DADasaradha Arangi

Dasaradha Arangi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dasaradha Arangi has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Privacy-Preserving Intelligent Framework for Soil-Fertility Prediction in Precision Agriculture

    by Dasaradha Arangi, Neelamadhab Padhy

    Context: Using sophisticated data-driven technologies, precision agriculture has emerged as a crucial strategy for enhancing agricultural production, sustainability, and resource management. In centralized learning approaches, farmers must share their farm data with a central server. This raises issues of data ownership, security, and privacy in distributed agricultural settings. Objective: In this paper, our primary objective is to develop a privacy-preserving intelligent framework for soil-fertility prediction in precision agriculture. This study aims to compare the predictive performance of several intelligent models and assess federated learning’s ability to enable safe, decentralized, and collaborative agricultural analytics. Materials and Methods: This study utilized 10 classical machine learning models (MLs) and five centralized MLP architectures (deep learning (DL) models) and evaluated them using performance metrics such as accuracy, precision, recall, F1-score, and Cohen’s Kappa for soil fertility. We also developed a privacy-preserving intelligent framework, adopting federated MLP training using the FedAvg (federated learning (FL) mechanism) with five clients and 20 communication rounds, using FedAvg (federated averaging aggregation). The dataset was divided into different farms to simulate real-world distributed agriculture systems. Results: From our experimental observations, the Extra Tree (ET) classifier obtained the highest accuracy of 93.94%, an F1-score of 93.99%, and a Kappa value of 0.90%. Similarly, the Shallow MLP model from DLs obtained an accuracy of 93.18% and a Kappa value of 0.8977. The FL framework achieved 84.47% accuracy and a Kappa score of 0.76. In addition, our framework preserves farm-level data privacy and removes the need for centralized data sharing. The experimental work demonstrates that distributed learning is a secure and collaborative option for smart agriculture. We have compared centralized classical ML, centralized MLP, and federated MLP training. The Shallow MLP model with a 128-64 neuron architecture achieved better performance.

  • Human-AI Collaboration and the Renegotiation of Managerial Authority: An Integrative Critical Review with a Multi-Case Analytical Framework for Agentic AI Adoption in Industry

    by Dasaradha Arangi, Sreemanthula Jhansi, Minhaz Husain, Yuvraj Khare, Balveer Singh

    The spread of agentic Artificial Intelligence (AI) systems that can autonomously plan, use tools, and perform multi-step tasks instead of offering single recommendations challenges long-held views on where managerial authority lies within organisations. Using a PRISMA-guided search across databases like Scopus, Web of Science, ABI/INFORM, Google Scholar, and industry-specific repositories, this comprehensive review synthesises research on agentic and generative AI, human-AI cooperation, algorithmic management, trust and explainability, decision-rights theory, and technology adoption. It explores how increasing AI autonomy shifts decision-making, accountability, and control from human managers to computational agents. Rather than merely summarising, the review critically organises findings around a five-stage transition from AI as a tool to an assistant, collaborator, decision agent, and finally an organisational actor, highlighting areas of consensus, debate, and gaps, especially in accountability, managerial discretion, and industry differences in autonomy governance. Drawing on theories such as agency, sociotechnical systems, and adoption models (TOE, TAM, UTAUT), the paper introduces a conceptual multi-case framework comparing agentic AI adoption in sectors such as healthcare, finance, manufacturing, retail, logistics, professional services, and IT. It proposes a model linking key factors influencing authority shifts and posits ten propositions for future testing. The review provides a shared vocabulary for authority shifts in AI contexts, extending control theories into AI environments, and guiding managers, boards, and policymakers in developing delegation, escalation, and accountability strategies. While the framework is conceptual and propositional without empirical validation, it outlines a future research agenda aimed at understanding how organisations can maintain meaningful human oversight as AI agents play a larger decision-making role.

