Electronics, Volume 12, Issue 19 (October-1 2023) – 200 articles

Digital Twins, which are virtual representations of physical systems mirroring their behavior, enable real-time monitoring, analysis, and optimization. Understanding and identifying the temporal dependencies included in the multivariate time series data that characterize the behavior of the system are crucial for improving the effectiveness of Digital Twins. Long Short-Term Memory (LSTM) networks have been used to represent complex temporal dependencies and identify long-term links in the Industrial Internet of Things (IIoT). This paper proposed a Digital Twin temporal dependency technique using LSTM to capture the long-term dependencies in IIoT time series data, estimate the lag between the input and intended output, and handle missing data. Autocorrelation analysis showed the lagged links between variables, aiding in the discovery of temporal dependencies. The system evaluated the LSTM model by providing it with a set of previous observations and asking it to forecast the value at future time steps. We conducted a comparison between our model and six baseline models, utilizing both the Smart Water Treatment (SWaT) and Building Automation Transaction (BATADAL) datasets. Our model’s effectiveness in capturing temporal dependencies was assessed through the analysis of the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF). The results of our experiments demonstrate that our enhanced model achieved a better long-term prediction performance. Full article

This paper proposes a weakly supervised cross-domain person re-identification (Re-ID) method based on small sample data. In order to reduce the cost of data collection and annotation, the model design focuses on extracting and abstracting the information contained in the data under limited conditions. In this paper, we focus on the problems of strong data dependence, weak cross-domain capability and low accuracy in Re-ID in weakly supervised scenarios. Our contributions are as follows: first, we implement a joint training framework with the help of small sample learning and cross-domain migration for Re-ID. Second, with the help of residual compensation and fusion attention module, the RCFA module is designed, and the model framework is built on this basis to improve the cross-domain ability of the model. Third, to solve the problem of low accuracy caused by insufficient data coverage of small samples, a fusion of shallow features and deep features is designed to enable the model to weighted fusion of shallow detail information and deep semantic information. Finally, by selecting different camera images in Market1501 dataset and DukeMTMC-reID dataset as small samples, respectively, and introducing another dataset data for joint training, we demonstrate the feasibility of this joint training framework, which can perform weakly supervised cross-domain Re-ID based on small sample data. Full article

Japanese adverbs are difficult to classify, with little progress made since the 1930s. Now in the age of large language models, linguists need a framework for lexical grouping that incorporates quantitative, evidence-based relationships rather than purely theoretical categorization. We herein address this need for the case of Japanese adverbs by developing a semantic positioning approach that incorporates large language model embeddings with fuzzy set theory to achieve empirical Japanese adverb groupings. To perform semantic positioning, we (i) obtained multi-dimensional embeddings for a list of Japanese adverbs using a BERT or RoBERTa model pre-trained on Japanese text, (ii) reduced the dimensionality of each embedding by principle component analysis (PCA), (iii) mapped the relative position of each adverb in a 3D plot using K-means clustering with an initial cluster count of $n=3$, (iv) performed silhouette analysis to determine the optimal cluster count, (v) performed PCA and K-means clustering on the adverb embeddings again to generate 2D semantic position plots, then finally (vi) generated a centroid distance matrix. Fuzzy set theory informs our workflow at the embedding step, where the meanings of words are treated as quantifiable vague data. Our results suggest that Japanese adverbs optimally cluster into $n=4$ rather than $n=3$ groups following silhouette analysis. We also observe a lack of consistency between adverb semantic positions and conventional classification. Ultimately, 3D/2D semantic position plots and centroid distance matrices were simple to generate and did not require special hardware. Our novel approach offers advantages over conventional adverb classification, including an intuitive visualization of semantic relationships in the form of semantic position plots, as well as a quantitative clustering “fingerprint” for Japanese adverbs that express vague language data as a centroid distance matrix. Full article

