Search

Respiratory viruses' detection is vitally important in coping with pandemics such as COVID-19. Conventional methods typically require laboratory-based, high-cost equipment. An emerging alternative method is Near-Infrared (NIR) spectroscopy, especially a portable one of the type that has the benefits of low cost, portability, rapidity, ease of use, and mass deployability in both clinical and field settings. One obstacle to its effective application lies in its common limitations, which include relatively low specificity and general quality. Characteristically, the spectra curves show an interweaving feature for the virus-present and virus-absent samples. This then provokes the idea of using machine learning methods to overcome the difficulty. While a subsequent obstacle coincides with the fact that a direct deployment of the machine learning approaches leads to inadequate accuracy of the modelling results. This paper presents a data-driven study on the detection of two common respiratory viruses, the respiratory syncytial virus (RSV) and the Sendai virus (SEV), using a portable NIR spectrometer supported by a machine learning solution enhanced by an algorithm of variable selection via the Variable Importance in Projection (VIP) scores and its Quantile value, along with variable truncation processing, to overcome the obstacles to a certain extent. We conducted extensive experiments with the aid of the specifically developed algorithm of variable selection, using a total of four datasets, achieving classification accuracy of: (1) 0.88, 0.94, and 0.93 for RSV, SEV, and RSV + SEV, respectively, averaged over multiple runs, for the neural network modelling of taking in turn 3 sessions of data for training and the remaining one session of an 'unknown' dataset for testing. (2) the average accuracy of 0.94 (RSV), 0.97 (SEV), and 0.97 (RSV + SEV) for model validation and 0.90 (RSV), 0.93 (SEV), and 0.91 (RSV + SEV) for model testing, using two of the datasets for model training, one for model validation and the other for model testing. These results demonstrate the feasibility of using portable NIR spectroscopy coupled with machine learning to detect respiratory viruses with good accuracy, and the approach could be a viable solution for population screening. [ABSTRACT FROM AUTHOR]

Reconfigurable intelligent surfaces (RIS) are expected to bring about a revolutionary transformation in vehicular networks, thus paving the way for a future characterized by connected and automated vehicles (CAV). An RIS is a planar structure comprising many passive elements that can dynamically manipulate electromagnetic waves to enhance wireless communication by reflecting, refracting, and focusing signals in a programmable manner. RIS exhibits substantial potential for improving vehicle-to-everything (V2X) communication through various means, including coverage enhancement, interference mitigation, improving signal strength, and providing additional layers of privacy and security. This article presents a comprehensive survey that explores the emerging opportunities arising from the integration of RIS into vehicular networks. To examine the convergence of RIS and V2X communications, the survey adopted a holistic approach, thus highlighting the potential benefits and challenges of this combination. In this study, we examined several applications of RIS-aided V2X communication. Subsequently, we delve into the fundamental emerging technologies that are expected to empower vehicular networks, encompassing mobile edge computing (MEC), non-orthogonal multiple access (NOMA), millimeter-wave communication (mmWave), Artificial Intelligence (AI), and visible light communication (VLC). Finally, to stimulate further research in this domain, we emphasize noteworthy research challenges and potential avenues for future exploration. [ABSTRACT FROM AUTHOR]

In the ever-evolving landscape of modern agriculture, the integration of advanced technologies has become indispensable for optimizing crop management and ensuring sustainable food production. This paper presents the development and implementation of a real-time AI-assisted push-broom hyperspectral system for plant identification. The push-broom hyperspectral technique, coupled with artificial intelligence, offers unprecedented detail and accuracy in crop monitoring. This paper details the design and construction of the spectrometer, including optical assembly and system integration. The real-time acquisition and classification system, utilizing an embedded computing solution, is also described. The calibration and resolution analysis demonstrates the accuracy of the system in capturing spectral data. As a test, the system was applied to the classification of plant leaves. The AI algorithm based on neural networks allows for the continuous analysis of hyperspectral data relative up to 720 ground positions at 50 fps. [ABSTRACT FROM AUTHOR]

