International Journal of Robotics and Machine Learning Technologies

STARGATE: A Spatio-Temporal Adaptive Rule Graph Framework for Anomaly Detection and Repair in Multivariate Temporal Data

Ramachandra Reddy Vangala

Modern cyber-physical systems, IoT infrastructures, financial platforms, and large-scale data analytics pipelines generate massive streams of multivariate temporal data. Such data is frequently affected by measurement noise, inconsistent records, missing values, and structural anomalies. Existing solutions typically address these challenges independently: time-series cleaning methods focus on statistical repairs, approximate nearest neighbor techniques optimize high-dimensional similarity search, temporal knowledge graph approaches detect anomalies in evolving relations, and differential privacy frameworks ensure privacy guarantees. However, these approaches remain fragmented and fail to jointly exploit correlations between temporal dynamics, semantic graph structure, query filtering, and privacy constraints. This fragmentation limits the reliability, interpretability, and scalability of modern data analytics pipelines. In this paper, we propose STARGATE, a novel Spatio-Temporal Adaptive Rule Graph framework that unifies anomaly detection, data repair, and privacy-aware querying for multivariate temporal knowledge graphs. STARGATE constructs a hierarchical rule graph that simultaneously encodes temporal constraints, semantic relations, and attribute labels. The framework integrates adaptive graph traversal for anomaly detection, constraint-based repair strategies for corrupted time-series, and labelaware navigation for efficient query processing. Furthermore, STARGATE introduces a personalized privacy mechanism that adapts repair and detection operations according to user-specific privacy parameters. Extensive experiments demonstrate that the proposed method improves anomaly detection accuracy by up to 28%, reduces repair latency by 40%, and enables. scalable query processing for high-dimensional temporal datasets.

M3-HGMA: A Multi-Modal, Multi-Agent Hierarchical Graph-Mamba Architecture for Explainable and Adaptive Clinical Intelligence

Somasekhar Gubbala

The rapid evolution of large language models, multimodal fusion architectures, genomic foundation models, and multi-agent systems has transformed artificial intelligence applications in healthcare. However, existing solutions remain task-specific, lacking a unified architecture capable of integrating heterogeneous modalities, structural biomedical representations, and decentralized decision intelligence. In this paper, we propose M3-HGMA (Multi-Modal, Multi-Agent Hierarchical Graph-Mamba Architecture), a novel and generalizable framework designed to unify multimodal representation learning, structural graph reasoning, similarityaware embedding aggregation, and decentralized multi-agent coordination for explainable clinical intelligence. M3-HGMA introduces three major innovations: (1) Hierarchical Cross-Modal Graph Fusion (HCGF) that integrates textual, visual, molecular, and genomic representations using cross-attention and graph-based structural encoders; (2) Similarity-Preserving Adaptive Pooling (SPAP), a novel extension of similaritybased embedding aggregation for long-context biomedical signals; and (3) an Explainable Clinical Decision Multi-Agent Layer (ECDMAL) that coordinates predictive modules using transparent, protocol-driven agents. Extensive experimental evaluation across simulated tasks including drug-drug interaction explanation, metabolic state prediction, dermatological classification, segmentationbased response assessment, and hospital resource allocation demonstrates superior performance, interpretability, and scalability compared to state-of-the-art baselines.

Assessing The Role of AI in Robotics A Dematel Methodology Approach

Suresh Pandipati

The future of AI-powered robotics promises a major transformation across various industries, offering remarkable potential to automate complex processes, boost human capabilities, and redefine numerous sectors. By utilizing machine learning, computer vision, and natural language processing, AI-driven robots can interact with their surroundings, make informed decisions, and learn from their experiences, all without direct human oversight. This fusion of robotics and AI enables machines to tackle delicate tasks such as performing surgeries in healthcare, as well as advancing manufacturing and logistics operations. In the near future, AI-powered robots are expected to become increasingly autonomous, adaptable, and proficient in managing tasks within ever-changing environments. Breakthroughs in machine perception will allow robots to better comprehend and respond to the world around them, enhancing safety and effectiveness. Furthermore, advancements in human-robot collaboration may lead to robots working alongside humans in sectors like education, hospitality, and services, improving productivity and user interactions. However, the rise of AI-powered robotics also raises important ethical, legal, and social concerns, such as job loss and privacy issues. To ensure these technologies benefit society, careful integration will be essential. Ultimately, AI-powered robots are set to play a crucial role in shaping the future, transforming how we live and work.

