Sensors, Volume 23, Issue 23 (December-1 2023) – 324 articles

The extinction efficiency of noble metal nanoparticles (NPs), namely gold (Au) and silver (Ag), are dependent on their size and surrounding dielectric. Exploiting the Localized Surface Plasmon Resonance (LSPR) phenomenon, the composition and structure of the NPs might be tailored to achieve a configuration that optimizes their response (sensitivity) to environmental changes. This can be done by preparing a bimetallic system, benefiting from the chemical stability of Au NPs and the higher scattering efficiency of Ag NPs. To enhance the LSPR sensing robustness, incorporating solid supports in the form of nanocomposite thin films is a suitable alternative. In this context, the NPs composed of gold (Au), silver (Ag), and their mixture in bimetallic Au-Ag NPs, were grown in a titanium dioxide (TiO₂) matrix using reactive DC magnetron sputtering. Thermal treatment at different temperatures (up to 700 °C) tuned the LSPR response of the films and, consequently, their sensitivity. Notably, the bimetallic film with Au/Ag atomic ratio 1 exhibited the highest refractive index sensitivity (RIS), with a value of 181 nm/RIU, almost one order of magnitude higher than monometallic Au-TiO₂. The nanostructural analysis revealed a wide NP size distribution of bimetallic NPs with an average size of 31 nm, covering about 20% of the overall surface area. These findings underscore the significant potential of bimetallic film systems, namely AuAg-TiO₂, in LSPR sensing enhancement. Full article

The robotics industry and associated technology applications are a vital support for modern production and manufacturing. With the intelligent development of the manufacturing industry, the application of collaboration robots and human-robot collaboration technology is becoming more and more extensive. In a human-robot collaboration scenario, there are uncertainties such as dynamic impediments, especially in the human upper limb, which puts forward a higher assessment of the manipulator’s route planning technology. As one of the primary branches of the artificial potential field (APF), the velocity potential field (VPF) offers the advantages of good real-time performance and convenient mathematical expression. However, the traditional VPF algorithm is prone to local oscillation phenomena near obstacles, which degrades the smoothness of the movement of the manipulators. An improved velocity potential field algorithm is proposed in this paper. This method solves the problem of sudden velocity change when the manipulator enters and departs the region of the potential field by setting new functions for attraction velocity and repulsion velocity functions. A virtual target point construction method is given to overcome the local oscillation problem of the manipulators near obstacles. The simulation and practical findings of the manipulators reveal that the improved VPF algorithm can not only avoid collision but also effectively reduce the local oscillation problem when dealing with the human upper limb as a dynamic obstacle. The implementation of this algorithm can increase the safety and real-time performance of the human-robot collaboration process and ensure that the collaborative robot is safer and smoother in the working process. Full article

With the recent rise in violent crime, the real-time situation analysis capabilities of the prevalent closed-circuit television have been employed for the deterrence and resolution of criminal activities. Anomaly detection can identify abnormal instances such as violence within the patterns of a specified dataset; however, it faces challenges in that the dataset for abnormal situations is smaller than that for normal situations. Herein, using datasets such as UBI-Fights, RWF-2000, and UCSD Ped1 and Ped2, anomaly detection was approached as a binary classification problem. Frames extracted from each video with annotation were reconstructed into a limited number of images of $3\times 3$, $4\times 3$, $4\times 4$, $5\times 3$ sizes using the method proposed in this paper, forming an input data structure similar to a light field and patch of vision transformer. The model was constructed by applying a convolutional block attention module that included channel and spatial attention modules to a residual neural network with depths of 10, 18, 34, and 50 in the form of a three-dimensional convolution. The proposed model performed better than existing models in detecting abnormal behavior such as violent acts in videos. For instance, with the undersampled UBI-Fights dataset, our network achieved an accuracy of 0.9933, a loss value of 0.0010, an area under the curve of 0.9973, and an equal error rate of 0.0027. These results may contribute significantly to solve real-world issues such as the detection of violent behavior in artificial intelligence systems using computer vision and real-time video monitoring. Full article

