作者机构：
[Tiancheng Zhang] Bi Shengyun Information Technology Co., LTD;[Hua Yang; Haifeng Zhang; Jie Xiao; Qi Wang; Shenyang Sheng; Chengwu Peng] School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China
会议名称：
2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
会议时间：
15 March 2024
会议地点：
Chongqing, China
会议论文集名称：
2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
摘要：
With the continuous development of artificial intelligence technology, deep learning methods have been widely used in smart agriculture. With the continuous progress of object detection algorithms, it is a future trend to introduce computer vision methods into smart agriculture. This paper proposes an improved YOLOv8 network model for detecting whether apple is still in a healthy state in smart agriculture systems. By introducing a better backbone network EfficientNet, features can be extracted from the data efficiently. In addition, by introducing a novel WIOU calculation function, the rectangular box can be computed better. In this experiment, the average accuracy of the improved YOLOv8-Enet is mAP0.5 and mAP 0.5:0.95, which are 7.1% and 6.5% higher than that of YOLOv8-base, respectively. The proposed YOLOv8-Enet model can effectively detect apple surface defect and provide theoretical and technical support for future research on vision of smart agriculture
摘要：
In recent years, the domain of diagnosing plant afflictions has predominantly relied upon the utilization of deep learning techniques for classifying images of diseased specimens; however, these classification algorithms remain insufficient for instances where a single plant exhibits multiple ailments. Consequently, we view the region afflicted by the malady of rice leaves as a minuscule issue of target detection, and then avail ourselves of a computational approach to vision to identify the affected area. In this paper, we advance a proposal for a Dense Higher-Level Composition Feature Pyramid Network (DHLC-FPN) that is integrated into the Detection Transformer (DETR) algorithm, thereby proffering a novel Dense Higher-Level Composition Detection Transformer (DHLC-DETR) methodology which can effectively detect three diseases: sheath blight, rice blast, and flax spot. Initially, the proposed DHLC-FPN is utilized to supersede the backbone network of DETR through amalgamation with Res2Net, thus forming a feature extraction network. Res2Net then extracts five feature scales, which are coalesced through the deployment of high-density rank hybrid sampling by the DHLC-FPN architecture. The fused features, in concert with the location encoding, are then fed into the transformer to produce predictions of classes and prediction boxes. Lastly, the prediction classes and the prediction boxes are subjected to binary matching through the application of the Hungarian algorithm. On the IDADP datasets, the DHLC-DETR model, through the utilization of data enhancement, elevated mean Average Precision (mAP) by 17.3% in comparison to the DETR model. Additionally, mAP for small target detection was improved by 9.5%, and the magnitude of hyperparameters was reduced by 324.9 M. The empirical outcomes demonstrate that the optimized structure for feature extraction can significantly enhance the average detection accuracy and small target detection accuracy of the model, achieving an average accuracy of 97.44% on the IDADP rice disease dataset.
期刊：
Chinese Control Conference,2019年2019-July:8944-8949 ISSN：1934-1768
通讯作者：
Jiang, Feng(jeff20@163.com)
作者机构：
[Hua Yang] School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan;430023, China;[Yunfei Zhang; Feng Jiang] School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan;430073, China;[Hua Yang] 430023, China
会议名称：
2019 Chinese Control Conference (CCC)
会议时间：
July 2019
会议地点：
Guangzhou, China
会议主办单位：
(1) School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan; 430023, China; (2) School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan; 430073, China
摘要：
The frequent fluctuations in international crude oil prices may affect the stability of the global economy and society. The fluctuation of crude oil prices has nonlinearity, uncertainty and volatility, which bring certain challenges for forecasting crude oil prices. In this paper we use hybrid model with the empirical mode decomposition (EMD) and Back Propagation Neural Network (BPNN) to predict the crude oil prices. To improve the accuracy of prediction, we firstly decompose the crude oil prices data into a series of independent intrinsic mode functions (IMFs) and residual sequences by the empirical mode decomposition method (EMD). Moreover we used BPNN to predict the Brent and WIT crude oil prices respectively. In order to show the effectiveness of the proposed method, we adopt three statistical criteria to evaluate the hybrid method. The empirical results show that EMD-BPNN has higher prediction accuracy than BPNN, the least square support vector regression (LSSVR) and EMD-LSSVR.