This article presents the classification of optoelectronics encoder faults in a permanent magnet synchronous motor (PMSM) drive system. This paper proposes the deep neural networks (DNNs) speed sensor faults classification application in the vector-controlled PMSM drive. This approach to the issue has not been discussed in the literature before. This work presents a solution based on early detection with the use of the model reference adaptive system (MRAS) estimator and fault classification based on artificial intelligence. The innovative nature of this work is also due to the simulation of speed sensor damage using the developed optoelectronics encoder model in the Matlab/Simulink environment. This work is focused on simulation studies, which have been supported by experimental results obtained on the MicroLabBox platform. This article compares two structures of deep neural networks in fault detection. The results were also compared with previous experimental studies on the classification of speed sensor failures using shallow neural networks. Full article

The concept of spectrum sensing has emerged as a fundamental solution to address the growing demand for accessing the limited resources of wireless communications networks. This paper introduces a straightforward yet efficient approach that incorporates multiple stages that are based on deep learning (DL) techniques to mitigate Radio Frequency (RF) impairments and estimate the transmitted signal using the time domain representation of received signal samples. The proposed method involves calculating the energies of the estimated transmitted signal samples and received signal samples and estimating the energy of the noise using these estimates. Subsequently, the received signal energy and the estimated noise energy, adjusted by a correction factor (k), are employed in binary hypothesis testing to determine the occupancy of the wireless channel under investigation. The proposed system demonstrates encouraging outcomes by effectively mitigating RF impairments, such as carrier frequency offset (CFO), phase offset, and additive white Gaussian noise (AWGN), to a considerable degree. As a result, it enables accurate estimation of the transmitted signal from the received signal, with 3.85% false alarm and 3.06% missed detection rates, underscoring the system’s capability to adaptively determine a decision threshold for energy detection. Full article

The Fourth Industrial Revolution, also known as Industrial 4.0, has greatly accelerated inter-connectivity and smart automation in industrial control systems (ICSs), which has introduced new challenges to their security. With the fast growth of the Internet of Things and the advent of 5G/6G, the collaboration of Artificial Intelligence (Al) and the Internet of Things (loT) in ICSs has also introduced lots of security issues as it highly relies on advanced communication and networking techniques. Frequent ICS security incidents have demonstrated that attackers have the ability to stealthily breach the current system defenses and cause catastrophic effects to ICSs. Thankfully, trusted computing technology, which has been a popular research topic in the field of information security in recent years, offers distinct advantages when applied to ICSs. In this paper, we first analyze the vulnerabilities of ICSs and the limitations of existing protection technologies. Then, we introduce the concept of trusted computing and present a security framework for ICSs based on Trusted Computing 3.0. Finally, we discuss potential future research directions. Full article

The space radiation environment has a radiation effect on electronic devices, especially the total ionizing dose effect, which seriously affects the service life of spacecraft on-orbit electronic devices and electronic equipment. Therefore, it is particularly important to enhance the radiation resistance of electronic devices. At present, many scientific research institutions still use the areal density equivalent aluminum method to calculate the shielding dose. This paper sets five common metal materials in aerospace through the GEANT4 Monte-Carlo simulation tool MULASSIS, individually calculating the absorption dose caused by single-energy electrons and protons in the silicon detector after shielding of five different materials, which have the same areal density of 0.8097 g/cm². By comparing the above data, it was found that depending on the particle energy, the areal density aluminum equivalent method would overestimate or underestimate the absorbed dose in the shielded silicon detector, especially for the ionization total dose shielding effect of low-energy electrons. The areal density aluminum equivalent method will greatly overestimate the shielding dose, so this difference needs to be taken into account when evaluating the ionizing dose of the electronics on a spacecraft to make the assessment more accurate. Full article

A CNN object detection method based on the structural reparameterisation technique using branch matching is proposed to address the problem of balancing accuracy and speed in object detection techniques. By the structural reparameterisation of the convolutional layer in the object detection network, the amount of computation and the number of parameters in the network inference are reduced, the memory overhead is lowered, and the use of the branch-matching method to improve the structural reparameterisation model improves the computational efficiency and speed of the network while maintaining the detection accuracy. Optimisation is also carried out in terms of target screening and loss function, and a new CPC NMS screening strategy was introduced to further improve the performance of the model. The experimental results show that the proposed method achieves competitive results on the PASCAL VOC2012 and MS COCO2017 datasets compared to the traditional object detection methods and the current mainstream models, achieving a better balance between the detection accuracy and detection speed. Full article

