Love is Armani

Jin Wei 한국콘텐츠학회 2017 ICCC International Digital Design Invitation Exhib Vol.2017 No.5

Ding Sheng

Jin Wei 한국콘텐츠학회 2015 ICCC International Digital Design Invitation Exhib Vol.2015 No.7

Comprehensive Evaluation of Impacts of Connecting Distributed Generation to the Distribution Network

Jin, Wei,Shi, Xuemei,Ge, Fei,Zhang, Wei,Wu, Hongbin,Zhong, Chengyuan The Korean Institute of Electrical Engineers 2017 Journal of Electrical Engineering & Technology Vol.12 No.2

In this paper, we study the various impacts of connecting distributed generation (DG) to the distribution network. The comprehensive evaluation index system (CEIS) of four hierarchies is established, considering economy, reliability and voltage quality, and the calculation methods of different indexes are presented. This paper puts forward an improved triangular fuzzy number analytic hierarchy process (ITFNAHP) to weight the second level indexes (SLI) and the third level indexes (TLI), and calculates the variation coefficient to weight the fourth level indexes (FLI). We calculate the comprehensive weight coefficients based on the weight coefficients of the SLI, TLI and FLI, and then calculate the comprehensive evaluation of satisfaction (CES) of different access schemes. On the basis of the IEEE 33-bus example system, simulations of the calculation methods and the comprehensive evaluation method are carried out under different DG access schemes according to the same total investment cost and the same permeability, respectively, and the simulation results are analyzed and discussed.

Study and Experimentation on Detection of Nicks inside of Porcelain with Acoustic Emission

Jin, Wei,Li, Fen Korea Multimedia Society 2006 멀티미디어학회논문지 Vol.9 No.12

An usual acoustic emission(AE) event has two widely characterized parameters in time domain, peak amplitude and event duration. But noise in AE measuring may disturb the signals with its parameters and aggrandize the signal incertitude. Experiment activity of detection of the nick inside of porcelain with AE was made and study on AE signal processing with statistic be presented in this paper in order to pick-up information expected from the signal with noise. Effort is concentrated on developing a novel arithmetic to improve extraction of the characteristic from stochastic signal and to enhance the voracity of detection. The main purpose discussed in this paper is to treat with signals on amplitudes with statistic mutuality and power density spectrum in frequency domain, and farther more to select samples for neural networks training by means of least-squares algorithm between real measuring signal and deterministic signals under laboratory condition. By seeking optimization with the algorithm, the parameters representing characteristic of the porcelain object are selected, while the stochastic interfere be weakened, then study for detection on neural networks is developed based on processing above.

Puzzlement Detection from Facial Expression Using Active Appearance Models and Support Vector Machines

Jinwei Wang,Xirong Ma,Jizhou Sun,Ziping Zhao,Yuanping Zhu 보안공학연구지원센터 2014 International Journal of Signal Processing, Image Vol.7 No.5

Affective state detection, as an emerging field of artificial intelligence, is the key to designing effective natural human-computer interaction, especially for e-learning. It will be helpful to make the computer understand learners’ perceptions and provide appropriate guidance, just like teachers in traditional face-to-face classroom learning. Puzzlement is the most frequent non-neutral affective state in learning, and it is usually a sign that learners need more information and guidance. In this paper, we explore a machine learning approach for puzzlement detection from natural facial expression. We use active appearance models (AAMs) to decouple shape and appearance parameters from the face video sequences. Support vector machines (SVMs) are utilized to classify puzzlement and non-puzzlement with several features derived from AAMs. Using a 10-fold cross validation, we achieve the highest recognition rate of 98.9%. Experimental results indicate the feasibility of automatic frame-level puzzlement detection.

The numerical investigation of tensile strength of coal model on the performance of coal plow using Particle Flow Code

Jinwei Fu,Hadi Haeri,Vahab Sarfarazi,Mohammad Fatehi Marji,Tong Li 국제구조공학회 2022 Structural Engineering and Mechanics, An Int'l Jou Vol.82 No.6

Effects of coal tensile strength and plow configuration on the coal fragmentation process was modeled by twodimensional particles flow code (PFC2D). Three tensile strength values, 0.5, 1,5 and 3.5 MPa were considered in this numerical study. The cutters of plow penetrated in the coal for 4 mm at a rate of 0.016 m/s. According to the PFC manual, the local damping factor was 0.7. Three failure mechanism of coal during the fragmentation process by plow were modelled. The coal material beneath the cutters showed the elastic, plastic and fracturing behaviors in this analysis. In all the models, the plastic zone was fractured and some micro-cracks were induced but the elastic zone remained undamaged. It was observed that the tensile strength affected the failure mechanism of coal significantly and as it increased the extent of the fractured zone underneath the plow cutter decreased during the fragmentation process.