The paper presents a method for estimating the inertia tensor components of a spacecraft that has expired its active life using measurement data of the Earth’s magnetic field induction vector components. The implementation of this estimation method is supposed to be carried out when cleaning up space debris in the form of a clapped-out spacecraft with the help of a space tug. It is assumed that a three-component magnetometer and a transmitting device are attached on space debris. The parameters for the rotational motion of space debris are estimated using this measuring system. Then, the known controlled action from the space tug is transferred to the space debris. Next, measurements for the rotational motion parameters are carried out once again. Based on the available measurement data and parameters of the controlled action, the space debris inertia tensor components are estimated. It is assumed that the measurements of the Earth’s magnetic field induction vector components are made in a coordinate system whose axes are parallel to the corresponding axes of the main body axis system. Such an estimation makes it possible to effectively solve the problem of cleaning up space debris by calculating the costs of the space tug working body and the parameters of the space debris removal orbit. Examples of numerical simulation using the measurement data of the Earth’s magnetic field induction vector components on the Aist-2D small spacecraft are given. Thus, the purpose of this work is to evaluate the components of the space debris inertia tensor through measurements of the Earth’s magnetic field taken using magnetometer sensors. The results of the work can be used in the development and implementation of missions to clean up space debris in the form of clapped-out spacecraft. Full article

With the development of wireless communication technology, unmanned aerial vehicles (UAV) are now widely used in many complex communication scenarios. When a UAV serves as an aerial base station for urban and rural ground users or marine users, it is necessary to consider the clustering of ground users and the energy efficiency of the UAV since the users are usually randomly distributed. For the scenario with randomly distributed ground users and different densities of ground users in urban and rural areas, a clustering and beamwidth optimization method for UAV-assisted wireless communication is proposed. Firstly, the energy efficiency expression of a UAV serving ground users was derived in a downlink wireless communication system assisted by a UAV. Secondly, based on the geographical location information of non-uniformly distributed users, an improved k-means method is proposed to cluster ground users, ensuring that the number of users in each cluster is within an appropriate range. Then, based on the clustering results, a fixed-point iteration (FPI) algorithm was proposed to design the optimal beamwidth of UAVs and improve their energy efficiency. Finally, the superiority of the proposed algorithm in improving energy efficiency was verified through simulation analysis, and the impact of parameters such as the cluster number and transmission power on system energy efficiency was also analyzed. Full article

Sensor-based human activity recognition is now well developed, but there are still many challenges, such as insufficient accuracy in the identification of similar activities. To overcome this issue, we collect data during similar human activities using three-axis acceleration and gyroscope sensors. We developed a model capable of classifying similar activities of human behavior, and the effectiveness and generalization capabilities of this model are evaluated. Based on the standardization and normalization of data, we consider the inherent similarities of human activity behaviors by introducing the multi-layer classifier model. The first layer of the proposed model is a random forest model based on the XGBoost feature selection algorithm. In the second layer of this model, similar human activities are extracted by applying the kernel Fisher discriminant analysis (KFDA) with feature mapping. Then, the support vector machine (SVM) model is applied to classify similar human activities. Our model is experimentally evaluated, and it is also applied to four benchmark datasets: UCI DSA, UCI HAR, WISDM, and IM-WSHA. The experimental results demonstrate that the proposed approach achieves recognition accuracies of 97.69%, 97.92%, 98.12%, and 90.6%, indicating excellent recognition performance. Additionally, we performed K-fold cross-validation on the random forest model and utilized ROC curves for the SVM classifier to assess the model’s generalization ability. The results indicate that our multi-layer classifier model exhibits robust generalization capabilities. Full article

