Electronics, Volume 12, Issue 1 (January-1 2023) – 252 articles

This paper proposes a unidirectional finite control set-predictive toque control (UFCS-PTC) method for a three-level neutral-point-clamped (3L-NPC) inverter fed interior permanent magnet synchronous motor (IPMSM). The proposed algorithm can lower the complexity of PTC fed by 3L-NPC by reducing the number of admissible voltage vectors (VVs) effectively. The candidate VVs are restricted within 60° of the voltage space voltage diagram (VSVD), which is the nearest to the flux trajectory for each 60° flux sector. After the segmentation of the VSVD and flux trajectory, the proposed method can keep VVs in one direction during the prediction process, which can result in significant torque/flux reduction. Therefore, the UFCS-PTC can reduce the number of admissible VVs from twenty-seven to six while achieving excellent steady-state performance in terms of reduced flux and torque ripples. Additionally, the proposed method eliminates the need for weighting factor calculation for neutral point voltage associated with a 3L-NPC inverter. The UFCS-PTC of IPMSM also has other features, such as improved balancing capability of the DC-link capacitors’ voltage, small computation time due to the reduced number of admissible voltage vectors considered in the cost function, and easy implementation. The effectiveness of the proposed method is verified through experimental results. Full article

The number of fraud occurrences in electronic banking is rising each year. Experts in the field of cybercrime are continuously monitoring and verifying network infrastructure and transaction systems. Dedicated threat response teams (CSIRTs) are used by organizations to ensure security and stop cyber attacks. Financial institutions are well aware of this and have increased funding for CSIRTs and antifraud software. If the company has a rule-based antifraud system, the CSIRT can examine fraud cases and create rules to counter the threat. If not, they can attempt to analyze Internet traffic down to the packet level and look for anomalies before adding network rules to proxy or firewall servers to mitigate the threat. However, this does not always solve the issues, because transactions occasionally receive a “gray” rating. Nevertheless, the bank is unable to approve every gray transaction because the number of call center employees is insufficient to make this possible. In this study, we designed a machine-learning-based rating system that provides early warnings against financial fraud. We present the system architecture together with the new ML-based scoring extension, which examines customer logins from the banking transaction system. The suggested method enhances the organization’s rule-based fraud prevention system. Because they occur immediately after the client identification and authorization process, the system can quickly identify gray operations. The suggested method reduces the amount of successful fraud and improves call center queue administration. Full article

About 5–10% of software engineers suffer from repetitive strain injury, and it would be better to provide an alternative way to write code instead of using a mouse and keyboard and sitting on a chair the whole day. Coding by voice is an attractive approach, and quite a bit of work has been done in that direction. At the same time, dictating plain Java text with low accuracy through the existing voice recognition engines or providing complex panels controlled by the voice makes the coding process even more complex. We argue that current programming languages are suitable for programming by hand, not by mouth. We try to solve this problem by designing a new programming language, VoiceJava, suitable for dictating. A Java program is constructed in a syntax-directed way through a sequence of VoiceJava commands. As a result, users do not need to dictate spaces, parentheses, and commas, reducing the vocal load. Full article

This paper designs a plant leaf expansion pressure non-destructive detection device, aiming to promote plant leaf expansion pressure research and achieve precision irrigation. The design is based on leaf expansion pressure probe technology, which can effectively monitor the plant leaf expansion pressure by detecting the feedback of the leaf under constant pressure. In this paper, the stability of the sensor and the calibration model is tested. The calibration experiments showed that the coefficient of determination R² of the sensor was over 0.99, the static test results showed that the range of the sensor was 0–300 kPa, and the fluctuation of the sensor was less than 0.2 kPa during the long-term stability test. The indoor comparison tests showed that there was a significant difference in the variation of leaf expansion pressure data between plants under drought conditions and normal conditions. The irrigation experiments showed that the leaf expansion pressure was very sensitive to irrigation. The correlation between the expansion pressure data and the environmental factors was analyzed. The correlation coefficient between expansion pressure and light intensity was found to be 0.817. The results of the outdoor experiments showed that there was a significant difference in the expansion pressure of plants under different weather conditions. The data show that the plant leaf expansion pressure non-destructive detection device designed in this paper can be used both as an effective means of detecting plant leaf expansion pressure and promoting the research of plant physiological feedback mechanisms and precision irrigation. Full article

