Shiguo Wang

Deformation and Failure Mechanisms of Extra-Deep Carbonate Rocks Under In Situ Conditions: An Experimental Study

Shiguo Wang, Yan Jin, Ping Zeng, Yunhu Lu et autres

The exploration of oil and gas resources is shifting toward ultra-deep and extra-deep reservoirs, including in the Tarim Basin, where various types of carbonate rocks are buried. Owing to the extreme burial depths, the mechanical behavior of these rocks under extra-deep conditions …

cn (code pays fourni par la source)

Severity classification of pepper verticillium wilt from UAV multispectral imagery using a fuzzy deep neural network

Lijian Lu, Jin Sheng Lei, Xinyan Qin, Shiguo Wang et autres

To address the problem of low classification accuracy and limited detection efficiency of pepper verticillium wilt (VW) caused by fuzzy, uncertain information, this study integrates fuzzy logic into a deep learning framework for verticillium wilt severity (VWS) classification based on unmanned aerial …

cn (code pays fourni par la source)

Impurity rates detection for pepper harvesting based on YOLOv8n-Seg-ASB and random forest

Lijian Lu, Jin Sheng Lei, Chenming Cheng, Shiguo Wang et autres

To address the inaccuracies and inefficiencies of pepper impurity rates detection caused by complex material compositions and variable harvesting environments, this paper proposes a detection technique based on deep and machine learning algorithms. First, a machine vision-based image acquisition device for pepper …

cn (code pays fourni par la source)

Parameter optimization and mechanism analysis of pepper spring-tooth drum picking device based on DEM

Jiaxuan Yang, Jin Sheng Lei, Xinyan Qin, Shiguo Wang et autres

To address the issues of unclear mechanisms and poor harvesting quality in mechanized pepper harvesting, a simulation model based on the discrete element method (DEM) is developed to analyze the harvesting process and optimize key parameters. Through theoretical analysis, kinematic models of …

cn (code pays fourni par la source)

Panoptic Segmentation Method Based on Feature Fusion and Edge Guidance

Shiguo Wang, Shuhua Teng

Panoptic segmentation, a pivotal research direction in computer vision, unifies pixel-level object and background recognition within a scene, crucial for applications like autonomous driving. However, existing methods, including State-of-the-Art models like Mask2Former, often exhibit limitations such as inadequate adaptation in multi-scale feature …

cn (code pays fourni par la source)

Panoptic Image Segmentation Method Based on Dynamic Instance Query

Shiguo Wang, Shuhua Teng

Panoptic segmentation, as a key task in the field of computer vision, holds significant importance in practical applications such as autonomous driving and robot vision. Currently, among deep-learning-based panoptic segmentation methods, query-based methods have received widespread attention. However, existing methods, such as …

cn (code pays fourni par la source)

Dual-Path Transformer with Spatial-Channel Attention for Enhanced Panoptic Segmentation

Shiguo Wang, Shuhua Teng

Panoptic segmentation is a key task in computer vision, aiming to achieve both instance-level and semantic-level segmentation. However, existing methods generally suffer from problems such as insufficient feature utilization, limited instance differentiation, and insufficient multi-scale information integration. To address these challenges, this …

cn (code pays fourni par la source)

Classification and Recognition of Soybean Quality Based on Hyperspectral Imaging and Random Forest Methods

Man Chen, Zhichang CHANG, Chengqian Jin, Gong Cheng et autres

To achieve the rapid and accurate classification and identification of soybean components, this study selected soybeans harvested by the 4LZ-1.5 soybean combine harvester as the research subject. Hyperspectral images of soybean samples were collected using the Pika L spectrometer, and spectral information …

cn (code pays fourni par la source)

Parameter Optimization and Mechanism Analysis of Pepper Spring-Tooth Drum Picking Device Based on Dem

Jiaxuan Yang, Jin Sheng Lei, Xinyan Qin, Shiguo Wang et autres

Severity Classification of Pepper Verticillium Wilt from Uav Multispectral Imagery Using a Fuzzy Deep Neural Network

Lijian Lu, Jin Sheng Lei, Xinyan Qin, Jianglong Zhang et autres

Iterative Bounded Distance Decoding With Random Flipping for Product-Like Codes

Guorong Li, Shiguo Wang, Shancheng Zhao

Product-like codes are widely used in high-speed communication systems since they can be decoded with low-complexity hard decision decoders (HDDs). To meet the growing demand of data rates, enhanced HDDs are required. In this paper, we propose a novel soft-aided HDD (SA-HDD), …

cn (code pays fourni par la source)

Toward Secrecy-Energy-Efficiency Optimization for UAV-Assisted Bidirectional Systems With Active Eavesdroppers

Shiguo Wang, Jingjing Wang, Rukhsana Ruby, Yongjian Zhang et autres

Ensuring secrecy information transmission with enhanced energy efficiency is one of the critical issues in unmanned aerial vehicles (UAVs)-assisted wireless systems owing to the open nature of wireless channels and the limited battery power. In this article, the secrecy energy efficiency (SEE) …

cn (code pays fourni par la source)