A5101819387- Smart Agriculture and AI
- Remote Sensing and Land Use
- Spectroscopy and Chemometric Analyses
- Industrial Vision Systems and Defect Detection
- Plant Molecular Biology Research
- Ziziphus Jujuba Studies and Applications
- Effects of Environmental Stressors on Livestock
- Agricultural Engineering and Mechanization
- Irrigation Practices and Water Management
- Video Surveillance and Tracking Methods
- Tree Root and Stability Studies
- Animal Behavior and Welfare Studies
- Plant and Fungal Interactions Research
- Remote Sensing in Agriculture
- Plant Reproductive Biology
- Advanced Neural Network Applications
- Pharmacological Effects of Natural Compounds
- High Entropy Alloys Studies
- Soil Mechanics and Vehicle Dynamics
- Plant Virus Research Studies
- Plant Gene Expression Analysis
- Textile materials and evaluations
- Lipid metabolism and biosynthesis
- Wood and Agarwood Research
- Leaf Properties and Growth Measurement
Shihezi University
2007-2024
Xinjiang Production and Construction Corps
2021-2024
Ministry of Agriculture and Rural Affairs
2020-2024
Dalian Minzu University
2021-2023
China Jiliang University
2020-2022
Shanghai Jiao Tong University
2021-2022
Chinese Academy of Inspection and Quarantine
2021-2022
State Key Laboratory of Food Science and Technology
2022
Nanchang University
2022
Xinjiang Academy of Agricultural Sciences
2022
The complexity of a supply chain makes product safety or quality issues extremely difficult to track, especially for the basic agricultural food chains people's daily diets. existing present several major problems, such as numerous participants, inconvenient communication caused by long cycles, data distrust between participants and centralized system. emergence blockchain technology effectively solves pain-point problem in traceability system chains. This paper proposes framework based on...
In recent years, the combination of hyperspectral imagery and deep learning has been widely used in agricultural Artificial Intelligence Things (AIoT), such as product quality assessment crop disease detection. However, this often comes at cost substantial computational power energy consumption. paper, we focused on data-efficient green computing for low-carbon jujube moisture content First, order to compress images capacity, a spectral selection algorithm based swarm intelligence was...
Acoustic waves offer a non-destructive, safe, and cost-effective means of monitoring the environment, with potential application in soil water content monitoring. However, extracting information from acoustic signals is still challenging. To tackle this issue, we have developed low-frequency swept signal detection device system. We conducted penetration testing using signals. The swept-frequency passing through were transformed into time–frequency spectrogram. Using Swin-Transformer model,...
High precision navigation along specific paths is required for plant protection operations in dwarf and densely planted jujube orchards southern Xinjiang. This study proposes a robotic path planning method dense planting of red based on the improved A* dynamic window approach (DWA) algorithms using Laser Radar to build maps. First, kinematic physical robot simulation models are established; map orchard constructed Radar. The robot’s position described an adaptive Monte Carlo positioning...
There are some problems with estrus detection in ewes large-scale meat sheep farming: mainly, the manual method is labor-intensive and contact sensor causes stress reactions ewes. To solve abovementioned problems, we proposed a multi-objective layer neural network-based for ewe crawling behavior recognition. The approach has four main parts. Firstly, to address problem of mismatch between our constructed dataset YOLO v3 anchor box size, propose obtain new size by clustering using K-means++...
Driven by edge computing, how to efficiently deploy the meta-learner LSTM in resource constrained FPGA terminal equipment has become a big problem. This paper proposes compression strategy based on meta-learning model, which combined structured pruning of weight matrix and mixed precision quantization. The was pruned into sparse matrix, then quantified reduce consumption. Finally, accelerator designed idea hardware–software cooperation. Experiments show that compared with mainstream hardware...
The non-destructive detection of soluble solids content (SSC) in fruit by near-infrared (NIR) spectroscopy has a good application prospect. At present, the portable devices is more common. construction an accurate and stable prediction model key for successful device. In this study, visible (Vis/NIR) spectra Korla fragrant pears were collected commercial measurement Different pretreatment methods used to preprocess raw spectra, partial least squares (PLS) was constructed predict SSC...
High-quality agricultural multi-view stereo reconstruction technology is the key to precision and informatization in agriculture. Multi-view methods are an important part of 3D vision technology. In method based on deep learning, effect feature extraction directly affects accuracy reconstruction. Aiming at actual problems orchard fruit tree reconstruction, this paper designs improved structure combination remote sensing artificial intelligence realize accurate jujube trunks. Firstly,...
The accurate recognition of tree trunks is a prerequisite for precision orchard yield estimation. Facing the practical problems complex environment and large data flow, existing object detection schemes suffer from key issues such as poor quality, low timeliness accuracy, weak generalization ability. In this paper, an improved YOLOv8 designed on basis flow screening enhancement lightweight jujube trunk detection. Firstly, frame extraction algorithm was proposed utilized to efficiently screen...
In this paper, a novel deep learning framework, fuzzy EfficientDet, is proposed to address the challenge of accurately detecting larch infested by Coleophora laricella pests in UAV imagery, where key innovation incorporation spatial attention mechanism (FSAM), which can effectively deal with problem model uncertainty due complexity environmental transformations and image features. First, study designs implements Global-Local Squeeze-and-Excitation Module, profoundly integrates global local...
Discrete element method (DEM) simulation is an important to analyze the interaction relationship between materials and equipment, develop machinery and/or equipment. However, it necessary input specific parameters when establishing a DEM model. In this study, interval values were measured through angle of repose tests fallen jujube fruit (FJF), for FJF established with EDEM software (DEM Solutions Ltd. Edinburgh, Scotland, UK). Then, Plackett-Burman design, steepest ascent search experiment,...
We propose a lightweight neural network-based method to detect the estrus behavior of ewes. Our suggested is mainly proposed solve problem not being able ewe in timely and accurate manner large-scale meat sheep farms. The three main steps our methodology include constructing dataset, improving network structure, detecting based on network. First, dataset was constructed by capturing images from videos with crawling behavior, data enhancement performed improve generalization ability model at...
The stubble after cotton harvesting was used as the detection object to achieve visual navigation operation for residual film recovery autumn. An improved (You Only Look Once v3) YOLOv3-based target algorithm proposed detect stubble. First, field images of recycling were collected. Considering inconsistency between size and shape, a segmented labeling data set is proposed. Secondly, Darknet-53 backbone original YOLOv3 network accommodate tiny targets. Next, prediction anchor box clustered...
In order to solve the problems of low efficiency and subjectivity manual observation in process group-sheep-aggression detection, we propose a video streaming-based model for detecting aggressive behavior group sheep. experiment, collected videos sheep's daily routine sheep pen. Using open-source software LabelImg, labeled data with bounding boxes. Firstly, YOLOv5 detects all each frame outputs coordinates information. Secondly, sort using tracking heuristic proposed this paper. Finally,...
Abstract Background Due to the high cost of data collection for magnetization detection media, sample size is limited, it not suitable use deep learning method predict its change trend. The prediction physical and chemical properties magnetized water fertilizer (PCPMWF) by meta-learning can help explore effects irrigation on crops. Method In this article, we propose a optimization model based meta-learner LSTM in field regression PCPMWF. meta-learning, used replace MAML’s gradient descent...