An Improved Crop Disease Identification Method Based on Lightweight Convolutional Neural Network by Tingzhong Wang, Honghao Xu, Yudong Hai, Yutian Cui, Ziyuan Chen

“…Identifying crop disease fast, intelligently and accurately, plays a vital role in agricultural informatization development, while existing methods are almost performed manually, which depends on expert experience, and thus the identifying result is inevitably influenced by personal preferences. …”
Get full text

Research on the Wetland Vegetation Classification Method Based on Cross-Satellite Hyperspectral Images by Min Yang, Jing Qin, Xiaodan Wang, Yanfeng Gu

“…It achieves similarity and addresses offsets. This method minimizes computational cost. Cross-sensor classification experiments were conducted, with comparative tests performed on a self-made wetland dataset. …”
Get full text

Research progress on the method of determining gas–water relative permeability curve in unconventional reservoirs by Sijie He, Feifei Fang, Kun Song, Xizhe Li, Jie Zhang, Jianqi Cao, Yu Wang, Xiaoliang Huang, Chaoliang Bian

“…The research results show: (1) The gas–water relative permeability curve has broad applications, and its precise measurement is essential for the efficient and economical development of gas reservoirs. (2) Current research on the unsteady-state method in unconventional reservoir applications generally focuses on improving the experimental method by combining the NMR, CT, and DPT techniques or optimizing the JBN method by considering the threshold pressure gradient, stress sensitivity, and gas slippage effect. (3) When experimenting with relative permeability curves in ultra-low permeability core samples is difficult or impossible, the indirect calculation can be used as an alternative to quickly obtaining numerous relative permeability curves. …”
Get full text

Overall Layout Method of Frame Structure Plane Based on Generative Adversarial Network by ZHONG Yan, LEI Xin, LONG Danbing, FANG Changjian, KANG Yongjun

“…This framework facilitates the design of the structural framework under the dual constraints of both architectural forms and predetermined structural elements. The core of this method involves constructing a model for the overall layout of the structural plan, which includes three main stages: constructing datasets, training and evaluating the model, and applying the model.MethodsIn the dataset construction stage, due to the limited number of data samples, and to reduce model training parameters, refine sample features, and improve training outcomes, this paper proposes three information representation methods for architecture, beams, and columns. …”
Get full text

A Novel THz Differential Spectral Clustering Recognition Method Based on t-SNE by Tie-Jun Li, Chih-Cheng Chen, Jian-jun Liu, Gui-fang Shao, Christopher Chun Ki Chan

Get full text

Hard Example Mining Method for Visual Perception Based on Multi-sensor Fusion by Jun LIN, Wenbo PAN, Jun YOU, Yanghan XU

“…Experiments show that hard samples in the mining autopilot scenes can be effectively collected by this method, and be used to improve the performance of object detection through incremental transfer learning signi ficantly. …”
Get full text

Optimization Method for Crop Growth Characteristics Based on Improved Locality Preserving Projection by Jia Dongyao, Hu Po, Zou Shengxiong

“…Finally, feature parameters set are obtained to extract local information of samples by improved LPP algorithm. The experiments show that the improved LPP algorithm has good adaptability, and the highest SVM classification accuracy rate of this method can reach more than 96%. …”
Get full text

A rolling bearing fault diagnosis method based on GADF-CWT-GCNN by ZHANG Xiaoli, LUO Xin, LI Min, LIANG Wang, WANG Fangzhen

“…In order to further verify the recognition ability of the model in the small sample environment, the sample sizes of 70%, 40% and 20% of the dataset are used to do experiments many times. …”
Get full text

A new machine learning method for rainfall classification: temporal random tree by Kokten Ulas Birant, Bita Ghasemkhani, Özlem Varlıklar, Derya Birant

“…To address this issue, the article proposes a novel method, named temporal random tree (TRT), in which recent training samples have a greater impact on the model’s decision-making process. …”
Get full text

Study on construction method of three-dimensional numerical model of coal with fracture structure by Zixin ZHANG, Yang YU, Jiandong YU, Zengjie NIU, Ding LANG, Yao ZHANG

