A5009499465- Software Testing and Debugging Techniques
- Software Reliability and Analysis Research
- Software Engineering Research
- Software System Performance and Reliability
- ECG Monitoring and Analysis
- Topic Modeling
- Remote-Sensing Image Classification
- Advanced Computational Techniques and Applications
- Higher Education and Teaching Methods
- Metaheuristic Optimization Algorithms Research
- Advanced Text Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Anomaly Detection Techniques and Applications
- Domain Adaptation and Few-Shot Learning
- EEG and Brain-Computer Interfaces
- Neural Networks and Applications
- Blind Source Separation Techniques
- Advanced Image Fusion Techniques
- Advanced Algorithms and Applications
- Time Series Analysis and Forecasting
- Advanced Malware Detection Techniques
- Multimodal Machine Learning Applications
- Remote Sensing and Land Use
- Heart Rate Variability and Autonomic Control
- Educational Technology and Assessment
Beijing University of Posts and Telecommunications
2016-2025
Peking University First Hospital
2025
Peking University
2025
Yunnan University
2023-2024
Nanjing University of Aeronautics and Astronautics
2023
Ministry of Industry and Information Technology
2023
Tongji Zhejiang College
2021
Jiyang College of Zhejiang A&F University
2021
East China Jiaotong University
2017-2021
University of California, Los Angeles
2021
In recent years, collaborative classification of multimodal data, e.g., hyperspectral image (HSI) and light detection ranging (LiDAR), has been widely used to improve remote sensing accuracy. However, existing fusion approaches for HSI LiDAR suffer from limitations. Fusing the heterogeneous features proved be challenging, leading incomplete utilization information category representation. Additionally, during extraction spatial HSI, spectral are often disjointed. It leads difficulty fully...
The prevention, evaluation, and treatment of hypertension have attracted increasing attention in recent years. As photoplethysmography (PPG) technology has been widely applied to wearable sensors, the noninvasive estimation blood pressure (BP) using PPG method received considerable interest. In this paper, a for estimating systolic diastolic BP based only on signal is developed. multitaper (MTM) used feature extraction, an artificial neural network (ANN) estimation. Compared with previous...
The cycling of iron (Fe) is often closely linked with that carbon, nitrogen, phosphorus and manganese. Therefore, alterations in the Fe cycle may be indicative concurrent overall changes biogeochemistry terrestrial aquatic ecosystems. Biogeochemical processes taking part frequently fractionate stable isotopes, leaving soil, plant other compartments ecosystems varied isotopic signatures. In this work, we reviewed isotope fractionation have been reported so far for While parent materials vary...
Abstract Background Screening of malignant hematological diseases is great importance for their diagnosis and subsequent treatment. This study constructed an optimal screening model based on routine blood cell parameters. Methods The venous samples 1751 patients collected from 10 tertiary hospitals in China were divided into a training set (1223 cases) validation (528 cases). In addition to the clinical diagnostic information set, 26 parameters including morphological selected using manual...
Bug fixing holds significant importance in software development and maintenance. Recent research has made substantial strides exploring the potential of large language models (LLMs) for automatically resolving bugs. However, a noticeable gap existing approaches lies oversight collaborative facets intrinsic to bug resolution, treating process as single-stage endeavor. Moreover, most solely take buggy code snippet input LLMs during patch generation stage. To mitigate aforementioned...
Recently, artificial intelligence techniques have been widely applied to address various specialized tasks in software engineering, such as code generation, defect identification, and bug repair. Despite the diffuse usage of static analysis tools automatically detecting potential defects, developers consider large number reported alarms expensive cost manual inspection be a key barrier using them practice. To automate process researchers utilize machine learning algorithms with set...
Atrial fibrillation (AF) is the most frequently encountered cardiac arrhythmia and often associated with other cardiovascular cerebrovascular diseases, such as ischemic heart disease, chronic failure, stroke. Automatic detection of AF by analyzing electrocardiogram (ECG) signals has an important application value. Using contaminated actual ECG signals, it not enough to only analyze atrial activity disappeared P wave appeared F in TQ segment. Moreover, best analysis method combine nonlinear...
The electrocardiogram (ECG) has become an important tool for the diagnosis of cardiovascular diseases. As long-term ECG recordings more common, driven partly by development intelligent hardware, requirement automatic analysis continues to grow. Research attempted use expert knowledge optimise ECG-related algorithms, however, visual is tedious and operator dependent. In previous studies, beat clustering approach based on self-organising maps been applied reduce amount time must spend. This...
Static analysis tools, automatically detecting potential source code defects at an early phase during the software development process, are diffusely applied in safety-critical fields. However, alarms reported by tools need to be inspected manually developers, which is inevitable and costly, whereas a large proportion of them found false positives. Aiming classifying into true positives, we propose defect identification model based on machine learning. We design set novel features variable...
It is a challenge to obtain accurate result in remote sensing images classification, which affected by many factors. In this paper, aiming at correctly identifying land use types reflec ted images, support vector machine, maximum likelihood classifier, backpropagation neural network, fuzzy c-means, and minimum distance classifier were combined construct three multiple systems (MCSs). Two MCSs implemented, namely, comparative major voting (CMV) Bayesian average (BA). One method called WA-AHP...
Currently, computational intelligence methods, especially artificial neural networks, are increasingly applied to many scenarios. We mainly attempt explore the task of fine-grained sentiment classification review data through and this is also known as aspect-based analysis (ABSA). propose a new technique called SenticGAT which multi-view features fusion model enhanced by an external database. encode information into syntactic dependency tree obtain graph with rich representation. Then we...
Heart rate variability has been proven to be an effective prediction of risk heart failure. The tradition method required manual feature extraction, thus may lead potential error. In order improve the robustness, a deep learning based on long short-term memory presented in this paper. Three RR interval length (N) for detection are used. Without pre-processing, obtain 82.47%, 85.13% and 84.91% accuracy N=50 (average time is 37. 8s), N=100 73. 9s), N=500 369. 5s), respectively. This makes it...
The increasing complexity of large-scale real-world programs necessitates the automation software testing. As a basic problem in testing, path-wise test data generation is especially important, which essence constraint optimization solved by search strategies. Therefore, processing efficiency selected algorithm key factor. Aiming at increase efficiency, hybrid intelligent proposed to efficiently solution space potential making full use both global and local methods. Branch bound adopted for...