A New Hybrid Algorithm for Invariance and Improved Classification Performance in Image Recognition

Shi, Rui-Xia,Jeong, Dong-Gyu The Institute of Internet 2020 International journal of advanced smart convergenc Vol.9 No.3

It is important to extract salient object image and to solve the invariance problem for image recognition. In this paper we propose a new hybrid algorithm for invariance and improved classification performance in image recognition, whose algorithm is combined by FT(Frequency-tuned Salient Region Detection) algorithm, Guided filter, Zernike moments, and a simple artificial neural network (Multi-layer Perceptron). The conventional FT algorithm is used to extract initial salient object image, the guided filtering to preserve edge details, Zernike moments to solve invariance problem, and a classification to recognize the extracted image. For guided filtering, guided filter is used, and Multi-layer Perceptron which is a simple artificial neural networks is introduced for classification. Experimental results show that this algorithm can achieve a superior performance in the process of extracting salient object image and invariant moment feature. And the results show that the algorithm can also classifies the extracted object image with improved recognition rate.

Effects of Wind Generation Uncertainty and Volatility on Power System Small Signal Stability

Shi, Li-Bao,Kang, Li,Yao, Liang-Zhong,Qin, Shi-Yao,Wang, Rui-Ming,Zhang, Jin-Ping The Korean Institute of Electrical Engineers 2014 Journal of Electrical Engineering & Technology Vol.9 No.1

This paper discusses the impacts of large scale grid-connected wind farm equipped with permanent magnet synchronous generator (PMSG) on power system small signal stability (SSS) incorporating wind generation uncertainty and volatility. Firstly, a practical simplified PMSG model with rotor-flux-oriented control strategy applied is derived. In modeling PMSG generator side converter, the generator-voltage-oriented control strategy is utilized to implement the decoupled control of active and reactive power output. In modeling PMSG grid side converter, the grid-voltage-oriented control strategy is applied to realize the control of DC link voltage and the reactive power regulation. Based on the Weibull distribution of wind speed, the Monte Carlo simulation technique based is carried out on the IEEE 16-generator-68-bus test system as benchmark to study the impacts of wind generation uncertainty and volatility on small signal stability. Finally, some preliminary conclusions and comments are given.

Robust Control for T-S Fuzzy Multi-particle Model of High-speed Train with Disturbances and Time-varying Delays

Rui Shi,Guangtian Shi 제어·로봇·시스템학회 2022 International Journal of Control, Automation, and Vol.20 No.9

This paper concerns the networked control issue of the speed and displacement of high-speed train (HST) with two independent time-varying delays in presence both in coupler forces and data transmission procedures. The dynamic of high-speed train is firstly described by a group of multiple particle models based on Takagi-Sugeno (TS) fuzzy descriptions. Afterwards, the system states are measured by the sensor and further transmitted to the remote controller via communication network. By using the available time-delayed state information, an output feedback control is mainly proposed. Since the process and network time-varying delays are simultaneously involved, a mode-dependent Lyapunov-Krasovskii functional (LKF) is constructed for achieving the mean-square exponential asymptotic stability (MSEAS) of the closed-loop systems. By assisting of a linear decoupling method, the controller design method is conveniently obtained. Finally, a numerical example is also provided to illustrate the effectiveness of the proposed method.

Naringin and Naringenin Relax Rat Tracheal Smooth by Regulating BKCa Activation

Rui Shi,Jia-Wen Xu,Zi-Ting Xiao,Ruo-Fei Chen,Yi-Lin Zhang,Jia-Bi Lin,Ke-Ling Cheng,Gu-Yi Wei,Pei-Bo Li,Wen-Liang Zhou,Wei-Wei Su 한국식품영양과학회 2019 Journal of medicinal food Vol.22 No.9

Naringin and its aglycone, naringenin, occur naturally in our regular diet and traditional Chinese medicines. This study aimed to detect an effective therapeutic approach for cough variant asthma (CVA) through evaluating the relaxant effect of these two bioactive herbal monomers as antitussive and antiasthmatic on rat tracheal smooth muscle. The relaxant effect was determined by measuring muscular tension with a mechanical recording system in rat tracheal rings. Cytosolic Ca2+ concentration was measured using a confocal imaging system in primary cultured tracheal smooth muscle cells. In rat tracheal rings, addition of both naringin and naringenin could concentration dependently relax carbachol (CCh)-evoked tonic contraction. This epithelium-independent relaxation could be suppressed by BaCl2, tetraethylammonium, and iberiotoxin (IbTX), but not by glibenclamide. After stimulating primary cultured tracheal smooth muscle cells by CCh or high KCl, the intracellular Ca2+ increase could be inhibited by both naringin and naringenin, respectively. This reaction was also suppressed by IbTX. These results demonstrate that both naringin and naringenin can relax tracheal smooth muscle through opening big conductance Ca2+-activated K+ channel, which mediates plasma membrane hyperpolarization and reduces Ca2+ influx. Our data indicate a potentially effective therapeutic approach of naringin and naringenin for CVA.