In this paper, we propose a compact and low-power mixed-signal approach to implementing convolutional operators that are often responsible for most of the chip area and power consumption of Convolutional Neural Network (CNN) processing chips. The convolutional operators consist of several multiply-and-accumulate (MAC) units. MAC units are the primary components that process convolutional layers and fully connected layers of CNN models. Analog implementation of MAC units opens a new paradigm for realizing low-power CNN processing chips, benefiting from less power and area consumption. The proposed mixed-signal convolutional operator comprises low-power binary-weighted current steering digital-to-analog conversion (DAC) circuits and accumulation capacitors. Compared with a conventional binary-weighted DAC, the proposed circuit benefits from optimum accuracy, smaller area, and lower power consumption due to its symmetric design. The proposed convolutional operator takes as input a set of 9-bit digital input feature data and weight parameters of the convolutional filter. It then calculates the convolutional filter’s result and accumulates the resulting voltage on capacitors. In addition, the convolutional operator employs a novel charge-sharing technique to process negative MAC results. We propose an analog max-pooling circuit that instantly selects the maximum input voltage. To demonstrate the performance of the proposed mixed-signal convolutional operator, we implemented a CNN processing chip consisting of 3 analog convolutional operators, with each operator processing a 3 × 3 kernel. This chip contains 27 MAC circuits, an analog max-pooling, and an analog-to-digital conversion (ADC) circuit. The mixed-signal CNN processing chip is implemented using a CMOS 55 nm process, which occupies a silicon area of 0.0559 mm² and consumes an average power of 540.6 μW. The proposed mixed-signal CNN processing chip offers an area reduction of 84.21% and an energy reduction of 91.85% compared with a conventional digital CNN processing chip. Moreover, another CNN processing chip is implemented with more analog convolutional operators to demonstrate the operation and structure of an example convolutional layer of a CNN model. Therefore, the proposed analog convolutional operator can be adapted in various CNN models as an alternative to digital counterparts. Full article

Biotin, or vitamin B7, is essential for metabolic reactions. It must be obtained from external sources such as food and biotin/vitamin supplements because it is not biosynthesized by mammals. Therefore, there is a need to monitor its levels in supplements. However, biotin detection methods, which include chromatographic, immune, enzymatic, and microbial assays, are tedious, time-consuming, and expensive. Thus, we synthesized a product called biotin-naphthoquinone, which produces chemiluminescence upon its redox cycle reaction with dithiothreitol and luminol; then it was used as a chemiluminescence sensor for biotin–avidin interaction. When a quinone biotinylated compound binds avidin, the chemiluminescence decreases noticeably due to the proximity between quinone and avidin, and when free biotin is added in a competitive assay, the chemiluminescence returns. The chemiluminescence is regained as the free biotin displaces biotinylated quinone in its complex with avidin, freeing biotin-naphthoquinone. Many experiments, including the use of a biotin-free quinone, proved the competitive nature of the assay. The competitive assay method used in this study was linear in the range of 1.0–100 µM with a detection limit of 0.58 µM. The competitive chemiluminescence assay could detect biotin in vitamin B7 tablets with good recovery of 91.3 to 110% and respectable precision (RSD < 8.7%). Full article

Automated optical inspection (AOI) plays a pivotal role in the quality control of contact lenses, safeguarding the safety and integrity of lenses intended for both medical and cosmetic applications. As the role of computer vision in defect detection expands, our study probes its effectiveness relative to traditional methods, particularly concerning subtle and irregular defects on the lens rim. In this research study, we propose a novel algorithm designed for the precise and automated detection of rim defects in contact lenses called “CLensRimVision”. This algorithm integrates a series of procedures, including image preprocessing, circle detection for identifying lens rims, polar coordinate transformation, setting defect criteria and their subsequent detection, and, finally, visualization. The method based on these criteria can be adapted either to thickness-based or area-based approaches, suiting various characteristics of the contact lens. This approach achieves an exemplary performance with a 0.937 AP score. Our results offer a richer understanding of defect detection strategies, guiding manufacturers and researchers towards optimal techniques for ensuring quality in the contact lens domain. Full article

In recent years, super-resolution imaging techniques have been intensely introduced to enhance the azimuth resolution of real aperture scanning radar (RASR). However, there is a paucity of research on the subject of sea surface imaging with small incident angles for complex scenarios. This research endeavors to explore super-resolution imaging for sea surface monitoring, with a specific emphasis on grounded or shipborne platforms. To tackle the inescapable interference of sea clutter, it was segregated from the imaging objects and was modeled alongside I/Q channel noise within the maximum likelihood framework, thus mitigating clutter’s impact. Simultaneously, for characterizing the non-stationary regions of the monitoring scene, we harnessed the Markov random field (MRF) model for its two-dimensional (2D) spatial representational capacity, augmented by a quadratic term to bolster outlier resilience. Subsequently, the maximum a posteriori (MAP) criterion was employed to unite the ML function with the statistical model regarding imaging scene. This hybrid model forms the core of our super-resolution methodology. Finally, a fast iterative threshold shrinkage method was applied to solve this objective function, yielding stable estimates of the monitored scene. Through the validation of simulation and real data experiments, the superiority of the proposed approach in recovering the monitoring scenes and clutter suppression has been verified. Full article

