Ku-band drive amplification and a 7-bit true-time-delay (TTD) function were realized as a part of a LTCC-based T/R module to increase integration. The 8-channel T/R module was fabricated and its key characteristics were measured, including a 3-bit (1/2/4 λ) TTD, 4-bit (0.25/0.5/1/2 λ) TTD, receive gain, noise figure and output power. The 8-channel T/R module can be further adopted to increase bandwidth and scanning angle of phased arrays without beam squint. Full article

Several market sectors are attracted by the potential of unmanned aerial vehicles (UAVs), such as delivery, agriculture, and cinema, among others. UAVs are becoming part of Internet of Things (IoT) networks in the development of autonomous and scalable solutions. However, these vehicles are gradually becoming attractive targets for cyberattacks. This study proposes the development of an efficient platform based on the Message Queuing Telemetry Transport (MQTT) protocol for UAV control and Denial-of-Service (DoS) detection embedded in the UAV system. For the efficiency test, latency, network and memory consumption on the platform were measured, in addition to the correlation between payload and delay time. The results of efficiency tests were collected for the three levels of quality of service (QoS). A strong correlation greater than 90% was found between delay and data size for all QoS levels, showing almost a linear proportion. In DoS detection, the best results were a true positive rate (TPR) of 0.97 with 16 features from the AWID2 dataset using LightGBM with Bayesian optimization and data balancing. Unlike other studies, the built platform shows efficiency for UAV control and guarantees security in the communication with the broker and in the Wi-Fi UAV network. Full article

Smart farms, as a part of high-tech agriculture, collect a huge amount of data from IoT devices about the conditions of animals, plants, and the environment. These data are most often stored locally and are not used in intelligent monitoring systems to provide opportunities for extracting meaningful knowledge for the farmers. This often leads to a sense of missed transparency, fairness, and accountability, and a lack of motivation for the majority of farmers to invest in sensor-based intelligent systems to support and improve the technological development of their farm and the decision-making process. In this paper, a data-driven intelligent monitoring system in a cloud environment is proposed. The designed architecture enables a comprehensive solution for interaction between data extraction from IoT devices, preprocessing, storage, feature engineering, modelling, and visualization. Streaming data from IoT devices to interactive live reports along with built machine learning (ML) models are included. As a result of the proposed intelligent monitoring system, the collected data and ML modelling outcomes are visualized using a powerful dynamic dashboard. The dashboard allows users to monitor various parameters across the farm and provides an accessible way to view trends, deviations, and patterns in the data. ML models are trained on the collected data and are updated periodically. The data-driven visualization enables farmers to examine, organize, and represent collected farm’s data with the goal of better serving their needs. Performance and durability tests of the system are provided. The proposed solution is a technological bridge with which farmers can easily, affordably, and understandably monitor and track the progress of their farms with easy integration into an existing IoT system. Full article

Rectification of vehicle plate images helps to improve the accuracy of license-plate recognition (LPR). It is a perspective-transformation process to project images as if taken from the front geometrically. To obtain the projection matrix, we require the (x, y) coordinates of four corner positions of plates in images. In this paper, we consider the problem of unsupervised domain adaptation for corner detection in plate images. We trained a model with plate images of one country, the source domain, and applied a domain adaptation scheme so that the model is able to work well on the plates of a different country, the target domain. For this study, we created a dataset of 22,096 Korea plate images with corner labels, which are source domain, and 6762 Philippines, which are target domain. To address this problem, we propose a heatmap-based corner-detection model, which outperforms existing scalar-regression methods, and an image classifier for mixed image of source and target images for domain adaptation. The proposed approach achieves better accuracy, which is 19.1% improvement if compared with baseline discriminator-based domain adaptation scheme. Full article