With the continuous development of the Internet of things (IoT) technology, the air-to-ground (ATG) system has attracted more and more attention. The system will effectively increase communication coverage and improve communication quality. The ATG system uses frequency reuse technology in the ground layer to further utilize frequency resources. This paper focuses mostly on the cochannel interference between the 5G BS and the ATG airborne CPE terminal in the 3.5 GHz range. The ATG airborne CPE terminal has to be further isolated from 5G BS in order to prevent interference. We must manage the transmitting power of the ATG airborne CPE terminal in order to comply with the additional isolation criteria. The RSRP value of 5G BS determines the transmit power of the ATG airborne CPE terminal. We creatively suggested a machine learning (ML) approach based on multihead attention to anticipate the RSRP of 5G BS because it is highly challenging for the ATG aerial CPE terminal to monitor the RSRP of 5G BS in real time. By comparing the suggested ML-based approach with the actual measured values, its efficacy is confirmed. Full article

With the rapid development of global communication technology, the problem of scarce spectrum resources has become increasingly prominent. In order to alleviate the problem of frequency use, rationally use limited spectrum resources and improve frequency utilization, spectrum prediction technology has emerged. Through the effective prediction of spectrum usage, the number of subsequent spectrum sensing processes can be slowed down, and the accuracy of spectrum decisions can be increased to improve the response speed of the whole cognitive radio technology. The rise of deep learning has brought changes to traditional spectrum predicting algorithms. This paper proposes a spectrum predicting method called Back Propagation-Long short-term memory Time Forecasting (B-LTF) by using Back Propagation-Long Short-term Memory (BP-LSTM) network model. According to the historical spectrum data, the future spectrum trend and the channel state of the future time node are predicted. The purpose of our research is to achieve dynamic spectrum access by improving the accuracy of spectrum prediction and better assisting cognitive radio technology. By comparing with BP, LSTM and Gate Recurrent Unit (GRU) network models, we clarify that the improved model of recurrent time network can deal with time series more effectively. The simulation results show that the proposed model has better prediction performance, and the change in time series length has a significant impact on the prediction accuracy of the deep learning model. Full article

Based on the discovery of the surge absorption capability of supercapacitors, a transient protector named supercapacitor-assisted surge absorber (SCASA) was designed and implemented in a commercial device. Despite its simplicity, the circuit topology consisted of a coupled inductor wound around a specially selected magnetic core. This paper elucidates the design aspects of SCASA coupled-inductor topologies with a special focus on the magnetic action of core windings during transient propagation. The non-ideal operation of the SCASA transformer was studied based on a semi-empirical approach with predictions made by using magnetizing and leakage permeances. The toroidal flux distribution through the transformer was also determined for a 6 kV/3 kA combinational surge, and these findings were validated by using a lightning surge simulator. In predicting the possible effects of magnetic saturation, the hysteresis properties of different powdered-iron and ferrite core types were considered to select the optimal design for surge absorption. The test results presented in this research revealed that X-Flux powdered-iron toroid and air-gapped EER ferrite yielded exceptional performance with ∼10% and ∼20% lower load–voltage clamping compared to that of the existing Kool $\mathsf{\mu }$u design. These prototypes further demonstrated a remarkable surge endurance, withstanding over 250 consecutive transients. This paper also covers details of three-winding design optimizations of SCASA and LTSpice simulations under the IEC 61000/IEEE C62.45 standard transient conditions. Full article

