A5083300528- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- Machine Learning in Bioinformatics
- Radiomics and Machine Learning in Medical Imaging
- Cytokine Signaling Pathways and Interactions
- Evolutionary Algorithms and Applications
- AI in cancer detection
- Face and Expression Recognition
- Machine Learning in Healthcare
- Cancer-related gene regulation
- HER2/EGFR in Cancer Research
- Metaheuristic Optimization Algorithms Research
- MicroRNA in disease regulation
- Parasitic infections in humans and animals
- Topic Modeling
- COVID-19 diagnosis using AI
- Amoebic Infections and Treatments
- Vehicle Dynamics and Control Systems
- Advanced Measurement and Detection Methods
- Artificial Intelligence in Law
- Neural Networks and Applications
- Hydraulic and Pneumatic Systems
- Lung Cancer Treatments and Mutations
- Computational Drug Discovery Methods
- Advanced Image and Video Retrieval Techniques
Northeastern University
2020-2024
Fuzhou University
2024
Universidad del Noreste
2021-2023
Hengshui University
2022
Tsinghua University
2022
Tsinghua–Berkeley Shenzhen Institute
2022
Eastern University
2021
Northeastern University
2021
Ajuntament de L’Hospitalet
2020
Italian Society of Physiotherapy
2020
Abstract Reservoir computing has attracted considerable attention due to its low training cost. However, existing neuromorphic hardware, focusing mainly on shallow-reservoir computing, faces challenges in providing adequate spatial and temporal scales characteristic for effective computing. Here, we report an ultra-short channel organic vertical transistor with distributed reservoir states. The carrier dynamics used map signals are enriched by coupled multivariate physics mechanisms, while...
The selection of critical features from microarray data as biomarkers holds significant importance in disease diagnosis and drug development. It is essential to reduce the number while maintaining their performance effectively minimize subsequent validation costs. However, processing often encounters challenge “curse dimensionality”. Existing feature-selection methods face difficulties reducing feature dimensionality ensuring classification accuracy, algorithm efficiency, optimal search...
As the number of modalities in biomedical data continues to increase, significance multi-modal becomes evident capturing complex relationships between biological processes, thereby complementing disease classification. However, current fusion methods for require more effective exploitation intra- and inter-modal interactions, application powerful is relatively rare. In this paper, we propose a novel method that addresses these limitations. Our proposed utilizes graph neural network 3D...
In view of the performance requirements (e.g., ride comfort, road holding, and suspension space limitation) for vehicle systems, this paper proposes an adaptive optimal control method quarter‐car active system by using approximate dynamic programming approach (ADP). Online law is obtained a single critic NN to solution Hamilton‐Jacobi‐Bellman (HJB) equation. Stability closed‐loop proved Lyapunov theory. Compared with classic linear quadratic regulator (LQR) approach, proposed ADP‐based...
In recent years, the discovery of clinical pathways (CPs) from electronic medical records (EMRs) data has received increasing attention because it can directly support doctors with explicit treatment knowledge, which is one key challenges in development intelligent healthcare services. However, existing work focused on topic probabilistic models, usually produce patterns similar activities, and such discovered do not take into account temporal process patient does meet needs practical applications.
The discovery of critical biomarkers is significant for clinical diagnosis, drug research and development. Researchers usually obtain from microarray data, which comes the dimensional curse. Feature selection in machine learning used to solve this problem. However, most methods do not fully consider feature dependence, especially real pathway relationship genes.Experimental results show that proposed method superior classical algorithms advanced number accuracy, selected features have more...
Design of an advanced automatic inspection system for aircraft parts based on luorescent penetrant analysisNon-destructive testing (NDT) has become increasingly important in improving the safety and reliability aerospace industry, especially high-temperature high-pressure turbine engine parts.Among various types NDT methods available, (FPI) is comparably more cost-eicient widely used parts.However, current FPI still requires considerable labour forces its processing, analysis procedures.In...
In bioinformatics, the rapid development of gene sequencing technology has produced an increasing amount microarray data. This type data shares typical characteristics small sample size and high feature dimensions. Searching for biomarkers from data, which expression features various diseases, is essential disease classification. selection therefore became fundemental analysis designs to remove irrelevant redundant features. There are a large number in severely degrade classification...
Abstract Background Finding significant genes or proteins from gene chip data for disease diagnosis and drug development is an important task. However, the challenge comes curse of dimension. It great significance to use machine learning methods find features build accurate classification model. Results The proposed method has proved superior published advanced hybrid feature selection traditional on different public microarray sets. In addition, biomarkers selected using our show a match...