Nowadays, in contemporary building and energy management systems (BEMSs), the predominant approach involves rule-based methodologies, typically employing supervised or unsupervised learning, to deliver energy-saving recommendations to building occupants. However, these BEMSs often suffer from a critical limitation—they are primarily trained on building energy data alone, disregarding crucial elements such as occupant comfort and preferences. This inherent lack of adaptability to occupants significantly hampers the effectiveness of energy-saving solutions. Moreover, the prevalent cloud-based nature of these systems introduces elevated cybersecurity risks and substantial data transmission overheads. In response to these challenges, this article introduces a cutting-edge edge computing architecture grounded in virtual organizations, federated learning, and deep reinforcement learning algorithms, tailored to optimize energy consumption within buildings/homes and facilitate demand response. By integrating energy efficiency measures within virtual organizations, which dynamically learn from real-time inhabitant data while prioritizing comfort, our approach effectively optimizes inhabitant consumption patterns, ushering in a new era of energy efficiency in the built environment. Full article

To ensure lateral stability during the cruising of a differential steering vehicle (DSV), this paper presents a curving adaptive cruise control (ACC) system coordinated with a differential steering control (DSC) system, which considers both longitudinal cruising capability and lateral stability on curved roads. Firstly, a DSV dynamics model is developed and a control strategy architecture for a curving ACC system is designed. Then, the car-following control strategy for the curving ACC system is designed based on the fuzzy model predictive control (FMPC) algorithm. The strategy aims to improve the economy and balances car following, safety, comfort and economy. Moreover, fuzzy logic rules are designed to update the weight coefficients of the performance indicators in real time. Finally, the lateral stability controller is designed based on the preview algorithm and the sliding mode control (SMC) algorithm. The simulation results show that the lateral stability of the DSV during the curving cruise is realized via the control of the differential drive torque of the two front wheels. The proposed FMPC controller and SMC controller based on the preview control algorithm satisfy the performance in terms of vehicle following and lateral stable driving in the process of cruising. Full article

In power semiconductor systems such as inverters, managing losses is critical for optimizing performance. Inverters, which convert DC to AC for applications such as renewable energy systems, motor drives, and power supplies, are significantly affected by the thermal performance of components such as metal-oxide-semiconductor field-effect transistors (MOSFETs). Efficient thermal management is critical for the longevity and performance of power electronic systems, especially in high-power applications. Designing effective thermal management strategies for inverters reduces losses, increases efficiency, and improves performance while considering space constraints and complex component interactions. In this study, power electronics simulations and computational fluid dynamics (CFD) thermal analysis were integrated to design the inverter. Using an integrated simulation, a thermal analysis was performed based on the inverter losses per module. A power electronics simulation was used to verify the validity of the loss values in the inverter design, and the CFD thermal analysis facilitated the visual analysis of the variables to be considered. The validity of the design was evaluated through experimental verification of the inverter system. A temperature saturation of 63.9 $\mathrm{℃}$ at 60$A_{rms}$ was recorded in the simulation, and a temperature saturation of 45 $\mathrm{℃}$ or less at 59$A_{rms}$ to 60$A_{rms}$ was obtained for each phase in the actual test. Considering the ambient temperature difference, it showed a difference of approximately 9.9 $\mathrm{℃}$. This conclusion allows us to reduce the high probability of risk derived by considering a small margin of safety for each variable in the design. This solution can be used to compactly design real inverters and solve complex thermal problems in power semiconductor-based systems. Finally, this study analyzes the similarities and differences between CFD simulations, power electronics simulations, and real-world experimental validation, highlighting the importance of thermal management in improving the efficiency of power electronic systems, particularly inverters. Full article

