The rapid deployment and usage of 5G and IoT networks in smart cities present significant challenges for cybersecurity, particularly regarding energy efficiency and attack detection. Existing intrusion detection systems often fail to balance high detection accuracy with low energy consumption, especially in resource-constrained environments. This research paper proposes an ontology-driven novel computational framework for energy-efficient Security Attack Identification and Detection (SAID) in 5G and IoT networks. The research framework proposed is a combination of cryptographic algorithms and semantic reasoning of ontologies to efficiently detect both known and unknown attacks, as well as to optimise energy consumption. The ontology provides a formalised semantic foundation for modelling attacks, vulnerabilities, network elements, and system states. Through this capability, the contextual knowledge can be modelled, thus allowing for context advancement and integrated attack detection. Through anomaly-based detection and machine learning techniques, cryptographic algorithms for secure communication and attack detection are made possible through a hybrid solution. Using machine learning algorithms to profile the network and to identify the anomalies, the hybrid attack detection is developed, while cryptographic algorithms can monitor the integrity and confidentiality of data exchange. After that, ever-changing. Experiments conducted using the CICIDS 2017 dataset demonstrate that the proposed framework improves attack detection accuracy by 22% and reduces energy consumption by 38% compared to traditional IDS solutions. The research paper outcome confirms the effectiveness of the proposed solution in energy-constrained environments, offering a scalable and robust method for cybersecurity in 5G and IoT networks. This work advances the integration of cryptographic solutions and ontology-based models in smart city applications, providing a path for future research on energy-efficient cybersecurity.

Mobile ad hoc networks (MANETs) are highly susceptible to routing and insider attacks due to their decentralized architecture, dynamic topology, and limited resources, which undermine the effectiveness of traditional signature- and rule-based intrusion detection systems (IDSs). This review provides a comprehensive and unified synthesis of trust-aware and optimization -assisted machine learning (ML) and deep learning (DL) intrusion detection frameworks developed for MANET security, covering publications from January 2019 to March 2026. Using a PRISMA-based selection process, 89 peer-reviewed studies were included in the analysis. Unlike prior surveys that address a single methodological stream, this review integrates attack taxonomy, observable network indicators, trust mechanisms, optimization strategies, learning models, datasets, evaluation metrics, and deployment feasibility within a single MANET-focused perspective. The review demonstrates that ML-based IDSs offer computationally lightweight detection using routing and forwarding features; DL models such as CNN, LSTM, and GRU capture complex spatial–temporal attack patterns; trust-aware frameworks strengthen resilience against insider and cooperative attacks through behavioural evidence accumulation; and meta-heuristic optimization methods including PSO, GWO, WOA, and GA improve feature selection, hyperparameter tuning, and energy-conscious decision-making. Hybrid frameworks that combine trust evaluation, optimization -assisted feature selection, and ML or DL classification consistently achieve the most favourable trade-off among detection accuracy, false alarm rate, adaptability, and energy efficiency under similar experimental conditions. Practical deployment challenges, including lightweight model design, dataset realism, validation leakage, communication overhead, and scalability under mobility, are critically examined. The review concludes by identifying open research directions in realistic MANET dataset construction, lightweight deep learning, robust trust management against collusion and on–off attacks, federated learning, blockchain-assisted trust transparency, and real-world testbed validation areas.

There has been significant growth in the number of people practicing Yoga, and as a result there is a growing need for advanced recognition systems and systems to measure how well a user performs their yoga postures. Most current recognition systems have demonstrated high levels of success in classifying yoga postures but none of these systems assess the quality of a user’s execution of a posture. This paper therefore introduces SuryaNet, a multi-task model with four technical contributions: (1) A Vision Transformer backbone that captures global spatial dependency relationships; (2) An Adaptive Spatial-Temporal Graph Convolutional Network (ST-GCNN) that models the skeletal topology; (3) Bidirectional Cross-Modal Transformer Fusion with learned gating for adaptive modality weighting; (4) Quality-Aware Contrastive Learning with Uncertainty-Weighted Multi-Task Optimization that jointly trains pose classification and continuous quality scoring. The results demonstrate that SuryaNet obtains 99.36

