Environmental Impact Assessment (EIA) is a critical process for evaluating the potential effects of development projects on the environment. Traditional EIA methods are often time-consuming and data-intensive. However, the manual generation of EIA reports is a time-consuming, data-intensive, and often subjective process. This paper introduces a novel agentic AI framework that leverages Microsoft Azure AI Foundry and Semantic Kernel to automate and enhance the generation of comprehensive EIA reports. Our framework employs a multi-agent system where specialized agents, orchestrated through a Multi-Agent Collaboration Protocol (MCP), work in concert to gather data, perform analysis, and synthesize findings. Communication between agents is facilitated by a robust Agent-to-Agent (A2A) protocol, ensuring seamless information exchange. To validate the efficacy of our approach, we present a rigorous agentic evaluation using state-of-the-art “LLM as a Judge” frameworks, including Prometheus and Langsmith, demonstrating the system's accuracy, coherence, and alignment with regulatory standards.

This paper presents a novel approach to optimize the coverage area of wireless sensor networks using a hybrid model combining differential evolution and neural networks. The proposed method enhances the placement and coverage efficiency of sensor nodes, addressing key challenges like energy consumption, node redundancy, and communication overhead. DE is utilized to explore optimal sensor placements, while neural networks predict network performance and guide the evolutionary process. The synergy between differential evolution’s global optimization and neural networks predictive capabilities leads to improved coverage and network longevity. A differential evolution-based hybrid approach ensures strategic placement of the sensor nodes with zero blind spots. Blind spots refer to sensor nodes in close range that perform unnecessary data transmission, leading to overlapping coverage. The model was designed via a dense neural network with several sensors and communication range as an input. The experimental results reveal that the proposed hybrid model can cover 52.3

Brain stroke prediction has become a very important part of preventive health, thus bringing the need of the application of the advanced deep learning techniques towards predicting the critical disease like brain stroke. Although many deep learning models are used in the recent past for the prediction of blockage in the brain but those learning models mainly suffer with the long term dependency issues. These can easily tackle with the help of LSTM model in association with the CNN.Towards overcome the issue of long term dependencies, we propose a hybrid model that based on CNN and LSTM model for the prediction of ischemic stroke with CT scan image.CNN is used for the feature extraction from the scanned image and LSTM is used for stroke prediction. Performance of the proposed work is compared with the existing standard CNN, RNN,LSTM and other model. The research outcomes show that the hybrid CNN-LSTM architecture exhibits encouraging performance and proven to be the best predictor for the brain stroke.

This document provides an in-depth analysis of how blockchain technology can greatly improve transparency, traceability, and accountability in fish and livestock supply chains, presenting the potential to transform this industry. Utilizing blockchain’s decentralized framework, which guarantees a secure and unchangeable record of transactions, problems associated with inefficiencies, fraud, and data manipulation in conventional supply chains can be efficiently resolved. This survey analyzes the present condition of blockchain applications in fish and livestock management, emphasizing their advantages and drawbacks. Furthermore, it highlights significant technical and regulatory challenges that impede wider acceptance, while recognizing potential future research avenues that could enhance processes from the production stage to the retail stage. The results intend to assist stakeholders in developing supply chains that are more sustainable, efficient, and transparent, fostering trust and complying with regulatory requirements.

SDN is a novel approach to networking by decoupling the control and data planes and allowing for centralized management and dynamic configuration. The paper looks into the core performance parameters critical to SDN functionality, focusing on their role in ensuring efficient, scalable, and reliable network operations. Additionally, it highlights optimization strategies and tools that address the challenges posed by these parameters. This research study aims to provide the desired broad perspective in development of innovative solutions to improve SDN performance in meeting the requirements of modern and emerging networking environments.

Salp Swarm Algorithm (SSA) is a bio-inspired optimization algorithm used in this paper to optimize the multiprocessor scheduling process in the current cyber-physical system. Although SSA is mainly utilized in terms of local search, in our case, an improved version has been introduced with the use of a Local Search Algorithm (LSA) and binary SSA, namely Improved SSA (ISSA). More to the point, eight optimization algorithms are compared with this proposed ISSA namely SSA, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Grey Wolf Optimizer (GWO), Jaya Algorithm (JAYA), Chaotic Squirrel Search Algorithm (CSSA), Quantum-inspired Binary Chaotic Salp Swarm Algorithm (QBCSSA) and Space Transformation Search (STS) with SSA is termed as STS-SSA. The performance of ISSA along with the other 6 meta-heuristic and 2 improved versions of SSA algorithms are compared with 12 traditional benchmark functions and evaluated for 100 and 300 dimensions. Convergent curves have also been demonstrated and the proposed ISSA has been shown to find a global optimum within the very initial phase of iterations. For calculating the efficiency of the proposed algorithm, the gear train design problem has been employed. The proposed algorithm has demonstrated higher accuracy rates and better convergent values than the other applied algorithms.