This paper analyzed the four series-parallel (SP) compensation topologies to achieve constant current (CC) and voltage (CV) output characteristics and zero phase angle (ZPA) input conditions with fewer compensation components in the capacitive power transfer (CPT) system. There are three main contributions. Firstly, the universal methodology of SP compensation topologies was constructed to achieve CC, CV output, and ZPA conditions. Secondly, four specific SP compensation topologies were investigated and summarized, including double-sided LC, double-sided CL, CL−LC, and LC−CL topologies. Their input–output characteristics are provided, and system efficiency is analyzed. Thirdly, the CL−LC and LC−CL topologies were proposed to realize ZPA conditions under CC and CV output without any external regulating circuit. A CV output LC−CL experiment prototype was implemented to validate the theoretical analysis. Full article

A control method that combines trajectory planning and backstepping is proposed for the antisway problem of underactuated overhead cranes under wind disturbance. First, a set of flat outputs is proposed so that the crane system dynamics can be represented by each order of flat outputs. Sufficient relevant constraints are given to ensure that the trolley can arrive at the desired position in a limited time under variable rope lengths, and that the swing angle can be suppressed when the payload is lifted or lowered during operation. The planned trajectory is obtained by solving for the optimal parameters of the flat output. Next, to reduce the deviation caused by wind disturbance on the actual control of the trajectory, a tracking controller is designed. Because the system output space and flat output space are differentiable homeomorphisms, the backstepping controller constructed based on the flat output can indirectly control the system output, which makes the backstepping method applicable to underactuated cranes. The simulation results show that the proposed method is effective and has strong robustness. Full article

This paper aims to solve one of the most challenging problems in designing VLSI chips for common goods, namely an efficient incorporation of security techniques while maintaining high performances of the VLSI implementation with a reduced hardware complexity. In this case, it is very important to maintain high performance at a low hardware complexity and the overheads introduced by the security techniques should be as low as possible. This paper proposes an improved approach based on a new VLSI algorithm for including the obfuscation technique in the VLSI implementation of one important DSP algorithm used in multimedia applications. The proposed approach is based on a new VLSI algorithm that decomposes type IV DCT into six quasi-cycle convolutions and allows an efficient incorporation of the obfuscation technique. The proposed method uses a regular and modular structure called quasi-cyclic convolution and the obtained architecture is based on the architectural paradigm of systolic arrays. In this way we can obtain the advantages introduced by systolic arrays, especially high speed, with an efficient utilization of the hardware structure. Moreover, using the proposed VLSI algorithm, we can obtain the important benefit of attaining hardware security. Thus, a more efficient VLSI architecture for type IV DCT can be obtained, with a significant reduction of the hardware complexity, and an efficient incorporation of an improved hardware security mechanism with low overheads. These features are very important for resource-constrained common goods. Full article

With the assistance of machine learning, difficult tasks can be completed entirely on their own. In a smart grid (SG), computers and mobile devices may make it easier to control the interior temperature, monitor security, and perform routine maintenance. The Internet of Things (IoT) is used to connect the various components of smart buildings. As the IoT concept spreads, SGs are being integrated into larger networks. The IoT is an important part of SGs because it provides services that improve everyone’s lives. It has been established that the current life support systems are safe and effective at sustaining life. The primary goal of this research is to determine the motivation for IoT device installation in smart buildings and the grid. From this vantage point, the infrastructure that supports IoT devices and the components that comprise them is critical. The remote configuration of smart grid monitoring systems can improve the security and comfort of building occupants. Sensors are required to operate and monitor everything from consumer electronics to SGs. Network-connected devices should consume less energy and be remotely monitorable. The authors’ goal is to aid in the development of solutions based on AI, IoT, and SGs. Furthermore, the authors investigate networking, machine intelligence, and SG. Finally, we examine research on SG and IoT. Several IoT platform components are subject to debate. The first section of this paper discusses the most common machine learning methods for forecasting building energy demand. The authors then discuss IoT and how it works, in addition to the SG and smart meters, which are required for receiving real-time energy data. Then, we investigate how the various SG, IoT, and ML components integrate and operate using a simple architecture with layers organized into entities that communicate with one another via connections. Full article

