Healthcare 4.0 is a recent e-health paradigm associated with the concept of Industry 4.0. It provides approaches to achieving precision medicine that delivers healthcare services based on the patient’s characteristics. Moreover, Healthcare 4.0 enables telemedicine, including telesurgery, early predictions, and diagnosis of diseases. This represents an important paradigm for modern societies, especially with the current situation of pandemics. The release of the fifth-generation cellular system (5G), the current advances in wearable device manufacturing, and the recent technologies, e.g., artificial intelligence (AI), edge computing, and the Internet of Things (IoT), are the main drivers of evolutions of Healthcare 4.0 systems. To this end, this work considers introducing recent advances, trends, and requirements of the Internet of Medical Things (IoMT) and Healthcare 4.0 systems. The ultimate requirements of such networks in the era of 5G and next-generation networks are discussed. Moreover, the design challenges and current research directions of these networks. The key enabling technologies of such systems, including AI and distributed edge computing, are discussed.

Background: In the future, extended reality technology will be widely used. People will be led to utilize virtual reality (VR) and augmented reality (AR) technologies in their daily lives, hobbies, numerous types of entertainment, and employment. Medical augmented reality has evolved with applications ranging from medical education to picture-guided surgery. Moreover, a bulk of research is focused on clinical applications, with the majority of research devoted to surgery or intervention, followed by rehabilitation and treatment applications. Numerous studies have also looked into the use of augmented reality in medical education and training. Methods: Using the databases Semantic Scholar, Web of Science, Scopus, IEEE Xplore, and ScienceDirect, a scoping review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) criteria. To find other articles, a manual search was also carried out in Google Scholar. This study presents studies carried out over the previous 14 years (from 2009 to 2023) in detail. We classify this area of study into the following categories: (1) AR and VR in surgery, which is presented in the following subsections: subsection A: MR in neurosurgery; subsection B: spine surgery; subsection C: oral and maxillofacial surgery; and subsection D: AR-enhanced human-robot interaction; (2) AR and VR in medical education presented in the following subsections; subsection A: medical training; subsection B: schools and curriculum; subsection C: XR in Biomedicine; (3) AR and VR for rehabilitation presented in the following subsections; subsection A: stroke rehabilitation during COVID-19; subsection B: cancer and VR, and (4) Millimeter-wave and MIMO systems for AR and VR. Results: In total, 77 publications were selected based on the inclusion criteria. Four distinct AR and/or VR applications groups could be differentiated: AR and VR in surgery (N = 21), VR and AR in Medical Education (N = 30), AR and VR for Rehabilitation (N = 15), and Millimeter-Wave and MIMO Systems for AR and VR (N = 7), where N is number of cited studies. We found that the majority of research is devoted to medical training and education, with surgical or interventional applications coming in second. The research is mostly focused on rehabilitation, therapy, and clinical applications. Moreover, the application of XR in MIMO has been the subject of numerous research. Conclusion: Examples of these diverse fields of applications are displayed in this review as follows: (1) augmented reality and virtual reality in surgery; (2) augmented reality and virtual reality in medical education; (3) augmented reality and virtual reality for rehabilitation; and (4) millimeter-wave and MIMO systems for augmented reality and virtual reality.

The demand for high-quality tomatoes to meet consumer and market standards, combined with large-scale production, has necessitated the development of an inline quality grading. Since manual grading is time-consuming, costly, and requires a substantial amount of labor. This study introduces a novel approach for tomato quality sorting and grading. The method leverages pre-trained convolutional neural networks (CNNs) for feature extraction and traditional machine-learning algorithms for classification (hybrid model). The single-board computer NVIDIA Jetson TX1 was used to create a tomato image dataset. Image preprocessing and fine-tuning techniques were applied to enable deep layers to learn and concentrate on complex and significant features. The extracted features were then classified using traditional machine learning algorithms namely: support vector machines (SVM), random forest (RF), and k-nearest neighbors (KNN) classifiers. Among the proposed hybrid models, the CNN-SVM method has outperformed other hybrid approaches, attaining an accuracy of 97.50% in the binary classification of tomatoes as healthy or rejected and 96.67% in the multiclass classification of them as ripe, unripe, or rejected when Inceptionv3 was used as feature extractor. Once another dataset (public dataset) was used, the proposed hybrid model CNN-SVM achieved an accuracy of 97.54% in categorizing tomatoes as ripe, unripe, old, or damaged outperforming other hybrid models when Inceptionv3 was used as a feature extractor. The performance metrics accuracy, recall, precision, specificity, and F1-score of the best-performing proposed hybrid model were evaluated.

Manual inspection of textiles is a long, tedious, and costly method. Technology has solved this problem by developing automatic systems for textile inspection. However, Jacquard fabrics present a challenge because patterns can be complex and seemingly random to systems. Only a few in-depth studies have been conducted on jacquard fabrics despite their important and intriguing nature. Previous studies on jacquard fabrics are of simple patterns. This paper introduces a new and novel field in fabrics defect detection. Complex-patterned jacquard fabrics are much more challenging. In this paper, novel defect detection models for jacquard-patterned fabrics are presented. Owing to the lack of available databases for jacquard fabrics, we compiled and experimented on our own novel dataset. Our dataset was collected from plain, undyed jacquard fabrics with different complex patterns. In this study, we used and tested several deep learning models with image pre-processing and convolutional neural networks (CNNs) for unsupervised detection of defects. We also used multispectral imaging, combining normal (RGB) and near-infrared (NIR) imaging to improve our system and increase its accuracy. We propose two systems: a semi-manual system using a simple CNN network for operation on separate patterns and an integrated automated system that uses state-of-the-art CNN architectures to run on the entire dataset without prior pattern specification. The images are preprocessed using contrast-limited adaptive Histogram Equalization (CLAHE) to enhance their features. We concluded that deep learning is efficient and can be used for defect detection in complex patterns. Proposed method of EfficientNet CNN gave high accuracy reaching 99% approximately. We also found that multispectral imaging is more advantageous and yields higher accuracy.

The accurate detection of P-wave arrival time is imperative for determining the hypocenter location of an earthquake. However, precise detection of onset time becomes more difficult when the signal-to-noise ratio (SNR) of the seismic data is low, such as during microearthquakes. In this letter, a stacked denoising autoencoder (SDAE) is proposed to smooth the background noise. The SDAE acts as a denoising filter for the seismic data. In the proposed algorithm, the SDAE is utilized to reduce background noise such that the onset time becomes more clear and sharp. Afterward, a hard decision with one threshold is used to detect the onset time of the event. The proposed algorithm is evaluated on both synthetic and field seismic data. As a result, the proposed algorithm outperforms the short-time average/long-time average and the Akaike information criterion algorithms. The proposed algorithm accurately picks the onset time of 94.1% for 407 field seismic waveforms with a standard deviation error of 0.10 s. In addition, the results indicate that the proposed algorithm can pick arrival times accurately for weak SNR seismic data with SNR higher than -14 dB.