Neural Linguistic Steganalysis via Multi-Head Self-AttentionRead the full article
Journal of Electrical and Computer Engineering publishes recent advances from the rapidly moving fields of both electrical engineering and computer engineering in the areas of circuits and systems, communications, power systems and signal processing.
Journal of Electrical and Computer Engineering maintains an Editorial Board of practicing researchers from around the world, to ensure manuscripts are handled by editors who are experts in the field of study.
Latest ArticlesMore articles
Research on Safe Driving Evaluation Method Based on Machine Vision and Long Short-Term Memory Network
The rapid development of transportation industry has brought some potential safety hazards. Aiming at the problem of driving safety, the application of artificial intelligence technology in safe driving behavior recognition can effectively reduce the accident rate and economic losses. Based on the presence of interference signals such as spatiotemporal background mixed signals in the driving monitoring video sequence, the recognition accuracy of small targets such as human eyes is low. In this paper, an improved dual-stream convolutional network is proposed to recognize the safe driving behavior. Based on convolutional neural networks (CNNs), attention mechanism (AM) is integrated into a long short-term memory (LSTM) neural network structure, and the hybrid dual-stream AM-LSTM convolutional network channel is designed. The spatial stream channel uses the CNN method to extract the spatial characteristic value of video image and uses pyramid pooling instead of traditional pooling, normalizing the scale transformation. The time stream channel uses a single-shot multibox detector (SSD) algorithm to calculate the adjacent two frames of video sequence for the detection of small objects such as face and eyes. Then, AM-LSTM is used to fuse and classify dual-stream information. The self-built driving behavior video image set is built. ROC, accuracy rate, and loss function experiments are carried out in the FDDB database, VOT100 data set, and self-built video image set, respectively. Compared with CNN, SSD, IDT, and dual-stream recognition methods, the accuracy rate of this method can be improved by at least 1.4%, and the average absolute error in four video sequences can be improved by more than 2%. On the contrary, in the self-built image set, the recognition rate of doze reaches 68.3%, which is higher than other methods. The experimental results show that this method has good recognition accuracy and practical application value.
High-Fidelity and High-Efficiency Digital Class-D Audio Power Amplifier
This study presents a high-fidelity and high-efficiency digital class-D audio power amplifier (CDA), which consists of digital and analog modules. To realize a compatible digital input, a fully digital audio digital-to-analog converter (DAC) is implemented on MATLAB and Xilinx System Generator, which consists of a 16x interpolation filter, a fourth-order four-bit quantized delta-sigma (ΔΣ) modulator, and a uniform-sampling pulse width modulator. The CDA utilizes the closed-loop negative feedback and loop-filtering technologies to minimize distortion. The audio DAC, which is based on a field-programmable gate array, consumes 0.128 W and uses 7100 LUTs, which achieves 11.2% of the resource utilization rate. The analog module is fabricated in a 0.18 µm BCD technology. The postlayout simulation results show that the CDA delivers an output power of 1 W with 93.3% efficiency to a 4 Ω speaker and achieves 0.0138% of the total harmonic distortion (THD) with a transient noise for a 1 kHz input sinusoidal test tone and 3.6 V supply. The output power reaches up to 2.73 W for 1% THD (with transient noise). The proposed amplifier occupies an active area of 1 mm2.
Electromagnetic Design and Flux Regulation Analysis of New Hybrid Excitation Generator for Electric Vehicle Range Extender
Aiming at the problem of uncontrollable magnetic field of permanent magnet generators, a new hybrid excitation generator (HEG) with parallel magnetic circuit is proposed. The HEG consists of combined permanent magnet rotor (PMR) and brushless electric excitation rotor (EER). The PMR has surface-mounted and embedded magnets. The PMR provides the main air gap field, and the brushless EER is used to adjust the air gap field. The operating principle and electromagnetic design scheme of the proposed generator are given in detail. Besides, the matching with two different types of rotors and the flux regulation characteristics is analyzed by using the finite element method. Finally, the output performance of the proposed generator including no-load and load characteristics and output voltage are tested. The results show that the two different types of rotors can be matched efficiently and operated reliably. The internal magnetic flux is easy to adjust in both directions, and the proposed HEG can output stable voltage in the range of wide speed and load.