(1) Background: Cooperative Intelligent Transportation Systems (C-ITS) will soon operate using 5G New-Radio (NR) wireless communication, overcoming the limitations of the current V2X (Vehicle-to-Everything) wireless communication technologies and increasing road-safety and driving efficiency. These innovations will also change the RF exposure levels of pedestrians and road-users in general. These people, in fact, will be exposed to additional RF sources coming from nearby cars and from the infrastructure. Therefore, an exposure assessment of people in the proximity of a connected car is necessary and urgent. (2) Methods: Two array antennas for 5G-V2X communication at 3.5 GHz were modelled and mounted on a realistic 3D car model for evaluating the exposure levels of a human model representing people on the road near the car. Computational simulations were conducted using the FDTD solver implemented in the Sim4Life platform; different positions and orientations between the car and the human model were assessed. The analyzed quantities were the Specific Absorption Rate on the whole body (SAR_wb), averaged over 10 g (SAR_10g) in specific tissues, as indicated in the ICNIRP guidelines. (3) Results: the data showed that the highest exposure levels were obtained mostly in the head area of the human model, with the highest peak obtained in the configuration where the main beam of the 5G-V2X antennas was more direct towards the human model. Moreover, in all configurations, the dose absorbed by a pedestrian was well below the ICNIRP guidelines to avoid harmful effects. (4) Conclusions: This work is the first study on human exposure assessment in a 5G-V2X scenario, and it expands the knowledge about the exposure levels for the forthcoming use of 5G in connected vehicles. Full article

In the recent past, a huge number of cameras have been placed in a variety of public and private areas for the purposes of surveillance, the monitoring of abnormal human actions, and traffic surveillance. The detection and recognition of abnormal activity in a real-world environment is a big challenge, as there can be many types of alarming and abnormal activities, such as theft, violence, and accidents. This research deals with accidents in traffic videos. In the modern world, video traffic surveillance cameras (VTSS) are used for traffic surveillance and monitoring. As the population is increasing drastically, the likelihood of accidents is also increasing. The VTSS is used to detect abnormal events or incidents regarding traffic on different roads and highways, such as traffic jams, traffic congestion, and vehicle accidents. Mostly in accidents, people are helpless and some die due to the unavailability of emergency treatment on long highways and those places that are far from cities. This research proposes a methodology for detecting accidents automatically through surveillance videos. A review of the literature suggests that convolutional neural networks (CNNs), which are a specialized deep learning approach pioneered to work with grid-like data, are effective in image and video analysis. This research uses CNNs to find anomalies (accidents) from videos captured by the VTSS and implement a rolling prediction algorithm to achieve high accuracy. In the training of the CNN model, a vehicle accident image dataset (VAID), composed of images with anomalies, was constructed and used. For testing the proposed methodology, the trained CNN model was checked on multiple videos, and the results were collected and analyzed. The results of this research show the successful detection of traffic accident events with an accuracy of 82% in the traffic surveillance system videos. Full article

Currently, Android is the most popular operating system among mobile devices. However, as the number of devices with the Android operating system increases, so does the danger of using them. This is especially important as smartphones increasingly authenticate critical activities(e-banking, e-identity). BotSense Mobile is a tool already integrated with some critical applications (e-banking, e-identity) to increase user safety. In this paper, we focus on the novel functionality of BotSense Mobile: the detection of malware applications on a user device. In addition to the standard blacklist approach, we propose a machine learning-based model for unknown malicious application detection. The lightweight neural network model is deployed on an edge device to avoid sending sensitive user data outside the device. For the same reason, manifest-related features can be used by the detector only. We present a comprehensive empirical analysis of malware detection conducted on recent data (May–June, 2022) from the Koodous platform, which is a collaborative platform where over 70 million Android applications were collected. The research highlighted the problem of machine learning model aging. We evaluated the lightweight model on recent Koodous data and obtained $f_1=0.77$ and high precision ($0.9$). Full article