The accelerated development of technologies within the Internet of Things landscape has led to an exponential boost in the volume of heterogeneous data generated by interconnected sensors, particularly in scenarios with multiple data sources as in smart cities. Transferring, processing, and storing a vast amount of sensed data poses significant challenges for Internet of Things systems. In this sense, data reduction techniques based on artificial intelligence have emerged as promising solutions to address these challenges, alleviating the burden on the required storage, bandwidth, and computational resources. This article proposes a framework that exploits the concept of data reduction to decrease the amount of heterogeneous data in certain applications. A machine learning model that predicts a distortion rate and its corresponding reduction rate of the imputed data is also proposed, which uses the predicted values to select, among many reduction techniques, the most suitable approach. To support such a decision, the model also considers the context of the data producer that dictates the class of reduction algorithm that is allowed to be applied to the input stream. The achieved results indicate that the Huffman algorithm performed better considering the reduction of time-series data, with significant potential applications for smart city scenarios. [ABSTRACT FROM AUTHOR]

The growing demand from the extended reality and wearable electronics market has led to an increased focus on the development of flexible human-machine interfaces (HMI). These interfaces require efficient user input acquisition modules that can realize touch operation, handwriting input, and motion sensing functions. In this paper, we present a systematic review of triboelectric-based contact localization electronics (TCLE) which play a crucial role in enabling the lightweight and long-endurance designs of flexible HMI. We begin by summarizing the mainstream working principles utilized in the design of TCLE, highlighting their respective strengths and weaknesses. Additionally, we discuss the implementation methods of TCLE in realizing advanced functions such as sliding motion detection, handwriting trajectory detection, and artificial intelligence-based user recognition. Furthermore, we review recent works on the applications of TCLE in HMI devices, which provide valuable insights for guiding the design of application scene-specified TCLE devices. Overall, this review aims to contribute to the advancement and understanding of TCLE, facilitating the development of next-generation HMI for various applications. [ABSTRACT FROM AUTHOR]

Pressure sensor-impregnated walkways transform a person's footfalls into spatiotemporal signals that may be sufficiently complex to inform emerging artificial intelligence (AI) applications in healthcare. Key consistencies within these plantar signals show potential to uniquely identify a person, and to distinguish groups with and without neuromotor pathology. Evidence shows that plantar pressure distributions are altered in aging and diabetic peripheral neuropathy, but less is known about pressure dynamics in chemotherapy-induced peripheral neuropathy (CIPN), a condition leading to falls in cancer survivors. Studying pressure dynamics longitudinally as people develop CIPN will require a composite model that can accurately characterize a survivor's gait consistencies before chemotherapy, even in the presence of normal step-to-step variation. In this paper, we present a state-of-the-art data-driven learning technique to identify consistencies in an individual's plantar pressure dynamics. We apply this technique to a database of steps taken by each of 16 women before they begin a new course of neurotoxic chemotherapy for breast or gynecologic cancer. After extracting gait features by decomposing spatiotemporal plantar pressure data into low-rank dynamic modes characterized by three features: frequency, a decay rate, and an initial condition, we employ a machine-learning model to identify consistencies in each survivor's walking pattern using the centroids for each feature. In this sample, our approach is at least 86% accurate for identifying the correct individual using their pressure dynamics, whether using the right or left foot, or data from trials walked at usual or fast speeds. In future work, we suggest that persistent deviation from a survivor's pre-chemotherapy step consistencies could be used to automate the identification of peripheral neuropathy and other chemotherapy side effects that impact mobility. [ABSTRACT FROM AUTHOR]

