pre- and post-intervention data were analyzed using a paired t-test. Results: Following the 6-week training protocol, participants demonstrated statistically significant improvements across all primary and secondary parameters (p < 0.001). MIP increased from 68.4 ± 7.2 cmH2O to 84.6 ± 6.8 cmH2O, and 6MWT distance improved by a mean of 74.2 meters. Exertional dyspnea on the Borg scale decreased significantly from 5.8 ± 1.1 to 3.2 ± 0.9. Conclusion: Integrating IMT with DeLorme progressive peripheral resistance exercise significantly enhances respiratory muscle strength, functional exercise tolerance, and ventilatory efficiency in active smokers. This dual-component approach addresses both central respiratory limitations and peripheral skeletal muscle deconditioning.

 

Published by: vikaspatanker

Authors: Brian Levi Okimaru, Betty Mayeku, Humphrey Juma kilwake

Abstract: The transition from junior to senior school under Kenya's Competency-Based Education (CBE) requires learners to select academic pathways that align with their competencies and interests. This transition presents a challenge because pathway selection requires personalized guidance while ensuring the privacy of sensitive student information. Existing educational recommender systems predominantly rely on centralized data processing, exposing learner data to privacy risks and limiting the secure exchange of information across institutions. This study proposes a privacy-preserving personalized pathway recommender system that integrates federated learning, cosine similarity, and Random Forest to support academic pathway recommendation without sharing raw student data. Cosine similarity was employed to model learner competency profiles and measure their alignment with predefined pathway requirements. The resulting similarity scores were incorporated into a Random Forest classifier through feature engineering to improve pathway prediction accuracy. A horizontal federated learning framework enabled multiple schools to collaboratively train the recommendation model by exchanging only model updates while retaining student records locally. The proposed model was evaluated using accuracy, precision, recall, and F1-score. Experimental results showed that integrating cosine similarity with Random Forest improved pathway classification performance, while the federated recommender system achieved an accuracy of 86.54%, outperforming the centralized recommender approach while preserving student privacy. The proposed framework provides an effective and privacy-preserving decision-support tool for personalized academic pathway recommendation within Kenya's Competency-Based Education. The study demonstrates that integrating federated learning with content-based filtering and machine learning can simultaneously enhance recommendation accuracy, personalization, and data privacy in educational environments.

DOI: http://doi.org/10.5281/zenodo.21126397

Published by: vikaspatanker