“…The threshold segmentation of coal sample slices is carried out by using the combined methods of CT scanning, rock mechanics experiment, image processing technology and RFPA3D-CT to extract the three-dimensional fracture structure of coal sample, establish a three-dimensional numerical model that is basically consistent with the internal fracture structure and mechanical properties of the studied coal sample, and embed RFPA3D-CT for uniaxial loading numerical simulation analysis. …”
Get full text

Traffic adversarial example attack and defense method based on explainable artificial intelligence by MA Bowen, GUO Yuanbo, TIAN Jiwei, MA Jun, HU Yongjin

“…Experiments show high attack success and transfer rates, and the proposed defense method effectively lowers adversarial example attack success rates, enhancing system robustness.…”
Get full text

A Discriminative Target Equation-Based Face Recognition Method for Teaching Attendance by Feng Xu, Haiwei Wang

“…For the face recognition process, the system uses the Ad boost algorithm based on Hear features to achieve face detection, preprocesses the face samples with gray normalization, rotation correction, and size correction, and uses the method based on LBP features to achieve face recognition. …”
Get full text

Efficient Positive Semidefinite Matrix Approximation by Iterative Optimisations and Gradient Descent Method by Vali Asimit, Runshi Wang, Feng Zhou, Rui Zhu

“…For example, in our experiments with noised data, the iterative quadratic programming algorithm performs best in more than 41% to 67% of the samples when the standard deviation of noise is 0.02, and the gradient descent method performs best in more than 70% of the samples when the standard deviation of noise is 0.2. …”
Get full text

New White Method of Parameters and Reliability Estimation for Transmuted Power Function Distribution by Makki A. Mohammed Salih, Jaafer Hmood Eidi

“…A simulation was used to generate random data that follow the (TPF) distribution on three experiments (E1 , E2 , E3)  of the real values of the parameters, and with sample size (n=10,25,50 and 100) and iteration samples (N=1000), and taking reliability times (0< t < 0) . …”
Get full text

Solutions of First-Order Volterra Type Linear Integrodifferential Equations by Collocation Method by Olumuyiwa A. Agbolade, Timothy A. Anake

“…Furthermore, standard and Chebyshev-Gauss-Lobatto collocation points were, respectively, chosen to collocate the approximate solution. Numerical experiments are performed on some sample problems already solved by homotopy analysis method and finite difference methods. …”
Get full text

Simple preparation method and selective adsorption performance of novel activated carbon particles by Shu Ling, An Yi, Wang Xiaohan, Qin Weipu, Yang Lin, Liu Xiangdong

“…These two tests were all repeated five times and the obtained samples were put together respectively. All adsorption quantities of the AC samples were analyzed by high performance liquid chromatography (HPLC) method.The adsorption results, both in gas and aerosol conditions, indicated that the modified AC particles could absorb more harmful substances, i. e., pyrene, cinnamonitrile, phenol, but much fewer aroma components, i. e., benzoic acid, thymol, than the original AC. …”
Get full text

Introducing a Method for Backflow Detection in Lobe Blowers through Ultrasonic Technique by Ali Monazami, Somaye Mohammadi, Mehdi Behzad

“… In sponge iron production plants utilizing the direct reduction method, it is very common to use lobe blowers to transfer process gas. …”
Get full text

Research on intrusion detection method for edge networks based on federated reinforcement learning by DING Kai, HUANG Yidu, TAO Ming, XIE Renping

“…To address this issue, a federated reinforcement learning-based intrusion detection method was proposed, and experiments were conducted using two datasets from the Internet of medical things (IoMT) and Internet of vehicles (IoV) scenarios. …”
Get full text

Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning by Wei Wang, Zhenkui Wu, Huafu Luo, Bin Zhang

“…In addition, an improved deep Q-network (DQN) method is proposed, which takes the directly collected information as the training samples and combines the environmental state characteristics of the robot and the target point to be reached as the input of the network. …”
Get full text

Thermal analysis of a reflection mirror by fluid and solid heat transfer method by Zhen Wang, Fang Liu, Chaofan Xue

“…The Shanghai HIgh-repetition-rate XFEL aNd Extreme light facility (SHINE) experiences high average thermal power and demands wavefront preservation. …”
Get full text