Comparative Analysis of Machine Learning Models for Laptop Price Prediction An Evaluation of Linear Regression, Histogram Gradient Boosting, and XGBoost Approaches

Satyanarayana Ballamudi, Rajendra Kattunga ,Venkata Pavan Kumar Aka

In the rapidly evolving landscape of technology-driven commerce, laptops have become indispensable for both personal and professional applications, with a vast array of models presenting varied specifications and features. The intricate interplay of hardware configurations and pricing frameworks underscores the necessity for robust predictive models that empower consumers and manufacturers to make well-informed choices.  This study delves into the critical challenge of accurately forecasting laptop prices by evaluating three machine learning methodologies: Linear Regression (LR), Histogram Gradient Boosting Regression (HGBR), and XGBoost Regression (XGBR). The research's importance is rooted in its capacity to refine pricing strategies, bolster market efficiency, and provide consumers with deeper insights into the value dynamics associated with different laptop specifications. The study leveraged an extensive dataset comprising 1,303 laptop entries, each characterized by 11 pivotal attributes encompassing processor type, RAM, storage capacity, screen dimensions, and graphical performance. Analytical techniques encompassed correlation assessment, feature significance determination, and comparative evaluation of model efficacy, employing key performance indicators such as the R² coefficient, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). XGBoost demonstrated a clear dominance over other predictive models, securing an R² value of 0.93559 on training data and 0.77524 on testing data. This superiority was further underscored by its markedly lower error margins, with an RMSE of 9,334.9 for training data, starkly contrasting the significantly higher 23,506.3 observed in Linear Regression. A thorough correlation analysis pinpointed RAM and processor specifications as the most decisive variables influencing price determination.  The study asserts that ensemble learning methodologies, particularly XGBoost, represent the most dependable strategy for forecasting laptop prices. Nonetheless, the research highlights key areas for refinement, especially in narrowing the discrepancy between training and testing performance. These insights hold substantial implications for stakeholders in the laptop industry, paving the way for the advancement of more sophisticated predictive frameworks. Furthermore, the study enriches the broader discourse on consumer electronics pricing, emphasizing the transformative role of machine learning in optimizing market dynamics and strategic decision-making.

Innovative Fabrication of Advanced Robots Using the Waspas Method A New Era in Robotics Engineering

Nagababu Kandula

The fabrication of advanced robots represents a pivotal intersection of cutting-edge materials science, artificial intelligence, and innovative manufacturing techniques. These robots are designed to perform complex tasks autonomously, from industrial automation and healthcare assistance to space exploration and disaster response. With breakthroughs in AI, 3D printing, and nanotechnology, modern robots are becoming more intelligent, agile, and capable than ever before. However, the rise of these machines also raises important questions about societal impacts, ethical considerations, and job displacement. The ongoing advancements in robot fabrication promise to reshape industries and redefine the role of automation in human life.

Chatbot for ERP User Support Using AI

Veeresh Dachepalli

The need for effective user assistance methods has increased due to the quick development of enterprise resource planning (ERP) systems. Traditional support models often strain resources and incur significant costs. This paper introduces AI-driven chatbots as a solution to streamline ERP user support, reduce overhead, and enhance user satisfaction. Leveraging advanced transformer-based Natural Language Processing (NLP) models, the proposed chatbot architecture facilitates real-time, accurate query resolution. Through a detailed exploration of methodology, implementation outcomes, and system capabilities, this study demonstrates the potential of AI chatbots to revolutionize ERP user assistance.

Predictive Modeling of Surface Roughness in Manufacturing A Study Using Multiple Machine Learning Techniques

Rakesh Mittapally

This study provides an in-depth study advanced machining processes and their optimization using various machine learning algorithms. The study focuses on key machining parameters such as cutting speed (m/min), feed rate (mm/rev), and cutting depth (mm), and rotation speed (RPM), investigating their effects on surface roughness (Ra) in manufacturing operations. This research addresses emerging challenges in modern manufacturing, particularly in the processing of advanced engineering materials for the aerospace, automotive, and precision industries. These algorithms were selected for their ability to manage complex and non-linear relationships in manufacturing data and for their proven performance in predictive modelling. The study explores how these methods can overcome traditional limitations in process planning and optimization, especially in situations where conventional empirical models are inadequate. Special attention is paid to the theoretical foundations of each algorithm, in which linear regression serves as a basic model, random forest regression provides improved predictive capabilities through ensemble learning, and support vector regression provides robust optimization through its ε-insensitive loss function approach. The research also explores the important relationship between machine parameter optimization and surface quality, emphasizing the importance of parameter optimization in achieving desired surface properties while maintaining production efficiency. This study advances the field by providing a structured methodology machine parameter optimization, particularly relevant to computer-aided process planning and advanced manufacturing processes. These findings have significant implications for industries requiring high-precision manufacturing, providing insights into How can machine learning methods be used effectively? optimize machining processes, reduce production costs, and improve surface quality in modern manufacturing operations.

