Journal of Circuits, Systems and Computers

Ground-based Interferometric Synthetic Aperture Radar (GB-InSAR) is a valuable technique for monitoring deformation of landslides. GB-InSAR can construct high-resolution 2D images in a range-doppler plane. However, it is difficult for geo-engineers who are unfamiliar with radar monitoring geometry to interpret the results. Geometric mapping method has been applied to the co-registration of terrain models and radar images for the deformation zonation, but the mismatching correction with GB-InSAR and terrain model is not fully investigated by existing researches. To address this issue, this paper proposes a method exploiting an optimum linear transformation based on ground control points (GCPs). The proposed method was evaluated on simulated data and a field campaign in an open pit mine. The deformation mapping result of the method was verified by a collapse event. The method proposed in this paper has an RMSE value ranging from 0.502 to 0.720m (@700m average monitoring range) when the average density of the terrain point cloud is 0.5m. Although this method cannot accurately evaluate the antenna footprint vector deflection parameters, it can meet the needs of coarse matching calibration in relatively flat slope sub-target areas of open-pit mines for engineering applications.

This paper presents a new capacitor charger for energy-harnessing applications such as energy transfer from a low-power battery to a load capacitor. The proposed structure uses a switching technique for step-by-step charging of the load capacitor. It comprises a control section, output stage metal-oxide-semiconductor field-effect transistors, and an external inductor. In order to improve the circuit efficiency under different power transfer scenarios, the switching capacitor charger operates at the boundary of continuous conduction mode and discontinuous conduction mode. Two blocks of peak current controller and zero current detector have been employed in a feedback loop to control the inductor current, which resulted in conduction power dissipation reduction. Also, the circuit with switching at low frequencies significantly reduces the switching loss. The performance of the proposed circuit is demonstrated using theoretical elaborations. In addition, the proposed structure is evaluated and simulated in a 0.18$\mu$m standard complementary metal-oxide semiconductor technology. Based on the obtained results, the efficiency of the presented circuit at 15.62mW input power is 96%, and the charging time is about 0.54ms, which is suitable for low-power applications.

It is crucial to capture the actual infection scale of communicable diseases. However, the official case numbers cannot equal to actual infection scale in society, because a large number of asymptomatic individuals are not recognized. To deal with this challenge, this paper takes COVID-19 as the object, and develops an improved SEIR dynamics model to estimate its actual infection scale. Generalized to the circumstances in this work, we improve the classical SEIR model by considering three implicit factors: self-recovered asymptomatic individuals, recovered individuals, and deceased individuals. The dynamics process inside the improved model is expressed using mathematical formulas, and the parameter estimation scheme is given accordingly. To evaluate the estimation effect of the proposal, we employ pandemic data from 10 representative countries to build experimental scenario. The results obtained through model fitting demonstrate that the estimated actual infection scale is approximately 10–30 times higher than the reported average “newly confirmed cases”. Furthermore, our findings reveal a noteworthy negative correlation between the transmission coefficient and vaccination rate, confirming the beneficial role of vaccination in mitigating COVID-19 spreading.

When the sources of renewable energy and numerous power electronic gadgets are introduced into the power system, which is related to the negative resistance features of power electronic gadgets, the power system with high power electronics often exhibits weak inertia. Also the stability of multi-converter grid-connected systems is adversely affected. To address these issues, a process of small disturbance stability analysis is proposed in this paper for the grid-connected systems of multiple grid-forming converters based on impedance ratio criterion. The Nyquist trajectory map of the system ratio of impedance in the complex plane is used in the suggested analytical method to estimate the quantity of RHPs in the right half-plane of the system, and the stability at the common points of the system is evaluated against the Nyquist criterion. In addition, the instability of grid-forming converters in grid-connected systems is reproduced by using grid-forming converters state space equation. Unlike the traditional methods of analysis, the method proposed in this paper can be applied to specifically judge the key equipment or control link of instability of the system, which provides guidance on optimizing the parameters of the system. Finally, simulation analysis is conducted to confirm that the model is accurate and that the proposed approach is applicable.

Recommender systems have been a kind of powerful tool to improve e-commerce benefits. Existing recommender systems mostly employ explicit features of products, such as description and attributes. However, visual characteristics contain fruitful implicit and intuitive information, and are always ignored by existing works. To deal with this issue, this paper proposes a novel intelligent recommender system via visual Transformer (ViT) model and convolutional neural network (CNN) structure. First, the ViT part is utilized to extract visual feature representation. By learning the visual similarity among products, it is expected to obtain a better scene understanding. Then, an improved CNN part is utilized to extract hidden association information from historical behaviors of users. It is expected to better perceive user preference and purchasing characteristics. The combination of two parts constructs the proposed recommender system. Finally, we make performance evaluation for the proposal on real-world e-commerce dataset. The results indicate that the proposal exhibits high recommendation accuracy and efficiency. Compared with other typical algorithms, our proposal can better understand product images and user behaviors, providing more personalized recommendation results.

