Abstract Kidney metabolic disorders are diagnosed by assessing protein levels in urine, which reflect renal health. Traditional detection methods are time-consuming and expensive. This study explores using the K-nearest neighbors (KNN) algorithm combined with advanced image segmentation for accurate urine protein detection. The research utilized a dataset of protein-level images captured by an ELP-type digital camera sensor, classifying them based on red, green, and blue (RGB) values. The KNN algorithm was tested with various K values (K = 3, K = 10, K = 20). Results showed that K = 3 provided the highest accuracy at 96.7%, with precision, recall, and F1-score of 97.0%, 96.7%, and 96.2%, respectively. Higher K values decreased accuracy, with K = 10 at 86.7% and K = 20 at 76.7%. These findings demonstrate that KNN can effectively predict protein levels, offering a promising and efficient alternative to traditional methods. The study also presents a prototype design for this detection approach.

Abstract Breast cancer remains one of the most prevalent and life-threatening diseases affecting women worldwide. Early detection is crucial for improving survival rates and treatment outcomes. This study proposes an advanced feature extraction method for classifying mammogram masses by combining multi-scale multi-orientation (MSMO) Gabor wavelets and gray-level co-occurrence matrix (GLCM) statistical features. MSMO Gabor filters extract detailed texture information across multiple scales and orientations, while GLCM captures statistical spatial relationships between pixel intensities. A feature selection process refines these features, enhancing classification accuracy. Experiments using Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM) datasets validate the approach with machine learning classifiers, including random forest (RF), decision tree (DT), support vector machine (SVM), k-nearest neighbors (k-NN), and deep neural network (DNN). RF outperformed other models and achieved 96.64% accuracy on MIAS dataset and 95.90% on DDSM dataset. Our approach shows the efficacy of optimally combining MSMO Gabor and GLCM features to advance computer-aided diagnosis systems for early and precise breast cancer detection.

Abstract Greenhouses play a key role in sustainable agriculture by addressing food security, climate change, and resource challenges. They enable year-round crop production under controlled conditions but are often labor-intensive and resource-inefficient. Advances in Internet of Things (IoT) technologies offer solutions by automating processes like crop monitoring, climate regulation, and irrigation control. These technologies optimize resource use, reduce waste, and enhance sustainability. This paper introduces an IoT-driven framework combining sensor technology and cloud computing to optimize greenhouse operations. Implemented in a smart greenhouse prototype, the framework includes web, desktop, and mobile applications for real-time operational control. These applications demonstrate IoT's potential in precision agriculture by promoting efficiency, sustainability, and scalability. The framework also supports AI-driven data collection and analysis, contributing to smarter decision-making. This practical, cost-effective, and eco-friendly solution addresses the growing demands of modern agriculture, advancing sustainability and technological integration in farming practices.

Abstract The increasing deployment of Internet of Things (IoT) networks has made them a target for sophisticated routing attacks, including blackhole, Sybil, rank, and wormhole attacks. To address these challenges, this paper proposes the adaptive trust-based secure routing protocol (ATBSRP), a novel framework that integrates trust evaluation, anomaly detection, and lightweight cryptographic mechanisms to enhance secure communication in IoT environments. The trust evaluation module dynamically assesses node behavior based on direct interactions, indirect recommendations, and historical trust scores, ensuring accurate and up-to-date trust values. The anomaly detection module uses a hybrid approach combining behavioral analysis, Gaussian mixture model (GMM)-based detection, and machine learning classifiers to effectively identify and mitigate malicious activities. Additionally, a lightweight cryptographic mechanism using elliptic curve cryptography (ECC), one-time hash chains, and a challenge-response mechanism safeguard data transmission with minimal computational overhead. The adaptive trust-based routing mechanism selects routes based on threshold-based trust scoring, ensures dynamic path adaptation in case of compromised nodes, and incorporates quality of service (QoS)-aware routing to maintain network efficiency. Experimental evaluations demonstrate that ATBSRP outperforms existing approaches in terms of packet delivery ratio (PDR ), end-to-end delay, throughput, routing overhead, and detection accuracy. The proposed framework offers a scalable, secure, and efficient solution for mitigating routing threats in IoT networks, ensuring reliable data transmission while minimizing network overhead.

Abstract Content-based retrieval (CBR) is an essential process to retrieve images from databases based on metadata from the image. Metadata in an image refers to image colors, textures, and shapes, or any other important information that can be derived from the image itself. The goal of CBR is to search for the relevant image and retrieve it from databases. Many CBR models achieved reliable results in analyzing the image. However, the computation cost of image retrieval is a challenging task due to the growth of image traits. This paper presents an Optimized Hybrid Ensemble Model (OHEM) R-2,C-1. The proposed model aims to improve the process of similarity matching for the efficient analysis of the query image while minimizing computation time. The purpose of OHEM is twofold. First, OHEM analyzes the features within the query image and performs similarity matching within the database, achieving this with reduced computational complexity. Subsequently, in accordance with the established objective function, it identifies and evaluates the pertinent features. Two distinct datasets, ROxford and RParis, are utilized to assess the model's performance. Several assessment criteria, including F1-score, recall, precision, and computation time, have been used to assess the model. The computation and evaluated outcomes are compared to six distinct algorithms, such as CSM, equilibrium propagation (EP), DCM, GA-based IR, and IRT. The comparison findings suggested that the proposed method performs better than the other models. R-2,C-1.