Forecasting Wind Power Generation Using Artificial Neural Network: “Pawan Danawi”—A Case Study from Sri Lanka
Wind power, as a renewable energy resource, has taken much attention of the energy authorities in many countries, as it is used as one of the major energy sources to satisfy the ever-increasing energy demand. However, careful attention is needed in identifying the wind power potential in a particular area due to climate changes. In this sense, forecasting both wind power generation and wind power potential is essential. This paper develops artificial neural network (ANN) models to forecast wind power generation in “Pawan Danawi”, a functioning wind farm in Sri Lanka. Wind speed, wind direction, and ambient temperature of the area were used as the independent variable matrices of the developed ANN models, while the generated wind power was used as the dependent variable. The models were tested with three training algorithms, namely, Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG), and Bayesian Regularization (BR) training algorithms. In addition, the model was calibrated for five validation percentages (5% to 25% in 5% intervals) under each algorithm to identify the best training algorithm with the most suitable training and validation percentages. Mean squared error (MSE), coefficient of correlation (R), root mean squared error ratio (RSR), Nash number, and BIAS were used to evaluate the performance of the developed ANN models. Results revealed that all three training algorithms produce acceptable predictions for the power generation in the Pawan Danawi wind farm with R > 0.91, MSE < 0.22, and BIAS < 1. Among them, the LM training algorithm at 70% of training and 5% of validation percentages produces the best forecasting results. The developed models can be effectively used in the prediction of wind power at the Pawan Danawi wind farm. In addition, the models can be used with the projected climatic scenarios in predicting the future wind power harvest. Furthermore, the models can acceptably be used in similar environmental and climatic conditions to identify the wind power potential of the area.
Modified Space Vector Modulation for Cascaded H-Bridge Multilevel Inverter with Open-Circuit Power Cells
In this research, a new space vector modulation control algorithm is proposed to increase the reliability of the cascaded H-bridge multilevel inverters in case of faulty situations, where one or several power cells do not function. Methods to detect faults ensure finding open-circuit module exactly, which is fast and easy to program. By giving a detailed analysis of the impact of the faulty power cells, optimal redundant level states are chosen such that highest possible output voltage can be achieved, while the balance of the three-phase line-to-line voltage is maintained and common-mode voltage is reduced. The proposed algorithm is generalized so that it can be applied to H-bridge inverters of any level. The validity of the method is verified by numerical simulations and experiment results with an 11-level cascaded H-bridge inverter.
An Improved Feedback Network Superresolution on Camera Lens Images for Blind Superresolution
Most of the recent advances in image superresolution (SR) assume that the blur kernel during downsampling is predefined (e.g., Bicubic or Gaussian kernel), but it is a difficult task to make it suitable for all the realistic images. In this paper, we propose an Improved Superresolution Feedback Network (ISRFN) which is designed free to predefine the downsampling blur kernel by dealing with real-world HR-LR image pairs directly without downsampling process. We propose ISRFN by modifying the layers and network structures of the famous Superresolution Feedback Network (SRFBN). We trained the ISRFN with the Camera Lens Database named City100, which produced the HR and LR on the same lens, respectively, free for downsampling, so our proposed ISRFN is free to estimate the blur kernel. Due to different camera lens (smartphone and DSLR) databases, we perform two series of experiments under two camera lenses-based City100 databases, respectively, to choose the optimum network structures; experiments make it clear that different camera lens-based databases have different optimum network structures. We also compare our two ISRFNs with the state-of-the-art algorithms on performance; experiments show that our proposed ISRFN outperforms other state-of-the-art algorithms.