Traditional backward recursion methods face a fundamental challenge in solving Markov Decision Processes (MDP), where there exists a contradiction between the need for knowledge of optimal expected payoffs and the inability to acquire such knowledge during the decision-making process. To address this challenge and strike a reasonable balance between exploration and exploitation in the decision process, this paper proposes a novel model known as Temporal Error-based Adaptive Exploration (TEAE). Leveraging reinforcement learning techniques, TEAE overcomes the limitations of traditional MDP solving methods. TEAE exhibits dynamic adjustment of exploration probabilities based on the agent’s performance, on the one hand. On the other hand, TEAE approximates the optimal expected payoff function for subprocesses after specific states and times by integrating deep convolutional neural networks to minimize the temporal difference error between the dual networks. Furthermore, the paper extends TEAE to DQN-PER and DDQN-PER methods, resulting in DQN-PER-TEAE and DDQN-PER-TEAE variants, which not only demonstrate the generality and compatibility of the TEAE model with existing reinforcement learning techniques but also validate the practicality and applicability of the proposed approach in a broader MDP reinforcement learning context. To further validate the effectiveness of TEAE, the paper conducts a comprehensive evaluation using multiple metrics, compares its performance with other MDP reinforcement learning methods, and conducts case studies. Ultimately, simulation results and case analyses consistently indicate that TEAE exhibits higher efficiency, highlighting its potential in driving advancements in the field. Full article

The $\mu -$synchronization issues of non-dissipative coupled networks with bounded disturbances and mixed delays are studied in this article. Different from existing works, three kinds of time delays, including internal delays, coupling delays, and impulsive sampling delays, have unidentified bounds and even evolve towards infinity over time, making the concerned network more practical. Considering $\mu -$stability theory and impulse inequality techniques, a hybrid non-delayed and time-delayed impulsive controller including both current and historical state information is designed, and several novel sufficient conditions are derived to make nonlinear complex networks achieve $\mu -$synchronization. Moreover, not only can the constriction of dissipative coupling conditions on network topology be relaxed, but also the restriction of various time delays on impulsive intervals can be weakened, which makes the theoretical achievements in this article more general than the previous achievements. Ultimately, numerical simulations confirm the effectiveness of our results. Full article

Cinematic Shot Attribute Analysis aims to analyze the intrinsic attributes of movie shots, such as movement and scale. In previous methods, specialized architectures were designed for each specific task and relied on the use of optical flow maps. In this paper, we consider shot attribute analysis as a unified task of motion–static weight allocation, and propose a motion–static dual-path architecture for recognizing various shot attributes. In this architecture, we design a new action cue generation module for adapting the end-to-end training process instead of a pre-trained optical flow network; and, to address the issue of limited samples in movie shot datasets, we design a fixed-size adjustment strategy to enable the network to directly utilize pre-trained vision transformer models while adapting to shot data inputs at arbitrary sample rates. In addition, we quantitatively analyze the sensitivity of different shot attributes to motion and static features for the first time. Subsequent experimental results on two datasets, MovieShots and AVE, demonstrate that our proposed method outperforms all previous approaches without increasing computational cost. Full article

Counterfactual reasoning explores what could have happened if the circumstances were different from what actually occurred. As a crucial subtask, counterfactual story generation integrates counterfactual reasoning into the generative narrative chain, which requires the model to preserve minimal edits and ensure narrative consistency. Previous work prioritizes conflict detection as a first step, and then replaces conflicting content with appropriate words. However, these methods mainly face two challenging issues: (a) the causal relationship between story event sequences is not fully utilized in the conflict detection stage, leading to inaccurate conflict detection, and (b) the absence of proper planning in the content rewriting stage results in a lack of narrative consistency in the generated story ending. In this paper, we propose a novel counterfactual generation framework called CLICK based on causal inference in event sequences and commonsense knowledge incorporation. To address the first issue, we utilize the correlation between adjacent events in the story ending to iteratively calculate the contents from the original ending affected by the condition. The content with the original condition is then effectively prevented from carrying over into the new story ending, thereby avoiding causal conflict with the counterfactual conditions. Considering the second issue, we incorporate structural commonsense knowledge about counterfactual conditions, equipping the framework with comprehensive background information on the potential occurrence of counterfactual conditional events. Through leveraging a rich hierarchical data structure, CLICK gains the ability to establish a more coherent and plausible narrative trajectory for subsequent storytelling. Experimental results show that our model outperforms previous unsupervised state-of-the-art methods and achieves gains of 2.65 in BLEU, 4.42 in ENTScore, and 3.84 in HMean on the TIMETRAVEL dataset. Full article

