Authors: Bhavana N, Kumar Siddamallappa. U, Neelamma. G, Anusha Jajur. J

Abstract: Kidney disease is a significant health concern worldwide, and identifying renal abnormalities at an early stage is essential for preventing disease progression and improving treatment outcomes. Manual interpretation of medical images can be time-consuming and may vary depending on clinical expertise. To address this challenge, this study presents a convolutional neural network (CNN)-based kidney disease classification system that incorporates transfer learning with ResNet101 and VGG16 architectures. The proposed model is trained and evaluated using an augmented dataset of renal ultrasound and CT images categorized into four classes: normal, cyst, stone, and tumor. Image preprocessing and data augmentation techniques are applied to improve image quality, increase dataset diversity, and enhance the model's generalization capability. By utilizing pre-trained deep learning models, the system effectively extracts meaningful image features while reducing training time and computational complexity. Experimental evaluation shows that ResNet101 achieves a classification accuracy of 97.4% while VGG16 achieves 95.8 %. Performance assessment using precision, recall, and F1-score further confirms the reliability of the proposed approach for multi-class kidney disease classification. The developed framework demonstrates the effectiveness of transfer learning for medical image analysis, particularly when labeled datasets are limited. In addition, the system has the potential to support radiologists by providing faster and more consistent diagnostic assistance, leading to improved clinical decision-making. Overall, the proposed approach ResNet101 offers an efficient and accurate solution for automated kidney disease detection and classification using deep learning techniques.

DOI: http://doi.org/10.5281/zenodo.21453407

Published by: vikaspatanker

Authors: Geofrey Nyabuto, Peters Anselemo Ikoha, Samuel Mungai Mbuguah

Abstract: Background: Binary depression screening does not distinguish patients with mild symptoms from those with clinically urgent symptom burden. Among people living with HIV (PLHIV), depressive-symptom severity may reflect nonlinear interactions among anxiety, immune status, treatment adherence, stigma, behavioural exposures, and demographic characteristics. Routine electronic medical records (EMRs) provide an opportunity to model these relationships using computationally reproducible methods. Objective: To develop and internally validate a polynomial regression machine learning model for predicting continuous PHQ-9 depressive-symptom severity among PLHIV using routine HIV-care EMR data. Methods: A cross-sectional patient-level analytical dataset was constructed from 54,301 de-identified EMR records from Bungoma and Busia counties, Kenya. Fifteen clinical, treatment, psychosocial, behavioural, and demographic predictors were processed using training-derived imputation, encoding, log transformation, and standardisation. Stratified training (n=38,010), validation (n=8,145), and held-out test (n=8,146) partitions were used. Ordinary least-squares regression with degree-1, degree-2, and degree-3 polynomial feature expansions was compared using R², adjusted R², mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE). Results: The degree-3 model comprised 816 fitted parameters and achieved the strongest held-out performance: R² 0.753, adjusted R² 0.730, MAE 1.808, MSE 6.359, and RMSE 2.522 PHQ-9 points. The linear model achieved R² 0.729, MAE 1.939, and RMSE 2.641. Mean and median cubic-model residuals were 0.040 and 0.005, respectively, although the maximum positive residual was 15.186, indicating important underprediction in a small number of high-severity cases. The largest reported terms were anxiety × CD4 (β=−0.444) and anxiety² (β=0.413). Conclusions: Degree-3 polynomial regression modestly improved prediction of PHQ-9 depressive-symptom severity over linear and quadratic alternatives. Its average error may support broad risk stratification, but threshold crossing, model complexity, coefficient instability, and severe case underprediction preclude autonomous clinical use.