The application of jointing multiple physical field sensing with electromagnetic (EM) wave manipulation is a hot research topic recently. Refined perception and unit-level independent regulation of metasurfaces still have certain challenges. In this paper, we propose a digital programmable metasurface that can adaptively achieve various EM functions by sensing the color changes of the incident light, which enables unit-level sensing and modulation. Integrating trichromatic sensors, FPGA, and algorithm onto the metasurface has established a metasurface architecture for electromagnetic scattering field modulation from complex optics to microwave wavelengths, which enables a wide variety of light sensing for modulation. The metasurface integrated with PIN diodes and trichromatic color sensors forms a complete intelligent system of adaptive and reconfigurable coding patterns, within the pre-designed control of FPGA. We fabricated the metasurface using standard printed circuit board (PCB) technology and measured the metasurface in far-fields. The measurement results show good agreement with the simulation results, verifying our design. We envision that the proposed programmable metasurface with visible light sensing will provide a new dimension of manipulation from this perspective. Full article

To accelerate the inference of machine-learning (ML) model serving, clusters of machines require the use of expensive hardware accelerators (e.g., GPUs) to reduce execution time. Advanced inference serving systems are needed to satisfy latency service-level objectives (SLOs) in a cost-effective manner. Novel autoscaling mechanisms that greedily minimize the number of service instances while ensuring SLO compliance are helpful. However, we find that it is not adequate to guarantee cost effectiveness across heterogeneous GPU hardware, and this does not maximize resource utilization. In this paper, we propose HetSev to address these challenges by incorporating heterogeneity-aware autoscaling and resource-efficient scheduling to achieve cost effectiveness. We develop an autoscaling mechanism which accounts for SLO compliance and GPU heterogeneity, thus provisioning the appropriate type and number of instances to guarantee cost effectiveness. We leverage multi-tenant inference to improve GPU resource utilization, while alleviating inter-tenant interference by avoiding the co-location of identical ML instances on the same GPU during placement decisions. HetSev is integrated into Kubernetes and deployed onto a heterogeneous GPU cluster. We evaluated the performance of HetSev using several representative ML models. Compared with default Kubernetes, HetSev reduces resource cost by up to 2.15× while meeting SLO requirements. Full article

Graph neural networks have a wide range of applications, such as citation networks, social networks, and knowledge graphs. Among various graph analyses, node classification has garnered much attention. While many of the recent network embedding models achieve promising performance, they usually require sufficient labeled nodes for training, which does not meet the reality that only a few labeled nodes are available in novel classes. While few-shot learning is commonly employed in the vision and language domains to address the problem of insufficient training samples, there are still two characteristics of the few-shot node classification problem in the non-Euclidean domain that require investigation: (1) how to extract the most informative knowledge for a class and use it on testing data and (2) how to thoroughly explore the limited number of support sets and maximize the amount of information transferred to the query set. We propose an InfoMax Classification-Enhanced Learnable Network (ICELN) to address these issues, motivated by Deep Graph InfoMax (DGI), which adapts the InfoMax principle to the summary representation of a graph and the patch representation of a node. By increasing the amount of information that is shared between the query nodes and the class representation, an ICELN can transfer the maximum amount of information to unlabeled data and enhance the graph representation potential. The whole model is trained using an episodic method, which simulates the actual testing environment to ensure the meta-knowledge learned from previous experience may be used for entirely new classes that have not been studied before. Extensive experiments are conducted on five real-world datasets to demonstrate the advantages of an ICELN over the existing few-shot node classification methods. Full article