  • Secure and Collaborative Crop Disease Prediction with Federated Deep Learning: Safeguarding Data Sovereignty in Agriculture

    by Sadananda Behera, Neelamadhab Padhy, Rasmita Panigrahi, Pradeep Kumar Mahapatro, Dasaradha Arangi

  • Open Access

    Comparative Evaluation of Machine Learning Classifiers for Breast Cancer Diagnosis: A Comprehensive Statistical Analysis

    by Sambit Subhankar Das, Atal Mahaprasad, Neelamadhab Padhy, Srikant Misra, Rasmita Panigrahi, Pradeep Kumar Mahapatro, Dasaradha Arangi

    Content/Background: Breast cancer is one of the most fatal cancers among women around the globe. The chances of surviving this cancer increase with early tumor detection, which is necessary for effective treatment. Traditional diagnostic techniques are ineffective and time-consuming, and they yield results that may be accurate or inaccurate. Therefore, our primary objective is to determine how a machine learning model can reduce diagnostic errors and provide accurate results. Objective: The main objective of this project is to build an ML-based classification model that can help doctors detect breast cancer early and more accurately. This project also aims to provide an interactive interface for easy access in healthcare settings. Materials/Methods: For this study, twelve machine learning classification algorithms are implemented and tested: Logistic Regression, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, Gradient Boosting, XGBOOST, Naive Bayes, AdaBoosting, Light GBM, CatBoost, and the Artificial Neural Network (ANN). This study used the Wisconsin Breast Cancer Dataset (WBCD) from the UCI ML Repository. It contains 569 patient samples and 30 features. This dataset has the following features: Radius, Texture, Area, Perimeter, Smoothness, Compactness, Concavity, and Fractional Dimension. The target variable is diagnosis, which is categorized as malignant vs. benign. Results: The fifteen models were analyzed, evaluated, and compared using five performance metrics: Accuracy, Precision, Recall, F1-Score, and AUC-ROC. Among the evaluated models, CatBoost, LoGR, and AdaBoost outperformed the others, with an Accuracy of 97.%, Precision of 97%, Recall of 97%, and AUC-ROC score of 99%. The AUC-ROC is nearly 99%, and the model has a high ability to differentiate between malignant and benign tumors.


  • Open Access

    Federated Edge Learning for Distributed Weed Detection in Precision Agriculture Using Multimodal Sensor Fusion

    by Dasaradha Arangi, Neelamadhab Padhy

    In this work, our goal is to develop a privacy-preserving distributed weed detection and management system. The proposed work integrates FEL (Federated Learning) and deep learning with multi-modal sensor fusion to enhance the model’s performance while minimising data transfer, latency, and energy consumption. In this study, we used multimodal sensors, such as LiDAR (Light Detection and Ranging), RGB (Red–Green–Blue) cameras, multispectral imaging devices, and soil moisture sensors placed in controlled agricultural plots. Deep learning models, such as Convolutional Neural Networks (CNNs), LSTM–CNN hybrids, and Vision Transformers, were trained using standardized parameters. A proposed Federated CNN (FedCNN) was deployed across multiple edge devices, each locally trained on sensor data without exchanging raw data, using FedAvg and FedProx algorithms. The experimental work revealed that the model FedCNN performed well in comparison to other models and achieved the highest accuracy of 94.1%, precision of 94.3%, recall of 93.9%, F1-score of 94.1%, and AUC of 94.1% during hybrid fusion strategies. We compared the centralized and federated learning performance.


  • Open Access

    Internet of Things-Enhanced Intelligent Agricultural Surveillance and Control System

    by Madina Jayanthi Rao, Bosubabu Sambana, Bondala Ramakrishna, Arangi Dasaradha, Malla Ramanaiah

    The Internet of Things (IoT) is a system that enables wirelessly linked devices to be tracked and managed remotely. It uses Ethernet protocols and the principles behind wireless sensor networks. Soil moisture monitoring, hydraulic pressure monitoring, soil testing, preventing trespassing through motion detection, and conserving energy are only some of the agricultural and irrigational operations that are the subject of this research. The implementation shown in this work breaks down larger systems into several smaller ones. A subsystem incorporates a vibration warning sensor, pump, and the ability to monitor soil moisture and hydraulic pressure to detect movement in and around the associated field. The second method will be utilized to deter intruders by picking up on their presence when they move within range of the necessary field barrier. Sensors for measuring current and voltage will be included for energy management regulation. It will be utilized for controlling the system. The main system will receive data through ZigBee from the first and second subsystems, monitor them, and then transfer them to the network router via ZigBee, where the necessary data will be shown on a website home page alongside the appropriate Ethernet protocols and current operating data.