Lulu Bei

Bio: Lulu Bei is an academic researcher from Xuzhou Institute of Technology. The author has contributed to research in topics: Power dividers and directional couplers & Wilkinson power divider. The author has an hindex of 1, co-authored 6 publications receiving 2 citations.

Image contour detection based on improved level set in complex environment

Abstract: An improved image segmentation model was established to achieve accurate detection of target contours under high noise, low resolution, and uneven illumination environments. The new model is based on the variational level set algorithm, which improves the C–V (Chan and Vese) model and GAC (Geodesic Active Contour) model, fuses the contour and area models to segment the image information, that is, the edge information and region information of the image are fused into the same "energy" functional. According to the geometric characteristics of the curve, GAC model can effectively avoid re parameterization and light insensitivity in the evolution process, and CV model can effectively distinguish the fuzzy boundary of the image by maximizing the gray difference between the target and the background, it has strong anti-noise performance. By solving the steady-state solution of the partial differential equation, the optimal solution of the energy model is solved. New method can improve the calculation accuracy, topological structure adaptability, anti-noise ability, and reduce the light sensitivity effectively. Experiment shows that the new model has good robustness, high real-time performance, and it can effectively improve detection accuracy.

A Hyperparameters automatic optimization method of time graph convolution network model for traffic prediction

Abstract: Smart transportation is an essential component of the smart city. Traffic prediction is an important issue in smart transportation. The convolutional neural networks (GCN) are an effective approach for traffic prediction. However, the GCN meets some challenges, such as stability of prediction precision and computation cost, in traffic prediction. The hyperparameters significantly affect the performance of GCN. We conduct a regression analysis between hyperparameters and GCN performance. Our simulation results show that there is the obvious optimal point of hyperparameters. Some empirical suggestion is given to adjust the hyperparameters based on the simulation results.

Out-of-Phase Power Divider with Complex Impedance Transformation Based on Miniaturized Isolation Network

Abstract: A compact three-layer circuit structure based on the double-sided parallel-strip lines (DSPSLs) is proposed in this article to design an out-of-phase power divider (PD) with miniaturized isolation ...

Power electronic transformer design with dual-PWM based on MATLAB/Simulink

Abstract: With the continuous development of new energy power generation and smart grid, Power Electronic Transformer (PET) has a good prospect for development because of its remarkable advantages. Based on the topology of AC/DC/AC, the modulation strategy with dual-PWM (Pulse Width Modulation) is adopted to control the operation of power electronic transformers in this paper. The PET structure consists of three units: importation portion, isolation portion and output portion. Model building and analyzing both at the input and output terminals are achieved step by step. And the simulation of the whole PET system with dual-PWM is accomplished with MATLAB/ Simulink. The simulation results show the control system stability and output voltage regulation precision are improved with feed-forward voltage decoupling vector control system. The correctness and effectiveness of the control strategy are demonstrated through the simulation. PETs play an important role in enhancing power supply reliability for Power Grid and promoting the new energy power generation development.

A novel microstrip array circular polarized antenna based on t-type power divider

Abstract: In underground wireless communication in the coal mines, it is necessary for antenna to have good penetration and multi-path resistance to coal dust and water mist. The circular polarization antenna has two orthogonal fields, horizontal and vertical, and the circular polarization antenna has better penetration in coal seam water mist than the linear polarization antenna under the same power. The circular polarization is divided into left rotation polarization and right rotation polarization, and the antenna can only receive signals in the same polarization direction. In the process of underground propagation, the signal is easily reflected by obstacles, changes the polarization direction, and is not received by the original polarization direction antenna. In the underground environment of the coal mine, it can be used as an effective solution to resist multi-path. An array circular polarization antenna based on T power divider and uniform rotary the feed network is proposed in this paper. The circuit structure of 16-unit micro-strip array circular polarization antenna is introduced. The structure and working principle of feed network and antenna are analyzed. Finally, simulation and experiment show that the antenna has the advantages of high front-to-back ratio, is suitable for long-distance and high orientation reading and writing applications, and is very suitable for RFID long-distance reading and writing applications in coal mine long and narrow environment. It has good application prospects and economic benefits.

Miniaturized Gysel power divider with nth harmonics suppression

Abstract: In this paper, a miniaturized Gysel power divider with nth harmonic suppression has been presented. The Gysel power divider retains its capability of high-power handling, while extreme size reduction makes it suitable for application in small-sized circuits with higher order harmonics rejection. A lowpass filter with high performance and appropriate characteristic has been placed instead of the conventional transmission lines a quarter wavelength. It results in the size reduction and harmonics rejection of the Gysel power divider, effectively. The presented Gysel power divider operated at center frequency of 0.764 GHz with fractional bandwidth of 36%. To substantiate the validity and efficiency of the proposed circuits, the designed power divider was fabricated and measured. It is seen that the results of the measurements and simulations are highly consistent together. The main frequency; the return loss of the port 1, the return loss of the port 2, isolation, and insertion loss are 28, 29, 32 and 1.3 dB, respectively. The overall circuit size is 22.1 mm × 65.7 mm.