Network slicing shows promise as a means to endow 5G networks with flexible and dynamic features. Network function virtualization (NFV) and software-defined networking (SDN) are the key methods for deploying network slicing, which will enable end-to-end (E2E) isolation services permitting each slice to be customized depending on service requirements. The goal of this investigation is to construct network slices through a machine learning algorithm and allocate resources for the newly created slices using dynamic programming in an efficient manner. A substrate network is constructed with a list of key performance indicators (KPIs) like CPU capacity, bandwidth, delay, link capacity, and security level. After that, network slices are produced by employing multi-layer perceptron (MLP) using the adaptive moment estimation (ADAM) optimization algorithm. For each requested service, the network slices are categorized as massive machine-type communications (mMTC), enhanced mobile broadband (eMBB), and ultra-reliable low-latency communications (uRLLC). After network slicing, resources are provided to the services that have been requested. In order to maximize the total user access rate and resource efficiency, Dijkstra’s algorithm is adopted for resource allocation that determines the shortest path between nodes in the substrate network. The simulation output shows that the present model allocates optimum slices to the requested services with high resource efficiency and reduced total bandwidth utilization. Full article

Traffic sign recognition is a complex and challenging yet popular problem that can assist drivers on the road and reduce traffic accidents. Most existing methods for traffic sign recognition use convolutional neural networks (CNNs) and can achieve high recognition accuracy. However, these methods first require a large number of carefully crafted traffic sign datasets for the training process. Moreover, since traffic signs differ in each country and there is a variety of traffic signs, these methods need to be fine-tuned when recognizing new traffic sign categories. To address these issues, we propose a traffic sign matching method for zero-shot recognition. Our proposed method can perform traffic sign recognition without training data by directly matching the similarity of target and template traffic sign images. Our method uses the midlevel features of CNNs to obtain robust feature representations of traffic signs without additional training or fine-tuning. We discovered that midlevel features improve the accuracy of zero-shot traffic sign recognition. The proposed method achieves promising recognition results on the German Traffic Sign Recognition Benchmark open dataset and a real-world dataset taken from Sapporo City, Japan. Full article

In the context of the Internet of Things (IoT), location-based applications have introduced new challenges in terms of location spoofing. With an open and shared wireless medium, a malicious spoofer can impersonate active devices, gain access to the wireless channel, as well as emit or inject signals to mislead IoT nodes and compromise the detection of their location. To address the threat posed by malicious location spoofing attacks, we develop a neural network-based model with single access point (AP) detection capability. In this study, we propose a method for spoofing signal detection and localization by leveraging a feature extraction technique based on a single AP. A neural network model is used to detect the presence of a spoofed unmanned aerial vehicle (UAV) and estimate its time of arrival (ToA). We also introduce a centralized approach to data collection and localization. To evaluate the effectiveness of detection and ToA prediction, multi-layer perceptron (MLP) and long short-term memory (LSTM) neural network models are compared. Full article

In this work, a flexible electrochemical sensor was developed for the detection of organophosphorus pesticides (OPs). To fabricate the sensor, graphene was generated in situ by laser-induced graphene (LIG) technology on a flexible substrate of polyimide (PI) film to form a three-electrode array, and pralidoxime (PAM) chloride was used as the probe molecule. CeO₂ was used to modify the working electrode to improve the sensitivity of the sensor because of its electrocatalytic effect on the oxidation of PAM, and the Ag/AgCl reference electrode was prepared by the drop coating method. The effects of the laser power, laser scanning speed, and CeO₂ modification on the electrochemical properties of the sensor were studied in detail. The results prove that the sensor has good repeatability, stability, and anti-interference ability, and it shows an excellent linear response in the chlorpyrifos concentration range from 1.4 × 10⁻⁸ M to 1.12 × 10⁻⁷ M with the detection limit of 7.01 × 10⁻¹⁰ M. Full article