With the advent of growing technologies and digitalization, smart factories and healthcare systems in the cloud are more focused towards task-driven event processing. Also, most of the IoT-enabled devices are the sources to provide important data for these tasks. IoT offers many benefits but security is a major concern as devices are more prone to attack vulnerabilities over the cloud, leading to system failures. To tackle this, we introduces a new method named as Rabin Cryptosystem Biometric Privacy Preserving User Authentication System (RCBP2U-AS), which aims to secure IoT enabled devices over the cloud. The method works with secret generation for devices communicating with gateways, ensuring security on unsecured networks. This includes a unique encryption model for on-demand secret generation and session key management. The method achieves user authentication and device authentication using the public key concept. Moreover, the decryption process involves unique sequence generation using private key with a Blum–Blum–Shub pseudo-random bit generation algorithm. The system demonstration includes biometric implementation with three factor authentication. This significantly form the basis for secure authentication during data exchange from low powered device to cloud servers via gateway. The paper includes formal and informal security analysis over replay, password guessing, and other types of attacks using the AVISPA simulation Tool [7]. The performance evaluation done under various test case environments. Different complexity analysis function evaluations are done. The experimental result shows that the proposed RCBP2U-AS has less computation overhead and can detect numbers of attacks for IoT enabled devices over cloud.

Sarcasm is a type of communication that involves using words with meanings opposite to their literal definition to create humor or mock someone. This form of communication can be confusing as it often uses positive words to express negative feelings, making it difficult for people to understand the speaker’s intention. Detecting sarcasm in text can be challenging as it changes the polarity of the sentence and the difference between the words used and the way it is spoken. As a result, sarcasm detection in news, comments, or tweets on social media poses a challenge for researchers. In this research, various word-level features have been studied to detect sarcasm from three benchmark datasets, which include the creation of an N-gram probability dictionary, negation words, and PoS tags. Different machine learning and hybrid deep learning models have been examined and compared with handcrafted features and also with word embedding features. The results demonstrate a maximum accuracy of 87

Breast cancer is one of the most common cancers among women worldwide and early detection plays a vital role to reduce the mortality rate. In this study, we propose a novel machine learning-based classification model for breast cancer classification, combining feature selection techniques and clas-sification algorithms. The Wisconsin Diagnostic Breast Cancer (WDBC) dataset is used, where feature selection is performed using Fisher Discriminant Ratio (FDR) and Pearson Correlation Coefficient (PCC). The selected features are then used to train and evaluate Support Vector Machine (SVM) and XGBoost classifiers. From the results it is observed that SVM, with features selected using fisher discriminant ratio performs better than other compared models with an accuracy of 97.66% and a recall of 98.52%, crucial for accurately identifying malignant cases. It is also observed that features like Radius mean, Perimeter mean, Compactness mean, Concative mean, Fractal dimension standard error, Texture worst value (mean of the three largest values) across all cells, Smoothness worst value (mean of the three largest values) across all cells, Compactness worst value (mean of the three largest values) across all cells are important features of breast cells for classifying the data into Malignant and Benign. This work emphasizes the potential of combining feature selection and machine learning for more accurate and efficient cancer diagnosis.

Over the past few decades, classification has consistently posed a significant computational challenge. This study presents an innovative ensemble classification model designed for data classification, drawing inspiration from Radial Basis Function, Extreme Learning Machine, Functional Linked Artificial Neural Network, and Artificial Neural Network. The study involved experimenting with various combinations of ensemble methods to construct an ensemble classifier. Remarkably, implementing the ensemble model using Radial Basis Function Network (RBFN), Artificial Neural Network (ANN), Extreme Learning Machine (ELM), and Functional Linked Artificial Neural Network (FLANN) yielded superior results when tested on benchmark datasets. The accuracy range of the ensemble method varies from 80% to 98% which is a good performance considering the diverge data sets used.

