Recent advancements in image processing and computer vision have brought significant transformations in healthcare technology, leading to significant improvements in diagnosis accuracy, cost-effectiveness, and time efficiency. Magnetic Resonance Imaging (MRI) is employed by the radiologist for its remarkable ability to detect even the most subtle brain abnormalities. This study considers a comprehensive analysis of the two prominent object identification frameworks, YOLOv5 and YOLOv7, leveraging state-of-the-art deep learning architectures to classify and detect brain cancers within MRI. The brain tumor dataset encompasses three distinct classes, including meningiomas, gliomas and pituitary tumors. To ensure precise segmentation of the tumor regions, the preprocessing phase incorporates advanced mask alignment techniques. This preprocessed dataset has been used to evaluate the performance of the deep learning models for brain tumor detection and classification. From the numerical results of YOLOv5, it was noticed that a recall score of 0.905 for box detection and 0.906 for mask segmentation, with a precision score of 0.94 and 0.936, respectively. At an IoU threshold of 0.5, both box detection and mask segmentation achieve a mAP of 0.947, whereas, at an IoU threshold of 0.5 to 0.95, they achieve mAPs of 0.666 and 0.657, respectively. In comparison, YOLOv7 exhibits strong performance with box detection accuracy of 0.936 and a mask segmentation accuracy of 0.935. The recall score are 0.904 for box detection and mask segmentation is 0.903. Notably, the mAP result at the IoU threshold of 0.5 are 0.94 for box detection and mask segmentation is 0.941. Over the broader IoU spectrum of 0.5 to 0.95, the mAP was 0.677 for box detection and 0.659 for mask segmentation. To underscore the novelty of the approach, the performance of the proposed framework is systematically compared with established methods such as RCNN, Faster RCNN, and Mask RCNN.

Classification is a common problem in various fields of life, and the key challenging task in data mining. The primary objective of the classification process to classify the given dataset in a defined class label for all data. Many research papers widely used classification in the medical sector. Various researches have been carried out to classify medical data using different techniques, such as High Order Neural Network (HONN) combined with Back-Propagation Neural Network (BPNN) as a learning algorithm. Due to the increased data complexity, the back-propagation algorithm faced problems of slow convergence. The Back-Propagation (BP) using the gradient descent technique has the possibility of getting stuck in local minima. So, the BP algorithm may cause difficulties in finding the global minima of the error function. This paper proposed a high-order Functional Link Neural Network (FLNN). The proposed FLNN model is integrated with a metaheuristic-based searching algorithm called Accelerated Particle Swarm Optimization (APSO). The performance of the proposed Accelerated Particle Swarm Optimization Functional Link Neural Network (APSOFLNN) model is validated with various medical datasets and compared to traditional techniques such as the proposed Accelerated Particle Swarm Optimization Functional Link Back-Propagation (APSOFLBP), and Artificial Bee Colony Functional Link Neural Network (ABCFLNN). The simulation results showed that the proposed APSOFLNN algorithm for the used benchmarked datasets shows good results in terms of the mean square error (MSE) and accuracy in comparison to the traditional techniques.

Author Profiling (AP) is a subsection of digital forensics that focuses on the detection of the author’s personal information, such as age, gender, occupation, and education, based on various linguistic features, e.g., stylistic, semantic, and syntactic. The importance of AP lies in various fields, including forensics, security, medicine, and marketing. In previous studies, many works have been done using different languages, e.g., English, Arabic, French, etc. However, the research on Roman Urdu is not up to the mark. Hence, this study focuses on detecting the author’s age and gender based on Roman Urdu text messages. The dataset used in this study is Fire’18-MaponSMS. This study proposed an ensemble model based on AdaBoostM1 and Random Forest (AMBRF) for AP using multiple linguistic features that are stylistic, character-based, word-based, and sentence-based. The proposed model is contrasted with several of the well-known models from the literature, including J48-Decision Tree (J48), Naïve Bays (NB), K Nearest Neighbor (KNN), and Composite Hypercube on Random Projection (CHIRP), NB-Updatable, RF, and AdaboostM1. The overall outcome shows the better performance of the proposed AdaboostM1 with Random Forest (ABMRF) with an accuracy of 54.2857% for age prediction and 71.1429% for gender prediction calculated on stylistic features. Regarding word-based features, age and gender were considered in 50.5714% and 60%, respectively. On the other hand, KNN and CHIRP show the weakest performance using all the linguistic features for age and gender prediction.

In this paper, we investigate a wireless communication scenario where polarization multiplexing is exploited to increase the spectral efficiency. Independent modems over each polarization are considered, with communication links affected by phase noise and Cross-Polarization Interference (XPI). We devise a novel per-polarization soft decision-directed iterative receiver with separate A Posteriori Probability (APP)-based synchronization and decoding. The synchronization algorithm relies on a Minimum Mean Square Error (MMSE)-basedMaster- Slave (MS) phase estimation followed by cancellation of the XPI on the polarization of interest and requires no statistical knowledge of the phase noise process. The performance of the proposed iterative receiver is investigated for a pilot symbolassisted Low-Density Parity-Check (LDPC)-coded Quadrature Amplitude Modulation (QAM) scheme.

Efficient irrigation scheduling is a major challenge in precision agriculture due to increasing water scarcity, climate variability, and growing agricultural demand. Conventional irrigation strategies based on fixed thresholds, heuristic rules, or classical optimization techniques often suffer from scalability limitations, inefficient resource allocation, and poor adaptability under dynamic environmental conditions. This paper presents a hybrid quantum-classical optimization framework for intelligent irrigation scheduling using the Quantum Approximate Optimization Algorithm (QAOA). The irrigation decision problem is formulated as a Quadratic Unconstrained Binary Optimization (QUBO) model integrating soil moisture conditions, irrigation constraints, and water allocation objectives. The proposed framework employs variational quantum optimization to determine optimal irrigation decisions while minimizing unnecessary water consumption. Experimental evaluations conducted using Qiskit-based simulations demonstrate that the proposed QAOA framework successfully generates irrigation decisions fully consistent with classical threshold-based optimization for the evaluated dataset. Comprehensive visualization analyses including soil moisture distribution, irrigation decision mapping, threshold boundary analysis, and water utilization comparison validate the correctness and interpretability of the proposed optimization mechanism. Although the current experimental setup primarily serves as a proof-of-concept validation, the results indicate strong scalability potential for future large-scale agricultural systems involving complex multi-objective optimization constraints. The proposed framework establishes a foundational architecture for future quantum-enabled precision agriculture systems integrating IoT sensing, real-time environmental monitoring, and intelligent resource optimization for sustainable smart farming applications.