In this study, a novel intelligent inverter fault diagnosis approach based on a stacked denoising autoencoder–generative adversarial network–long short-term memory (SDAE-GAN-LSTM) under an imbalanced sample is proposed for a three-phase permanent-magnet synchronous motor (PMSM) drive system. The proposed method can address the problem of unbalanced fault data samples and improve the accuracy of fault classification. Concretely speaking, firstly, the stacked denoising autoencoder (SDAE) is pre-trained to obtain the optimum decoder network. Afterward, a new generator of generative adversarial networks (GANs) is designed to generate high-quality samples by migrating the pre-trained optimal decoder network to the hidden layer and output layer of the generator of GANs. Additionally, a new model of long short-term memory (LSTM) based on the second discriminator of the GANs is presented for fault diagnosis. The generator of GANs is cross-trained using the reconstruction error gained by SDAE and the fault diagnosis error obtained by LSTM, resulting in the generation of high-quality samples for fault discrimination. Simulation and experimental results demonstrate the effectiveness of the proposed fault diagnosis approach, and the average fault identification accuracy reaches 98.63%. Full article

Knowledge tracing (KT) aims to trace a learner’s understanding or achievement of knowledge based on learning history. The surge in online learning systems has intensified the necessity for automated measurement of students’ knowledge states. In particular, in the case of learning in the English proficiency assessment field, such as TOEIC, it is required to model the knowledge states by reflecting on the difficulty of questions. However, previous KT approaches often overly complexify their model structures solely to accommodate difficulty or consider it only for a secondary purpose such as data augmentation, hindering the adaptability of potent and general-purpose models such as Transformers to other cognitive components. Addressing this, we investigate the integration of question difficulty within KT with a potent general-purpose model for application in English proficiency assessment. We conducted empirical studies with three approaches to embed difficulty effectively: (i) reconstructing input features by incorporating difficulty, (ii) predicting difficulty with a multi-task learning objective, and (iii) enhancing the model’s output representations from (i) and (ii). Experiments validate that direct inclusion of difficulty in input features, paired with enriched output representations, consistently amplifies KT performance, underscoring the significance of holistic consideration of difficulty in the KT domain. Full article

A network intrusion detection tool can identify and detect potential malicious activities or attacks by monitoring network traffic and system logs. The data within intrusion detection networks possesses characteristics that include a high degree of feature dimension and an unbalanced distribution across categories. Currently, the actual detection accuracy of some detection models is relatively low. To solve these problems, we propose a network intrusion detection model based on multi-head attention and BiLSTM (Bidirectional Long Short-Term Memory), which can introduce different attention weights for each vector in the feature vector that strengthen the relationship between some vectors and the detection attack type. The model also utilizes the advantage that BiLSTM can capture long-distance dependency relationships to obtain a higher detection accuracy. This model combined the advantages of the two models, adding a dropout layer between the two models to improve the detection accuracy while preventing training overfitting. Through experimental analysis, the network intrusion detection model that utilizes multi-head attention and BilSTM achieved an accuracy of 98.29%, 95.19%, and 99.08% on the KDDCUP99, NSLKDD, and CICIDS2017 datasets, respectively. Full article