With the advent of the information age, the massive increase of English text data puts forward higher requirements for text analysis and processing. The aim of this study is to accurately evaluate the semantic complexity of English text through an autoencoder structure based on bidirectional attention. This paper first analyzes the importance of automatic classification of semantic complexity in English text, and then builds an autoencoder structure based on bidirectional attention, which captures bidirectional information in text, and then uses the autoencoder structure for feature extraction and dimension reduction, which further strengthens the model’s ability to capture semantic complexity. Finally, A Bidirectional Attention Self-Encoding English Text Semantic Complexity Automatic Grading Model (BSETG) is established. This study conducted experimental verification based on semantic Evaluation (SemEval) dataset, convolutional neural network (CNN)/Daily Mail dataset and Penn Treebank dataset, and conducted a comparative analysis with existing semantic complexity evaluation methods. The experimental results show that the overall accuracy of BSETG algorithm is maintained between 70% and 90%, the response speed of BSETG algorithm is relatively fast, and the success rate of BSETG algorithm is relatively stable to a large extent.

Media processing applications can tolerate error up to a certain limit due to the perceptual limitations of the human eye. Since adders are ubiquitous in power-hungry media processing applications, they can be approximated without much compromise in quality. An adder with better error characteristics without significant compromise in area and power is required to meet the future demands of ever-increasing computational needs. In order to achieve the same, a novel segmentation technique has been proposed. By varying the number of bits in each segment, three different designs are proposed, each with its advantage. Each proposed adder is segmented into three portions, namely Most Significant Portion (MSP), Intermediate Significant Portion (ISP) and Least Significant Portion (LSP). The sub-adder’s sum in each portion is computed concurrently to reduce the critical path delay.

The proposed heterogeneous adder (HEAD) designs achieve better accuracy than the state-of-the-art designs. Synthesis results show that HEAD consumes less area up to 41.8% and consumes less power ranging from 0.8% to 51%, than existing adders. Exhaustive simulations are carried out on benchmarking image sharpening application to prove that the proposed adders obtain a better quality-effort tradeoff than the existing designs.

The fast Fourier transform (FFT) is a widely used algorithm for computing the discrete Fourier transform (DFT) in real-time signal processing. Achieving high performance with minimal resource usage is crucial for any real-time application. This paper introduces an architecture based on coordinate rotation digital computer (CORDIC) for implementing a radix-$2^2$ FFT. Traditional FFT implementations require complex twiddle factor multiplications, which is not cost-effective in terms of hardware utilization. To address this issue, we have proposed a radix-8 CORDIC-based approach integrated with FFT computation. The proposed radix-8 CORDIC requires fewer stages than the conventional radix-2 CORDIC, enhancing computational efficiency and reducing hardware utilization. The feedforward radix-$2^2$ FFT architecture is presented where the butterflies of the FFT are computed with the help of radix-8 CORDIC. A total of three FFT architectures are developed supporting 16-, 1024- and 2048-point FFTs. The proposed FFT architectures are developed using Verilog-HDL code and implemented on a Virtex-7 field-programmable gate array (FPGA). The FPGA-based radix-$2^2$ FFT achieves a clock frequency of 323.4MHz and utilizes minimal FPGA resources. Processing of 2048 data samples takes only 4.06$\mu$S by the proposed FPGA-based design. Additionally, two ASICs have been designed: the 1024-point FFT ASIC occupies an area of 1.079mm², and the 2048-point FFT ASIC occupies an area of 1.544 mm². The proposed FFT ASICs have better-normalized area per FFT and energy per FFT than the state-of-the-art designs.

Real-time images of faces captured in different spectrum bands are considered heterogeneous images. Heterogeneous Face Recognition (HFR) matches faces across domains and is crucial to public safety. This paper proposes an HFR approach based on Deep Neural Networks (DNN). Feature maps are extracted from two images, such as gallery and sketch images, using Squirrel Search Heterogeneous Convolutional-Capsule- Bidirectional Gated Recurrent Unit (S2HConv-Caps-BiGRU). As a method of efficiently recognizing faces, coupled representation similarity metric (CRSM) will use the measure for the similarity of two feature maps. The experimental results will be evaluated to state-of-the-art (SOTA) statistical measures in terms of accuracy, recall, Jaccard score, dice score, mean square error (MSE), image similarity, performance and root mean square error (RMSE). Compared to other SOTA, the model produces the best results. The accuracy value of a CUFS dataset is 98.7%.

