With the development of intelligent transportation systems, vehicular edge computing (VEC) has played a pivotal role by integrating computation, storage, and analytics closer to the vehicles. VEC represents a paradigm shift towards real-time data processing and intelligent decision-making, overcoming challenges associated with latency and resource constraints. In VEC scenarios, the efficient scheduling and allocation of computing resources are fundamental research areas, enabling real-time processing of vehicular tasks and intelligent decision-making. This paper provides a comprehensive review of the latest research in Deep Reinforcement Learning (DRL)-based task scheduling and resource allocation in VEC environments. Firstly, the paper outlines the development of VEC and introduces the core concepts of DRL, shedding light on their growing importance in the dynamic VEC landscape. Secondly, the state-of-the-art research in DRL-based task scheduling and resource allocation is categorized, reviewed, and discussed. Finally, the paper discusses current challenges in the field, offering insights into the promising future of VEC applications within the realm of intelligent transportation systems.

Abstract Deep learning-based object detection models have become a preferred choice for crop detection tasks in crop monitoring activities due to their high accuracy and generalization capabilities. However, their high computational demand and large memory footprint pose a challenge for use on mobile embedded devices deployed in crop monitoring settings. Various approaches have been taken to minimize the computational cost and reduce the size of object detection models such as channel and layer pruning, detection head searching, backbone optimization, etc. In this work, we approached computational lightening, model compression, and speed improvement by discarding one or more of the three detection scales of the YOLOv5 object detection model. Thus, we derived up to five separate fast and light models, each with only one or two detection scales. To evaluate the new models for a real crop monitoring use case, the models were deployed on NVIDIA Jetson nano and NVIDIA Jetson Orin devices. The new models achieved up to 21.4% reduction in giga floating-point operations per second (GFLOPS), 31.9% reduction in number of parameters, 30.8% reduction in model size, 28.1% increase in inference speed, with only a small average accuracy drop of 3.6%. These new models are suitable for crop detection tasks since the crops are usually of similar sizes due to the high likelihood of being in the same growth stage, thus, making it sufficient to detect the crops with just one or two detection scales.

Attention Deficit/Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder in childhood that often persists into adulthood. Objectively diagnosing ADHD can be challenging due to the reliance on subjective questionnaires in clinical assessment. Fortunately, recent advancements in artificial intelligence (AI) have shown promise in providing objective diagnoses through the analysis of medical images or activity recordings. These AI-based techniques have demonstrated accurate ADHD diagnosis; however, the growing complexity of deep learning models has introduced a lack of interpretability. These models often function as black boxes, unable to offer meaningful insights into the data patterns that characterize ADHD. OBJECTIVE: This paper proposes a methodology to interpret the output of an AI-based diagnosis system for combined ADHD in age and gender-stratified populations. METHODS: Our system is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks (CNNs) to classify spectrograms of activity windows. These windows are interpreted using occlusion maps to highlight the time-frequency patterns explaining ADHD activity. RESULTS: Significant differences in the frequency patterns between ADHD and controls both in diurnal and nocturnal activity were found for all the populations. Temporal dispersion also presented differences in the male population. CONCLUSION: The proposed interpretation techniques for CNNs highlighted gender- and age-related differences between ADHD patients and controls. Leveraging these differences could potentially lead to improved diagnostic accuracy, especially if a larger and more balanced dataset is utilized. SIGNIFICANCE: Our findings pave the way for the development of an AI-based diagnosis system for ADHD that offers interpretability, thereby providing valuable insights into the underlying etiology of the disease.

This paper proposes a complete convolutional formulation for 2D multimodal pairwise image registration problems based on free-form deformations. We have reformulated in terms of discrete 1D convolutions the evaluation of spatial transformations, the regularization term, and their gradients for three different multimodal registration metrics, namely, normalized cross correlation, mutual information, and normalized mutual information. A sufficient condition on the metric gradient is provided for further extension to other metrics. The proposed approach has been tested, as a proof of concept, on contrast-enhanced first-pass perfusion cardiac magnetic resonance images. Execution times have been compared with the corresponding execution times of the classical tensor product formulation, both on CPU and GPU. The speed-up achieved by using convolutions instead of tensor products depends on the image size and the number of control points considered, the larger those magnitudes, the greater the execution time reduction. Furthermore, the speed-up will be more significant when gradient operations constitute the major bottleneck in the optimization process.

Recently, an efficient implementation of convolution-based free form deformations (FFD) has been proposed for both groupwise 3D monomodal and 2D pairwise multimodal registrations. However, there is still an unmet need in the field for groupwise L-D multimodal registration with L≥2. In this correspondence, we address this need and present a solution for achieving accurate registration using two popular metrics: Renyi entropy and PCA2.