Gaze is a significant behavioral characteristic that can be used to reflect a person’s attention. In recent years, there has been a growing interest in estimating gaze from facial videos. However, gaze estimation remains a challenging problem due to variations in appearance and head poses. To address this, a framework for 3D gaze estimation using appearance cues is developed in this study. The framework begins with an end-to-end approach to detect facial landmarks. Subsequently, we employ a normalization method and improve the normalization method using orthogonal matrices and conduct comparative experiments to prove that the improved normalization method has a higher accuracy and a lower computational time in gaze estimation. Finally, we introduce a dual-branch convolutional neural network, named FG-Net, which processes the normalized images and extracts eye and face features through two branches. The extracted multi-features are then integrated and input into a fully connected layer to estimate the 3D gaze vectors. To evaluate the performance of our approach, we conduct ten-fold cross-validation experiments on two public datasets, namely MPIIGaze and EyeDiap, achieving remarkable accuracies of 3.11° and 2.75°, respectively. The results demonstrate the high effectiveness of our proposed framework, showcasing its state-of-the-art performance in 3D gaze estimation. Full article

The energy consumption of a building is significantly influenced by the habits of its occupants. These habits not only pertain to occupancy states, such as presence or absence, but also extend to more detailed aspects of occupant behavior. To accurately capture this information, it is essential to use tools that can monitor occupant habits without altering them. Invasive methods such as body sensors or cameras could potentially disrupt the natural habits of the occupants. In our study, we primarily focus on occupancy states as a representation of occupant habits. We have created a model based on artificial neural networks (ANNs) to ascertain the occupancy state of a building using environmental data such as CO₂ concentration and noise level. These data are collected through non-intrusive sensors. Our approach involves rule-based a priori labeling and the use of a long short-term memory (LSTM) network for predictive purposes. The model is designed to predict four distinct states in a residential building. Although we lack data on actual occupancy states, the model has shown promising results with an overall prediction accuracy ranging between 78% and 92%. Full article

In this paper, the precise design of a high-power amplifier (HPA) is shown, along with the problems associated with the stability of “on-wafer” measurements. Here, techniques to predict possible oscillations are discussed to ensure the stability of a monolithic microwave-integrated circuit (MMIC). In addition, a deep reflection is made on the instabilities that occur when measuring both on wafer and using a mounted chip. Stability techniques are used as tools to characterize measurement results. Both a precise design and instabilities are shown through the design of a three-stage X-band HPA in gallium nitride (GaN) from the WIN Semiconductors Corp. foundry. As a result, satisfactory performance was obtained, achieving a maximum output power equal to 42 dBm and power-added efficiency of 32% at a 20 V drain bias. In addition to identifying critical points in the design or measurement of the HPA, this research shows that the stability of the amplifier can be verified through a simple analysis and that instabilities are often linked to errors in the measurement process or in the characterization of the measurement process. Full article

Traffic state data are key to the proper operation of intelligent transportation systems (ITS). However, traffic detectors often receive environmental factors that cause missing values in the collected traffic state data. Therefore, aiming at the above problem, a method for imputing missing traffic state data based on a Diffusion Convolutional Neural Network–Generative Adversarial Network (DCNN-GAN) is proposed in this paper. The proposed method uses a graph embedding algorithm to construct a road network structure based on spatial correlation instead of the original road network structure; through the use of a GAN for confrontation training, it is possible to generate missing traffic state data based on the known data of the road network. In the generator, the spatiotemporal features of the reconstructed road network are extracted by the DCNN to realize the imputation. Two real traffic datasets were used to verify the effectiveness of this method, with the results of the proposed model proving better than those of the other models used for comparison. Full article

Adaptive information-sampling approaches enable efficient selection of mobile robots’ waypoints through which the accurate sensing and mapping of a physical process, such as the radiation or field intensity, can be obtained. A key parameter in the informative sampling objective function could be optimized balance the need to explore new information where the uncertainty is very high and to exploit the data sampled so far, with which a great deal of the underlying spatial fields can be obtained, such as the source locations or modalities of the physical process. However, works in the literature have either assumed the robot’s energy is unconstrained or used a homogeneous availability of energy capacity among different robots. Therefore, this paper analyzes the impact of the adaptive information-sampling algorithm’s information function used in exploration and exploitation to achieve a tradeoff between balancing the mapping, localization, and energy efficiency objectives. We use Gaussian process regression (GPR) to predict and estimate confidence bounds, thereby determining each point’s informativeness. Through extensive experimental data, we provide a deeper and holistic perspective on the effect of information function parameters on the prediction map’s accuracy (RMSE), confidence bound (variance), energy consumption (distance), and time spent (sample count) in both single- and multi-robot scenarios. The results provide meaningful insights into choosing the appropriate energy-aware information function parameters based on sensing objectives (e.g., source localization or mapping). Based on our analysis, we can conclude that it would be detrimental to give importance only to the uncertainty of the information function (which would explode the energy needs) or to the predictive mean of the information (which would jeopardize the mapping accuracy). By assigning more importance to the information uncertainly with some non-zero importance to the information value (e.g., 75:25 ratio), it is possible to achieve an optimal tradeoff between exploration and exploitation objectives while keeping the energy requirements manageable. Full article

