Zhiqiang Wei

ORCID: 0000-0002-6965-0162
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • EEG and Brain-Computer Interfaces
  • ECG Monitoring and Analysis
  • Image Retrieval and Classification Techniques
  • Advanced Image and Video Retrieval Techniques
  • Nanomaterials for catalytic reactions
  • Bariatric Surgery and Outcomes
  • Diet and metabolism studies
  • Non-Invasive Vital Sign Monitoring
  • Graphene and Nanomaterials Applications
  • Advanced Nanomaterials in Catalysis
  • Adsorption and biosorption for pollutant removal
  • Multimodal Machine Learning Applications
  • Machine Learning in Bioinformatics
  • Food Supply Chain Traceability
  • Domain Adaptation and Few-Shot Learning
  • Body Contouring and Surgery
  • 3D Shape Modeling and Analysis
  • Immune Response and Inflammation
  • Plant chemical constituents analysis
  • Vestibular and auditory disorders
  • Intelligent Tutoring Systems and Adaptive Learning
  • Botanical Studies and Applications
  • Image and Video Quality Assessment
  • Conducting polymers and applications
  • Ferroptosis and cancer prognosis

Ocean University of China
2010-2025

Jilin University
2024-2025

Shaanxi University of Science and Technology
2022-2025

Qingdao University
2025

Jilin Medical University
2024

Union Hospital
2024

Longgang Central Hospital
2024

Peking University Shenzhen Hospital
2022

Nanjing Forestry University
2020

Beijing University of Chinese Medicine
2020

ECG is a non-invasive tool used to detect cardiac arrhythmias. Many arrhythmias classification solutions with various features have been reported in literature. In this work, new method combined novel morphological feature proposed for accurate recognition and of First, the events signals are detected. Then, parametric morphology, i.e., amplitude, interval duration, extracted from selected regions. Next, analyzing QRS complex morphology changes as visual patterns well clustering-based...

10.1109/access.2020.2979256 article EN cc-by IEEE Access 2020-01-01

Abstract Using amino acid residues in peptide generation has solved several key problems, including precise control of sequence order, customized peptides for property modification, and large-scale synthesis. Proteins contain unknown residues. Extracting them the synthesis drug-like can create novel structures with unique properties, driving drug development. Computer-aided design molecules solve high-cost low-efficiency problems traditional discovery process. Previous studies faced...

10.1093/bib/bbae444 article EN cc-by-nc Briefings in Bioinformatics 2024-07-25

10.1109/jstars.2025.3534474 article EN cc-by IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025-01-01

Visual question answering (VQA) is a challenging task that requires models to understand both visual and linguistic inputs produce accurate answers. However, VQA often exploit biases in datasets make predictions rather than reasoning based on the inputs. Prior approaches debiasing have suggested implementation of supplementary model, deliberately designed exhibit bias, which subsequently informs training resilient target model. Nevertheless, such techniques merely quantify model’s divergence...

10.1145/3715141 article EN ACM Transactions on Multimedia Computing Communications and Applications 2025-01-30

Red pigment (RP) was extracted from the peels of Zanthoxylum bungeanum Maxim (PZB) by ultrasonic-assisted extraction (UAE) in this work. Box⁻Behnken design⁻response surface methodology (BBD-RSM) employed to research efficiency RP extraction. Based on optimization RSM, results showed that optimal conditions were as follows: liquid⁻solid ratio 31 mL/g, time 41 min, and temperature 27 °C, under these conditions, actual absorbance value 0.615 ± 0.13%, highly agreeing with predicted model....

10.3390/molecules23051109 article EN cc-by Molecules 2018-05-08

Monochamus alternatus is an important insect pest in pine forests of southern China and the dispersing vector wood nematode, Bursaphelenchus xylophilus, which leads to wilt disease (PWD). Microbiome M. may contribute survival larvae host trees. In order investigate intestinal bacterial structure during pupae stages trees, infer function symbiotic bacteria, we used 16S rRNA gene Illumina sequencing obtain compare community composition foregut, midgut, hindgut larvae, pupal intestines, larval...

10.3390/insects11060376 article EN cc-by Insects 2020-06-17

Endothelial cells (ECs) play a vital role in promoting the progression of malignant cells, and they exhibit heterogeneity their phenotypic characteristics. We aimed to explore initiating ECs osteosarcoma (OS) investigate potential interaction with cells.We obtained scRNA-seq data from 6 OS patients, datasets were batch-corrected minimize variations among samples. Pseudotime analysis was performed origin differentiation ECs. CellChat employed examine communication between endothelial gene...

10.3389/fonc.2023.1200203 article EN cc-by Frontiers in Oncology 2023-05-03

Abstract To evaluate the efficacy and nutrition of single-anastomosis duodenal-ileal bypass with sleeve gastrectomy (SADI-S) in Chinese obese patients first postoperative year. Clinical data 66 who underwent SADI-S surgery at China-Japan Union Hospital Jilin University from November 2018 to May 2022 were retrospectively collected. The weight, body mass index (BMI), percentage excess weight loss (%EWL), total (%TWL) recorded 3, 6, 12 months after surgery. Moreover, metabolic disease remission...