Tuned mass dampers (TMDs) are a useful control of vibrations for tall buildings and can be considered equal to burdens such as breezes and earthquakes. The better limits for TMD are to reduce the earthquake vibrations of tall buildings including soil–structure interaction (SSI) influences. This study proposes the multi-objective Black Widow Optimization (BWO) with Elman neural network (ENN) computation that is brought on to find the optimal limits of TMD. Considering that this proposed model analyzed the mass, stiffness, and damping ratio of TMD to get the maximum accelerations and displacement of 40 story building model, from the execution results, starting from this proposed BWO–Elman model to the expected methodology, the most outrageous TMD limits are better, likewise, the reduction of acceleration and displacement are 25% and 19.86% in the proposed study. This study assists the researchers with a better understanding of earthquake vibration and leads the fashioners to achieve superior TMD for tall designs. The impact of vibration control on the displacements and accelerations of both controlled and uncontrolled buildings is investigated in this work. It uses a MATLAB software technique to analyze their modal replies, moreover, this proposed optimal TMD model is compared with conventional techniques by acceleration and stiffness parameters.

Facial expression detection technology is a flexible tool utilized in many different industries that allows for a better understanding of human behavior and emotional responses. Its applications span a broad spectrum of societal requirements, from enhancing marketing strategies to bolstering security protocols and assisting in the diagnosis of mental health issues. By using the power of artificial intelligence and computer vision, facial expression recognition (FER) helps businesses to adapt, grow and build deeper interactions between people and the technology and environments they live in. Its primary goal remains to facilitate better understanding, communication and decision-making in order to bring in a new wave of technical innovation that is driven by people’s needs. Facial emotion recognition, which makes use of computer vision and artificial intelligence, not only improves the capacity to understand and react to human emotions but also opens the door to more personalized and empathic interactions in an increasingly digital environment. In this paper, unique method of facial emotion recognition based on sophisticated feature extraction techniques combined with a hybrid ensemble learning technique. In particular, hierarchical cascade regression neural networks (HCRNN) for face landmark identification, VGG-19 for feature extraction and Random Forests are considered as classification techniques. In order to accomplish reliable and accurate emotion recognition from facial images, this method takes advantage of the complementary capabilities of both approaches. Initially, we utilized a deep convolutional neural network (CNN) called VGG-19 to extract high-level features from face images. Pre-trained on extensive image datasets, VGG-19 has proven to be highly effective at capturing complex visual representations. These characteristics function as an all-inclusive description of facial expressions, encompassing both general trends and minute details. HCRNN for facial landmark detection, which precisely locates important face features including the mouth, nose and eyes. Facial landmark predictions are iteratively improved by this hierarchical cascade architecture, which also handles occlusions and changes in illumination and position. Lastly, we use an ensemble learning technique called Random Forests to classify emotions. Multiple decision trees’ predictions are combined by random forests, which offer robustness against overfitting and efficiently handle high-dimensional feature fields. High accuracy and generalization capabilities are achieved in the facial emotion classification process by Random Forests, which combine the feature representations retrieved by VGG-19 with the localized facial landmarks recognized by HCRNN. We tested the suggested strategy on benchmark face emotion detection datasets and compared its results with the most advanced techniques available. Performance measures like accuracy of 98.89%, precision 96.52%, recall 96%, F1-score 99% and receiver operating characteristic (ROC) curve of 97.24% analysis were used to evaluate how well hybrid strategy worked and how much better it was at identifying emotions in facial images. The outcomes of experiments show how method has practical applications in human–computer interaction, healthcare and other fields.

FIR filter design and implementation are the requirements of most DSP systems. The design objective of the FIR filter is nondifferentiable, nonlinear and multimodal in nature. Therefore, FIR filter design through optimization methods is most frequently employed. In the proposed work, COOT bird optimization-based FIR filters are designed. The FIR filters based on particle swarm optimization (PSO) and flower pollination optimization (FPA) algorithms are also designed for comparison. The objective function based on mean square error minimization is formulated. The low-pass, high-pass, band-pass and band-stop FIR filters of different order are designed to show the efficacy of the proposed method. COOT provides minimum passband and stopband ripples, fast convergence and less execution time for all the designed filters. The proposed technique is also compared with the existing approaches and provides a reduction in passband ripples, stopband ripples and stopband attenuation. To reduce the complexity of FIR filters, multiplierless techniques canonical signed digit (CSD), factorized canonical signed digit (FCSD) and distributed arithmetic (DA) are utilized for the implementation of FIR filters on Basys-3 (Artix-7) FPGA Board. The multiplier-based architecture is also implemented for comparison. Hardware resource utilization and dynamic power consumption of each architecture are compared. DA showed 92.16, 89.96 and 90.11% reduction in the number of LUTs, and 91.16, 89.68 and 89.77% reduction in dynamic power consumption from the multiplier, CSD and FCSD-based architectures, respectively.