This study proposes a novel memetic algorithm (MA) for the blind equalisation of digital multiuser channels with direct‐sequence/code‐division multiple‐access sharing scheme. Equalisation involves two different tasks, the estimation of (i) channel response and (ii) transmitted data. The corresponding channel model is first analysed and then the MA is developed for this specific communication system. Convergence, population diversity and near–far resistance have been analysed. Numerical experiments include comparative results with traditional multiuser detectors as well as with other nature‐inspired approaches. The proposed receiver is proved to allow higher transmission rates over existing channels while supporting stronger interferences as well as fading and time‐variant effects. Required computation requisites are kept moderate in most of the cases. The proposed MA saves 80% of computation time with respect to a standard genetic algorithm and about 15% with respect to a similar two‐stage MA, while keeping a statistically significant higher performance. Besides, complexity increases only by a factor of 5, when the number of active users doubles, instead of found for the optimum maximum likelihood algorithm. The proposed method also exhibits high near–far resistance and achieves accurate channel response estimates, becoming an interesting and viable alternative to so far proposed methods.

Attention Deficit/Hyperactivity Disorder (ADHD) is the most common neurobehavioral disorder in children and adolescents. However, its etiology is still unknown, and this hinders the existence of reliable, fast and inexpensive standard diagnostic methods. OBJECTIVE: This paper proposes an end-to-end methodology for automatic diagnosis of the combined type of ADHD. METHODS: Diagnosis is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks to classify spectrograms of activity windows. RESULTS: We achieve up to [Formula: see text] average sensitivity, [Formula: see text] specificity and AUC values over [Formula: see text]. Overall, our figures overcome those obtained by actigraphy-based methods reported in the literature as well as others based on more expensive (and not so convenient) acquisition methods. CONCLUSION: These results reinforce the idea that combining deep learning techniques together with actimetry can lead to a robust and efficient system for objective ADHD diagnosis. SIGNIFICANCE: Reliance on simple activity measurements leads to an inexpensive and non-invasive objective diagn-ostic method, which can be easily implemented with daily devices.

Object detection systems mounted on Unmanned Aerial Vehicles (UAVs) have gained momentum in recent years in light of the widespread use cases enabled by such systems in public safety and other areas. Machine learning has emerged as an enabler for improving the performance of object detection. However, there is little existing work that has studied the performance of the machine learning approach, which is computationally resource demanding, in a portable mobile platform for UAV based object detection in user mobility scenarios. This paper evaluates an integrated real-world testbed for this scenario, by employing commercial-off-the-shelf devices including a UAV system and a machine-learning-enabled mobile platform. It presents benchmarking results about the performance of popular machine learning and computer vision frameworks such as TensorFlow and OpenCV and the associated algorithms such as YOLO, embedded in a smartphone execution environment of limited resources. The results highlight opportunities and provide insights into technical gaps to be filled to realize real-time machine-learning-based object detection on a mobile platform with constrained resources.

The Fast Marching method is widely employed in several fields of image processing. Some years ago a Multi-Stencil version (MSFM) was introduced to improve its accuracy by solving the equation for a set of stencils and choosing the best solution at each considered node. The following work proposes a modified numerical scheme for MSFM to take into account the variation of the local cost, which has proven to be second order. The influence of the stencil set choice on the algorithm outcome with respect to stencil orthogonality and axis swapping is also explored, where stencils are taken from neighborhoods of varying radius. The experimental results show that the proposed schemes improve the accuracy of their original counterparts, and that the use of permutation-invariant stencil sets provides robustness against shifted vector coordinates in the stencil set.

Telehealth has shown potential to improve access to healthcare cost-effectively in respiratory illness. However, it has failed to live up to expectation, in part because of poor objective measures of symptoms such as cough events, which could lead to early diagnosis or prevention. Considering the burden that these conditions constitute for national health systems, an effort is needed to foster telehealth potential by developing low-cost technology for efficient monitoring and analysis of cough events. This paper proposes the use of local Hu moments as a robust feature set for automatic cough detection in smartphone-acquired audio signals. The final system feeds a k-nearest-neighbor classifier with the extracted features. To properly evaluate the system in a diversity of noisy backgrounds, we contaminated real cough audio data with a variety of sounds including noise from both indoor and outdoor environments and noncough events (sneeze, laugh, speech, etc.). The created database allows flexible settings of signal-to-noise ratio levels between background sounds and events (cough and noncough). This evaluation was complemented using real patient data from an outpatient clinic. The system is able to detect cough events with high sensitivity (up to 88.51%) and specificity (up to 99.77%) in a variety of noisy environments, overcoming other state-of-the-art audio features. Our proposal paves the way for ubiquitous cough monitoring with minimal disruption in daily activities.