Road instance segmentation is vital for autonomous driving, yet the current algorithms struggle in complex city environments, with issues like poor small object segmentation, low-quality mask edge contours, slow processing, and limited model adaptability. This paper introduces an enhanced instance segmentation method based on SOLOv2. It integrates the Bottleneck Transformer (BoT) module into VoVNetV2, replacing the standard convolutions with ghost convolutions. Additionally, it replaces ResNet with an improved VoVNetV2 backbone to enhance the feature extraction and segmentation speed. Furthermore, the algorithm employs Feature Pyramid Grids (FPGs) instead of Feature Pyramid Networks (FPNs) to introduce multi-directional lateral connections for better feature fusion. Lastly, it incorporates a convolutional Block Attention Module (CBAM) into the detection head for refined features by considering the attention weight coefficients in both the channel and spatial dimensions. The experimental results demonstrate the algorithm’s effectiveness, achieving a 27.6% mAP on Cityscapes, a 4.2% improvement over SOLOv2. It also attains a segmentation speed of 8.9 FPS, a 1.7 FPS increase over SOLOv2, confirming its practicality for real-world engineering applications. Full article

This paper provides a clear demonstration that a coplanar stripline (CPS) as a balanced line can act to re-establish the phase balance in the presence of phase deviation from a 180° distance between two input signal lines connected to the CPS. A half-wave delay line splitter connected to a CPS works as a balun to feed a balanced antenna, such as a quasi-Yagi antenna. This type of balun structure has been widely used to feed balanced antennas with a frequency bandwidth of up to 60%. Nevertheless, no clear explanation has been given regarding how the broadband antennas could be implemented with this type of balun structure. In this paper, through 3D EM simulations and measurements, it is shown that the half-wave delay line splitter indeed only results in the 180° phase balance at one frequency, but the subsequently connected CPS acts to recover the phase balance between the signal lines. The CPS can recover the phase balance within a phase imbalance of ~π/3, which determines the usable bandwidth of this structure. For a demonstration, with a center frequency of 10 GHz, samples of the half-wave delay line splitter connected to a CPS are fabricated and measured. Full article

The vehicle routing problem (VRP) is a common problem in logistics and transportation with high application value. In the past, many methods have been proposed to solve the vehicle routing problem and achieved good results, but with the development of neural network technology, solving the VRP through neural combinatorial optimization has attracted more and more attention by researchers because of its short inference time and high parallelism. PMOCO is the most state-of-the-art multi-objective vehicle routing optimization algorithm. However, in PMOCO, preferences are often uniformly selected, which may lead to uneven Pareto sets and may reduce the quality of solutions. To solve this problem, we propose a multi-objective vehicle routing optimization algorithm based on preference adjustment, which is improved from PMOCO. We incorporate the weight adjustment method in PMOCO that is able to adapt to different approximate Pareto fronts and to find solutions with better quality. We treat the weight adjustment as a sequential decision process and train it through deep reinforcement learning. We find that our method could adaptively search for a better combination of preferences and have strong robustness. Our method is experimented on multi-objective vehicle routing problems and obtained good results (about 6% improvement compared with PMOCO with 20 preferences). Full article

Water electrolysis is a clean, non-polluting way of producing hydrogen that has seen rapid development in recent years. It offers the possibility of resolving the issue of excessive carbon emissions in conventional hydrogen production methods. In addition, waste heat recovery in hydrogen fuel cells can significantly increase the efficiency of energy use. Thus, to combine the electric power system, the hydrogen energy system, and the district heating system, this research suggests a novel optimal multi-energy complementary electricity–hydrogen–heat model. Rooftop photovoltaics, energy storage batteries, electric boilers, and hydrogen energy systems made up of hydrogen generation, hydrogen storage, and hydrogen fuel cells are all included in the suggested model. Furthermore, the electricity–hydrogen–heat system can be connected successfully using waste heat recovery in hydrogen fuel cells to create a coordinated supply of heat and power. In this work, the waste heat of hydrogen fuel cells is taken into account to increase the efficiency of energy use. To show the effectiveness of the suggested optimal multi-energy complementary model, many case studies have been conducted. Full article