With the rapid development of intelligent manufacturing technology, the structure of industrial equipment has become more sophisticated, resulting in frequent equipment failures. However, traditional anomaly diagnosis methods suffer the issues of insufficient accuracy and are always unable to identify anomalies in time. To solve the above problems, a deep learning-based equipment anomaly diagnosis method in industrial production scenarios is proposed in this paper. Specifically, a combination model based on Selective Kernel (SK) convolution blocks is designed to improve the accuracy of anomaly identification; a lightweight model based on Depthwise Separable Convolution (DSC) and Attention Mechanism (AM) is proposed to improve the timeliness of anomaly identification; an anomaly analysis and intelligent diagnosis framework is established and implemented to automatically complete anomaly identification tasks for different equipment and practical problems. Finally, we conduct extensive experiments to validate the effectiveness of our methods. The experimental results show that the accuracy of our anomaly identification method is as high as 99.07$\%$, and the calculation amount of the lightweight model is reduced by 84.95$\%$ compared to the baseline model.

In an era of consumer electronics, effective consumption recommendation contributes a lot to improving benefits for online shopping operators. However, consumers and products constitute a complex heterogeneous information network, in which extraction of structural features is essential. To construct more fine-grained feature space for modeling, we introduce the graph neural network (GNN) theory for this purpose. Accordingly, a multi-scale GNN-based personalized recommender system for online consumption decision is proposed in this paper. Firstly, we set up an encoder for consumption decision based on a multi-scale GNN structure, and define the loss function. Two realistic datasets are utilized as the research scenario, in order to complete the feature combination of online consumption. Then, personalized recommendation settings are completed based on a recurrent neural network structure. And a graph learning module is embedded in it to integrate cross-attention mechanism to establish the consumption decision algorithm. Finally, the proposed method is tested by comparing with relevant research methods under several metrics: adaptability, success rate, and stability. The results show that the proposed method has achieved some improvement in accuracy, coverage, and recommendation speed.

A single-inductor multi-source energy harvesting system that can harvest three types of ambient energy was presented. The system can self-supply using an integrated self-starting circuit that does not require an external battery. It performs hybrid modulation of pulse-frequency modulation (PFM) and pulse-width modulation (PWM) and realizes adaptive asynchronous control for input and output, achieving higher system stability and better energy aggregation. Adaptive maximum power point tracking (MPPT) was implemented to generate inductor charging control signals with different frequencies and duty cycles according to different input sources, enabling the inductor to operate in discontinuous mode (DCM) under different input conditions. The energy harvesting system was designed using a 0.18-$\mu$m CMOS process. The simulation results show that the system can realize low-voltage self-startup as low as 200mV and can provide a stable output of 1.4V to the load with a 1V harvested voltage to self-supply. The highest conversion efficiency of the system is 76.43%@$R_{\mathrm{\text{load}}}=10$k$\mathrm{\Omega }$, and the average power consumption in sleep mode is 2.38$\mu$W.

In this paper, an ultra-wideband substrate integrated coaxial line (SICL) array based on silicon-based MEMS process is proposed for high-speed data transmission. A quasi-coaxial transition array is designed to connect the SICL array with grounded-coplanar waveguides (GCPWs). Moreover, a stepped-impedance matching structure is introduced to reduce the discontinuities and improve the transmission performance. For high efficiency design, a Bayesian Optimization (BO)-based approach is adopted to optimize dimensions of the proposed SICL array. The objective function is set to be the weighted combination of the bandwidth and the crosstalk of the proposed array structure to obtain wide bandwidth and low crosstalk simultaneously. With the proposed BO-based approach, iteration times can be reduced by approximately 99.9% compared with the parametric sweep method. A 40-channel SICL array is designed and fabricated under silicon-based Micro-electromechanical Systems (MEMS) process. Ultra-wideband of 110GHz is measured in each channel with the insertion loss less than 3dB and the return loss larger than 15dB. The couplings between two adjacent channels are no more than $-$30dB. Good eye diagram and low bit error rate (BER) are achieved for each channel at data rate of 95Gb/s and hence the total data rate can reach 3.8Tb/s. The bandwidth density of the proposed SICL array is 0.164Gb/s/$\mu$m, which is much higher than those of the conventional SICLs.