Dynamic Adaptive Streaming over HTTP (DASH) is a popular over-the-top video content distribution technique that adapts the streaming session according to the user's network condition typically in terms of downlink bandwidth. This video quality adaptation can be achieved by scaling the frame quality, spatial resolution or frame rate. Despite the flexibility on the video quality scaling methods, each of these quality scaling dimensions has varying effects on the Quality of Experience (QoE) for end users. Furthermore, in video streaming, the changes in motion over time along with the scaling method employed have an influence on QoE, hence the need to carefully tailor scaling methods to suit streaming applications and content type. In this work, we investigate an intelligent DASH approach for the latest video coding standard H.265 and propose a heuristic QoE-aware cost-efficient adaptation scheme that does not switch unnecessarily to the highest quality level but rather stays temporarily at an intermediate quality level in certain streaming scenarios. Such an approach achieves a comparable and consistent level of quality under impaired network conditions as commonly found in Internet and mobile networks while reducing bandwidth requirements and quality switching overhead. The rationale is based on our empirical experiments, which show that an increase in bitrate does not necessarily mean noticeable improvement in QoE. Furthermore, our work demonstrates that the Signal-to-Noise Ratio (SNR) and the spatial resolution scalability types are the best fit for our proposed algorithm. Finally, we demonstrate an innovative interaction between quality scaling methods and the polarity of switching operations. The proposed QoE-aware scheme is implemented and empirical results show that it is able to reduce bandwidth requirements by up to 41% whilst achieving equivalent QoE compared with a representative DASH reference implementation.

Simultaneous wireless information and power transfer (SWIPT) offers novel designs that could enhance the sustainability and resilience of communication systems. Due to the very limited receiving power from radio frequency (RF) signals, optimal splitting strategies play an essential role for many SWIPT systems. This paper investigates optimal power splitting from the outage perspective by formulating the power, information and joint outage performance using a Markov chain, and studying the boundary conditions for achieving an energy- neutral state. Our results show that: 1)the power splitting factor is the key factor of intrinsic trade-off between power and information outage; and 2) the proposed polynomial method can obtain the optimal power splitting factor which leads to the minimum joint outage probability.

This paper presents a new, practical infrared video based surveillance system, consisting of a resolution-enhanced, automatic target detection/recognition (ATD/R) system that is widely applicable in civilian and military applications. To deal with the issue of small numbers of pixel on target in the developed ATD/R system, as are encountered in long range imagery, a super-resolution method is employed to increase target signature resolution and optimise the baseline quality of inputs for object recognition. To tackle the challenge of detecting extremely low-resolution targets, we train a sophisticated and powerful convolutional neural network (CNN) based faster-RCNN using long wave infrared imagery datasets that were prepared and marked in-house. The system was tested under different weather conditions, using two datasets featuring target types comprising pedestrians and 6 different types of ground vehicles. The developed ATD/R system can detect extremely low-resolution targets with superior performance by effectively addressing the low small number of pixels on target, encountered in long range applications. A comparison with traditional methods confirms this superiority both qualitatively and quantitatively.

The potential of telemedicine in respiratory health care has not been completely unveiled in part due to the inexistence of reliable objective measurements of symptoms such as cough. Currently available cough detectors are uncomfortable and expensive at a time when generic smartphones can perform this task. However, two major challenges preclude smartphone-based cough detectors from effective deployment namely, the need to deal with noisy environments and computational cost. This paper focuses on the latter, since complex machine learning algorithms are too slow for real-time use and kill the battery in a few hours unless specific actions are taken. In this paper, we present a robust and efficient implementation of a smartphone-based cough detector. The audio signal acquired from the device's microphone is processed by computing local Hu moments as a robust feature set in the presence of background noise. We previously demonstrated that pairing Hu moments and a standard k-NN classifier achieved accurate cough detection at the expense of computation time. To speed-up k-NN search, many tree structures have been proposed. Our cough detector uses an improved vantage point (vp)-tree with optimized construction methods and a distance function that results in faster searches. We achieve 18× speed-up over classic vp-trees, and 560× over standard implementations of k-NN in state-of-the-art machine learning libraries, with classification accuracies over 93%, enabling real-time performance on low-end smartphones.