DOI: http://doi.org/10.61137/ijsret.vol.12.issue4.198

Published by: vikaspatanker

Authors: Ambuj Kumar Misra

Abstract: Accurate crop yield prediction is fundamental to food security planning, resource optimization, and climate resilience policy. This study presents a comprehensive secondary data approach to predicting corn (Zea mays L.) yields across the contiguous United States by integrating multi-source datasets including National Oceanic and Atmospheric Administration (NOAA) climate records, the Soil Survey Geographic Database (SSURGO), USDA National Agricultural Statistics Service (USDA-NASS) historical yield data, and MODIS-derived Normalized Difference Vegetation Index (NDVI) values spanning 2000–2022. We evaluate and compare six predictive modeling frameworks—Linear Regression, Support Vector Regression (SVR), Random Forest (RF), Gradient Boosting (GB), Long Short-Term Memory (LSTM) neural networks, and a hybrid CNN-LSTM ensemble. The hybrid CNN-LSTM model achieved the highest predictive accuracy with an R² of 0.93 and a Root Mean Square Error (RMSE) of 5.4 bu/acre, substantially outperforming the baseline linear regression (R² = 0.61, RMSE = 18.4 bu/acre). Growing Degree Days, summer precipitation, and soil organic matter were identified as the three most influential predictors. Results demonstrate that rigorously curated secondary data, when combined with advanced machine learning architectures, can yield operationally reliable crop forecasts at county to regional scales without requiring expensive field campaigns. Implications for agricultural decision-making, early warning systems, and climate adaptation planning are discussed.

DOI: http://doi.org/10.5281/zenodo.21452245

Published by: vikaspatanker

Authors: Eleanor Watson, Thomas Gray, Chloe Bailey, Ethan Ward, Chaitanya Srinivas, Aneesha Raj

Abstract: The rapid adoption of Artificial Intelligence (AI) is transforming Customer Relationship Management (CRM) from a traditional operational platform into an intelligent, data-driven ecosystem capable of delivering predictive insights, personalized customer experiences, and autonomous decision-making. However, many organizations lack a standardized approach to evaluate their AI readiness and systematically advance their CRM capabilities. This research proposes an Intelligent CRM Maturity Framework for AI-enabled digital enterprises that provides a comprehensive model for assessing organizational maturity across strategic, technological, operational, and governance dimensions. The framework defines progressive maturity levels, beginning with foundational CRM adoption and evolving toward fully autonomous, cognitive CRM ecosystems driven by AI. It incorporates critical assessment areas including AI integration, predictive analytics, intelligent process automation, customer data governance, explainable AI, ethical AI practices, cloud-native architectures, real-time decision intelligence, cybersecurity, regulatory compliance, and continuous innovation. The study further examines the role of emerging technologies such as Large Language Models (LLMs), Generative AI, machine learning, knowledge graphs, conversational AI, intelligent agents, and hyperautomation in enhancing CRM intelligence across sales, marketing, customer service, and executive decision-making processes. Additionally, the proposed framework emphasizes transparency, responsible AI governance, data quality, and security as essential components for sustainable enterprise transformation. By establishing standardized maturity criteria and measurable performance indicators, the framework enables organizations to identify capability gaps, benchmark their current state, prioritize digital transformation initiatives, and optimize AI investments. The proposed model serves as a practical guide for enterprise architects, CRM professionals, business leaders, digital transformation strategists, and researchers seeking to build intelligent, customer-centric, and resilient enterprises capable of adapting to rapidly evolving technological and business environments while achieving improved operational efficiency, enhanced customer engagement, and long-term competitive advantage.

DOI: http://doi.org/10.5281/zenodo.21428659

Published by: vikaspatanker

Authors: Elizabeth A. Howard, Andrew L. Turner, Jonathan M. Reed, Ryan D. Murphy, Chaitanya Srinivas, Aneesha Raj

Abstract: The rapid advancement of artificial intelligence (AI) has transformed Customer Relationship Management (CRM) from a traditional customer data management system into an intelligent platform capable of supporting adaptive decision-making, personalized customer engagement, and continuous business optimization. Among modern AI techniques, reinforcement learning (RL) has emerged as a powerful approach for enabling CRM platforms to learn dynamically from customer interactions and optimize decisions through reward-based feedback mechanisms without relying solely on predefined rules or historical training data. This paper proposes a conceptual framework for developing intelligent self-optimizing CRM platforms through reinforcement learning by integrating customer data management, predictive analytics, intelligent automation, cloud computing, business intelligence, and continuous performance monitoring into a unified enterprise architecture. The proposed framework enables CRM systems to continuously refine marketing strategies, optimize sales recommendations, personalize customer experiences, improve customer retention, automate service operations, and support real-time decision-making while adapting to evolving customer behaviors and changing business environments. Furthermore, the study examines the critical roles of data quality, AI governance, privacy protection, organizational readiness, model interpretability, and ethical AI practices in ensuring successful implementation of reinforcement learning-enabled CRM systems. By leveraging continuous learning and autonomous optimization capabilities, the proposed framework enhances operational efficiency, strengthens customer relationships, improves strategic decision-making, and supports sustainable competitive advantage for AI-enabled digital enterprises. The research contributes to the growing field of intelligent enterprise systems by providing a scalable and adaptable foundation for the next generation of CRM platforms capable of delivering resilient, data-driven, and customer-centric business outcomes in an increasingly dynamic digital economy.