Jowar, an essential food grain grown in many regions is for helping to decide the food security. But its productivity is heavily affected by environmental factors: temperature, humidity, soil fertility and nutrient levels. This paper presents an innovative solution for improving Jowar crop yield using Machine Learning (ML) and Internet of Things (IoT) technologies. It is the main objective of this study to construct a predictive model, utilizing ML methods for prediction of Jowar crop yield. This model will rely on information of soil properties, environmental conditions (temperature, rainfall), nutrient concentration, latitude and soil ph. This model will help farmers to take crop management and resource allocation decisions factually leading to increase in the Jowar crop yield. ML is used to analyze and model the relationships with these data points. In the next stage, IoT will be implemented for Real time monitoring of Jowar crop using sensors-Environmental factors and soil parameters. Preliminary results show that the ML model can be used for estimating Jowar crop yield, and adoption of IoT technology would help to obtain meaningful on time data for aforementioned purpose. By integrating ML with IoT, the motivation of this research is to work toward sustainable improvement of Jowar crop for farmers to increase their productivity. The results indicate that the Gradient Boosting model effectively estimates yields of Jowar across Kharif and Rabi crop season used in the dataset. This is an example of how machine learning when incorporated with IoT-based monitoring could avert well-informed and green agriculture decision-making.

Abstract Magnetic resonance imaging (MRI) is hard to categorize properly in terms of interclass similarity, there is data imbalance, and sensitive clinical decision-making: but the performance of convolutional neural networks (CNNs) highly relies on effective, yet computationally costly, hyperparameter tuning. To find solutions to such issues, the given paper proposes a hybrid solution to the problems of the Aquila Optimizer and Harris Hawks Optimization, i.e., Aquila Optimizer-Harris Hawks Optimization (AO-HHO) framework, to integrate the positive qualities of extremely good global exploration of the Aquila Optimizer and the good local exploitation process of a Harris Hawks Optimization to achieve balanced and robust CNN hyperparameter optimization. On a publicly accessible dataset of 7, 023 brain MRI images divided into glioma, meningioma, pituitary tumor, and non-tumor, the proposed algorithm has been tested on with fine-tuning critical hyperparameters, such as learning rate, batch size, number of filters, dropout rate, and optimizer type. The rate of accuracy, precision, recall and F1-score of the AO-HHO-tuned CNN is invariably high than the conventional metaheuristic algorithms, including the Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Whale Optimization Algorithm (WOA) that are approximately 78–83. The proposed method also helps in reducing the cost of computing. It takes only 77.85 s to train, while the baseline optimizers take more than 300 s. This shows that AO–HHO is a reliable, accurate, and computationally efficient framework that can be used for medical imaging decision-support applications that need to be done in real time and with limited resources.

This paper focuses on the recognition of cipher encryption keys via machine learning, specifically Vigen & egrave;re and Advanced Encryption Standard (AES) ciphers. It does this by analyzing pairs of plaintexts with their associated ciphertexts. It is a study that attempts to achieve a classification model for the task of predicting the encryption key between pairs of plaintexts and ciphertext without knowledge of the encryption key. A set of different plaintexts, ciphertext, and keys have been used to train the model. The results had proved the success of machine learning over existing encryption techniques, also illuminating their potential weaknesses and further giving impetus to the field of cryptanalysis.

The CASE model improves the traditional wireless communication approach by deploying an energy-efficient information-centric algorithm that also enables the tiny low-powered communication nodes of the wireless network to work efficiently with the context-aware energy-saving interface. CAES introduces buffer optimization and a smart routing process among all the low-capacity tiny nodes. Moreover, the gathering of Context-aware energy-saving information also takes care of the performance as well as the management of the traffic load of the entire wireless network. Toward the objectives of the proposed algorithm, which ensure a high ratio of content delivery with an efficient energy saving and energy utilizing scheme, this paper is trying to design a type of Wi-Fi environment that carry the data packet and delivery services carefully without falling down the connection or losing the data contents. In addition to this, this paper concentrate on the measurement of Expected Production Quality (EPQ) values, using loss and quality functions based on various quality parameters to be calculated as one of the measured parts of this research work that defines the ratio of reliability and efficiency of CAES. Further, the implementation of CAES defines the improvement of this research work in the form of managing various quality of communication parameters such as packets delivery ratio, end-to-end Delay and throughput measurement. This manuscript proposes a novel version of the context-aware routing mechanism in a wireless network since traditional wireless communication protocols like SADODV, RAEED-EA are not vulnerable to offer best of communication services. This work aims to manage common communication quality parameters such as Packet Delivery Ratio, End to End Delay and Throughput to be improved using information-centric route management services under denial-of-service (DoS) attacks by implementing context-aware energy saving (CAES), which simultaneously deploys energy efficiency and buffer optimization. This paper simulates and compare the resulting parameters with traditional protocols which defines the importance and role of CAES model for the future of Communication Technology.