Fall detection is a major problem in healthcare systems, especially for elderly people who are the most vulnerable. It is important to design and implement not only an accurate fall detection system (FDS) but also a system with a real-time response. The achievement of high accuracy and fast response time together allows the development of a system that helps saving lives, time and money in healthcare industry. This paper presents the design, simulation and implementation of a novel FDS using the Shimmer wearable sensor. The discrete wavelet transform (DWT) is applied for preprocessing the data coming from the Shimmer platform, principal component analysis (PCA) is used for dimensionality reduction and feature extraction and finally, a binary decision tree (DT) is utilized for classification purpose. The system is simulated in MATLAB prior to the implementation on the Zynq system-on-chip (SoC) for hardware acceleration. DWT is executed on the processing system (PS) of the Zynq platform in a software manner while PCA and DT are both implemented on the programmable logic (PL) for hardware acceleration. PCA and DT are developed in C and synthesized in Vivado high level synthesis (HLS) tool to transform the C based designed into a register transfer level (RTL) implementation. Various optimization techniques are explored in Vivado HLS. The performance of the FDS in terms of accuracy of the classifier is 88.4% while the overall resources used in PL of the Zynq vary between 2% and 23% depending on the running frequency and optimization technique used.

This paper proposes a topology-preserving multiresolution elastic registration method based on a discrete Markov random field of deformations and a block-matching procedure. The method is applied to the object-based interpolation of tomographic slices. For that purpose, the fidelity of a given deformation to the data is established by a block-matching strategy based on intensity- and gradient-related features, the smoothness of the transformation is favored by an appropriate prior on the field, and the deformation is guaranteed to maintain the topology by imposing some hard constraints on the local configurations of the field. The resulting deformation is defined as the maximum a posteriori configuration. Additionally, the relative influence of the fidelity and smoothness terms is weighted by the unsupervised estimation of the field parameters. In order to obtain an unbiased interpolation result, the registration is performed both in the forward and backward directions, and the resulting transformations are combined by using the local information content of the deformation. The method is applied to magnetic resonance and computed tomography acquisitions of the brain and the torso. Quantitative comparisons offer an overall improvement in performance with respect to related works in the literature. Additionally, the application of the interpolation method to cardiac magnetic resonance images has shown that the removal of any of the main components of the algorithm results in a decrease in performance which has proven to be statistically significant.

Attention-Deficit Hyperactivity Disorder (ADHD) is the most common mental health problem in childhood and adolescence. Its diagnosis is commonly performed in a subjective manner since current objective measurements are either expensive or time-consuming. However, subjective methods tend to overestimate the severity of the pathology. In this paper, we propose a novel methodology for automatic diagnosis of ADHD based on signal processing methods. The method is constructed in two stages: 1) An automatic activity/rest detection filter which allows for a separate analysis of both types of periods and 2) A feature extraction module based on nonlinear regularity quantification of either the global signal or the detected epochs. Results on real data show that the proposed methodology can discriminate between patients and controls with sensibility and specificity values approaching 80%.

A realistic log-compressed law for ultrasound images based on a real device is proposed. The model takes into account the linear behavior of the logarithmic amplifier for small signal gain which transforms image values in a different way as the classical models do. Additionally, for recovery purposes, a method for the estimation of the compression parameters is also proposed when a realistic log-compressed law is considered. Results with synthetic images show that the proposed method achieved a consistent Rayleigh parameter estimate with a very low error. Experiments with real images show that the inversion method is consistent through the whole acquisition process when parameters of the logarithmic amplifier are assumed constant.

This paper proposes a novel method to detect anomalies in network traffic, based on a nonrestricted α-stable first-order model and statistical hypothesis testing. To this end, we give statistical evidence that the marginal distribution of real traffic is adequately modeled with α-stable functions and classify traffic patterns by means of a Generalized Likelihood Ratio Test (GLRT). The method automatically chooses traffic windows used as a reference, which the traffic window under test is compared with, with no expert intervention needed to that end. We focus on detecting two anomaly types, namely floods and flash-crowds, which have been frequently studied in the literature. Performance of our detection method has been measured through Receiver Operating Characteristic (ROC) curves and results indicate that our method outperforms the closely-related state-of-the-art contribution described in. All experiments use traffic data collected from two routers at our university-a 25,000 students institution-which provide two different levels of traffic aggregation for our tests (traffic at a particular school and the whole university). In addition, the traffic model is tested with publicly available traffic traces. Due to the complexity of α-stable distributions, care has been taken in designing appropriate numerical algorithms to deal with the model.