Inertial measurement units (IMUs) have been validated for measuring sagittal plane lower-limb kinematics during moderate-speed running, but their accuracy at maximal speeds remains less understood. This study aimed to assess IMU measurement accuracy during high-speed running and maximal effort sprinting on a curved non-motorized treadmill using discrete (Bland–Altman analysis) and continuous (root mean square error [RMSE], normalised RMSE, Pearson correlation, and statistical parametric mapping analysis [SPM]) metrics. The hip, knee, and ankle flexions and the pelvic orientation (tilt, obliquity, and rotation) were captured concurrently from both IMU and optical motion capture systems, as 20 participants ran steadily at 70%, 80%, 90%, and 100% of their maximal effort sprinting speed (5.36 ± 0.55, 6.02 ± 0.60, 6.66 ± 0.71, and 7.09 ± 0.73 m/s, respectively). Bland–Altman analysis indicated a systematic bias within ±1° for the peak pelvic tilt, rotation, and lower-limb kinematics and −3.3° to −4.1° for the pelvic obliquity. The SPM analysis demonstrated a good agreement in the hip and knee flexion angles for most phases of the stride cycle, albeit with significant differences noted around the ipsilateral toe-off. The RMSE ranged from 4.3° (pelvic obliquity at 70% speed) to 7.8° (hip flexion at 100% speed). Correlation coefficients ranged from 0.44 (pelvic tilt at 90%) to 0.99 (hip and knee flexions at all speeds). Running speed minimally but significantly affected the RMSE for the hip and ankle flexions. The present IMU system is effective for measuring lower-limb kinematics during sprinting, but the pelvic orientation estimation was less accurate. Full article

Individuals who are Blind and Visually Impaired (BVI) take significant risks and dangers on obstacles, particularly when they are unaccompanied. We propose an intelligent head-mount device to assist BVI people with this challenge. The objective of this study is to develop a computationally efficient mechanism that can effectively detect obstacles in real time and provide warnings. The learned model aims to be both reliable and compact so that it can be integrated into a wearable device with a small size. Additionally, it should be capable of handling natural head turns, which can generally impact the accuracy of readings from the device’s sensors. Over thirty models with different hyper-parameters were explored and their key metrics were compared to identify the most suitable model that strikes a balance between accuracy and real-time performance. Our study demonstrates the feasibility of a highly efficient wearable device that can assist BVI individuals in avoiding obstacles with a high level of accuracy. Full article

Coronavirus has caused many casualties and is still spreading. Some people experience rapid deterioration that is mild at first. The aim of this study is to develop a deterioration prediction model for mild COVID-19 patients during the isolation period. We collected vital signs from wearable devices and clinical questionnaires. The derivation cohort consisted of people diagnosed with COVID-19 between September and December 2021, and the external validation cohort collected between March and June 2022. To develop the model, a total of 50 participants wore the device for an average of 77 h. To evaluate the model, a total of 181 infected participants wore the device for an average of 65 h. We designed machine learning-based models that predict deterioration in patients with mild COVID-19. The prediction model, 10 min in advance, showed an area under the receiver characteristic curve (AUC) of 0.99, and the prediction model, 8 h in advance, showed an AUC of 0.84. We found that certain variables that are important to model vary depending on the point in time to predict. Efficient deterioration monitoring in many patients is possible by utilizing data collected from wearable sensors and symptom self-reports. Full article

