A5089981149- Advanced Chemical Sensor Technologies
- Olfactory and Sensory Function Studies
- Biochemical Analysis and Sensing Techniques
- EEG and Brain-Computer Interfaces
- Smart Agriculture and AI
- Spectroscopy and Chemometric Analyses
- Plant Disease Management Techniques
- Plant Virus Research Studies
- Plant and Biological Electrophysiology Studies
- Graphene research and applications
- Plant and animal studies
- Water Quality Monitoring and Analysis
- Meat and Animal Product Quality
- Quantum and electron transport phenomena
- Thermal Radiation and Cooling Technologies
- Plant Molecular Biology Research
- Neural Networks and Applications
- Dye analysis and toxicity
Northeast Electric Power University
2021-2025
Electric Power University
2022
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,...
The electronic tongue (e-tongue) is a bionic-based taste detection instrument that shows promising prospect for food quality classification. However, in the current research, classification with e-tongue heavily dependent on labeled training data, which time-consuming data collection practical applications and affects generalization performance of models Data augmentation can increase diversity samples, thus improving model. Therefore, this study, method e-tongue, namely, computational model...
Abstract Effective evaluation of taste sensation can be achieved by analyzing electronic tongue (e-tongue) data. Research on the an e-tongue nerve conduction mechanisms is limited, which obviously affects performance e-tongues. Therefore, in this paper, a method for evaluating based human mechanisms, computational model pathways (CMTP), proposed. However, limited physiological basis CMTP parameters influences results. To achieve excellent performance, parameter optimization algorithm with...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
The taste electroencephalogram (EEG) evoked by the stimulation can reflect different brain patterns and be used in applications such as sensory evaluation of food. However, considering computational cost efficiency, EEG data with many channels has to face critical issue channel selection. This paper proposed a selection method called class activation mapping attention (CAM-Attention). CAM-Attention combined convolutional neural network spatial (CNN-CSA) model gradient-weighted (Grad-CAM)...
For humans, taste is essential for perceiving food's nutrient content or harmful components. The current sensory evaluation of mainly relies on artificial and electronic tongue, but the former has strong subjectivity poor repeatability, latter not flexible enough. This work proposed a strategy acquiring recognizing electroencephalogram (EEG), aiming to decode people's objective perception through EEG. Firstly, according experimental paradigm, EEG subjects under different stimulation was...
Abstract Crop diseases have a significant impact on crop yields, necessitating the need for rapid and accurate detection of disease types treatment. Traditional methods suffer from complexity, inefficiency, human interference. This study proposes an optimized method to reduce computational resource consumption enhance feature learning capability.Firstly, convolutional neural network (CNN) is improved using depthwise separable group convolution (DSGC) technique easy deployment CNN in embedded...
Odor sensory evaluation has a broad application in food, clothing, cosmetics, and other fields. Traditional artificial poor repeatability, the machine olfaction represented by electronic nose (E-nose) is difficult to reflect human feelings. Olfactory electroencephalogram (EEG) contains odor individual features associated with olfactory preference, which unique advantages evaluation. However, difficulty of cross-subject EEG recognition greatly limits its application. It worth noting that...
In the food field, sensory evaluation of texture, aroma, and flavor still relies on artificial machine perception, but results by professionals are not universal, machines cannot obtain psychological information. this work, an electroencephalogram (EEG) analysis method based functional brain network was proposed, which effectively realized odor recognition pleasantness recognition. Firstly, a self-developed generator used to induce olfactory EEG, signals were collected preprocessed....
Thermionic emission is a tunneling phenomenon, which depicts that electrons on the surface of conductor can be pulled out into vacuum when they are subjected to high electrical tensions while being heated hot enough overtake their work functions. This principle has led great success so-called tubes in early 20th century. To date, major challenges still remain miniaturization channel transistor for on-chip integration modern solid-state integrated circuits. Here, by introducing nano-sized...