A5032245448- Neural dynamics and brain function
- Advanced Memory and Neural Computing
- Advanced Algorithms and Applications
- Data Mining Algorithms and Applications
- Neuroscience and Neural Engineering
- EEG and Brain-Computer Interfaces
- Advanced Image Fusion Techniques
- Rough Sets and Fuzzy Logic
- Functional Brain Connectivity Studies
- Image and Signal Denoising Methods
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Remote Sensing and Land Use
- Neural Networks and Applications
- Time Series Analysis and Forecasting
- Advanced Neuroimaging Techniques and Applications
- Spinal Cord Injury Research
- Industrial Technology and Control Systems
- Medical Image Segmentation Techniques
- Data Management and Algorithms
- Transcranial Magnetic Stimulation Studies
- Image Processing Techniques and Applications
- Neural Networks and Reservoir Computing
- Advanced Sensor and Control Systems
- Artificial Immune Systems Applications
Hebei University of Technology
2016-2025
Hainan University
2025
Sanya University
2025
Chinese Academy of Medical Sciences & Peking Union Medical College
2025
Peking Union Medical College Hospital
2025
Beijing Jiaotong University
2023-2024
Northwestern Polytechnical University
2002-2024
Yunnan University
2023
China Shipbuilding Industry Corporation (China)
2010-2022
China Academy of Launch Vehicle Technology
2022
The leaf area index (LAI) is a critical parameter for characterizing plant foliage abundance, canopy structure changes, and vegetation productivity in ecosystems. Traditional phenological measurements are often destructive, time-consuming, labor-intensive. This paper proposes high-throughput 3D point cloud data processing pipeline to segment field soybean plants estimate their LAI. obtained from UAV equipped with LiDAR camera. First, PointNet++ model was applied simplify the segmentation...
Photoluminescent metallopolymers displaying photo-stimuli-responsive properties are emerging as promising materials with versatile applications in photo-rewritable patterns, wearable UV sensors, and optical encryption anti-counterfeiting. However, integrating these into practical that require fast response times, lightweight qualities, fatigue resistance, multiple capabilities poses challenges. In this study, luminescent photochromic lanthanide (Ln) rapid self-healing developed by...
This study aimed to explore structural and functional reorganization of the brain in early stages spinal cord injury (SCI) identify areas that contribute motor recovery.We studied 25 patients with SCI, including 10 good recovery 15 poor recovery, along matched healthy controls.The mean period post-SCI was 9.2 6 3.5 weeks recoverers 8.8 2.6 recoverers.All participants underwent MRI on a 3-T magnetic resonance system.We evaluated differences cross-sectional area at C2/C3 level, cortical...
The classification of mental tasks is one key issues EEG-based brain computer interface (BCI). Differentiating classes from EEG signals challenging because are nonstationary and nonlinear. Owing to its powerful capacity in solving nonlinearity problems, support vector machine (SVM) method has been widely used as a tool. Traditional SVMs, however, assume that each feature sample contributes equally accuracy, which not necessarily true real applications. In addition, the parameters SVM kernel...
Tumor detection using medical images plays a key role in practices. One challenge tumor is how to handle the nonlinear distribution of real data. Owing its ability learning data without any prior knowledge, one-class support vector machines (SVMs) have been applied detection. The conventional SVMs, however, assume that each feature sample has same importance degree for classification result, which not necessarily true applications. In addition, parameters SVM and kernel function also affect...
Traditional sequential pattern mining methods were designed for symbolic sequence. As a collection of measurements in chronological order, time series needs to be discretized into sequences, and then users can apply discover interesting patterns series. The discretization will not only cause the loss some important information, which partially destroys continuity series, but also ignore order relations between time-series values. Inspired by order-preserving matching, this article explores...
Nonoverlapping sequential pattern mining is an important type of (SPM) with gap constraints, which not only can reveal interesting patterns to users but also effectively reduce the search space using Apriori (anti-monotonicity) property. However, existing algorithms do focus on attributes interest users, meaning that methods may discover many frequent are redundant. To solve this problem, article proposes a task called nonoverlapping three-way (NTP) mining, where categorized according three...
Gap constraint sequential pattern mining (SPM), as a kind of repetitive SPM, can avoid too many useless patterns. However, this method is difficult for users to set suitable gap without prior knowledge and each character considered have the same effects. To tackle these issues, article addresses self-adaptive One-off Weak-gap Strong Pattern (OWSP) mining, which has three characteristics. First, it determines adaptively according sequence. Second, all characters are divided into two groups:...
Motor imagery (MI) refers to the mental rehearsal of movement in absence overt motor action, which can activate or inhibit cortical excitability. EEG mu/beta oscillations recorded over human cortex have been shown be consistently suppressed during both imagination and performance movements, although specific effect on brain function remains confirmed. In this study, Granger causality (GC) was used construct functional network subjects resting state based order explore effects function....
Discovering frequent trends in time series is a critical task data mining. Recently, order-preserving matching was proposed to find all occurrences of pattern series, where the relative order (regarded as trend) and an occurrence sub-time whose coincides with pattern. Inspired by matching, existing (OPP) mining algorithm employs calculate support, which leads low efficiency. To address this deficiency, paper proposes called efficient OPP miner (EFO-Miner) OPPs. EFO-Miner composed four parts:...
Photoluminescent materials are widely used for information storage and anticounterfeiting, while most of them have the disadvantages static performance weak processability, which is still a challenging task in developing dynamic anticounterfeiting with high security levels. Herein, we fabricated novel photostimuli-responsive dual-emitting luminescent material UPTES-SPn-Tb-hfa, was obtained by introducing photochromic molecule spiropyran (SP) lanthanide complex (Tb-hfa) into...
Next location prediction plays an essential role in location-based applications. Many works have been employed to predict the next of object (e.g. a vehicle), given its historical records. However, existing methods not fully addressed importance contextual features, such as short-term traffic flows. In this paper, we propose deep learning-based model incorporate features into prediction. First, conduct similarity mining among candidate locations. Second, trajectories, including both...
Sequential pattern mining (SPM) with gap constraints (or repetitive SPM or tandem repeat discovery in bioinformatics) can find frequent subsequences satisfying constraints, which are called positive sequential patterns (PSPGs). However, classical cannot the missing items PSPGs. To tackle this issue, paper explores negative (NSPGs). We propose an efficient NSPG-Miner algorithm that mine both PSPGs and NSPGs simultaneously. effectively reduce candidate patterns, we a join strategy generate at...
This research focuses on developing an innovative machine learning-based intelligent optimization and recommendation system for marathon runners' personalized training schemes. The aims to provide accurate dynamically adjusted guidance athletes through real-time monitoring, effect evaluation recommendation. First, the uses advanced wearable technology achieve monitoring of multiple physiological athletic data during athlete training, including but not limited heart rate variability, lactate...