A5100722644- Speech Recognition and Synthesis
- Bioinformatics and Genomic Networks
- Image and Video Quality Assessment
- Digital Mental Health Interventions
- Linguistics and Cultural Studies
- Statistics Education and Methodologies
- Wildlife-Road Interactions and Conservation
- Ferroptosis and cancer prognosis
- Land Use and Ecosystem Services
- Environmental Quality and Pollution
- Educational Assessment and Improvement
- Plant Parasitism and Resistance
- Machine Learning in Bioinformatics
- Misinformation and Its Impacts
- EEG and Brain-Computer Interfaces
- Anomaly Detection Techniques and Applications
- Text Readability and Simplification
- Plant-Microbe Interactions and Immunity
- MicroRNA in disease regulation
- Topic Modeling
- Civil and Geotechnical Engineering Research
- Neural and Behavioral Psychology Studies
- Advanced Computing and Algorithms
- Gene expression and cancer classification
- Mobile Crowdsensing and Crowdsourcing
China Geological Survey
2025
Tianjin Normal University
2025
First Technical University
2024
University of Ontario Institute of Technology
2022-2024
University of Science and Technology of China
2022-2023
Hangzhou Dianzi University
2022
University of Alberta
2021
Jilin University
2019
PRG S&Tech (South Korea)
2019
Abstract Motivation Deep neural network (DNN) algorithms were utilized in predicting various biomedical phenotypes recently, and demonstrated very good prediction performances without selecting features. This study proposed a hypothesis that the DNN models may be further improved by feature selection algorithms. Results A comprehensive comparative was carried out evaluating 11 on three conventional algorithms, i.e. convolution (CNN), deep belief (DBN) recurrent (RNN), recent DNNs,...
The rapid construction of expressways in China has brought significant economic and social benefits, but it also imposed substantial ecological pressures, particularly sensitive regions. Landscape risk assessment, as an important means to predict measure the adverse effects human activities on environment, is being paid more attention. However, most studies focus static landscape mosaic pattern lack dynamic analysis. Moreover, they mainly effect road operation stage, ignoring monitoring...
Background/Objectives: Switching between different tasks incurs switch costs. Previous research has demonstrated that rewards can enhance performance in cognitive tasks. However, prior studies have primarily focused on the overall improvement task performance, with limited how types of function under various conditions. This study aims to investigate distinct effects immediate and delayed conditions (repeated trials task-switching trials) explore underlying neural mechanisms, particularly...
Lung cancer is the leading cause of deaths in world and usually divided into non-small cell lung (NSCLC) small cancer. NSCLC dominant accounts for 85% total cases. Currently, therapeutic method not so satisfactory, thus identification new biomarkers critical clinical therapy this disease. Datasets miRNA gene expression were obtained from NCBI database. The differentially expressed genes (DEGs) miRNAs (DEMs) analyzed by GEO2R tools. DEG-DEM interaction was built via miRNA-targeted miRWalk....
The mental-health impact of the Covid-19 pandemic and related restrictions isolation have been immense. In this paper, we present a system designed to break down loneliness isolation, allow people share their stories, complaints, emotions, gratitude anonymously with one another. Using chatbot interface collect visitor custom visualization reveal past comments from others, Covid Connect links together through shared experiences. collected data also serves reflect experiences community...
E-commerce platforms provide entrances for customers to enter mini-apps meet their specific shopping needs. At the entrance of a mini-app, trigger item recommended based on customers' historical preferences, is displayed attract mini-app. Existing Click-Through Rate (CTR) prediction approaches have two significant weaknesses: (i) A portion customer entries driven by interest in mini-app itself rather than item. In such cases, highly hinging tend recommend similar items, thus misunderstanding...
Leticia Farias Wanderley, Nicole Zhao, Carrie Demmans Epp. Proceedings of the 2021 Conference North American Chapter Association for Computational Linguistics: Human Language Technologies. 2021.
Target Speaker Voice Activity Detection (TS-VAD) is a widely used technique for detecting the voice of target speaker in input audio stream. However, training TS-VAD model requires accurate frame-level labels indicating temporal localization speaker, which labor-intensive human-annotators especially when contains overlapping segments. We aim to investigate how train with clip-level indicate presence or absence speaker's stream, without duration information. This problem falls under category...
The collection and labeling of data is a labor-intensive task this has given rise to large market for crowdsourcing transactions. While there are many publicly available video datasets, task-specific still scarce requires Customized annotation services required. Even with excellent auxiliary models tools, lengthy time-consuming task. To address these challenges, paper provides new effective method in which the annotator no longer just annotations, but also plays role reviewer review results...