The technologies of undersea detection and communication, seabed sensor networks, and geophysical detection using electromagnetic waves have emerged as research focal points within the field of marine science and engineering. However, most studies have focused on the propagation of electromagnetic fields over long distances within the shallow “sea-seabed” environment. This paper introduces a quasi-static approximation method to address the Sommerfeld numerical integration challenge within the near-field region, employing the horizontal electric dipole (HED) as a model. It derives the Sommerfeld numerical integral expressions under conditions where the wave-number ratio at the “seawater-air” boundary does not adhere to the requirement of |k₀/k₁| << 1 (where subscripts 0 and 1 denote seawater and air media, respectively). Building upon this, the paper simplifies the Bessel-Fourier infinite integral term within the integral expression to obtain Sommerfeld numerical integral approximations for the propagation of electromagnetic fields in the near region of extremely low frequency (ELF) within seawater. The study further conducts simulations and calculations to determine amplitude variations in electromagnetic field intensity generated by an ELF HED at different frequencies, dipole heights, and observation point depths. It concludes with an analysis of electromagnetic field propagation characteristics at the seawater-air boundary. Experimental findings highlight the lateral wave as the primary mode of electromagnetic wave propagation at this interface. Full article

This paper presents the design and performance analysis of a wideband charge-pump phase-locked loop (CPPLL) characterized by low reference spur and low phase noise. The proposed CPPLL, operating as a wideband phase-locked loop (PLL) with a reference frequency of 100 MHz, achieves a wide tuning range of 40% from 2.0 GHz to 3.0 GHz. A clock feedthrough suppressed charge pump with additional bias current branches is used to reduce the PLL’s loop reference spur. The 4-stage current mode logic (CML) divide-by-2/3 circuit is utilized in the frequency divider to achieve high-speed frequency division. The circuit of an AND gate and latch in the 2/3 divider adopts a full differential symmetric structure to minimize the phase error of high-frequency differential signals. The voltage-controlled oscillator (VCO) is designed to provide a wide tuning range while optimizing the trade-off between the phase noise and power consumption. The fabricated PLL is implemented using a 0.13 µm CMOS process. Experimental measurements reveal a reference spur of −74.39 dBc at an oscillation frequency of 2.4 GHz. Moreover, the CPPLL achieves phase noise of −102.55 dBc/Hz@100 kHz and −127.15 dBc/Hz@1 MHz, while consuming 33.6 mW under a 1.2 V supply voltage. The integrated root-mean-square (rms) jitter, measured from 10 kHz to 10 MHz, is 340.99 fs, and the figure-of-merit (FoM) is −234.08 dB at a carrier frequency of 2.4 GHz, highlighting the potential of the proposed PLL for integrated circuit applications. Full article

A one-dimensional mono-pulse microstrip antenna plays an important role in target detection, tracking, recognition and imaging. However, feeding and coupling are the main reasons for the large size of the mono-pulse antenna, which is not conducive to miniaturization and integration. A miniaturized mono-pulse antenna is proposed to reduce the size and improve the integration in antenna design. The proposed antenna has a more compact size and good isolation, with a well-maintained radiation pattern and zero depth. The antenna unit size is 0.19 λ₀ × 0.19 λ₀ × 0.006 λ₀. The overall antenna size is 78 mm × 78 mm × 1.48 mm (0.63 λ₀ × 0.63 λ₀ × 0.0012 λ₀). In this communication, a general decoupling feeding network for two-element microstrip array antennas is also designed. Experiment validations confirm that the operating frequency of the designed antenna system is at 2.45 GHz with a gain of 5.54 dBi. The return loss of the sum and difference ports is 16.14 dB and 15.2 dB, respectively. The isolation of the ports is 36.6 dB. The proposed miniaturized mono-pulse antenna is approximately 64% smaller in size compared to previous versions. Full article

In this study, we propose a hybrid model for Perspective-n-Point (PnP)-based 6D object pose estimation called FusionNet that takes advantage of convolutional neural networks (CNN) and Transformers. CNN is an effective and potential tool for feature extraction, which is considered the most popular architecture. However, CNN has difficulty in capturing long-range dependencies between features, and most CNN-based models for 6D object pose estimation are bulky and heavy. To address these problems, we propose a lighter-weight CNN building block with attention, design a Transformer-based global dependency encoder, and integrate them into a single model. Our model is able to extract dense 2D–3D point correspondences more accurately while significantly reducing the number of model parameters. Followed with a PnP header that replaces the PnP algorithm for general end-to-end pose estimation, our model showed better or highly competitive performance in pose estimation compared with other state-of-the-art models in experiments on the LINEMOD dataset. Full article