Deep learning has rapidly increased in popularity, leading to the development of perception solutions for autonomous driving. The latter field leverages techniques developed for computer vision in other domains for accomplishing perception tasks such as object detection. However, the black-box nature of deep neural models and the complexity of the autonomous driving context motivates the study of explainability in these models that perform perception tasks. Moreover, this work explores explainable AI techniques for the object detection task in the context of autonomous driving. An extensive and detailed comparison is carried out between gradient-based and perturbation-based methods (e.g., D-RISE). Moreover, several experimental setups are used with different backbone architectures and different datasets to observe the influence of these aspects in the explanations. All the techniques explored consist of saliency methods, making their interpretation and evaluation primarily visual. Nevertheless, numerical assessment methods are also used. Overall, D-RISE and guided backpropagation obtain more localized explanations. However, D-RISE highlights more meaningful regions, providing more human-understandable explanations. To the best of our knowledge, this is the first approach to obtaining explanations focusing on the regression of the bounding box coordinates. [ABSTRACT FROM AUTHOR]

The accurate measurement of joint angles during patient rehabilitation is crucial for informed decision making by physiotherapists. Presently, visual inspection stands as one of the prevalent methods for angle assessment. Although it could appear the most straightforward way to assess the angles, it presents a problem related to the high susceptibility to error in the angle estimation. In light of this, this study investigates the possibility of using a new approach to angle calculation: a hybrid approach leveraging both a camera and LiDAR technology, merging image data with point cloud information. This method employs AI-driven techniques to identify the individual and their joints, utilizing the cloud-point data for angle computation. The tests, considering different exercises with different perspectives and distances, showed a slight improvement compared to using YOLO v7 for angle calculation. However, the improvement comes with higher system costs when compared with other image-based approaches due to the necessity of equipment such as LiDAR and a loss of fluidity during the exercise performance. Therefore, the cost–benefit of the proposed approach could be questionable. Nonetheless, the results hint at a promising field for further exploration and the potential viability of using the proposed methodology. [ABSTRACT FROM AUTHOR]

The popularity and demand for high-quality date palm fruits (Phoenix dactylifera L.) have been growing, and their quality largely depends on the type of handling, storage, and processing methods. The current methods of geometric evaluation and classification of date palm fruits are characterised by high labour intensity and are usually performed mechanically, which may cause additional damage and reduce the quality and value of the product. Therefore, non-contact methods are being sought based on image analysis, with digital solutions controlling the evaluation and classification processes. The main objective of this paper is to develop an automatic classification model for varieties of date palm fruits using a convolutional neural network (CNN) based on two fundamental criteria, i.e., colour difference and evaluation of geometric parameters of dates. A CNN with a fixed architecture was built, marked as DateNET, consisting of a system of five alternating Conv2D, MaxPooling2D, and Dropout classes. The validation accuracy of the model presented in this study depended on the selection of classification criteria. It was 85.24% for fruit colour-based classification and 87.62% for the geometric parameters only; however, it increased considerably to 93.41% when both the colour and geometry of dates were considered. [ABSTRACT FROM AUTHOR]

In a seismic context, it is fundamental to deploy distributed sensor networks for Structural Health Monitoring (SHM). Indeed, regularly gathering data from a structure/infrastructure gives insight on the structural health status, and Artificial Intelligence (AI) technologies can help in exploiting this information to generate early warnings useful for decision-making purposes. With a perspective of developing a remote monitoring platform for the built environment in a seismic context, the authors tested self-sensing concrete beams in loading tests, focusing on the measured electrical impedance. The formed cracks were objectively assessed through a vision-based system. Also, a comparative analysis of AI-based and statistical prediction methods, including Prophet, ARIMA, and SARIMAX, was conducted for predicting electrical impedance. Results show that the real part of electrical impedance is highly correlated with the applied load (Pearson's correlation coefficient > 0.9); hence, the piezoresistive ability of the manufactured specimens has been confirmed. Concerning prediction methods, the superiority of the Prophet model over statistical techniques was demonstrated (Mean Absolute Percentage Error, MAPE < 1.00%). Thus, the exploitation of electrical impedance sensors, vision-based systems, and AI technologies can be significant to enhance SHM and maintenance needs prediction in the built environment. [ABSTRACT FROM AUTHOR]