期刊：
2018 NINTH INTERNATIONAL CONFERENCE ON INTELLIGENT CONTROL AND INFORMATION PROCESSING (ICICIP),2018年:128-133
通讯作者：
Jiang, Feng
作者机构：
[Yang, Hua] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Hubei, Peoples R China.;[Jiang, Feng; Zhang, Jie] Zhongnan Univ Econ & Law, Sch Stat & Math, Wuhan 430073, Hubei, Peoples R China.
通讯机构：
[Jiang, Feng] Z;Zhongnan Univ Econ & Law, Sch Stat & Math, Wuhan 430073, Hubei, Peoples R China.
会议名称：
9th International Conference on Intelligent Control and Information Processing (ICICIP)
会议时间：
NOV 09-11, 2018
会议地点：
Wanzhou, PEOPLES R CHINA
会议主办单位：
[Yang, Hua] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Hubei, Peoples R China.^[Zhang, Jie;Jiang, Feng] Zhongnan Univ Econ & Law, Sch Stat & Math, Wuhan 430073, Hubei, Peoples R China.
关键词：
Greenhouse gas emissions;clustering methods;model-based method
摘要：
The emission of greenhouse gas (GG) is a prime cause of global warming. But the emission reduction may lower economic growth rate. Since different countries have different industrial structure, the criteria of proper emission reduction is important for every country. In this paper we consider four GGs including carbon dioxide, nitrogen oxides, methane and nitrous oxide. Based on Gaussian hybrid model, we make clustering analysis for 31 European countries in 2017. The empirical analysis reveals that clustering membership becomes more distinct compared with k-means approach. In addition, the results show that 31 countries are grouped into four classes and Germany and France in the emissions of GGs are higher than others.
会议名称：
2nd International Conference on Optimization and Control (ICOCO)
会议时间：
DEC 07-09, 2015
会议地点：
Chongqing, PEOPLES R CHINA
会议主办单位：
[Jiang, Feng] Zhongnan Univ Econ & Law, Sch Math & Stat, Wuhan 430073, Peoples R China.^[Yang, Hua] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.^[Tian, Tianhai] Monash Univ, Sch Math Sci, Melbourne, Vic 3800, Australia.
关键词：
Ait-Sahalia-Rho model;Boundedness;Convergence in probability
摘要：
The Ait-Sahalia-Rho model is an important tool to study a number of financial problems, including the term structure of interest rate. However, since the functions of this model do not satisfy the linear growth condition, we cannot study the properties for the solution of this model by using the traditional techniques. In this paper we overcome the mathematical difficulties due to the nonlinear growth condition by using numerical simulation. Thus we first discuss analytical properties of the model and the convergence property of numerical solutions in probability for the Ait-Sahalia-Rho model. Finally, an example for option pricing is given to illustrate that the numerical solution is an effective method to estimate the expected payoffs.
摘要：
In this work, the problem on the exponential stability for second-order neutral stochastic partial differential equations with infinite delays is considered in the presence of impulses under some conditions. By employing the new integral inequality technique, some algebraic criteria of stability are established for the concerned problem and some existing results are generalized and improved. Finally, an illustrative example is given to demonstrate the effectiveness of the obtained results. (C) 2016 Elsevier Inc. All rights reserved.
摘要：
The study of evolution systems driven by noises including Brownian motion, impulses, Poisson jump in Hilbert spaces has been reported extensively and applied in many fields such as engineering, physics, economics and biology. In this paper, a class of stochastic evolution jump-diffusions driven by impulses are studied. Some sufficient conditions which ensure pth moment exponential stability of mild solution for the stochastic evolution jump-diffusions driven by impulses are given. The existing results are generalized.