The fast and accurate detection of steel surface defects has become an important goal of research in various fields. As one of the most important and effective methods of detecting steel surface defects, the successive generations of YOLO algorithms have been widely used in these areas; however, for the detection of tiny targets, it still encounters difficulties. To solve this problem, the first modified PP-YOLOE algorithm for small targets is proposed. By introducing Coordinate Attention into the Backbone structure, we encode channel relationships and long-range dependencies using accurate positional information. This improves the performance and overall accuracy of small target detection while maintaining the model parameters. Additionally, simplifying the traditional PAN+FPN components into an optimized FPN feature pyramid structure allows the model to skip computationally expensive but less relevant processes for the steel surface defect dataset, effectively reducing the computational complexity of the model. The experimental results show that the overall average accuracy (mAP) of the improved PP-YOLOE algorithm is increased by 4.1%, the detection speed is increased by 2.06 FPS, and the accuracy of smaller targets (with a pixel area less than 322) that are more difficult to detect is significantly improved by 13.3% on average, as compared to the original algorithm. The detection performance is also higher than that of the mainstream target detection algorithms, such as SSD, YOLOv3, YOLOv4, and YOLOv5, and has a high application value in industrial detection. Full article

Studies have shown that in today’s urban areas, drivers lose a significant amount of time searching for available on-street parking spaces. Cruising drivers cause numerous problems, such as wasting gasoline and emitting gasses that lead to air pollution. To solve this issue, the parking industry and academia have made great efforts to lessen cruising drivers’ problems by providing on-street parking management solutions that can help enhance the efficient use of limited free on-street parking spaces. However, these solutions have two main limitations, scalability and privacy. This paper proposes a systematic literature review that examines the on-street parking management solutions that are currently in use, with a particular focus on their scalability and privacy limitations. According to the findings, there is a growing interest in on-street parking management solutions; however, the scalability of the systems used is a significant challenge since the servers that collect and manage parking availability have to perform intensive computation and communication with the drivers. Additionally, privacy concerns are a major issue, as the solutions often collect and store personal information such as drivers’ locations. The review concludes with recommendations for future research and development of these solutions to address both limitations and promote their widespread adoption. Full article

The Frangi neuron proposed in this work is a complex element that allows high-level Hessian-based image processing. Its adaptive parameters (weights) can be trained using a minimum number of training data. In our experiment, we showed that just one image is enough to optimize the values of the weights. An intuitive application of the Frangi neuron is to use it in image segmentation process. In order to test the performance of the Frangi neuron, we used diverse medical datasets on which second-order structures are visualized. The Frangi network presented in this paper trained on a single image proved to be significantly more effective than the U-net trained on the same dataset. For the datasets tested, the network performed better as measured by area under the curve receiver operating characteristic (ROC AUC) than U-net and the Frangi algorithm. However, the Frangi network performed several times faster than the non-GPU implementation of Frangi. There is nothing to prevent the Frangi neuron from being used as part of any other network as a component to process two-dimensional images, for example, to detect certain second-order features in them. Full article

Anomaly-based intrusion detection systems identify the computer network behavior which deviates from the statistical model of typical network behavior. Binary classifiers based on supervised machine learning are very accurate at classifying network data into two categories: normal traffic and anomalous activity. Most problems with supervised learning are related to the large amount of data required to train the classifiers. Feature selection can be used to reduce datasets. The goal of feature selection is to select a subset of relevant input features to optimize the evaluation and improve performance of a given classifier. Feature scaling normalizes all features to the same range, preventing the large size of features from affecting classification models or other features. The most commonly used supervised machine learning models, including decision trees, support vector machine, k-nearest neighbors, weighted k-nearest neighbors and feedforward neural network, can all be improved by using feature selection and feature scaling. This paper introduces a new feature scaling technique based on a hyperbolic tangent function and damping strategy of the Levenberg–Marquardt algorithm. Full article