The early and accurate detection of plant diseases is essential for ensuring food security, enhancing crop yields, and facilitating precision agriculture. Manual methods are labour-intensive and prone to error, especially under varying environmental conditions. Artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), has advanced automated disease identification through image classification. However, challenges persist, including limited generalisability, small and imbalanced datasets, and poor real-world performance. Unlike previous reviews, this paper critically evaluates model performance in both lab and real-time field conditions, emphasising robustness, generalisation, and suitability for edge deployment. It introduces recent architectures such as GreenViT, hybrid ViT–CNN models, and YOLO-based single- and two-stage detectors, comparing their accuracy, inference speed, and hardware efficiency. The review discusses multimodal and self-supervised learning techniques to enhance detection in complex environments, highlighting key limitations, including reliance on handcrafted features, overfitting, and sensitivity to environmental noise. Strengths and weaknesses of models across diverse datasets are analysed with a focus on real-time agricultural applicability. The paper concludes by identifying research gaps and outlining future directions, including the development of lightweight architectures, integration with Deep Convolutional Generative Adversarial Networks (DCGANs), and improved dataset diversity for real-world deployment in precision agriculture.

Computer vision aims to enable machines to understand the visual world. Computer vision encompasses numerous tasks, namely action recognition, object detection and image classification. Much research has been focused on solving these tasks, but one that remains relatively uncharted is light enhancement (LE). Low-light enhancement (LLE) is crucial as computer vision tasks fail in the absence of sufficient lighting, having to rely on the addition of peripherals such as sensors. This review paper will shed light on this (focusing on video enhancement) subfield of computer vision, along with the other forementioned computer vision tasks. The review analyzes both traditional and deep learning-based enhancers and provides a comparative analysis on recent models in the field. The review also analyzes how popular computer vision tasks are improved and made more robust when coupled with light enhancement algorithms. Results show that deep learners outperform traditional enhancers, with supervised learners obtaining the best results followed by zero-shot learners, while computer vision tasks are improved with light enhancement coupling. The review concludes by highlighting major findings such as that although supervised learners obtain the best results, due to a lack of real-world data and robustness to new data, a shift to zero-shot learners is required.

Brain–Computer Interface (BCI) technology facilitates direct communication between the human brain and external devices by interpreting brain wave patterns associated with specific motor imagery tasks, which are derived from EEG signals. Although BCIs allow applications such as robotic arm control and smart assistive environments, they face major challenges, mainly due to the large variation in EEG characteristics between and within individuals. This variability is caused by low signal-to-noise ratio (SNR) due to both physiological and non-physiological artifacts, which severely affect the detection rate (IDR) in BCIs. Advanced multi-stage signal processing pipelines, including efficient filtering and decomposition techniques, have been developed to address these problems. Additionally, numerous feature engineering techniques have been developed to identify highly discriminative features, mainly to enhance IDRs in BCIs. In this review, several pre-processing techniques, including feature extraction algorithms, are critically evaluated using deep learning techniques. The review comparatively discusses methods such as wavelet-based thresholding and independent component analysis (ICA), including empirical mode decomposition (EMD) and its more sophisticated variants, such as Self-Adaptive Multivariate EMD (SA-MEMD) and Ensemble EMD (EEMD). These methods are examined based on machine learning models using SVM, LDA, and deep learning techniques such as CNNs and PCNNs, highlighting key limitations and findings, including different performance metrics. The paper concludes by outlining future directions.

The increasing interconnectivity and digital transformation of Communication, Navigation, and Surveillance (CNS) systems have expanded their attack surface, rendering traditional perimeter-based security models inadequate for protecting these critical infrastructures. Zero Trust Architecture (ZTA), founded on the principle of “never trust, always verify,” offers a paradigm shift towards continuous, context-aware security. This paper presents a literature review investigating the application of ZTA principles to secure modern CNS ecosystems, following the guidelines of the International Civil Aviation Organization (ICAO) through its Cybersecurity Strategy and Plan. We analyze the alignment of ZTA core tenets—such as least-privilege access, micro-segmentation, and continuous authentication—with the unique operational requirements of CNS systems. This paper also presents a cybersecurity framework, under development within the Future Communications Digital Infrastructure (FCDI) project of the SESAR JU program, which aims to assist CNS stakeholders in collaboratively identifying cybersecurity threats within their scope of responsibility. The review critically examines implementation challenges for specific CNS subsystems: secure aeronautical communications (e.g., LDACS), resilient PNT (Positioning, Navigation, and Timing) services, and integrated surveillance networks (e.g., ADS-B, multilateration). Furthermore, we identify and evaluate domain-specific challenges, including integration with legacy avionics and ground systems, managing stringent latency and reliability constraints, and protecting against sophisticated threats targeting supply chains and data fusion processes. By synthesizing current research and practical deployment insights, this review aims to provide a foundational reference for aerospace engineers, cybersecurity specialists, and policymakers, offering a roadmap to enhance the cyber-resilience of vital CNS infrastructure in an era of evolving digital threats.