Investigation of the tensile behavior of joint filling under experimental test and numerical simulation

Jinwei Fu,Hadi Haeri,Vahab Sarfarazi,Mohammad Fatehi Marji,Mengdi Guo 국제구조공학회 2022 Structural Engineering and Mechanics, An Int'l Jou Vol.81 No.2

In this paper, tensile behavior of joint filling has been investigated under experimental test and numerical simulation (particle flow code). Two concrete slabs containing semi cylinder hole were prepared. These slabs were attached to each other by glue and one cubic specimen with dimension of 19 cm×15 cm×6 cm was prepared. This sample placed in the universal testing machine where the direct tensile stress can be applied to this specimen by implementing a special type of load transferring device which converts the applied compressive load to that of the tensile during the test. In the present work, two different joint filling thickness i.e., 3 mm and 6 mm were prepared and tested in the laboratory to measure their direct tensile strengths. Concurrent with experimental test, numerical simulation was performed to investigate the effect of hole diameter, length of edge notch, filling thickness and filling length on the tensile behavior of joint filling. Model dimension was 19 cm×15 cm. hole diameter was change in four different values of 2.5 cm, 5 cm, 7.5 cm and 10 cm. glue lengths were different based on the hole diameter, i.e., 12.5 cm for hole diameter of 2.5 cm, 10 cm for hole diameter of 5 cm, 7.5 cm for hole diameter of 7.5 cm and 5 cm for hole diameter of 10 cm. length of edge notch were changed in three different value i.e., 10%, 30% and 50% of glue length. Filling thickness were changed in three different value of 3 mm, 6 mm and 9 mm. Tensile strengths of glue and concrete were 2.37 MPa and 6.4 MPa, respectively. The load was applied at a constant rate of 1 kg/s. Results shows that hole diameter, length of edge notch, filling thickness and filling length have important effect on the tensile behavior of joint filling. In fixed glue thinks and fixed joint length, the tensile strength was decreased by increasing the hole diameter. Comparing the results showed that the strength, failure mechanism and fracture patterns obtained numerically and experimentally were similar for both cases.

Quaternion Markov Splicing Detection for Color Images Based on Quaternion Discrete Cosine Transform

( Jinwei Wang ),( Renfeng Liu ),( Hao Wang ),( Bin Wu ),( Yun-qing Shi ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.7

With the increasing amount of splicing images, many detection schemes of splicing images are proposed. In this paper, a splicing detection scheme for color image based on the quaternion discrete cosine transform (QDCT) is proposed. Firstly, the proposed quaternion Markov features are extracted in QDCT domain. Secondly, the proposed quaternion Markov features consist of global and local quaternion Markov, which utilize both magnitude and three phases to extract Markov features by using two different ways. In total, 2916-D features are extracted. Finally, the support vector machine (SVM) is used to detect the splicing images. In our experiments, the accuracy of the proposed scheme reaches 99.16% and 97.52% in CASIA TIDE v1.0 and CASIA TIDE v2.0, respectively, which exceeds that of the existing schemes.

Model and Optimize the Magnetic Composite Fluid (MCF) Polishing Process with Machine Learning Modeling and Intelligent Optimization Algorithm

Jinwei Fan,Xingfei Ren,Ri Pan,Peitong Wang,Haohao Tao 한국정밀공학회 2022 International Journal of Precision Engineering and Vol.23 No.9

In the magnetic composite fluid (MCF) polishing process, appropriate polishing parameters are the basis of achieving high-quality polishing without damage. Appropriate polishing parameters are mainly based on an accurate polishing model and an excellent polishing parameters optimization algorithm. However, due to the complicated principle of MCF polishing and various influencing elements, traditional modeling methods have the limitations of low accuracy, poor application, and difficulty in correcting. Therefore, it is challenging to obtain the optimal polishing quality by optimizing the polishing parameters based on the traditional model. This study proposed an online modeling approach considering data cleaning based on machine learning modeling, and the particle swarm optimization (PSO) algorithm was used to optimize polishing parameters. Then, copper polishing experiments were carried out to validate the modeling and optimization methods. The results demonstrate that the proposed machine learning online modeling method can establish an accurate MCF polishing model, and the nano-scale fine polishing of copper can be achieved by the optimized polishing parameters of PSO, and the surface roughness of the copper sample was reduced by 85% to 0.031 μm.

Input Signal Reconstruction based on Improved Moving Least Squares for Nonlinear Mul-tiple-input Multiple-output Sensor

Jinwei SUN,Dan LIU,Xin LIU,Guo WEI 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8

Meshless methods popularized in recent years are attractive choices for solving discontinuous and large de-formation problems. As one of the most popular methods to form trial function, Moving Least Squares (MLS) can ac-curately fulfill input signal reconstruction of nonlinear multiple-input multiple-output sensor. However, the parameter matrix obtained from MLS approximation sometimes is ill-conditioned even singular, which makes the signal estima-tion incorrect. By considering this problem, a novel method, the Improved Moving Least Squares (IMLS) is applied to data reconstruction in this paper. The algebra system based on IMLS method is not ill-conditioned with the weighted orthogonal functions replaced as the basis functions. Furthermore the estimation of sensor input signals can be obtainedwithout calculating the inversions of any matrices, and the computing procedure is also faster than that of MLS method.At last the comparison of approximation accuracy between these two methods is presented and illustrates that IMLS is more superior in signals regression for nonlinear multiple-input multiple-output sensors.