Groundwater, a vital resource for various purposes, faces increasing threats to its quality due to factors like overuse, pollution and climate change. In the semi-arid climate of the state of Telangana, India, exacerbated by intensive agricultural practices, groundwater quality is a significant concern. This study presents a machine learning-based approach for predicting and managing groundwater quality in Telangana, utilizing a stacking ensemble method. Our proposed approach combines decision trees (DT) with meta-models such as logistic regression, K-nearest neighbors (K-NN), Bayesian ridge regression (BRR) and random forest (RF). Trained on a comprehensive dataset from the Telangana Open Data portal (2018-2021), the stacking ensemble demonstrates superior performance, achieving an accuracy of 96.07%, surpassing the best individual model (DT) at 92.68%. It not only enhances predictive capabilities but also provides insights into the spatial distribution of groundwater quality, identifying areas vulnerable to contamination. These findings offer valuable information for policymakers, environmental scientists and water resource managers, guiding informed decision-making for sustainable water resource management in Telangana. This research contributes to the ongoing discourse on environmental conservation and the imperative for effective groundwater management.

The rapid evolution of mobile devices has greatly advanced secure medical image transmission, yet challenges persist due to resource limitations and security concerns inherent to these devices. In response, this paper introduces a Dynamic Energy-Efficient Offloading Algorithm (DEEO), seamlessly integrated into the Mobile Edge-Cloud Computing (MECC) environment. DEEO empowers mobile devices to efficiently offload computationally intensive secure image transmission tasks to the nearest edge server or fog access point. This integration optimizes resource utilization, minimizes energy consumption, and ensures the confidentiality and integrity of sensitive medical image data. Through rigorous evaluations and comparative analysis, our approach demonstrates clear superiority over existing solutions. This integrated framework is poised to significantly enhance healthcare applications, offering heightened efficiency, elevated security, and an overall improved user experience.

In an era dominated by interconnected technologies, the persistent threat of intrusion attacks looms ominously, leaving individuals and organizations vulnerable to devastating consequences. The insidious nature of these attacks not only compromises sensitive information but also jeopardizes the very fabric of digital trust. As the frequency and sophistication of intrusions escalate, there is an urgent need for robust defenses to safeguard against these malicious incursions. This paper addresses this pressing concern by delving into the realm of deep learning, a cutting-edge field that holds the promise of fortifying our digital fortresses. We present a comprehensive analysis of various deep learning approaches, rigorously tested on two benchmark datasets: UNSW-NB15 and 5G-NIDD. These datasets serve as battlegrounds where our models are trained and tested to discern their efficacy in the critical task of intrusion detection.

Mobile connectivity and smart devices are spreading worldwide. As a result, the use of mobile devices and applications is rising exponentially. Therefore, nowadays hackers target such smart devices to steal information and misuse it for malicious purposes. It becomes absolutely essential to protect sensitive information such as app. permissions, login credentials, browse history, media contents etc. from intruders. Security can be breached easily if smart techniques are not devised to safeguard mobile data. In this article, an attempt is made to classify the different types of malware and to protect the sensitive information on Android devices that significantly reduce network congestion and improve network throughput by increasing data transmission. The proposed hybrid approach consists of AdaBoost, random forest and deep learning methods jointly classify the sophisticated malware. The empirical results indicate that this achieves better classification and detection accuracy and is capable of identifying the potential threat more efficiently.

The gathering, processing, transmission, sharing, and storage of healthcare data was the core idea behind Healthcare 4.0. Currently, most of the existing solutions for offering smart healthcare services rely on cloud-based platforms. The main issues with current healthcare systems include storage overhead, processing speed, scalability, single points of failure, bandwidth requirements, and device connectivity. The recent challenges in the healthcare system motivated us to develop a system by integrating the Internet of Medical Things (IoMT), Blockchain, fog computing, and InterPlanetary File System (IPFS) to achieve decentralization, scalability, security, immutability, and data privacy. In this paper, we propose a novel IoMT and Blockchain framework with fog node computing to reduce latency and speed up processing, as well as to reduce the network congestion, bandwidth requirements, and the main Blockchain network overload. Untrusted devices are connected to the system using a proxy monitor, which records the device’s activity. In addition, the interplanetary file system (IPFS) is integrated with the Blockchain network to store patient data and files in order to ensure the system’s decentralization, scalability, security, and privacy. Moreover, we evaluate the proposed framework in terms of security, scalability, latency, storage, efficiency, and performance. The experimental analysis shows that the proposed framework makes access, searches, uploads, and downloads faster and more secure.

The cardiotocogram (CTG) is the main technique used in clinical practice for monitoring fetal well-being. Eighteen machine learning single models were initially tested on the CTG dataset in this article. The four top models are then combined to create the Stacking Integration Model which is then contrasted with the Blender Model created in the same way utilizing a soft voting ensemble method. The best model described in this study outperformed the conventional machine learning models in a variety of Classification Model evaluations, achieving accuracy rate of 0.986, F1 score of 0.986, precision rate of 0.986, recall rate of 0.986, and MCC of 0.979, AUC of 1.