Modeling study on repeat purchase intention on silk products based on the electronic commercial platform

Shi, Rui,Li, Gaihang,Liu, Guolian The Costume Culture Association 2012 服飾文化硏究 Vol.20 No.6

Based on the literature on customer's repeat purchase intention, customer's repeat purchase intention was explored, customer's repeat purchase intention has been a crucial factor influencing consumer behaviors, In this research, the development of models on repeat purchase intention repurchase was indicated. Based on the electronic commerce platform, we focus on the customer's repeat purchase intention on silk products, This paper mainly explores the e-commerce purchase frequency (EPF), customer perceived value (CPV), perceived risk of e-commerce (EPR), and customer satisfaction (CS). The influence of the four factors on repeat purchase intention (RPI) is investigated. In the results, we found that CPV and CS have positive correlations with repeat purchase intention, The EPR has a negative correlation with RPI and has no significant influence on RPI. The result can provide meaningful suggestions for silk product retailers.

On the massive metal accumulation on the eastern margin of the North China Craton and the prospecting evaluation – a case study of Jiaojia gold concentration belt

Rui Shi,Jianping Chen 한국지질과학협의회 2015 Geosciences Journal Vol.19 No.4

North China Craton, with characteristics of the multistage tectonic evolution, has experienced a long geological history of more than 3.8 billion years, which records almost all the major geological events from the early crust development stage to the Mesozoic and has formed rich mineral resources and unique dominant minerals. Jiaodong terrane, on the eastern margin of the North China Craton, has become the basement after experiencing the evolution of Precambrian formation. Controlled by the tectonic regime in the Mesozoic, this terrane witnessed the strong crust-mantle interaction, and became the largest gold producer in China after forming the massive metal accumulation and an outbreak of large-scale metallogenic events. Previous scholars have conducted extensive researches on the metallogenic theory of Jiaodong Gold Concentrating Area and applied it to prospecting and exploration; with the increasing difficulty in prospecting and the deployment of deep prospecting, finding out the new prospecting methods has become the study focus. Based on the analysis of the regional tectonic evolution and the research on the metallogenic theory of the massive metal concentration, this paper has summed up some favorable geological conditions for ore-formation and ore-controlling, and with Jiaojia gold concentration belt as a case study and combined with the geophysical and geochemical data in this area, this paper has deduced the deep mineralization space with the three-dimensional geological modeling technique, which has achieved the integration of metallogenic theory and prospecting methods. The result indicates that forecast areas deep resources in the Jiaojia gold concentration belt is 842.88 t. More importantly, it delineated 7 undeveloped predicted targets for deep prospecting which provided a scientific basis for prospecting exploration.

Modeling study on repeat purchase intention on silk products based on the electronic commercial platform

Rui Shi,Gaihang Li 복식문화학회 2012 服飾文化硏究 Vol.20 No.6

A New Bank-card Number Identification Algorithm Based on Convolutional Deep Learning Neural Network

Rui-Xia Shi,정동규 한국인터넷방송통신학회 2022 International journal of advanced smart convergenc Vol.11 No.4

Recently bank card number recognition plays an important role in improving payment efficiency. In this paper we propose a new bank-card number identification algorithm. The proposed algorithm consists of three modules which include edge detection, candidate region generation, and recognition. The module of ‘edge detection’ is used to obtain the possible digital region. The module of ‘candidate region generation’ has the role to expand the length of the digital region to obtain the candidate card number regions, i.e. to obtain the final bank card number location. And the module of ‘recognition’ has Convolutional deep learning Neural Network (CNN) to identify the final bank card numbers. Experimental results show that the identification rate of the proposed algorithm is 95% for the card numbers, which shows 20% better than that of conventional algorithm or method.

A New Hybrid Algorithm for Invariance and Improved Classification Performance in Image Recognition

Rui-Xia Shi,정동규 한국인터넷방송통신학회 2020 Journal of Advanced Smart Convergence Vol.9 No.3

It is important to extract salient object image and to solve the invariance problem for image recognition. In this paper we propose a new hybrid algorithm for invariance and improved classification performance in image recognition, whose algorithm is combined by FT(Frequency-tuned Salient Region Detection) algorithm, Guided filter, Zernike moments, and a simple artificial neural network (Multi-layer Perceptron). The conventional FT algorithm is used to extract initial salient object image, the guided filtering to preserve edge details, Zernike moments to solve invariance problem, and a classification to recognize the extracted image. For guided filtering, guided filter is used, and Multi-layer Perceptron which is a simple artificial neural networks is introduced for classification. Experimental results show that this algorithm can achieve a superior performance in the process of extracting salient object image and invariant moment feature. And the results show that the algorithm can also classifies the extracted object image with improved recognition rate.

Modeling study on repeat purchase intention on silk products based on the electronic commercial platform

( Rui Shi ),( Gaihang Li ) 복식문화학회 2012 服飾文化硏究 Vol.20 No.6

Based on the literature on customer`s repeat purchase intention, customer`s repeat purchase intention was explored, customer`s repeat purchase intention has been a crucial factor influencing consumer behaviors, In this research, the development of models on repeat purchase intention repurchase was indicated. Based on the electronic commerce platform, we focus on the customer`s repeat purchase intention on silk products, This paper mainly explores the e-commerce purchase frequency (EPF), customer perceived value (CPV), perceived risk of e-commerce (EPR), and customer satisfaction (CS). The influence of the four factors on repeat purchase intention (RPI) is investigated. In the results, we found that CPV and CS have positive correlations with repeat purchase intention, The EPR has a negative correlation with RPI and has no significant influence on RPI. The result can provide meaningful suggestions for silk product retailers.