Wine quality assessment in the modern viticulture industry faces significant challenges due to reliance on subjective expert evaluation, leading to inconsistencies, scalability limitations, and high costs in commercial applications. Traditional approaches lack standardization and struggle with large-scale quality control processes. This comprehensive study evaluates the effectiveness of advanced machine learning techniques for wine quality prediction using a dataset of 6,497 samples (1,599 red wine and 4,898 white wine)0.14 original physicochemical features that were expanded to 34 through feature engineering, plus the quality target variable and addressed class imbalance using SMOTE. Our methodology integrates traditional algorithms (Logistic Regression, SVM, KNN), ensemble methods (Random Forest, XGBoost, LightGBM, Voting and Stacking ensembles), deep neural networks, and a novel application of transfer learning from white wine quality models to enhance red wine quality prediction. Results demonstrate superior performance of ensemble methods across evaluation metrics, with Random Forest achieving up to 95% accuracy and 0.994 AUC score in optimized configurations, while Voting and Stacking ensembles consistently delivered robust performance (81.5% accuracy, 85.3% F1 score) across varied testing conditions. Feature importance analysis using SHAP revealed that alcohol content, sulfur dioxide levels, and volatile acidity are the most influential predictors, with complex interaction patterns between chemical properties. Transfer learning showed promising results with faster convergence but slightly lower accuracy than models trained from scratch. This research advances both the methodological framework for wine quality prediction and provides actionable insights for the wine industry by identifying critical chemical determinants of wine quality.

Load balancing (LB) is a critical aspect of Cloud Computing (CC), enabling efficient access to virtualized resources over the internet. It ensures optimal resource utilization and smooth system operation by distributing workloads across multiple servers, preventing any server from being overburdened or underutilized. This process enhances system reliability, resource efficiency, and overall performance. As cloud computing expands, effective resource management becomes increasingly important, particularly in distributed environments. This study proposes a novel approach to resource prediction for cloud network load balancing, incorporating federated learning within a blockchain framework for secure and distributed management. The model leverages Dilated and Attention-based 1-Dimensional Convolutional Neural Networks with bidirectional long short-term memory (DA-DBL) to predict resource needs based on factors such as processing time, reaction time, and resource availability. The integration of the Random Opposition Coati Optimization Algorithm (RO-COA) enables flexible and efficient load distribution in response to real-time network changes. The proposed method is evaluated on various metrics, including active servers, makespan, Quality of Service (QoS), resource utilization, and power consumption, outperforming existing approaches. The results demonstrate that the combination of federated learning and the RO-COA-based load balancing method offers a robust solution for enhancing cloud resource management.

With the aid of cutting-edge technology that makes life easier and more accessible, the world has changed through time to become a better place. With home automation, a number of the home’s components may be controlled remotely. The primary goal of building a wireless, low-cost home automation smart control system was to provide the security, reduce power consumption and enable automated control from a distance. Home automation is a useful concept and offers a number of advantages, including improved comfort and quality of life as well as security in every house by enabling users to manage electrical devices with their fingers within its range. It makes use of the microcontroller, and Wi-Fi is utilized for connection with the application. The paper is exploring the cloud connectivity with embedded board to perform the home automation system along with security based on the basic protocols of IOT. This manuscript proposed a home automation system for intelligent lighting, gas detection, plant watering system, water tank monitoring and password-based home security system. Developed system includes ready-to-deploy software and real-time HTTP and MQTT protocols monitoring through smartphones or PCs.

This manuscript provides a comprehensive exploration of quantum computing and communication’s foundational elements, employing Qiskit—an open-source quantum computing framework. It delves into the simulation of fundamental quantum blocks and the intricacies of two-qubit entanglement, presenting findings through graphical analyses. The discussion extends to quantum logic gates, including X, Y, Z and CNOT. This study not only examines the construction and application of quantum circuits. The simulation with Qiskit programming presents the basic quantum circuits and its outcomes after measurement.