Traffic flow forecasting, as one of the important components of intelligent transport systems (ITS), plays an indispensable role in a wide range of applications such as traffic management and city planning. However, complex spatial dependencies and dynamic changes in temporal patterns exist between different routes, and obtaining as many spatial-temporal features and dependencies as possible from node data has been a challenging task in traffic flow prediction. Current approaches typically use independent modules to treat temporal and spatial correlations separately without synchronously capturing such spatial-temporal correlations, or focus only on local spatial-temporal dependencies, thereby ignoring the implied long-term spatial-temporal periodicity. With this in mind, this paper proposes a long-term spatial-temporal graph convolutional fusion network (LSTFGCN) for traffic flow prediction modeling. First, we designed a synchronous spatial-temporal feature capture module, which can fruitfully extract the complex local spatial-temporal dependence of nodes. Second, we designed an ordinary differential equation graph convolution (ODEGCN) to capture more long-term spatial-temporal dependence using the spatial-temporal graph convolution of ordinary differential equation. At the same time, by integrating in parallel the ODEGCN, the spatial-temporal graph convolution attention module (GCAM), and the gated convolution module, we can effectively make the model learn more long short-term spatial-temporal dependencies in the processing of spatial-temporal sequences.Our experimental results on multiple public traffic datasets show that our method consistently obtained the optimal performance compared to the other baselines. Full article

Smart energy management and control systems can improve the efficient use of electricity and maintain the balance between supply and demand. This paper proposes the modeling of a decentralized energy management system (EMS) to reduce system operation costs under renewable generation and load uncertainties. There are three stages of the proposed strategy. First, this paper applies an autoregressive moving average (ARMA) model for forecasting PV and wind generations as well as power demand. Second, an optimal generation scheduling process is designed to minimize system operating costs. The well-known algorithm of particle swarm optimization (PSO) is applied to provide optimal generation scheduling among PV and WT generation systems, fuel-based generation units, and the required power from the main grid. Third, a demand response (DR) program is introduced to shift flexible load in the microgrid system to achieve an active management system. Simulation results demonstrate the performance of the proposed method using forecast data for hourly PV and WT generations and a load profile. The simulation results show that the optimal generation scheduling can minimize the operating cost under the worst-case uncertainty. The load-shifting demand response reduced peak load by 4.3% and filled the valley load by 5% in the microgrid system. The proposed optimal scheduling system provides the minimum total operation cost with a load-shifting demand response framework. Full article

The quality of yarn is essential in the control of the fabrics processes. There is some commercial equipment that measures the quality of yarn based on sensors, of different types, used for collecting data about some textile yarn characteristic parameters. The irregularity of the textile thread influences its physical properties/characteristics and there may be a possibility of a break in the textile thread during the fabric manufacturing process. This can contribute to the occurrence of unwanted patterns in fabrics that deteriorate their quality. The existing equipment, for the above-mentioned purpose, is characterized by its high size and cost, and for allowing the analysis of only few yarn quality parameters. The main findings/results of the study are the yarn analysis method as well as the developed algorithm, which allows the analysis of defects in a more precise way. Thus, this paper presents the development and results obtained with the design of a mechatronic prototype integrating a computer vision system that allows, among other parameters, the analysis and classification, in real time, of the hairs of the yarn using artificial intelligence techniques. The system also determines other characteristics inherent to the yarn quality analysis, such as: linear mass, diameter, volume, twist orientation, twist step, average mass deviation, coefficient of variation, hairiness coefficient, average hairiness deviation, and standard hairiness deviation, as well as performing spectral analysis. A comparison of the obtained results with the designed system and a commercial equipment was performed validating the undertaken methodology. Full article

There are a variety of potential uses for the classification of eye conditions, including tiredness detection, psychological condition evaluation, etc. Because of its significance, many studies utilizing typical neural network algorithms have already been published in the literature, with good results. Convolutional neural networks (CNNs) are employed in real-time applications to achieve two goals: high accuracy and speed. However, identifying drowsiness at an early stage significantly improves the chances of being saved from accidents. Drowsiness detection can be automated by using the potential of artificial intelligence (AI), which allows us to assess more cases in less time and with a lower cost. With the help of modern deep learning (DL) and digital image processing (DIP) techniques, in this paper, we suggest a CNN model for eye state categorization, and we tested it on three CNN models (VGG16, VGG19, and 4D). A novel CNN model named the 4D model was designed to detect drowsiness based on eye state. The MRL Eye dataset was used to train the model. When trained with training samples from the same dataset, the 4D model performed very well (around 97.53% accuracy for predicting the eye state in the test dataset). The 4D model outperformed the performance of two other pretrained models (VGG16, VGG19). This paper explains how to create a complete drowsiness detection system that predicts the state of a driver’s eyes to further determine the driver’s drowsy state and alerts the driver before any severe threats to road safety. Full article