Curvilinear object segmentation in medical images based on ODoS filter and deep learning network

Abstract: Automatic segmentation of curvilinear objects in medical images plays an important role in the diagnosis and evaluation of human diseases, yet it is a challenging uncertainty in the complex segmentation tasks due to different issues such as various image appearances, low contrast between curvilinear objects and their surrounding backgrounds, thin and uneven curvilinear structures, and improper background illumination conditions. To overcome these challenges, we present a unique curvilinear structure segmentation framework based on an oriented derivative of stick (ODoS) filter and a deep learning network for curvilinear object segmentation in medical images. Currently, a large number of deep learning models emphasize developing deep architectures and ignore capturing the structural features of curvilinear objects, which may lead to unsatisfactory results. Consequently, a new approach that incorporates an ODoS filter as part of a deep learning network is presented to improve the spatial attention of curvilinear objects. Specifically, the input image is transfered into four-channel image constructed by the ODoS filter. In which, the original image is considered the principal part to describe various image appearance and complex background illumination conditions, a multi-step strategy is used to enhance the contrast between curvilinear objects and their surrounding backgrounds, and a vector field is applied to discriminate thin and uneven curvilinear structures. Subsequently, a deep learning framework is employed to extract various structural features for curvilinear object segmentation in medical images. The performance of the computational model is validated in experiments conducted on the publicly available DRIVE, STARE and CHASEDB1 datasets. The experimental results indicate that the presented model yields surprising results compared with those of some state-of-the-art methods.

Design of dual-band Wilkinson power divider based on novel stubs using PSO algorithm

Abstract: In this paper, a new dual-band Wilkinson power divider (WPD) is designed and fabricated using novel low and high impedance stubs instead of quarter-wavelength transmission lines. The proposed circuit was analyzed using odd and even mode analysis, and the optimal values of design parameters were obtained using the particle swarm optimization algorithm. The designed power divider has input reflection coefficients (S11) of −22.1 and −17 dB at the first operating frequency of 2.2 GHz and the second operating frequency of 14.2 GHz, respectively. It also improves stop-band and fractional bandwidth (FBW) while maintaining a simple topology. The proposed WPD suppresses undesired harmonics from the second to the fifth with an attenuation level of less than −20 dB in the first band and generates a broad stop-band (4.4–11.5 GHz). In the first band, the FBW is 54.5%, and in the second band, it is 20.1%.

The design and implementation of Matlab-based nonlinear data fitting for infrared sensors

Abstract: Infrared range measurement has important applications in industrial robotics and automation, but the accuracy needs to be improved in the traditional design scheme. Therefore, in this design, the function methods such as polynomial least squares fitting and nonlinear least squares fitting are written based on Matlab platform to solve the transfer function of the experimentally measured data, and the data conversion and processing in the microcontroller improves the measurement accuracy of the system.

A cloud-oriented siamese network object tracking algorithm with attention network and adaptive loss function

Abstract: Abstract Aiming at solving the problems of low success rate and weak robustness of object tracking algorithms based on siamese network in complex scenes with occlusion, deformation, and rotation, a siamese network object tracking algorithm with attention network and adaptive loss function (SiamANAL) is proposed. Firstly, the multi-layer feature fusion module for template branch (MFFMT) and the multi-layer feature fusion module for search branch (MFFMS) are designed. The modified convolutional neural networks (CNN) are used for feature extraction through the fusion module to solve the problem of features loss caused by too deep network. Secondly, an attention network is introduced into the SiamANAL algorithm to calculate the attention of template map features and search map features, which enhances the features of object region, reduces the interference of background region, and improves the accuracy of the algorithm. Finally, an adaptive loss function combined with pairwise Gaussian loss function and cross entropy loss function is designed to increase inter-class separation and intra-class compactness of classification branches and improve the accuracy rate of classification and the success rate of regression. The effectiveness of the proposed algorithm is verified by comparing it with other popular algorithms on two popular benchmarks, the visual object tracking 2018 (VOT2018) and the object tracking benchmark 100 (OTB100). Extensive experiments demonstrate that the proposed tracker achieves competitive performance against state-of-the-art trackers. The success rate and precision rate of the proposed algorithm SiamANAL on OTB100 are 0.709 and 0.883, respectively. With the help of cloud computing services and data storage, the processing performance of the proposed algorithm can be further improved.