10.1038/s41598-024-57289-3 article EN cc-by Scientific Reports 2024-03-19

High dropout rate of MOOC is criticized while a dramatically increasing number learners are appealed to these online learning platforms. Various works have been done on analysis and prediction dropout. Machine techniques widely applied this field. However, single classifier may not always perform reliable for predictions. In work, we study MOOC. A technique proposed predict dropouts using activity information learners. We two-layer cascading with combination three different machine...

10.1109/iccse.2017.8085583 article EN 2017-08-01

Abstract This study aimed to retrospectively analyze the perioperative and postoperative follow-up data of patients with super obesity who had undergone RYGB, SG, BPD/DS, SADI-S. A retrospective observational was conducted 60 bariatric surgery. total 34 men 26 women were included in this study. The participants an average preoperative BMI 53.81 ± 3.25 kg/m 2 . body weight all four patient groups decreased significantly at 3, 6, 12 months postoperatively compared values. Additionally, TWL (%)...

10.1038/s41598-024-60983-x article EN cc-by Scientific Reports 2024-05-07

In this study, a new approach using novel ensemble classification algorithm based on ECG morphological features is proposed for accurate detection of heart ventricular and atrial abnormalities. First, the raw signal preprocessed main character waves are detected. Second, combination extracted from selected segments. The feature set contains parameters, visual pattern QRS complex, principle components third level fourth four-level Sym8 wavelet-decomposed waveform. Next, algorithm, with key...

10.1109/access.2021.3071273 article EN cc-by IEEE Access 2021-01-01

Osteoarthritis (OA) is a metabolic disorder and able to be relieved by traditional Chinese medicines. However, the effect of Ligusticum wallichii on OA unknown.Cytokine IL-1β L. extracts were used stimulate primary mouse chondrocytes. MTT assay was measure cell viability. The mRNA protein level each gene test qRT-PCR western blotting, respectively. rate apoptotic measured flow cytometry. GC/MS-based metabolomics utilized characterize variation metabolome.Here, we found that attenuated...

10.1186/s13020-020-0295-0 article EN cc-by Chinese Medicine 2020-02-01

Purpose: To compare the effects of raw hawthorn (RH) and charred (CH) on functional dyspepsia (FD) intestinal flora (IF).Methods: A rat model FD was established through use a chronic stimulator. Rat models were evaluated by rat's physical state, body weight, diet, histopathological examination. After RH or CH administration, digestive function rats determining gastric emptying propulsion rate, diversity flora.Results: both improved rate in group when compared to control (p < 0.05). yielded...

10.4314/tjpr.v18i2.16 article EN cc-by Tropical Journal of Pharmaceutical Research 2019-03-12

Food safety events occur frequently due to kinds of reasons. Thus build an aquatic product traceability system is imperative. Many countries have already established food system. However, existing solutions can not be applied directly in the because a set requirements. According particularity breeding, this paper put forwards integrated RFID technology. The covers with entire life-circle seafood. To solve data sharing, presents model using distributed database. On basis, analyzes SFP...

10.1109/icsess.2010.5552384 article EN 2010-07-01

<title>Abstract</title> <bold>Background </bold>As a modification of the duodenal switch (DS), single-anastomotic ileo-ileal bypass combined with sleeve gastrectomy (SADI-S) has recently gained popularity and been successfully employed for weight loss remission type 2 diabetes mellitus (T2DM). However, current studies predominantly focus on patients severe obesity. <bold>Objectives </bold> In this study, we present first comparison duodenoileal (SG) mid-term treatment Chinese diabetic BMI...

10.21203/rs.3.rs-5658350/v1 preprint EN cc-by Research Square (Research Square) 2024-12-30

Drug-target affinity prediction is a key challenge in the drug discovery process. Recent advances have demonstrated great potential of deep learning predicting affinities; however, existing approaches learn representation drug-target complex insufficiently, leading to suboptimal performance. Here, we propose Multiscale Hybrid Attention Network for Drug-Target Affinity prediction, named MHAN-DTA, which aims address problem insufficient feature mining thereby improving To empower model with...

10.1109/jbhi.2024.3518619 article EN IEEE Journal of Biomedical and Health Informatics 2024-01-01

Understanding the function of proteins is great significance for revealing disease pathogenesis and discovering new targets. Benefiting from explosive growth protein universal, deep learning has been applied to accelerate annotation cycle different biological modalities. However, most existing learning-based methods not only fail effectively fuse modalities, resulting in low-quality representations, but also suffer convergence suboptimal solution caused by sparse label representations....

10.1038/s42003-024-07411-y article EN cc-by-nc-nd Communications Biology 2024-12-27
Coming Soon ...