One of the most pressing issues in the field of mobile robotics is power delivery. In the past, we have proposed a powered floor based solution. In this article, we propose a system which combines a powered floor with a robot pose estimation system. The floor on which the mobile robots stand is composed of an array of interdigitated conductors that provide DC power supply; the stripes of conductors are interwoven similarly to what happens in a carpet, thus creating a sort of checkerboard of positive and negative pads. The robots are powered through sliding contacts. The power supply voltage is modulated with a binary encoding that uniquely identifies each conductor stripe power line; in this way, each robot is able to self-localize, by exploiting the information coming from the contacting pins. We describe the theoretical framework that allows concurrent power delivery and localization (with error boundaries). Then, we present the experimental evaluation that we performed using a prototype realization of the proposed powered floor system. Full article

Transcendental functions are an important part of algorithms in many fields. However, the hardware accelerators available today for transcendental functions typically only support one such function. Hardware accelerators that can support miscellaneous transcendent functions are a waste of hardware resources. In order to solve these problems, this paper proposes a reconfigurable hardware architecture for miscellaneous floating-point transcendental functions. The hardware architecture supports a variety of transcendental functions, including floating-point sine, cosine, arctangent, exponential and logarithmic functions. It adopts the method of a lookup table combined with a polynomial computation and reconfigurable technology to achieve the accuracy of two units of least precision $\left(ulp\right)$ with 3.75 KB lookup tables and one core computing module. In addition, the hardware architecture uses retiming technology to realize the different operation times of each function. Experiments show that the hardware accelerators proposed can operate at a maximum frequency of 220 MHz. The full-load power consumption and areas are only 0.923 mW and $1.40\times {10}^4\mathsf{\mu }$m${}^2$, which are reduced by 47.99% and 38.91%, respectively, compared with five separate superfunction hardware accelerators. Full article

In terms of the Internet and communication, security is the fundamental challenging aspect. There are numerous ways to harm the security of internet users; the most common is phishing, which is a type of attack that aims to steal or misuse a user’s personal information, including account information, identity, passwords, and credit card details. Phishers gather information about the users through mimicking original websites that are indistinguishable to the eye. Sensitive information about the users may be accessed and they might be subject to financial harm or identity theft. Therefore, there is a strong need to develop a system that efficiently detects phishing websites. Three distinct deep learning-based techniques are proposed in this paper to identify phishing websites, including long short-term memory (LSTM) and convolutional neural network (CNN) for comparison, and lastly an LSTM–CNN-based approach. Experimental findings demonstrate the accuracy of the suggested techniques, i.e., 99.2%, 97.6%, and 96.8% for CNN, LSTM–CNN, and LSTM, respectively. The proposed phishing detection method demonstrated by the CNN-based system is superior. Full article

Cardiovascular diseases, which include all heart and circulatory diseases, are among the major death-causing diseases in women. Cardiovascular diseases are not subject to screening programs, and early detection can reduce their mortal effect. Recent studies have shown a strong association between severe Breast Arterial Calcifications and cardiovascular diseases. The aim of this study is to use the screening programs for breast cancer to detect the high severity of BACs and therefore to obtain indirect information about coronary diseases. Previous attempts in the literature on the detection of BACs from digital mammograms still need improvements to be used as a standalone technique. In this study, a dataset of mammograms with BACs is divided into 4 grades of severity, and this study aims to improve their classification through a transfer learning approach to overcome the need for a large dataset of training. The performances achieved in this study by using pre-trained models to detect four Breast Arterial Calcifications severity grades reached an accuracy of 94% during testing. Therefore, it is possible to benefit from the advantage of Deep Learning models to define a rapid marker of BACs along Brest Cancer screening programs. Full article