Enterprise Sales Compensation Optimization: A Machine Learning Framework for Accurate Payout Forecasting

Raghavendra Sunku

This research develops and evaluates machine learning models for predicting sales compensation payouts based on key performance metrics. Using a comprehensive dataset of sales performance indicators, three regression algorithms were systematically compared to identify the optimal predictive model for compensation administration systems. Research Significance: Sales compensation prediction is critical for organizational budgeting, performance management, and ensuring fair compensation structures. Traditional manual calculation methods are prone to errors and inefficiencies, making automated predictive models essential for modern sales operations. This study addresses the need for accurate, data-driven compensation forecasting systems that can enhance transparency and reliability in sales management processes. Methodology: Algorithm Analysis Three machine learning algorithms were implemented and evaluated: Random Forest Regressor (RFR), AdaBoost Regressor (ABR), and Gradient Boosting Regressor (GBR). Models were trained on historical sales data and validated using standard train-test split methodology. Performance was assessed using multiple regression metrics including R², RMSE, MAE, and additional error measures to ensure comprehensive evaluation. Input Parameters: Sales Volume, Number of Deals, Average Deal Size. Output Parameter: Compensation Payout Results: Gradient Boosting Regressor demonstrated superior performance with perfect training accuracy and excellent generalization capability. The analysis revealed strong correlation between sales volume and compensation, validating performance-based incentive structures. All models showed acceptable predictive accuracy, with GBR providing the most reliable compensation forecasting.

Keywords: Sales compensation prediction, machine learning, gradient boosting, performancev

Machine Learning-Based Robotic Control: A Dual Approach Using Linear and Support Vector Regression

Rajender Radharam

The study on Data Robot Implementation explores the development, modeling, and performance evaluation of intelligent robotic systems that combine both traditional control methods and data-driven machine learning approaches. It explores the transition from continuous-time to discrete-time implementations, emphasizing challenges such as stability, computational delays, and measurement effects. The research uses linear regression (LR) and support vector regression (SVR) techniques to model and predict algorithm performance within a robotic system using parameters such as processing speed, sensor accuracy, energy consumption, and algorithm performance. Statistical analysis revealed high model accuracy, with R2 values exceeding 0.98 for both methods, indicating exceptional predictive reliability. LR demonstrated simplicity and interpretability, while SVR demonstrated superior generalization and nonlinear mapping capabilities. Correlation analysis indicates strong positive relationships between system variables, confirming that improved processing capabilities and sensor accuracy significantly improve automation performance. This study underscores the effectiveness of integrating machine learning algorithms into robot control systems to improve automation outcomes, providing a foundation for future implementations in industrial, healthcare, and intelligent manufacturing environments. The results confirm that data-driven modeling provides a robust framework for predicting, adapting, and optimizing robot performance in complex operational environments.

Enterprise-Level Emphasis Operational Analytics: Predicting Healthcare Encounter Resolution Success Using Machine Learning

Nagababu Kandula

Enterprise-Level Emphasis, commonly known as ELE, is a key component of Humana’s healthcare administration infrastructure designed to address one of the most persistent challenges in the health insurance industry – accurate claims processing and encounter data management.[1]  At its core, ELE serves as a specialized operational framework that identifies, investigates, and resolves discrepancies in healthcare encounter records, ensuring that both providers and members receive appropriate reimbursement and coverage while complying with regulatory requirements. The foundation of ELE’S operations lies in its systematic approach to encounter data verification. [2] Healthcare encounters encompass every interaction between patients and healthcare providers, from routine office visits to complex surgical procedures and ongoing chronic care management. Each encounter generates a vast amount of data that must be accurately captured, coded, and processed through insurance systems. When discrepancies arise due to coding errors, incomplete documentation, duplicate submissions, or system processing issues – ELE teams efficiently investigate and take action to resolve these matters. [3] This proactive approach prevents payment delays, reduces claim denials, and reduces the administrative burden on healthcare providers who partner with Humana. ELE’S operating model combines advanced analytics with human expertise to create a comprehensive resolution process. Sophisticated algorithms and data-processing tools scan millions of appointment records and identify patterns that suggest errors or discrepancies.