A5030348380- Hydrological Forecasting Using AI
- ECG Monitoring and Analysis
- Emotion and Mood Recognition
- Non-Invasive Vital Sign Monitoring
- Pulsars and Gravitational Waves Research
- GNSS positioning and interference
- Meteorological Phenomena and Simulations
- Technology and Human Factors in Education and Health
- Heart Rate Variability and Autonomic Control
- Hydrology and Watershed Management Studies
- Mental Health Research Topics
- Astronomical Observations and Instrumentation
Sichuan University
2025
Central University of Finance and Economics
2023
Southeast University
2022
South Dakota School of Mines and Technology
2021
Objective.This paper presents a novel dual-branch framework for estimating blood pressure (BP) using photoplethysmography (PPG) signals. The method combines deep learning with clinical prior knowledge and models different time periods (morning, afternoon, evening) to achieve precise, cuffless BP estimation.Approach.Preprocessed single-channel PPG signals are input into two feature extraction branches. first branch converts dimensions 2D uses pre-trained Mobile Vision Transformer-v2...
Abstract The detection of pulsar signals is a highly intensive task. Numerous artificial intelligence (AI) and machine learning techniques (ML) have been proposed to classify non-pulsar signals. While existing improve classification efficiency, these methods are limited when it comes dealing with large volumes astronomical data, the extreme problem class imbalance , polarization high recall precision. In this paper, accurately signals, Gradient Boosting (XgBoost), Light Machine (LightGBM)...
To detect the psychological abnormality of college students, we used big data technology and a machine learning algorithm. The questionnaire star was to collect collected were pre-processed for selection cleaning. six attributes related abnormalities extracted according correlation coefficient. support vector (SVM) detection warning model constructed, parameters determined obtain best effect. accuracy SVM in detecting abnormal status reached 95%, which better than that other methods. Hence,...