Abstract To address the challenge of quantitatively identifying mixed gases, we developed a gas concentration identification algorithm based on the sparrow search algorithm (SSA) and optimized support vector regression (SVR). The Tent chaotic mapping operator is employed to initialize the population, enhancing population diversity, and improving the algorithm’s global search capability. By optimizing SVR parameters with SSA, we propose an enhanced TSSA-SVR model. Evaluated on mixed gas datasets, TSSA-SVR achieves a prediction accuracy of 94.47%, outperforming comparative algorithms such as Genetic Algorithm (GA)-SVR and PSO-SVR, while demonstrating improved convergence compared to the baseline SSA-SVR. The experimental results demonstrate significant performance enhancements, offering an effective solution for precise gas concentration identification in complex environments.

Abstract This study focuses on improving the mobility and self-reliance of blind students to navigate university campuses. The main objective of this study was to design and develop a Smart Guide application, integrating a smart stick and application to help blind students navigate the university and its buildings safely and adequately. This system applies a combination of different components such as an obstacle sensor positioned on the stick to detect any obstacle, a global positioning system (GPS) module for instantaneous location tracking, and light sensors to make students aware of the changes in environmental lighting and to assist connection between the blind students, their guardians, and building security guards, enabling timely assistance in case of walking difficulties or emergencies. The Arduino board technology was employed for hardware integration, implementing ultrasonic and light sensors, and GPS modules, although the application is developed using Arduino IDE and XCode IDE. An iterative waterfall development methodology was utilized to implement this smart stick. The primary results demonstrate that the obstacles have been detected by the system successfully and are aware of users at the time, while the GPS module’s effectiveness assures connectivity with guardians and security. The safety and mobility of blind students have been significantly enhanced by the system’s real-time location tracking and environmental observation. This study exhibits the development of merging sustaining hardware and software solutions to enhance availability for visually impaired students in university and provide an innovative and balanced system for extensive application. Future studies will focus on advancing navigation competence in outdoor environments and managing challenges related to emergency buttons and sensors.

Abstract This study examines the challenges and sentiments surrounding the adoption of new farming technologies and government schemes in India’s agriculture sector. Researchers gathered 491 reviews to identify key adoption challenges and analyzed 1,390 tweets to assess sentiments (positive, neutral, or negative) on these topics. Using count vectorizer, term frequency-inverse document frequency (TF-IDF), and FastText for feature extraction, TF-IDF with logistic regression achieved the highest accuracy at 0.91. The findings highlight major obstacles in the adoption of new farming technologies and schemes, analyze sentiment trends with six machine learning models and two deep learning models, and recommend enhanced communication, training, and awareness initiatives to boost adoption among farmers.

Abstract Due to the growth of loads in distribution networks and the increase in demand for electrical energy, providing energy from traditional sources has become a cause of huge losses, high costs, and environmental pollution. To avoid these problems, clean energy sources are the desired way to solve these problems by integrating Photovoltaic Distribution Generators (PVDG) into Radial Distribution Networks (RDN). Furthermore, detecting the optimal locations and sizes of PVDG is determined by modern approaches of optimization algorithms such as Mountain Gazelle Optimizer (MGO) and Eel and Grouper Optimizer (EGO). The proposed algorithms are applied to Multi-Objective Functions (MOF), including technical objective functions (OFs) and economic OF. Active Power Loss Index (APLI), Reactive Power Loss Index (RPLI), Voltage Deviation Index (VDI), and Voltage Stability Index (VSI) are the technical OFs, while the investment cost of PVDG (ICDG) is the economic OF. The efficiency and effectiveness of the proposed approaches are crucial and are achieved by the implemention of the standard test system (IEEE 69 bus), in addition to the Iraqi RDN (Iraqi 77 bus). Moreover, the simulation results carried out by the proposed algorithms have been verified for accuracy and validity compared with the results of previous articles. The overall performance of the networks is improved after incorporating the optimal allocations of PVDG in RDN; the voltage profile level and VSI are maximized for all buses, while the active and reactive power losses are minimized for all lines. On the other hand, the simulation results showed the dominance of the EGO technique over the MGO technique according to the speed and smoothness of convergence to the best solution with the minimum number of iterations.

Abstract This study optimizes 3D print orientation to minimize support material, printing time, and surface roughness using non-dominated sorting genetic algorithm II (NSGA-II). Traditional NSGA-II can stagnate due to static parameters; thus, integration with Q-learning dynamically adjusts these parameters based on rewards. Q-learning, a variant of reinforcement learning (RL), initially promotes population diversity for broad exploration and later exploits optimal solutions near the Pareto front. Results show that the hybrid approach significantly enhances Pareto-front quality, improving efficiency by reducing support material (2.1%), printing time (3.8%), and surface roughness (1.9%). Validation confirms practical applicability of generated solutions for fused deposition modeling (FDM).