Abdulwaheed Musa

Postpartum depression (PPD) affects approximately 10–20% of women globally, yet remains significantly underdiagnosed due to stigma, limited clinical access, and reliance on infrequent self-report screening. Recent advances in deep learning (DL) and the proliferation of behavioral data from wearables, smartphones, and social media offer new opportunities for continuous and objective PPD prediction. This systematic review synthesizes DL-based approaches for PPD detection using behavioral data published between 2020 and 2026, following PRISMA 2020 guidelines. A total of 4,312 records were identified, of which 50 studies met the inclusion criteria after screening. The review evaluates Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Transformer-based models, and multimodal architectures across diverse behavioral modalities. Comparative analysis across the reviewed studies suggests that multimodal deep learning architectures generally demonstrate improved predictive performance in specific experimental settings, although direct cross-study comparisons remain challenging due to dataset heterogeneity, label variability, and differences in evaluation protocols. Key challenges identified include limited dataset diversity, insufficient explainability, and a lack of clinical validation. This review provides a structured taxonomy, quantitative comparison, and future research directions to guide the development of robust, equitable, and clinically deployable PPD prediction systems.

Optimization and techno-economic analysis of hybrid renewable systems in Nigeria

Indoor localization based on Wi-Fi Channel State Information (CSI) continues to gain prominence as a practical, infrastructure-free solution for position estimation in dynamic indoor environments. However, CSI fingerprints are highly sensitive to environmental variations such as furniture displacement, door and window states, device heterogeneity, and temporal drift, which introduce domain shifts that significantly degrade localization accuracy. Recent domain adaptation methods mitigate these discrepancies, yet most rely solely on aligning marginal or conditional distributions and neglect the geometric structure of feature manifolds, often resulting in class confusion and distorted local neighborhoods. This study proposes a Geometry-Aware Deep Joint Multi-Domain Adaptation Network (G-DJMDAN) that integrates a deep residual CSI encoder, multi-layer distribution alignment, and a novel graph-based geometry-preservation module to maintain spatial topology across domains. By jointly optimizing classification loss, MK-MMD, LMMD, and Laplacian regularization, the framework produces more stable, discriminative embeddings under diverse environmental changes. Comprehensive experiments conducted across multiple real-world domain-shift scenarios—including temporal variation, furniture layout changes, and mixed perturbations—show that G-DJMDAN reduces median localization error by up to 34.7% compared with DJMDAN and achieves statistically significant improvements over CNN, DANN, DAN, JAN, and DSAN baselines. Visualization using t-SNE further confirms that the proposed geometry module effectively preserves manifold structure and mitigates target-domain collapse. Overall, the results demonstrate that incorporating geometric constraints into domain adaptation provides a robust and scalable pathway for high-precision indoor localization in non-stationary environments.

Solar energy is the cleanest and most abundant form of energy that can be obtained from the Sun. Solar panels convert this energy to generate solar power, which can be used for various electrical purposes, particularly in rural areas. Maximum solar power can be generated only when the Sun is perpendicular to the panel, which can be achieved only for a few hours when using a fixed solar panel system, hence the development of an automatic solar tracking system. Over the years, different solar tracking systems have been proposed and developed, and a few have been reviewed in the literature. However, the existing review works have not adequately provided a comprehensive survey and taxonomies of these solar tracking systems to show the trends and possible further research direction. This paper aims to bridge these gaps by extensively reviewing these time-based solar tracking systems based on axis rotation and drive types. Lessons learned from the comprehensive review have been highlighted and discussed. Finally, critical open research issues are identified and elaborated.

The rapid increase in data traffic caused by the proliferation of smart devices has spurred the demand for extremely large-capacity wireless networks. Thus, faster data transmission rates and greater spectral efficiency have become critical requirements in modern-day networks. The ubiquitous 5G is an end-to-end network capable of accommodating billions of linked devices and offering high-performance broadcast services due to its several enabling technologies. However, the existing review works on 5G wireless systems examined only a subset of these enabling technologies by providing a limited coverage of the system model, performance analysis, technology advancements, and critical design issues, thus requiring further research directions. In order to fill this gap and fully grasp the potential of 5G, this study comprehensively examines various aspects of 5G technology. Specifically, a systematic and all-encompassing evaluation of the candidate 5G enabling technologies was conducted. The evolution of 5G, the progression of wireless mobile networks, potential use cases, channel models, applications, frequency standardization, key research issues, and prospects are discussed extensively. Key findings from the elaborate review reveal that these enabling technologies are critical to developing robust, flexible, dependable, and scalable 5G and future wireless communication systems. Overall, this review is useful as a resource for wireless communication researchers and specialists.

The need for high speed data traffic on mobile devices has risen because of the permeating use of gadgets, such as mobile smart phones, notepads and tablets that are constantly running on data. In order to meet these requirements, mobile network providers must set up both tiny cells, high-capacity and very dense, base stations (BSs). This is to cover not only a vast area but also including hotspots with quick, adaptable, and robust supply. The overall spectral efficiency of 5G networks must be improved, and the operations and deployment costs must be decreased. This paper evaluates and compares the performance of Strict Fractional Frequency Reuse (FFR) and Frequency Reuse Factor-3 (FRF-3) according to the cell throughput and cell spectral efficiency with the theoretical peak throughput and peak spectral efficiency as specified in NR 3GPP specifications. The results from the simulation revealed that the FFR performs much better than the FRF-3, however, it is still not efficient in relation to the peak values.

Evolution of technology has been rapid in recent years and with the wide acceptance of 5G/6G networks, Internet of Things (IoT), Machine Learning (ML), blockchain technologies, there must be a methodology of interconnecting them across large proximity or regions to centralized servers. Existing mobile technologies are not suitable to ensure communications between these devices, and this has necessitated the need to create Low Power Wide Area Network (LPWAN). The LPWAN, assuming a set of networks, is considered to have subsets including Sigfox, LoRaWAN, NB-IoT and others. For any real system, there is always collision between packets upon arrival, thereby subtracting and extracting the weaker ones. In this work, a Repetitive Interference Mitigation algorithm is proposed, with focus on power differences between User Equipment (UE) and guard subcarriers. This process ensures decryption of the packets that arrive at the same time. Usage of just one guard subcarriers and multiple iterations of the developed technique is suitable to ensure a very good system performance and has a throughput of 36% as compared with other methods.

Radio waves are attenuated by atmospheric phenomena such as snow, rain, dust, clouds, and ice, which absorb radio signals. Signal attenuation becomes more severe at extremely high frequencies, usually above 10 GHz. In typical equatorial and tropical locations, rain attenuation is more prevalent. Some established research works have attempted to provide state-of-the-art reviews on modeling and analysis of rain attenuation in the context of extremely high frequencies. However, the existing review works conducted over three decades (1990 to 2022), have not adequately provided comprehensive taxonomies for each method of rain attenuation modeling to expose the trends and possible future research directions. Also, taxonomies of the methods of model validation and regional developmental efforts on rain attenuation modeling have not been explicitly highlighted in the literature. To address these gaps, this paper conducted an extensive literature survey on rain attenuation modeling, methods of analyses, and model validation techniques, leveraging the ITU-R regional categorizations. Specifically, taxonomies in different rain attenuation modeling and analysis areas are extensively discussed. Key findings from the detailed survey have shown that many open research questions, challenges, and applications could open up new research frontiers, leading to novel findings in rain attenuation. Finally, this study is expected to be reference material for the design and analysis of rain attenuation.