Internet-of-Things systems are increasingly being installed in buildings to transform them into smart ones and to assist in the transition to a greener future. A common feature of smart buildings, whether commercial or residential, is environmental sensing that provides information about temperature, dust, and the general air quality of indoor spaces, assisting in achieving energy efficiency. Environmental sensors though, especially when combined, can also be used to detect occupancy in a space and to increase security and safety. The most popular methods for the combination of environmental sensor measurements are concatenation and neural networks that can conduct fusion in different levels. This work presents an evaluation of the performance of multiple late fusion methods in detecting occupancy from environmental sensors installed in a building during its construction and provides a comparison of the late fusion approaches with early fusion followed by ensemble classifiers. A novel weighted fusion method, suitable for imbalanced samples, is also tested. The data collected from the environmental sensors are provided as a public dataset. Full article

The Celestial Object Rendering TOol (CORTO) offers a powerful solution for generating synthetic images of celestial bodies, catering to the needs of space mission design, algorithm development, and validation. Through rendering, noise modeling, hardware-in-the-loop testing, and post-processing functionalities, CORTO creates realistic scenarios. It offers a versatile and comprehensive solution for generating synthetic images of celestial bodies, aiding the development and validation of image processing and navigation algorithms for space missions. This work illustrates its functionalities in detail for the first time. The importance of a robust validation pipeline to test the tool’s accuracy against real mission images using metrics like normalized cross-correlation and structural similarity is also illustrated. CORTO is a valuable asset for advancing space exploration and navigation algorithm development and has already proven effective in various projects, including CubeSat design, lunar missions, and deep learning applications. While the tool currently covers a range of celestial body simulations, mainly focused on minor bodies and the Moon, future enhancements could broaden its capabilities to encompass additional planetary phenomena and environments. Full article

This work presents the performance analysis of space-time block codes (STBCs) for vehicle-to-vehicle (V2V) fast-fading channels in scenarios with modified line-of-sight (LOS). The objective is to investigate how the V2V MIMO (multiple-input multiple-output) system performance is influenced by two important impairments: deterministic ground reflections and an increased Doppler frequency (time-variant channels). STBCs of various coding rates (using an approximation model) are evaluated by assuming antenna elements distributed over the surface of two contiguous vehicles. A multi-ray model is used to study the multiple constructive/destructive interference patterns of the transmitted/received signals by all pairs of Tx–Rx antenna links considering ground reflections. A double scattering model is used to include the effects of stochastic channel components that depend on the Doppler frequency. The results show that STBCs are capable of counteracting fades produced by destructive self-interference components across a range of inter-vehicle distances and for a range of Doppler frequency values. Notably, the effectiveness of STBCs in deep fades is shown to outperform schemes with exclusive receive diversity, despite the interference created by the loss of orthogonality in time-varying channels with a moderate increase of Doppler frequency (mainly due to higher vehicle speeds, higher frequency or shorter time slots). Higher-order STBCs with rate losses are also evaluated using an approximation model, showing interesting gains even for low coding rate performance, particularly when accompanied by a multiple antenna receiver. Overall, these results can shed light on how to exploit transmit diversity in time-varying vehicular channels with modified LOS. Full article

Due to problems such as the shooting light, viewing angle, and camera equipment, low-light images with low contrast, color distortion, high noise, and unclear details can be seen regularly in real scenes. These low-light images will not only affect our observation but will also greatly affect the performance of computer vision processing algorithms. Low-light image enhancement technology can help to improve the quality of images and make them more applicable to fields such as computer vision, machine learning, and artificial intelligence. In this paper, we propose a novel method to enhance images through Bézier curve estimation. We estimate the pixel-level Bézier curve by training a deep neural network (BCE-Net) to adjust the dynamic range of a given image. Based on the good properties of the Bézier curve, in that it is smooth, continuous, and differentiable everywhere, low-light image enhancement through Bézier curve mapping is effective. The advantages of BCE-Net’s brevity and zero-reference make it generalizable to other low-light conditions. Extensive experiments show that our method outperforms existing methods both qualitatively and quantitatively. Full article