The widespread usage of mobile devices and their seamless adaptation to each user’s needs through useful applications (apps) makes them a prime target for malware developers. Malware is software built to harm the user, e.g., to access sensitive user data, such as banking details, or to hold data hostage and block user access. These apps are distributed in marketplaces that host millions and therefore have their forms of automated malware detection in place to deter malware developers and keep their app store (and reputation) trustworthy. Nevertheless, a non-negligible number of apps can bypass these detectors and remain available in the marketplace for any user to download and install on their device. Current malware detection strategies rely on using static or dynamic app extracted features (or a combination of both) to scale the detection and cover the growing number of apps submitted to the marketplace. In this paper, the main focus is on the apps that bypass the malware detectors and stay in the marketplace long enough to receive user feedback. This paper uses real-world data provided by an app store. The quantitative ratings and potential alert flags assigned to the apps by the users were used as features to train machine learning classifiers that successfully classify malware that evaded previous detection attempts. These results present reasonable accuracy and thus work to help to maintain a user-safe environment. Full article

Stone pavements are present in many cities and their historical and cultural importance is well recognized. However, there are no standard monitoring methods for this type of pavement that allow road managers to define appropriate maintenance strategies. In this study, a novel method is proposed in order to monitor the road surface conditions of stone pavements in a quick and easy way. Field tests were carried out in an Italian historic center using accelerometer sensors mounted on both a car and a bicycle. A post-processing phase of that data defined the comfort perception of the road users in terms of the a_wz index, as described in the ISO 2631 standard. The results derived from the dynamic surveys were also compared with the corresponding values of typical pavement indicators such as the International Roughness Index (IRI) and the Pavement Condition Index (PCI), measured only on a limited portion of the urban road network. The network’s implementation in a Geographic Information System (GIS) represents the surveys’ results in a graphical database. The specifications of the adopted method require that the network is divided into homogeneous sections, useful for measurement campaign planning, and adopted for the GIS’ outputs representation. The comparisons between IRI-a_wz (R² = 0.74) and PCI-a_wz (R² = 0.96) confirmed that the proposed method can be used reliably to assess the stone pavement conditions on the whole urban road network. Full article

Anticipatory event-related potentials (ERPs) precede upcoming events such as stimuli or actions. These ERPs are usually obtained in cued sensory–motor tasks employing a warning stimulus that precedes a probe stimulus as in the contingent negative variation (CNV) paradigms. The CNV wave has been widely studied, from clinical to brain–computer interface (BCI) applications, and has been shown to emerge in medial frontoparietal areas, localized in the cingulate and supplementary motor areas. Several dated studies also suggest the existence of a prefrontal CNV, although this component was not confirmed by later studies due to the contamination of ocular artifacts. Another lesser-known anticipatory ERP is the prefrontal negativity (pN) that precedes the uncued probe stimuli in discriminative response tasks and has been localized in the inferior frontal gyrus. This study aimed to characterize the pN by comparing it with the CNV in cued and uncued tasks and test if the pN could be associated with event preparation, temporal preparation, or both. To achieve these aims, high-density electroencephalographic recording and advanced ERP analysis controlling for ocular activity were obtained in 25 volunteers who performed 4 different visuomotor tasks. Our results showed that the pN amplitude was largest in the condition requiring both time and event preparation, medium in the condition requiring event preparation only, and smallest in the condition requiring temporal preparation only. We concluded that the prefrontal CNV could be associated with the pN, and this activity emerges in complex tasks requiring the anticipation of both the category and timing of the upcoming stimulus. The proposed method can be useful in BCI studies investigating the endogenous neural signatures triggered by different sensorimotor paradigms. Full article

Recently, the transformer model has progressed from the field of visual classification to target tracking. Its primary method replaces the cross-correlation operation in the Siamese tracker. The backbone of the network is still a convolutional neural network (CNN). However, the existing transformer-based tracker simply deforms the features extracted by the CNN into patches and feeds them into the transformer encoder. Each patch contains a single element of the spatial dimension of the extracted features and inputs into the transformer structure to use cross-attention instead of cross-correlation operations. This paper proposes a reconstruction patch strategy which combines the extracted features with multiple elements of the spatial dimension into a new patch. The reconstruction operation has the following advantages: (1) the correlation between adjacent elements combines well, and the features extracted by the CNN are usable for classification and regression; (2) using the performer operation reduces the amount of network computation and the dimension of the patch sent to the transformer, thereby sharply reducing the network parameters and improving the model-tracking speed. Full article