The rapid growth of the Internet of Medical Things (IoMT) has introduced significant security and privacy challenges in managing and protecting medical data. This paper proposes a secure federated cloud storage system designed to address these challenges using a hybrid heuristic attribute-based encryption (ABE) scheme integrated with a permissioned Blockchain. The proposed system enhances data confidentiality and integrity by first collecting medical information and then encrypting it with ABE using an optimal key generated by the Hybrid Mexican Axolotl with Energy Valley Optimizer (HMO-EVO). The encrypted data is securely stored in a permissioned blockchain, ensuring robust access control and protection against data breaches. For effective healthcare monitoring, the system employs federated learning with a Multi-scale Bi-Long Short-Term Memory and Gated Recurrent Unit (MBiLSTM-GRU) to predict diseases accurately. This federated approach allows for decentralized training of deep learning models, preserving patient data privacy while leveraging collective learning. Experimental results show that the proposed system outperforms conventional methods in terms of security, efficiency, and predictive accuracy. This research offers a comprehensive framework for secure medical data management, combining the strengths of federated learning and blockchain technology to address the critical issues of data ownership, regulatory compliance, and privacy in IoMT networks.

The rate of economic expansion is directly related to agricultural production. The presence of illness in plants is quite widespread, which is one of the reasons why plant disease detection is important in the agricultural industry. When safeguards are not taken in this area, plants incur severe effects that affect the quality, quantity, or productivity of the associated products. In order to monitor big crop farms with minimal manpower and to detect disease signs as soon as they first appear on plant leaves, it is preferable to employ an automated technique for plant disease detection. Visual features play an important role to find diseases in plants through leaves. Visual features along with deep learning techniques are a growing area of research and application in today's era. Industries like Facebook AI research contributed to deep learning and self-learning model in the last few years. This paper presents a work carried out on a self-learning model to detect and classify defective plants using CNN with a Siamese network. Large datasets of annotated data are often needed for convolutional neural networks but are rarely available on demand. It takes a lot of time and effort to personally choose, photograph, and annotate each leaf to get this data. This work addresses the issue of limited plant picture data by examining the effectiveness of various data augmentation methods when combined with transfer learning. This paper systematically showcases results related to visual feature representation, similarity computation, and experimental to compare the proposed work. Our goal with paper is to bridge the performance gap with lot many existing techniques of deep learning.

The Healfit website is a dedicated platform that aims to change the way we think about healthy eating. This unique online service allows customers to order healthful meals from a broad menu from the comfort of their own homes. Healfit promotes well-being by offering a variety of nutritional options, catering to a wide range of dietary preferences, and encouraging a seamless user experience. It emphasizes the user-friendly interface, which makes food selection and ordering simple. Users may easily customize their meals to meet their nutritional needs, making it an excellent alternative for health-conscious people. The website's powerful search and filtering capabilities ensure that users can easily find meals that meet their dietary needs. Healfit prioritises openness by offering precise nutritional information for each menu item, allowing consumers to make educated decisions. The platform's dedication to user pleasure extends to its fast delivery services, which ensure that fresh and nutritious meals are delivered on time. The Healfit website, with an aim to promote healthier eating habits, has the potential to dramatically contribute to individuals' overall well-being. It not only makes ordering nutritious meals easier, but it also serves as a significant aid in choosing healthier food choices, leading to enhanced health and vigour.

