A5101874104- Smart Agriculture and AI
- Spectroscopy and Chemometric Analyses
- Soil Mechanics and Vehicle Dynamics
- Advanced Chemical Sensor Technologies
- Agricultural Engineering and Mechanization
- Spectroscopy Techniques in Biomedical and Chemical Research
- Remote Sensing in Agriculture
- Meat and Animal Product Quality
- Soil Management and Crop Yield
- Listeria monocytogenes in Food Safety
- Network Security and Intrusion Detection
- Identification and Quantification in Food
- Granular flow and fluidized beds
- Leaf Properties and Growth Measurement
- Cell Image Analysis Techniques
- Neural Networks and Applications
- Robotics and Sensor-Based Localization
- Anomaly Detection Techniques and Applications
- Date Palm Research Studies
- Remote Sensing and Land Use
- Horticultural and Viticultural Research
- Aerodynamics and Acoustics in Jet Flows
- QR Code Applications and Technologies
- Engineering and Test Systems
- Power Systems Fault Detection
Shandong University of Technology
2014-2025
North China University of Technology
2025
State Ethnic Affairs Commission
2025
Shanghai East Hospital
2024
Shanghai Institute of Pollution Control and Ecological Security
2024
Shandong Academy of Agricultural Machinery Sciences
2021
University of Electronic Science and Technology of China
2021
Wuhan University of Technology
2021
Hokkaido University
2013-2014
Nanyang Technological University
2004
The booming development of artificial intelligence (AI) has brought excitement to many research fields that could benefit from its big data analysis capability for causative relationship establishment and knowledge generation. In toxicology studies using zebrafish, the microscopic images videos illustrate developmental stages, phenotypic morphologies, animal behaviors possess great potential facilitate rapid hazard assessment dissection toxicity mechanism environmental pollutants. However,...
High-impedance fault detection poses significant challenges for distribution network maintenance and operation. We propose a dual-path neural high-impedance detection. To enhance feature extraction, we use Gramian Angular Field algorithm to transform 1D zero-sequence voltage signals into 2D images. Our dual-branch simultaneously processes both representations: the CNN extracts spatial features from transformed images, while GRU captures temporal raw signals. optimize model performance,...
Fruit and vegetable picking robots are affected by the complex orchard environment, resulting in poor recognition segmentation of target fruits vision system. The environment is changeable. For example, change light intensity will lead to unclear surface characteristics fruit; easy overlap with each other blocked branches leaves, which makes shape incomplete difficult accurately identify segment one one. Aiming at various difficulties a two-stage instance method based on optimized mask...
Automatic navigation, as one of the modern technologies in farming automation, enables unmanned driving and operation agricultural vehicles. In this research, ZPTM (Zigzag Path Tracking Method) was proposed to reduce complexity path planning by using a point cloud consisting series anchor points with spatial information, which are obtained from orthophotos taken UAVs (Unmanned Aerial Vehicles) represent curved zigzag. A local straight created linking two adjacent points, forming target be...
For yield measurement of an apple orchard or the mechanical harvesting apples, there needs to be accurate identification target fruit. However, in a natural scene, affected by apple’s growth posture and camera position, are many kinds images, such as overlapped apples; mutual shadows leaves; stems; etc. It is challenge accurately locate apples. They will influence positioning time recognition efficiency then affect apple-harvesting robots accuracy measurement. In response this problem,...
Fruit detection and recognition has an important impact on fruit vegetable harvesting, yield prediction growth information monitoring in the automation process of modern agriculture, actual complex environment orchards poses some challenges for accurate detection. In order to achieve green fruits orchard environments, this paper proposes object method based optimized YOLOX_m. First, model extracts features from input image using CSPDarkNet backbone network obtain three effective feature...
The inhibitory control dysfunction associated with the cognitive symptoms resulting from repetitive subconcussion (SC) is frequent. Implementing temporally resolved and likely related to dynamic interactions in functional brain networks. However, investigations of activity these networks using electroencephalography (EEG) are often limited specific frequency bands without entirely utilizing spatiotemporal rhythmic information. Therefore, we proposed an innovative framework for constructing a...
In this study, we aimed to establish the predictive models of starch content in rice (with husk) using a hyperspectral imaging system (HSI) for collection 87 different varieties China.
In the complex orchard environment, efficient and accurate detection of object fruit is basic requirement to realize yield measurement automatic harvesting. Sometimes it hard differentiate between fruits background because similar color, challenging due ambient light camera angle by which photos have been taken. These problems make detect green in environments. this study, a two-stage dense framework (D2D) was proposed The model based on multi-scale feature extraction target using pyramid...
To better address the difficulties in designing green fruit recognition techniques machine vision systems, a new detection model is proposed. This an optimization of FCOS (full convolution one-stage object detection) algorithm, incorporating LSC (level scales, spaces, channels) attention blocks network structure, and named FCOS-LSC. The method achieves efficient localization images affected by overlapping occlusions, lighting conditions, capture angles. Specifically, improved feature...
Detecting anomaly logs is a great significance step for guarding system faults. Due to the uncertainty of abnormal log types, lack real and accurately labeled datasets. Existing technologies cannot be enough detecting complex various point anomalies by using human-defined rules. We propose detection method based on Generative Adversarial Networks (GAN). This uses Encoder-Decoder framework Long Short-Term Memory (LSTM) network as generator, takes keywords input encoder, decoder outputs...
The objective of this research was to develop an automatically guided rice transplanter by using RTK-GNSS and IMU as navigation sensors. used in commercially available manually-operated. Automatic operation mechanisms were developed instead manual functions including turning, stop, going forward reverse. Sensor fusion integrate measurements sensors calculate the absolute heading direction transplanter. A headland turning method proposed ensure process considering that a relatively large slip...
Due to the low working efficiency of apple harvesting robots, there is still a long way go for commercialization. The machine performance and extended operating time are two research aspects improving efficiencies this study focused on proposed round-the-clock operation mode. influences light, temperature, humidity, etc., environment at night relatively complex, thus restricts robot. Three different artificial light sources (incandescent lamp, fluorescent LED lights) were selected auxiliary...
The aim of this study was to develop a general-purpose electric off-road robot vehicle by using automatic control technologies. prototype used in commercially-purchased electricity utility that designed originally for manual operations. A manipulating unit, an steering system and speed were developed integrated into CAN-bus network operating on functions (forward, reverse, park or stop), realizing desired angles maintaining constant speed, respectively, the mode automation. An autonomous...