A5085698884- Advanced Chemical Sensor Technologies
- Spectroscopy and Chemometric Analyses
- Olfactory and Sensory Function Studies
- Biochemical Analysis and Sensing Techniques
- Insect Pheromone Research and Control
- Gas Sensing Nanomaterials and Sensors
- EEG and Brain-Computer Interfaces
- Bone health and treatments
- Neural Networks and Applications
- Remote-Sensing Image Classification
- Meat and Animal Product Quality
- Food Supply Chain Traceability
- Bone health and osteoporosis research
- Energy Load and Power Forecasting
- Phonocardiography and Auscultation Techniques
- Machine Learning and ELM
- Advanced Algorithms and Applications
- Fuzzy Logic and Control Systems
- Water Quality Monitoring and Analysis
- Sparse and Compressive Sensing Techniques
- Image and Signal Denoising Methods
- Smart Grid and Power Systems
- Face and Expression Recognition
- Functional Brain Connectivity Studies
- Bone and Joint Diseases
Northeast Electric Power University
2015-2025
Hokkaido University
2024-2025
Electric Power University
2018-2025
Sensor Electronics (United States)
2025
University of Dental Medicine
2024
Inner Mongolia Electric Power (China)
2023-2024
Chongqing University
2024
Beihang University
2022
China Meteorological Administration
2022
Shanghai Jiao Tong University
2021
Towards developing effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by electroencephalogram (EEG), is highly demanded. Traditional works classify EEG signals without considering the topological relationship among electrodes. However, neuroscience research has increasingly emphasized network patterns dynamics. Thus, Euclidean structure electrodes might not adequately reflect interaction between signals. To fill gap, a novel deep...
High precision and fast fault diagnosis is an important guarantee for the safe reliable operation of machinery. In recent years, due to strong recognition ability, data-driven technology based on deep learning has attracted enormous attention. The module proposed by many scholars achieved excellent results, but some them are too complex deploy in practice, high costs. this article, efficient feature extraction method convolutional neural networks (CNN) was proposed, high-precision task...
The quality of soybeans from different growing areas is different. It common for low-quality to fake high-quality soybeans. This paper proposes a lightweight residual convolutional neural network (LRCNN) combined with an electronic nose (e-nose) realize soybean traceability. Firstly, obtain gas information through the e-nose. Then, according characteristics e-nose detection data, grouped heterogeneous kernel-based convolution (GHConv) proposed, which effectively reduces number parameters...
Paraffin odor intensity is an important quality indicator when a paraffin inspection performed. Currently, level assessment mainly dependent on artificial sensory evaluation. In this paper, we developed analysis system to classify and grade four kinds of samples. The original feature set was optimized using Principal Component Analysis (PCA) Partial Least Squares (PLS). Support Vector Machine (SVM), Random Forest (RF), Extreme Learning (ELM) were applied three different data sets for...
Multi-sensor data fusion can provide more comprehensive and accurate analysis results. However, it also brings some redundant information, which is an important issue with respect to finding a feature-mining method for intuitive efficient analysis. This paper demonstrates based on variable accumulation find the best expression form variables’ behavior affecting beer flavor. First, e-tongue e-nose were used gather taste olfactory information of beer, respectively. Second, principal component...
The quality of rice produced in different origins is different, and the gas reflects external sensory information rice. Based on electronic nose (e-nose) instrument, from obtained. An effective feature processing method a key issue to improve detection performance e-nose. In this work, fast pearson graph convolutional network (FPGCN) proposed identify features extracted by e-nose sensors realize origin tracking correlation coefficient (PCC) value, between quantified construct Laplacian...
At present, the sensory evaluation of food mostly depends on artificial and machine perception, but is greatly interfered with by subjective factors, perception difficult to reflect human feelings. In this article, a frequency band attention network (FBANet) for olfactory electroencephalogram (EEG) was proposed distinguish difference in odor. First, EEG evoked experiment designed collect EEG, preprocessing such as division, completed. Second, FBANet consisted feature mining self-attention,...
Heart sound is an important physiological signal that contains rich pathological information related with coronary stenosis. Thus, some machine learning methods are developed to detect artery disease (CAD) based on phonocardiogram (PCG). However, current lack sufficient clinical dataset and fail achieve efficient feature utilization. Besides, the require complex processing steps including empirical extraction classifier design. To CAD detection, we propose multiscale attention convolutional...
A synergetic strategy to extract and select the effective information of sensor signal for e-nose.
Deep learning methods have made some achievements in the automatic skin lesion recognition, but there are still problems such as limited training samples, too complicated network structure, and expensive computational costs. Considering inherent power-efficiency, biological plausibility good image recognition performance of spiking neural networks (SNNs), this paper we make malignant melanoma benign melanocytic nevi lesions classification using convolutional SNNs with unsupervised...
A short-term power load forecasting (STPLF) model based on the Improved Whale Optimization Algorithm (IWOA) optimized Kernel Extreme Learning Machine (KELM) is proposed to address problems of high randomness and low accuracy electricity loads. The KELM constructed, IWOA used optimize core penalty parameters establish IWOA-KELM model. Combined with actual data a certain region, analysis results show that convergence speed method are greatly improved compared IWOA-BP, IWOA-SVM IWOA-ELM methods.