Cyber-physical system is one of the essential components of wireless sensor network (WSN). WSN conjointly senses, collects, analyzes and communicates data on recognized items at service part before transmitting this data to the owner of the network. Blackhole, Grayhole, Flooding, Scheduling are the common WSN attacks that rapidly damage the system. Intrusion detection systems, such as WSN have drawbacks, like less detection rates, high computation costs and high percentage of false alarms, because sensor nodes have limited resources. Therefore, a Self Attention Generative Adversarial Capsule Network as an intrusion detection scheme for WSN (SAGACN-ID-WSN) is proposed in this paper to address the aforementioned issues. Initially, the data are amassed from WSN-DS dataset. Then, the data are sent for pre-processing. The input data are preprocessed using the Guided Box Filtering (GBF) method. Then, the preprocessed data are provided to the Atomic Orbital Search (AOS), Tasmanian Devil Optimization (TDO) and Ebola Optimization Search (EOS) algorithms for feature selection. The attacks are divided into four categories: normal, Grayhole attack, Black hole attack, flooding attack, and scheduling attack. The proposed ID-WSN is implemented in Network simulator 2 (NS-2) utilizing the dataset of WSN-DS. The metrics, like accuracy, precision, recall, F-measure, ROC and computational time are analyzed. The proposed SAGACN-ID-WSN technique attains 25.5%, 20.12% and 20.7% high accuracy, 51.136%, 59.04% and 32.81%; higher precision, 2.292%, 1.51% and 3.915% lower error rate compared to the existing models, like Dataset for Intrusion Detection Systems in WSN (SLGBM-ID-WSN), multi-layer machine learning-based ID-WSN (NB-RF-ID-WSN), deep learning and entity embedding-base intrusion detection systems in WSN, respectively.

This paper presents novel and low computational complexity spline adaptive filtering (SAF) algorithms based on partial coefficients selection and adaption. They are addressed partial update SAF normalized least mean squares (PU-SAF-NLMS) algorithms. The PU-SAF-NLMS equations are established via the steepest gradient descent constraint to the proposed cost function. In the proposed algorithms, the filter coefficients are updated based on periodic, sequential, and selective rules, leading to reduction in computational complexity. Furthermore, the convergence speed of PU-SAF-NLMS algorithms is close to the conventional SAF-NLMS. Moreover, the convergence analysis of algorithms is studied. Ultimately, the performance of the presented algorithms is appraised through several experimental results.

In this paper, a voltage differencing buffered amplifier (VDBA)-based second-order sinusoidal oscillator (SO) configuration, which provides voltage output at low impedance, is proposed. The circuit employs single VDBA, three resistors and two grounded capacitors, which presume its easy monolithic integration with preferred circuit simplicity. The nonidealities of VDBA due to parasitic and tracking errors are taken into consideration to study the nonideal behavior of proposed SO. Mathematical modeling of phase noise is computed in the paper. Active and passive sensitivities are calculated for the proposed configuration and are found to be less than unity rendering circuit insensitive to component variations followed by phase noise study. The functionality of the proposed topology is validated through cadence virtuoso ADE spectre tool at 180-nm technology node. Experimental verification is executed through commercially available ICs AD844 by good results. The total harmonic distortion (THD) is found to be below 3.5%. The observed frequency of oscillation is found to be in close agreement with the theoretical values. The PVT and Monte Carlo statistical analyses are also carried out to confirm the sensitivity of the proposed SO.

In response to the poor decision-making caused by aerodynamic coupling and model linearization in the trajectory correction model, it is proposed to use a reinforcement learning method to establish a Constrained Markov Decision Process (CMDP) model between action prediction and action constraint. Taking a classical two-dimensional trajectory correction projectile for study, the cost function within constraints of thruster violations is built, so that the sequential prediction is transformed to solve the Constrained Reinforcement Learning (CRL) problem. Accordingly, a method combined with the policy gradient algorithm based on Lagrange operator with the model prediction algorithm is proposed. The test results show that the trained optimal policy model achieves a probability of over 65% and the correction projectile falls within a radius of 5 meters from the preset target point (CEP $<$5m). Simulation examples have verified the decision-making of correction action sequences autonomously using the trained model, resulting in correction errors of 1.79 1.1 and 0.42m in the $x,y$ and z directions, respectively, demonstrating high correction accuracy and autonomous decision-making capability.