Alzheimer’s disease (AD) is the most prevalent neurodegenerative disorder worldwide, affecting approximately 56.9 million people in 2021 and projected to reach 152 million by 2050. Its defining pathological features, amyloid-beta plaques and neurofibrillary tangles, accumulate for up to two decades before cognitive symptoms emerge, placing the preclinical and mild cognitive impairment (MCI) stages at the centre of the early detection problem. Despite this, current diagnostic practice in routine clinical settings remains unreliable, with post-mortem studies placing the specificity of clinical AD diagnosis between 44.3 and 70.8% even in specialist memory clinics. Machine learning (ML) and deep learning (DL) applied to neuroimaging and electrophysiological data have emerged as candidate tools for closing this diagnostic gap, yet whether the accuracy figures reported in published studies translate into clinically useful performance on independent data remains unresolved. This study presents a structured comparative review of machine learning and deep learning methods reported across four publicly available Alzheimer’s disease datasets, namely the Alzheimer’s Disease Neuroimaging Initiative (ADNI), the Open Access Series of Imaging Studies (OASIS), the OpenNeuro ds004504 electroencephalography (EEG) dataset, and the Kaggle Alzheimer’s magnetic resonance imaging (MRI) dataset. Thirteen model families are examined through the published literature rather than through new experiments, and for each model and dataset combination, the best accuracy reported in the source study is recorded alongside the model’s mathematical formulation. All performance figures reported in this abstract and throughout the paper are taken from the published studies reviewed, not from new experiments conducted by the authors. Across the reviewed studies, deep learning architectures pre-trained on ImageNet and fine-tuned on neuroimaging data are reported to produce the highest accuracy on MRI classification tasks. Residual Network (ResNet)-101 is reported at 98.21 percent on ADNI and 97.45 percent on OASIS, while the IncepRes fusion architecture reaches 98.35% on OASIS by combining multi-scale feature extraction from InceptionV3 with residual connectivity from ResNet152V2. Traditional machine learning classifiers remain competitive on tabular clinical and biomarker data, with Extreme Gradient Boosting (XGBoost) reaching 91% on ADNI multiclass features. Logistic Regression achieves 82 to 85% on binary ADNI classification and is the only classifier in this review that provides explicit per-feature prediction contributions without post hoc tooling. Gaussian Naïve Bayes achieves 80 to 83% on the same task. On the OpenNeuro EEG dataset, K-nearest neighbours (KNN) with singular value decomposition (SVD) entropy features achieves 91% binary accuracy, with feature engineering quality determining performance more reliably than classifier architecture. Eight principal findings emerge from the cross-dataset analysis. Binary classification consistently outperforms multiclass by 10 to 30% across all datasets, reflecting the genuine biological ambiguity of the mild cognitive impairment category. Dataset size and augmentation predict reported accuracy more reliably than model architecture. Ensemble methods outperform individual classifiers by 5 to 8% in nearly every imaging study. Deeper architectures can overfit small clinical cohorts. EEG models trail MRI models by approximately 10 to 15% on comparable binary tasks. Cross-dataset generalisation has not been systematically evaluated in most studies, and the few that have tested it report accuracy drops of 5 to 10% or more when models encounter data from different scanners or cohorts. Eight recurring limitations constrain the clinical utility of these findings. Small sample sizes and limited demographic diversity, severe class imbalance inflating raw accuracy metrics, poor cross-dataset generalisation driven by scanner heterogeneity, limited deep learning interpretability, the dominance of binary over multiclass tasks, the absence of longitudinal modelling despite available datasets, inadequate standardisation of preprocessing and evaluation protocols, and the signal-to-noise ratio constraints specific to EEG recordings of elderly patients collectively define the gap between benchmark performance and clinical readiness. Future work must prioritise multi-centre training cohorts, multimodal fusion architectures, longitudinal progression modelling, and standardised interpretability evaluation as non-optional requirements for any system intended for clinical deployment.

Motor Imagery (MI)-based brain–computer interfaces (BCIs) offer promising solutions for enhancing communication and motor functions in individuals with neurological impairments. However, decoding EEG signals accurately is difficult because of their poor signal-to-noise ratio and variability across subjects and sessions. In addition, EEG signals are sensitive to noise. Moreover, the low spatial resolution of EEG signals makes model generalization unreliable due to differences between signals across subjects. While several deep learning models have been developed, a fair comparison remains difficult due to differences in pre-processing, training procedures, and evaluation protocols. This study provides a systematic, controlled comparison of five deep learning approaches for subject-specific classification—EEGNet, EEG-TCNet, ShallowConvNet, DeepConvNet, and CTNet—using the BCI Competition IV datasets 2a and 2b. To enable an unbiased comparison, all models are trained using the same pipeline, with uniform pre-processing and training. Apart from classical accuracy scores, the effect of a constant set of hyper-parameters on the training dynamics, generalization capacity, and the susceptibility to overfitting is evaluated. The performance of the above-stated models is evaluated based on training dynamics, computational efficiency, accuracy, and the quality of the features learned by the models. Using the five-dimensional analysis framework consisting of quantitative performance metrics, training curves, confusion matrix analysis, ROC analysis, and t-SNE visualization techniques, the performance of the brain–computer interfaces is comprehensively analyzed. The experimental analysis confirms that CTNet outperforms other models, with accuracy values of 82.56% and 86.42% on the BCI competition IV datasets 2a and 2b, respectively. The EEGNet model is recognized as having the most potential in the field of real-time applications, owing to its light structure; meanwhile, the DeepConvNet model shows signs of overfitting, despite showing good accuracy. These findings highlight that model training characteristics and sensitivity to the hyper-parameters are important factors in evaluating deep learning models for MI-EEG classification problems.