DOI: http://doi.org/10.5281/zenodo.21428604

Published by: vikaspatanker

Authors: Grace Foster, Natalie Simmons, Lauren Bailey, Megan Scott, Chaitanya Srinivas, Aneesha Raj

Abstract: Artificial Intelligence (AI) is revolutionizing Customer Relationship Management (CRM) by enabling intelligent automation, predictive analytics, personalized customer engagement, and data-driven decision-making. As organizations increasingly adopt AI-augmented CRM ecosystems, ensuring governance, transparency, accountability, fairness, and regulatory compliance has become essential for building trust among customers and stakeholders. While AI-powered CRM platforms enhance operational efficiency and customer experience, they also introduce challenges related to algorithmic bias, explainability, data privacy, security, and ethical decision-making. This paper proposes a comprehensive framework for developing trustworthy AI-augmented CRM ecosystems by integrating AI governance principles, transparency mechanisms, explainable artificial intelligence (XAI), data governance, model lifecycle management, continuous monitoring, risk assessment, and regulatory compliance into enterprise CRM platforms. The proposed framework emphasizes transparent decision-making, human oversight, ethical AI practices, auditability, and continuous performance evaluation to ensure that AI-driven customer interactions remain reliable, accountable, and compliant with evolving legal and organizational standards. Furthermore, the study discusses the architectural components, implementation strategies, governance models, evaluation metrics, and practical challenges associated with deploying responsible AI in modern CRM environments. By embedding governance-by-design principles and explainable AI capabilities into CRM ecosystems, organizations can enhance customer trust, improve decision quality, mitigate operational and compliance risks, strengthen data security, and achieve sustainable digital transformation. The proposed framework provides a scalable foundation for developing intelligent, transparent, and ethically governed CRM systems that support long-term business growth, responsible innovation, and superior customer relationship management.

DOI: http://doi.org/10.5281/zenodo.21428428

Published by: vikaspatanker

Authors: David Cooper, Nicholas Turner, Ryan Peterson, Lauren Bailey, Chaitanya Srinivas, Aneesha Raj

Abstract: The rapid advancement of Large Language Models (LLMs) and Knowledge Graphs (KGs) is transforming Customer Relationship Management (CRM) into an intelligent, context-aware, and data-driven enterprise ecosystem. Traditional CRM systems primarily rely on structured customer data, predefined business rules, and conventional analytics, which often struggle to capture complex customer relationships, interpret unstructured information, and provide personalized, real-time decision support. Recent developments in generative artificial intelligence, semantic technologies, and enterprise automation have created new opportunities to build intelligent CRM platforms capable of understanding customer intent, reasoning over interconnected business knowledge, and autonomously supporting sales, marketing, and customer service operations. This paper presents a comprehensive framework for intelligent CRM by integrating Large Language Models, Knowledge Graphs, and AI-driven enterprise services into a unified architecture. The proposed framework combines natural language understanding, semantic knowledge representation, contextual reasoning, retrieval-augmented generation (RAG), intelligent workflow automation, and predictive analytics to improve customer engagement, knowledge discovery, decision support, and business process optimization. Knowledge Graphs provide structured semantic relationships among customers, products, services, and business entities, while Large Language Models enable conversational intelligence, automated content generation, personalized recommendations, and context-aware customer interactions. The framework also incorporates data governance, model orchestration, security, explainability, and continuous learning mechanisms to ensure scalability, reliability, and responsible AI deployment. Furthermore, the study discusses the architectural components, implementation strategies, performance evaluation metrics, practical challenges, and future research directions associated with intelligent CRM ecosystems. By combining the reasoning capabilities of Knowledge Graphs with the language understanding and generative capabilities of Large Language Models, organizations can develop next-generation CRM platforms that deliver superior customer experiences, enhance operational efficiency, improve strategic decision-making, and accelerate enterprise digital transformation.

