Artificial Intelligence (AI) based generative models have advanced rapidly, making it possible to generate highly realistic synthetic media. These technologies build new opportunities for creative and legitimate use in various domains, but they also give rise to significant concerns about digital trust and privacy. Though it has various legitimate uses, it can also be used to generate harmful content, often known as "deepfake". It can cause political misinformation, non-consensual content generation and financial fraud that costs millions. These consequences are harmful for democracy, healthcare and the legal system. One of the growing concerns is the emergence of deepfake in medical imaging, where fabrication and manipulation of diagnostic scans and clinical imagery directly threaten patient safety, healthcare integrity and medical forensics. This paper presents a systematic literature review (SLR) of various deepfake generation and detection methods based on Artificial intelligence. Following the PRISMA framework, relevant studies are identified from major scientific databases, including IEEE Xplore, Scopus, ScienceDirect, SpringerLink, Google scholar and ACM Digital Library. Following a PRISMA-based search and screening process, 142 primary studies were selected from an initial pool of studies, based on predefined inclusion, exclusion, and quality-assessment criteria. Some literature published prior to 2021 is additionally cited for contextual background, separate from the 142 primary studies reviewed. The selected literature is analysed and categorised into different deepfake generation and detection methods. Furthermore, benchmark datasets, evaluation protocols and comparative performance trends are analysed. Key challenges such as dataset bias, poor generalization, adversarial vulnerability and lack of explainability are discussed. Future research directions are outlined. This review aims to serve as a useful reference for researchers and practitioners working on reliable deepfake detection systems.
Modern agriculture is increasingly driven by data-centric and artificial intelligence (AI)-enabled approaches to improve productivity, resource efficiency, and precision in decision-making. In this context, computer vision datasets have emerged as critical resources for enabling automated agricultural analysis. This study presents a large-scale, data-centric review of agricultural computer vision datasets using a PRISMA-guided systematic review methodology. A systematic search of the peer-reviewed data journals Scientific Data and Data in Brief, conducted through 31 January 2026, identified 2,308 records, from which 253 eligible dataset publications were retained after duplicate removal and eligibility screening based on predefined inclusion and exclusion criteria. We systematically analyze the dataset landscape across multiple dimensions, including vision tasks, annotation strategies, acquisition environments, sensing modalities, and geographic distribution. Furthermore, we propose a unified multi-dimensional taxonomy that organizes datasets based on task orientation, semantic content, and design characteristics, enabling structured comparison and informed dataset selection. Our analysis identifies key limitations, including sampling bias, underrepresentation of crops and regions, inconsistent annotation practices, and limited interoperability, which collectively hinder reproducibility and model generalization. Additionally, challenges in dataset accessibility and the absence of standardized benchmarking frameworks restrict effective knowledge transfer. Finally, we outline critical directions for future research, emphasizing standardized dataset design, scalable annotation frameworks, and robust evaluation protocols to support the development of reliable and generalizable agricultural AI systems.
Accurate and reliable water quality monitoring (WQM) has become increasingly important due to rapid urbanization, industrialization, climate change, and anthropogenic activities that threaten global freshwater resources. Conventional water quality assessment methods primarily rely on manual sampling and laboratory analysis, which are labour-intensive, time-consuming, costly, and unsuitable for continuous real-time monitoring of large-scale aquatic environments. Recent advances in Artificial Intelligence (AI), the Internet of Things (IoT), and sensing technologies have enabled intelligent, data-driven approaches capable of modelling complex nonlinear relationships, detecting contamination events, and improving predictive decision-making. This study presents a systematic literature review (SLR) of AI-based water quality monitoring using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. A systematic search of IEEE Xplore, Scopus, Web of Science, ScienceDirect, and SpringerLink identified studies published between 2020 and 2026, of which 91 met the predefined inclusion and exclusion criteria. Review and survey articles were excluded from the analytical corpus so that secondary literature was not pooled with primary studies. A structured taxonomy is developed to characterise the strengths, limitations, interpretability and reported applicability of these model families. Because the included studies differ in target variable, dataset, preprocessing and validation protocol, no pooled performance comparison across model categories is reported and no meta-analysis was undertaken. The review identifies key challenges, including heterogeneous datasets, limited model generalization, overfitting, computational complexity, sensor calibration issues, data inconsistency, and the lack of standardized benchmark datasets. Furthermore, emerging research directions comprising Explainable Artificial Intelligence (XAI), Federated Learning, Edge AI, Graph Neural Networks, Digital Twins, Foundation Models, and multimodal environmental intelligence are discussed. The findings provide researchers, practitioners and policymakers with a structured reference to the current evidence base on AI-based water quality monitoring, together with the methodological limitations of that evidence, to inform the development of future monitoring systems for sustainable water resource management.
Touchless gesture recognition by vision represents a promising sterile and non-contact human-computer interface (HCI) for clinical settings, where sterility and continuous workflow are paramount, yet its practical deployment remains substantially unrealised. This systematic review evaluates the deployment of RGB, RGB-D, and skeletal-vision systems across operating rooms, intensive care units, and rehabilitation settings. Following PRISMA guidelines, literature published between 2018 and 2026 was analysed, with emphasis on clinically deployed and near-clinical systems rather than purely algorithmic benchmarks. Recent deep learning methods, such as convolutional neural networks (CNNs), long short-term memory (LSTM) networks, transformers, and multimodal fusion models, have been shown to achieve laboratory accuracy of more than 95
Real-world learning scenarios often exhibit asymmetries between training and inference, where additional or higher-quality information is available only during training. The Learning Under Privileged Information (LUPI) paradigm provides a formal framework to study such settings. Despite research interest over the years, the extensive literature on LUPI remains highly fragmented. In this survey, we present a comprehensive and structured overview of research on LUPI and its related formulations. We review 107 papers published between 2009 and 2025 and propose a novel unified taxonomy based on two core dimensions: the underlying machine learning models, spanning both shallow and deep architectures, and the methodological strategies used to integrate privileged information. Additionally, we provide an extensive overview of the various application domains and the particular types of privileged modalities used. We also discuss key insights and open challenges, focusing on how and when privileged information can be effectively leveraged in modern machine learning systems.