The Block chain is a peer to peer, distributed ledger in which members must establish consensus to record every new input and transactions that are stored by all members. Over the last decade, block chain technology has grown in popularity, attracting interest from a wide range of industries, including finance, manufacturing, energy, and government sectors, health, and agriculture supply chains, land registrations, and digital identifications (IDs). Block chain facilitates better opportunities and benefits in agriculture, as well as building trust between farmers and consumers and allowing the creation of reliable food supply chains. The Chapter discusses how block chain and smart contracts can improve productivity, transparency, and traceability in agricultural insurance, smart farming, and agricultural food supply chain transactions (AFSC). By applying Block chain agri-food supply chain tracking was made easy and won the trust from different stakeholders, which was a real benefit to the real heroes of the country. The consumer can research the history of a product they are thinking about buying and consume food in their cart, learning about the entire process from planting to harvesting, transporting, and selling. Food fraud may be reduced by using the traceability and integrity of financial information to detect untrustworthy intermediaries and business practices that exploit both independent farmers and cooperatives. The agricultural industry will be transformed by block chain for supply chain management. All phases of the agriculture supply chain are being simplified, enhancing food safety and preventing the sale of counterfeit goods. Access to agricultural finance services for farmers and companies could also be facilitated by the technology. This Paper presents a review and research challenges on the existing block chain based IoT applications in the agriculture domain where maximum research focuses on food supply chain and its security of Internet of things with Block chain. The chapter presents how block chain and smart contracts can increase productivity, transparency and traceability could be very effective in Agricultural insurance, smart farming, transactions of agricultural food supply chains.

Trend of using the software in daily life is increasing day by day. Software system development is growing more difficult as these technologies are integrated into daily life. Therefore, creating highly effective software is a significant difficulty. The quality of any software system continues to be the most important element among all the required characteristics. Nearly one-third of the total cost of software development goes toward testing. Therefore, it is always advantageous to find a software bug early in the software development process because if it is not found early, it will drive up the cost of the software development. This type of issue is intended to be resolved via software fault prediction. There is always a need for a better and enhanced prediction model in order to forecast the fault before the real testing and so reduce the flaws in the time and expense of software projects. The various machine learning techniques for classifying software bugs are discussed in this paper.

Supply chain optimization has recently emerged as a key research area in process operations and management. There has been a great deal of research done on facility sites and layouts, inventory and distribution planning, capacity and production planning, and complex scheduling. This information only briefly and infrequently addresses issues unique to the pharmaceutical sector. Moreover, effective supply chain management is a problem in any industry, but there is added complexity and risk in healthcare due to the direct impact that a supply chain disruption might have on patient security and health outcomes. One solution for improving the security, authenticity, data provenance, and utility of the health supply chain is blockchain technology. Our goal is to present an overview of the potential problems connected with the adoption and use of blockchain in the medical supply chain, with a focus on the public health, medical device, and pharmaceutical supply sectors.

Preventing the digital content from being copied, manipulated and illegal ownership claims is one of the biggest challenges that appeared with the widespread usage of computing facilities.Watermarking is one way to tag a digital document with a watermark, perceptible or imperceptible, so as to later prove the ownership or authenticity of the document, in case the need arises.Robust and Fragile watermarking is used in case of proving ownership and authenticity, respectively.This paper proposes a watermarking approach based on Discrete Wavelet Transform (DWT), Hessenberg Decomposition (HD) and Singular Value Decomposition (SVD) approach, augmented with Firefly Algorithm (FA).To make the approach blind, the proposed technique uses Hu's invariant moments which are invariant against rotation, scaling and translation (RST) attack over the image.In the resulting watermarked image, the watermark is imperceptible, which make it suitable for a large class of watermarking applications.In the proposed approach, a given colour image is subjected to 2 Level DWT for decomposing into sub-bands, namely LL, LH, HL and HH bands.These coefficients of HH band are fed as input for HD.The output is operated for SVD for obtain U, S and V matrices.The Hu's invariant moments are scaled and mapped to binary string using logarithm scaling.The binary matrix, corresponding to binary watermark, is XoRed with the invariant moments, in a repeated manner, to obtain a new binary matrix, of the same dimension as count of 2X2 partitions of S. The watermark is embedded by changing the orthogonal V matrices.The magnitude of the change is computed with Firefly algorithm considering the robustness and imperceptibility as the trade-off parameters.The firefly algorithm is one of the nature inspired optimization algorithm.The proposed watermarking approach is capable of withstanding JPEG compression attack, filtering attacks and noise.PSNR and SSIM are used as the quality metric for accessing the watermarked image quality.It turns out that the proposed watermarking technique gives a considerable improvement over robustness and imperceptibility as compared to the benchmark approaches.The performance of the proposed approach as compared to the benchmark approach, increases in linear manner with the dimension of the image under consideration, reaching from 1 percent to 4 percent for image dimensions ranging from 400X400 to 1200X1200 pixels.