Simultaneous location and mapping (SLAM) technology is key in robot autonomous navigation. Most visual SLAM (VSLAM) algorithms for dynamic environments cannot achieve sufficient positioning accuracy and real-time performance simultaneously. When the dynamic object proportion is too high, the VSLAM algorithm will collapse. To solve the above problems, this paper proposes an indoor dynamic VSLAM algorithm called YDD-SLAM based on ORB-SLAM3, which introduces the YOLOv5 object detection algorithm and integrates deep information. Firstly, the objects detected by YOLOv5 are divided into eight subcategories according to their motion characteristics and depth values. Secondly, the depth ranges of the dynamic object and potentially dynamic object in the moving state in the scene are calculated. Simultaneously, the depth value of the feature point in the detection box is compared with that of the feature point in the detection box to determine whether the point is a dynamic feature point; if it is, the dynamic feature point is eliminated. Further, multiple feature point optimization strategies were developed for VSLAM in dynamic environments. A public data set and an actual dynamic scenario were used for testing. The accuracy of the proposed algorithm was significantly improved compared to that of ORB-SLAM3. This work provides a theoretical foundation for the practical application of a dynamic VSLAM algorithm. Full article

Speech synthesis is a technology that converts text into speech waveforms. With the development of deep learning, neural network-based speech synthesis technology is being researched in various fields, and the quality of synthesized speech has significantly improved. In particular, Grad-TTS, a speech synthesis model based on the denoising diffusion probabilistic model (DDPM), exhibits high performance in various domains, generates high-quality speech, and supports multi-speaker speech synthesis. However, speech synthesis for an unseen speaker is not possible. Therefore, this study proposes an effective zero-shot multi-speaker speech synthesis model that improves the Grad-TTS structure. The proposed method enables the reception of speaker information from speech references using a pre-trained speaker recognition model. In addition, by converting speaker information via information perturbation, the model can learn various types of speaker information, excluding those in the dataset. To evaluate the performance of the proposed method, we measured objective performance indicators, namely speaker encoder cosine similarity (SECS) and mean opinion score (MOS). To evaluate the synthesis performance for both the seen speaker and unseen speaker scenarios, Grad-TTS, SC-GlowTTS, and YourTTS were compared. The results demonstrated excellent speech synthesis performance for seen speakers and a performance similar to that of the zero-shot multi-speaker speech synthesis model. Full article

The mobility of low Earth orbit (LEO) satellites causes the LEO satellite network to experience topology changes. Topology change includes periodic topology change that occurs naturally and unpredictable topology change that occurs due to instability of the inter-satellite link between satellites. Periodic and unpredictable topology change causes frequent topology change, requiring massive communications throughout the network due to frequent route convergence. LEO satellites have limited onboard power because they operate on batteries. The waste of limited satellite onboard resources shortens the lifespan of the satellite, and achieving stable end-to-end transmission is challenging for the network. In this regard, minimizing communication overhead is a fundamental consideration when designing a routing scheme. In this paper, we propose a distributed detour routing scheme with minimal communication overhead. This routing scheme consists of a rapid detour, selective flooding, and link recovery procedures. When a link failure occurs in the network, a rapid detour can detect link failure using only a precalculated routing table. Subsequently, selective flooding searches for the optimal detour point within the minimum hop region and flood to detour point. After link recovery, a procedure is defined to traverse the pre-detour path and switch it back to the original path. The simulation results show that the proposed routing scheme achieves a reduction of communication overhead by 97.6% compared with the n-hop flooding approach. Full article

The traditional vehicular ad hoc network (VANET), which is evolving into the internet of vehicles (IoV), has drawn great attention for its enormous potential in road safety improvement, traffic management, infotainment service support, and even autonomous driving. IEEE 802.11p, as the vital standard for wireless access in vehicular environments, has been released for more than one decade and its evolution, IEEE 802.11bd, has also been released for a few months. Since the analytical models for the IEEE 802.11p/bd medium access control (MAC) play important roles in terms of performance evaluation and MAC protocol optimization, a lot of analytical models have been proposed. However, the existing analytical models are still not accurate as a result of ignoring some important factors of the MAC itself and real communication scenarios. Motivated by this, a novel analytical model is proposed, based on a novel two-dimensional (2-D) Markov chain model. In contrast to the existing studies, all the important factors are considered in this proposed model, such as the backoff freezing mechanism, retry limit, post-backoff states, differentiated packet arrival probabilities for empty buffer queue, and queue model of packets in the buffer. In addition, the influence of the capture effect under a Nakagami-m fading channel has also been considered. Then, the expressions of successful transmission, collided transmission, normalized unsaturated throughput, and average packet delay are all meticulously derived, respectively. At last, the accuracy of the proposed analytical model is verified via the simulation results, which show that it is more accurate than the existing analytical models. Full article