Several pathogens that spread through the air are highly contagious, and related infectious diseases are more easily transmitted through airborne transmission under indoor conditions, as observed during the COVID-19 pandemic. Indoor air contaminated by microorganisms, including viruses, bacteria, and fungi, or by derived pathogenic substances, can endanger human health. Thus, identifying and analyzing the potential pathogens residing in the air are crucial to preventing disease and maintaining indoor air quality. Here, we applied deep learning technology to analyze and predict the toxicity of bacteria in indoor air. We trained the ProtBert model on toxic bacterial and virulence factor proteins and applied them to predict the potential toxicity of some bacterial species by analyzing their protein sequences. The results reflect the results of the in vitro analysis of their toxicity in human cells. The in silico-based simulation and the obtained results demonstrated that it is plausible to find possible toxic sequences in unknown protein sequences. Full article

Since the conventional split–merge algorithm is sensitive to the object scale variance and splitting starting point, a piecewise split–merge polygon-approximation method is proposed to extract the object contour features. Specifically, the contour corner is used as the starting point for the contour piecewise approximation to reduce the sensitivity of the contour segment for the starting point; then, the split–merge algorithm is used to implement the polygon approximation for each contour segment. Both the distance ratio and the arc length ratio instead of the distance error are used as the iterative stop condition to improve the robustness to the object scale variance. Both the angle and length as two features describe the shape of the contour polygon; they have a strong coupling relationship since they affect each other along the contour order relationship. To improve the description correction of the contour, these two features are combined to construct a Coupled Hidden Markov Model to detect the object by calculating the probability of the contour feature. The proposed algorithm is validated on ETHZ Shape Classes and INRIA Horses standard datasets. Compared with other contour-based object-detection algorithms, the proposed algorithm reduces the feature number and improves the object-detection rate. Full article

Electromyography (EMG) is a multidisciplinary field that brings together allied health (kinesiology and physical therapy) and the engineering sciences (biomedical and electrical). Since the physical sciences are used in the measurement of a biological process, the presentation of the theoretical foundations of EMG is most conveniently conducted using math and physics. However, given the multidisciplinary nature of EMG, a course will most likely include students from diverse backgrounds, with varying levels of math and physics. This is a pedagogical paper that outlines an approach for teaching foundational concepts in EMG to kinesiologists and physical therapists that uses a combination of analogies, visual descriptions, and qualitative analysis of biophysical concepts to develop an intuitive understanding for those who are new to surface EMG. The approach focuses on muscle fiber action potentials (MFAPs), motor unit action potentials (MUAPs), and compound muscle action potentials (CMAPs) because changes in these waveforms are much easier to identify and describe in comparison to the surface EMG interference pattern (IP). Full article

Infectious diseases remain a common problem in low- and middle-income countries, including in Vietnam. Tetanus is a severe infectious disease characterized by muscle spasms and complicated by autonomic nervous system dysfunction in severe cases. Patients require careful monitoring using electrocardiograms (ECGs) to detect deterioration and the onset of autonomic nervous system dysfunction as early as possible. Machine learning analysis of ECG has been shown of extra value in predicting tetanus severity, however any additional ECG signal analysis places a high demand on time-limited hospital staff and requires specialist equipment. Therefore, we present a novel approach to tetanus monitoring from low-cost wearable sensors combined with a deep-learning-based automatic severity detection. This approach can automatically triage tetanus patients and reduce the burden on hospital staff. In this study, we propose a two-dimensional (2D) convolutional neural network with a channel-wise attention mechanism for the binary classification of ECG signals. According to the Ablett classification of tetanus severity, we define grades 1 and 2 as mild tetanus and grades 3 and 4 as severe tetanus. The one-dimensional ECG time series signals are transformed into 2D spectrograms. The 2D attention-based network is designed to extract the features from the input spectrograms. Experiments demonstrate a promising performance for the proposed method in tetanus classification with an F1 score of 0.79 ± 0.03, precision of 0.78 ± 0.08, recall of 0.82 ± 0.05, specificity of 0.85 ± 0.08, accuracy of 0.84 ± 0.04 and AUC of 0.84 ± 0.03. Full article