Spin-Hall-effect nano-oscillators are promising beyond the CMOS devices currently available, and can potentially be used to emulate the functioning of neurons in computational neuromorphic systems. As they oscillate in the 4–20 GHz range, they could potentially be used for building highly accelerated neural hardware platforms. However, due to their extremely low signal level and high impedance at their output, as well as their microwave-range operating frequency, discerning whether the SHNO is oscillating or not carries a great challenge when its state read-out circuit is implemented using CMOS technologies. This paper presents the first CMOS front-end read-out circuitry, implemented in 180 nm, working at a SHNO oscillation frequency up to 4.7 GHz, managing to discern SHNO amplitudes of 100 µV even for an impedance as large as 300 Ω and a noise figure of 5.3 dB_{300 Ω}. A design flow of this front end is presented, as well as the architecture of each of its blocks. The study of the low-noise amplifier is deepened for its intrinsic difficulties in the design, satisfying the characteristics of SHNOs. Full article

Agriculture plays an essential role in Mexico’s economy. The agricultural sector has a 2.5% share of Mexico’s gross domestic product. Specifically, tomatoes have become the country’s most exported agricultural product. That is why there is an increasing need to improve crop yields. One of the elements that can considerably affect crop productivity is diseases caused by agents such as bacteria, fungi, and viruses. However, the process of disease identification can be costly and, in many cases, time-consuming. Deep learning techniques have begun to be applied in the process of plant disease identification with promising results. In this paper, we propose a model based on convolutional neural networks to identify and classify tomato leaf diseases using a public dataset and complementing it with other photographs taken in the fields of the country. To avoid overfitting, generative adversarial networks were used to generate samples with the same characteristics as the training data. The results show that the proposed model achieves a high performance in the process of detection and classification of diseases in tomato leaves: the accuracy achieved is greater than 99% in both the training dataset and the test dataset. Full article

One of the most expensive and fatal natural disasters in the world is forest fires. For this reason, early discovery of forest fires helps minimize mortality and harm to ecosystems and forest life. The present research enriches the body of knowledge by evaluating the effectiveness of an efficient wildfire and smoke detection solution implementing ensembles of multiple convolutional neural network architectures tackling two different computer vision tasks in a stage format. The proposed architecture combines the YOLO architecture with two weights with a voting ensemble CNN architecture. The pipeline works in two stages. If the CNN detects the existence of abnormality in the frame, then the YOLO architecture localizes the smoke or fire. The addressed tasks are classification and detection in the presented method. The obtained model’s weights achieve very decent results during training and testing. The classification model achieves a 0.95 F1-score, 0.99 accuracy, and 0.98e sensitivity. The model uses a transfer learning strategy for the classification task. The evaluation of the detector model reveals strong results by achieving a 0.85 mean average precision with 0.5 threshold ([email protected]) score for the smoke detection model and 0.76 mAP for the combined model. The smoke detection model also achieves a 0.93 F1-score. Overall, the presented deep learning pipeline shows some important experimental results with potential implementation capabilities despite some issues encountered during training, such as the lack of good-quality real-world unmanned aerial vehicle (UAV)-captured fire and smoke images. Full article

In this paper, the electromagnetic characteristics of a novel integrated multi-winding inductive filtering converter transformer, including two parallel-connected delta filter windings with zero impedance, are studied. First, based on Ansoft, a 3D FEM model of the novel converter transformer is built according to its structural parameters and material characteristics. Next, the external circuit connection based on the established 3D FEM model is realized so the corresponding field-circuit coupling model can be established under three different working conditions. On this basis, the electric field characteristics, magnetic field characteristics, winding electromagnetic force characteristics, and core loss characteristics of the novel converter transformer with different conditions are analyzed. The results show that because the harmonic current is effectively suppressed, the flux chain passing through the windings of the novel converter transformer is closer to the sinusoidal wave and the harmonic magnetic potential is effectively suppressed; the electromagnetic force received by each winding of the converter transformer and the high-frequency vibration component are significantly reduced; and the transformer core loss is also significantly reduced. The research on the internal electromagnetic characteristics of the integrated multi-winding inductive filter converter transformer reveals the mechanism of reducing vibration and noise. Full article