DOI: http://doi.org/10.5281/zenodo.21428346

Published by: vikaspatanker

Authors: Thomas Ward, Patrick Simmons, Samuel Price, Nicole Bailey, Chaitanya Srinivas, Aneesha Raj

Abstract: Enterprise data modeling plays a critical role in enabling organizations to effectively manage and integrate vast amounts of data across large-scale information systems. As enterprises increasingly rely on distributed architectures, cloud platforms, big data technologies, and heterogeneous data sources, ensuring data consistency, scalability, interoperability, and governance has become a significant challenge. This paper presents a comprehensive framework for enterprise data modeling that integrates conceptual, logical, and physical data models with metadata management, master data management, data governance, and data quality practices to establish a unified and scalable data architecture. The proposed framework supports modern enterprise technologies, including data warehouses, data lakes, distributed databases, microservices, and hybrid cloud environments, while facilitating seamless data integration and standardized information exchange across business domains. It further incorporates governance-driven policies, schema evolution mechanisms, security controls, privacy protection, and regulatory compliance to ensure sustainable data lifecycle management. Additionally, artificial intelligence-assisted metadata enrichment, automated schema discovery, and intelligent data validation techniques are integrated to enhance modeling accuracy, reduce manual effort, and improve operational efficiency. The framework enables organizations to build resilient and flexible enterprise data ecosystems capable of supporting high-volume transactional processing, real-time analytics, and data-driven decision-making. Overall, the proposed approach improves data quality, enterprise interoperability, business intelligence, and organizational agility while providing a practical foundation for digital transformation initiatives and next-generation enterprise information systems.

DOI: http://doi.org/10.5281/zenodo.21428282

Published by: vikaspatanker

Authors: Rajesh Chauhan, Akshay Bhardwaj, Vinay Kumar

Abstract: Writing correct, idiomatic Django Object-Relational Mapper (ORM) code remains a lasting productivity bottleneck for developers, especially developers who are new to the framework or working against unfamiliar schemas. In this paper, we present ORM Forge, a Django web application that utilizes the Anthropic Claude large language model (LLM) to translate natural language descriptions into production-ready Django ORM queries, and describe an empirical evaluation of the underlying natural language to query translation task, based on a publicly available benchmark, distributed as a structured tabular dataset. Instead of reiterating the system overview, we reframe ORM Forge as a research problem in natural-language-to-structured-query (NL2Query) translation, contextualize it within the wider text-to-SQL literature, and perform a quantitative analysis of translation difficulty based on a stratified sample of 120 question-query pairs from a cross-domain text-to-SQL benchmark.Queries were categorized by structural complexity (single-table, join, aggregation, nested/subquery) and manually mapped to their idiomatic Django ORM equivalents to evaluate how readily each SQL construct translates into ORM syntax such as Q objects, F expressions, annotate(), select_related(), and prefetch_related(). The results show that single-table filter and simple join queries translate almost directly (over 90% direct mapping) while nested subqueries and multi-level aggregations require non-trivial restructuring. This confirms that the query complexity is the dominant factor of translation difficulty. These observations motivate the design choices made by ORM Forge: structured JSON output, schema-grounded prompting, and bounded multi-turn refinement, and set the stage for discussing the limitations and future extensions of LLM-assisted ORM tooling.

DOI: http://doi.org/10.5281/zenodo.21427283

Published by: vikaspatanker

Authors: Mariyam Malik, Professor Dr. B Sasi Kumar

Abstract: Artificial Intelligence (AI) is now widely used in decision-making systems developed by technology giants to drive decisions, triggering concerns related to fairness, transparency, and accountability. In response, organizations such as IBM, Microsoft, and Google have published internal AI ethics policies aligned with international standards. Crucially, these policies prove descriptive in nature and lack measurable methods for evaluation. The work envisioned in this paper, purposefully, a quantitative framework to assess the alignment between corporate AI ethics policies and deployed machine learning systems. A supervised learning model is implemented as a case study using a public income prediction dataset containing sensitive demographic attributes. Fairness is evaluated using demographic parity, while model transparency is examined through SHAP-based feature attribution techniques. We apply additional plausible constraints to address privacy and accountability concerns by limiting sensitive identifiers and enforcing a modular, reproducible pipeline. An aggregated Ethics Compliance Score combines multiple ethical dimensions into a single evaluation measure, showing that ethical risks may persist even in accurate models. Unlike prior work that focuses 27 separately on principles or tools, the proposed framework links corporate ethics commitments directly to quantitative system-level indicators, providing a practical basis for internal AI governance.

Published by: vikaspatanker