作者机构：
[Liu, Jianguo; Yang, Hua] Huazhong Univ Sci & Technol, Sch Automat, Wuhan, Hubei, Peoples R China.;[Yang, Hua] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Hubei, Peoples R China.;[Jiang, Feng] Zhongnan Univ Econ & Law, Sch Stat & Math, Wuhan, Hubei, Peoples R China.
会议名称：
7th International Conference on Intelligent Control and Information Processing (ICICIP)
会议时间：
DEC 01-04, 2016
会议地点：
Siem Reap, CAMBODIA
会议主办单位：
[Yang, Hua;Liu, Jianguo] Huazhong Univ Sci & Technol, Sch Automat, Wuhan, Hubei, Peoples R China.^[Yang, Hua] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Hubei, Peoples R China.^[Jiang, Feng] Zhongnan Univ Econ & Law, Sch Stat & Math, Wuhan, Hubei, Peoples R China.
关键词：
locally exponential stability;jump-diffusion systems with parameter;mild solution
摘要：
Stochastic jump systems have great potential in finance engineering and stochastic control. In this paper, we mainly consider stability of stochastic jump-diffusion systems with parameter. We establish the criteria of locally exponential stability of mild solutions of the systems by using stochastic integral inequalities technique. We extend some existing results to more general cases. Finally, we use an example to show our result.
摘要：
This paper investigates the stability of second-order stochastic neutral partial functional differential equations driven by impulsive noises. Some sufficient conditions ensuring pth moment exponential stability of the second-order stochastic neutral partial functional differential equations driven by impulsive noises are obtained by establishing a new impulsive-integral inequality. These existing results are generalized and improved by the present study. Finally, an example is given to show the effectiveness of our results.
期刊：
Advances in Difference Equations,2016年2016(1):1-11 ISSN：1687-1839
通讯作者：
Jiang, Feng
作者机构：
[Jiang, Feng] Zhongnan Univ Econ & Law, Sch Stat & Math, Wuhan 430073, Hubei, Peoples R China.;[Yang, Hua] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Hubei, Peoples R China.;[Yang, Hua] Huazhong Univ Sci & Technol, Sch Automat, Wuhan 430074, Hubei, Peoples R China.;[Tian, Tianhai] Monash Univ, Sch Math Sci, Melbourne, Vic 3800, Australia.
通讯机构：
[Jiang, Feng] Z;Zhongnan Univ Econ & Law, Sch Stat & Math, Wuhan 430073, Hubei, Peoples R China.
关键词：
Exponential Stability;Stochastic System;Mild Solution;Fixed Point Theory;Integral Inequality
摘要：
The paper is concerned with stability for second-order stochastic neutral partial functional systems subject to infinite delays and impulses. Some sufficient conditions ensuring pth moment exponential stability of the second-order stochastic systems are given by gaining a new integral inequality with impulses. Some earlier results are generalized and improved.
摘要：
This paper is mainly discussed almost sure exponential stability for mild solution of neutral stochastic hybrid evolution systems. Some conditions ensured the stability of mild solution of the systems are given. The earlier results are generalized and improved.
作者机构：
[Liu, Jianguo; Yang, Hua] Huazhong Univ Sci & Technol, Sch Automat, Wuhan, Peoples R China.;[Yang, Hua] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.;[Jiang, Feng] Zhongnan Univ Econ & Law, Sch Math & Stat, Wuhan, Peoples R China.
会议名称：
2015 Sixth International Conference on Intelligent Control and Information Processing (ICICIP)
关键词：
exponential stability;Hurwitz matrix;feedback control
摘要：
Stability plays an important role in the practice. In this paper, exponential stability of nonlinear dynamic systems with delay is discussed. Some conditions which guarantee exponential stability of the nonlinear dynamic systems are given by by Hurwitz matrix theory. Finally, an example is given to illustrate the theoretical result.
摘要：
This paper is mainly discussed exponential stability in pth moment for mild solution of a class of semilinear neutral stochastic jump-diffusion systems. Some conditions ensured the stability of mild solution of the systems are given by employing some inequalities. The earlier results are generalized and improved.