High-frequency wood drying is the modern method used in raw wood drying so that treated wood can be used further in various processes. Such systems are used because of the economy, energy efficiency, obtaining of good mechanical properties of the wood after treatment, as well as reducing time consumption. Therefore, it is extremely important to understand each component of such systems and processes. The mentioned systems are implemented using high-frequency generators based on vacuum tubes (VT). Their development and, in particular, optimization are by far more complex than the transistor systems; therefore, the development is now compelled to rely on computer modelling and simulation. In this research, a high-frequency (HF) generator of 20 kW output power and 1.5–15 MHz adjustable frequency based on VT was produced and then, with the corresponding model for VT itself and the rest of the developed circuit, was followed by computer simulation and real-system measurement. The model parameters were adjusted, which provided additional system optimization. An extra match of the results from the simulation and measurement was obtained; thus, the optimization was performed faster and more precisely. In addition, an easier and quicker way of adjusting parameters of the PID controller using a developed software-based control system was attained. The problems of cooling the VT anode under high DC voltage, as well as temperature measurement in the HF electric field, have been solved. Full article

As a clean and renewable energy source with huge reserves, the development of ocean wave energy has important strategic significance. Harvesting ocean wave energy through novel triboelectric nanogenerators (TENGs) has shown promising application prospects. For this technology, the integration of TENG units is the crucial step to realize large-scale network commercialization. All aspects of the TENG networking process are systematically summarized in this review, including the topology design and the circuit-connection scheme. Advancing the research on the large-scale TENG network is expected to make great contributions to achieve carbon neutrality. Full article

The current work employs the HMC830 phase-locked loop chip to design a frequency synthesizer operating in the L-band. The frequency synthesizer can provide a local oscillation signal for the RF receiver front end. This article employs the phase-locked synthesis technique to describe the design scheme. Due to the advantages of the passive loop filters, such as simplicity, low cost, and low phase noise, a passive fourth-order RLC loop filter is proposed to improve the output signal quality and reduce phase noise. The performance of this loop filter is compared with the passive fourth-order RC loop filter. The effects of these two loop filters on phase noise, loop capture time, and spur suppression are analyzed. Subsequently, the design scheme, simulation analysis, and test results of the frequency synthesizer are presented under these two loop filters. The test results indicate that the passive fourth-order RLC loop filter outperforms the passive fourth-order RC loop filter; its output signal phase noise is higher than −100 dBc/Hz@1 kHz, loop capture time is less than 100 us, and spur suppression is better than 60 dBc. This frequency synthesizer can provide high-performance local oscillation signals for wireless communication equipment such as transmitters and receivers. It meets the application requirements of many radio communication circuit structures and has good application prospects. Full article

Aiming at the problems of the large amount of model parameters and false and missing detections of multi-scale drone targets, we present a novel drone detection method, YOLOv4-MCA, based on the lightweight MobileViT and Coordinate Attention. The proposed approach is improved according to the framework of YOLOv4. Firstly, we use an improved lightweight MobileViT as the feature extraction backbone network, which can fully extract the local and global feature representations of the object and reduce the model’s complexity. Secondly, we adopt Coordinate Attention to improve PANet and to obtain a multi-scale attention called CA-PANet, which can obtain more positional information and promote the fusion of information with low- and high-dimensional features. Thirdly, we utilize the improved K-means++ method to optimize the object anchor box and improve the detection efficiency. At last, we construct a drone dataset and conduct a performance experiment based on the Mosaic data augmentation method. The experimental results show that the mAP of the proposed approach reaches 92.81%, the FPS reaches 40 f/s, and the number of parameters is only 13.47 M, which is better than mainstream algorithms and achieves a high detection accuracy for multi-scale drone targets using a low number of parameters. Full article