http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Practical Approach to Indoor Path Loss Modeling Based on Deep Learning
Shengjie Ma,Hong Cheng,Hyukjoon Lee 한국정보과학회 2021 Journal of Computing Science and Engineering Vol.15 No.2
Deep learning has become one of the most powerful prediction approaches, and it can be used to solve classification and regression problems. We present a novel deep learning-based indoor Wi-Fi path loss modeling approach. Specifically, we propose a local area multi-line scanning algorithm that generates input images based on measurement locations and a floor plan. As the input images contain information regarding the propagation environment between the fixed access points (APs) and measurement locations, a convolutional neural network (CNN) model can be trained to learn the features of the indoor environment and approximate the underlying functions of the Wi-Fi signal propagation. The proposed deep learning-based indoor path loss model can achieve superior performance over 3D ray-tracing methods. The average root mean square error (RMSE) between the predicted and measured received signal strength values in the two scenarios is 4.63 dB.
Shengjie Yao,Lei Sun,Xudong Ma 대한기계학회 2016 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.30 No.5
This paper presents the deformation behavior and crashworthiness of electric resistance welded mild steel tubes with axial gradient microstructures in quasi-static compression. Three sets of tubes were prepared, and regions of each tube were Induction heated and directly quenched (IH-DQ). The effect of the length to diameter (L/D) ratio, and length of the IH-DQ region on crushing characteristics was investigated, and compared with untreated tubes. The compression tests revealed that improved energy absorption can be obtained in IHDQ tubes if the collapse is controlled by the formation of a concertina buckling mode. However, there was a tendency to produce mixed or Euler buckling modes as the ratio of L/D increased. Meanwhile, the results of the crush experiments and the FEM models showed that the heat-treatment process should be precisely controlled to produce the correct type of microstructure, and circumferential uniformity of microstructure distribution.
Self-Supervised Rigid Registration for Small Images
( Ruoxin Ma ),( Shengjie Zhao ),( Samuel Cheng ) 한국인터넷정보학회 2021 KSII Transactions on Internet and Information Syst Vol.15 No.1
For small image registration, feature-based approaches are likely to fail as feature detectors cannot detect enough feature points from low-resolution images. The classic FFT approach’s prediction accuracy is high, but the registration time can be relatively long, about several seconds to register one image pair. To achieve real-time and high-precision rigid registration for small images, we apply deep neural networks for supervised rigid transformation prediction, which directly predicts the transformation parameters. We train deep registration models with rigidly transformed CIFAR-10 images and STL-10 images, and evaluate the generalization ability of deep registration models with transformed CIFAR-10 images, STL-10 images, and randomly generated images. Experimental results show that the deep registration models we propose can achieve comparable accuracy to the classic FFT approach for small CIFAR-10 images (32×32) and our LSTM registration model takes less than 1ms to register one pair of images. For moderate size STL-10 images (96×96), FFT significantly outperforms deep registration models in terms of accuracy but is also considerably slower. Our results suggest that deep registration models have competitive advantages over conventional approaches, at least for small images.
Xu, Shengjie,Tang, Yujia,Chen, Kejie,Zhang, Zongke,Ma, Tao,Tang, Wenyong The Society of Naval Architects of Korea 2020 International Journal of Naval Architecture and Oc Vol.12 No.1
The pressure responsiveness property of a skirt-cushion system, which is closely related to the overall performance of Air Cushion Vehicles (ACVs), has always been the difficulty and challenging problem involving cushion aerodynamics and flexible skirt dynamics. Based on a widely used bag and finger skirt-cushion system, the pressure responsiveness properties are investigated numerically. The physical process and mechanism are analyzed and a numerical method for evaluating the pressure responsiveness property is proposed. A cushion-skirt information communication platform is also presented for interchanging the force and the skirt configuration between cushion aerodynamics and flexible skirt dynamics. The pressure responsiveness of a typical skirt-cushion system is calculated and the results demonstrate that the pressure responsiveness property helps alleviate the influence of the cushion height changing on the overall performance of ACVs. Finally, the influences of skirt geometrical and cushion aerodynamic parameters on the pressure responsiveness properties are discussed systematically, giving insight into the design of skirt-cushion systems.
Xu, Shengjie,Tang, Yujia,Chen, Kejie,Zhang, Zongke,Ma, Tao,Tang, Wenyong The Society of Naval Architects of Korea 2020 International Journal of Naval Architecture and Oc Vol.12 No.-
The pressure responsiveness property of a skirt-cushion system, which is closely related to the overall performance of Air Cushion Vehicles (ACVs), has always been the difficulty and challenging problem involving cushion aerodynamics and flexible skirt dynamics. Based on a widely used bag and finger skirt-cushion system, the pressure responsiveness properties are investigated numerically. The physical process and mechanism are analyzed and a numerical method for evaluating the pressure responsiveness property is proposed. A cushion-skirt information communication platform is also presented for interchanging the force and the skirt configuration between cushion aerodynamics and flexible skirt dynamics. The pressure responsiveness of a typical skirt-cushion system is calculated and the results demonstrate that the pressure responsiveness property helps alleviate the influence of the cushion height changing on the overall performance of ACVs. Finally, the influences of skirt geometrical and cushion aerodynamic parameters on the pressure responsiveness properties are discussed systematically, giving insight into the design of skirt-cushion systems.
Guohua Sheng,Shengji Jin,Lintao Ma,Quan Bai,Chao Xu,Xiaoyu Wang 대한토목학회 2024 KSCE Journal of Civil Engineering Vol.28 No.1
The concept of seismic robustness is proposed by combining the concept of seismic performance and structural robustness. The existing qualitative, quantitative and evaluation methods of seismic robustness are all direct researched on the whole structure, and the influence mechanism of its internal components on the overall seismic robustness is still unclear. It is very important to establish a clear relationship between component design and structural seismic robustness for the structural design, reinforcement design and final evaluation of structural seismic robustness. Based on this, taking the column as the starting point, a quantitative method for the seismic robustness of RC frame by the seismic robustness index is proposed, which takes into account the resistance vulnerability of column and influence of column on the storey drift ratios (SDRs). In which, the resistance vulnerability is represented by the defined control vulnerability coefficient Pimax, and the influence on the SDRs are represented by the storey drift ratio importance coefficients (SDRCs) . The method not only reflects the essential mechanical properties of the column, but also reflects the effects brought about by different SALs. The feasibility of the method is demonstrated by numerical examples of two types of failures (assuming single column and two columns failure), and four optimization design proposals are proposed for it. The analysis shows that of the target columns to the floor where the target columns located are obviously greater than those on the remaining floors of the target frame. The seismic robustness index R decreases sharply with the increase of the seismic action level (SAL). R is different compare single column failure with two columns failure under 4 SALs. The most effective way to improve the R of the frame under a certain SAL is to retrofit its control column.