A5044899323- Smart Agriculture and AI
- Remote Sensing in Agriculture
- Advanced Computing and Algorithms
- Context-Aware Activity Recognition Systems
- Advanced Vision and Imaging
- Speech and Audio Processing
- Music and Audio Processing
- Speech Recognition and Synthesis
- Indoor and Outdoor Localization Technologies
- Identification and Quantification in Food
- Image Processing Techniques and Applications
- Energy Efficient Wireless Sensor Networks
- Emotion and Mood Recognition
- Educational Technology and Pedagogy
Shandong Youth University of Political Science
2020-2021
Zhejiang Sci-Tech University
2012-2014
Identification and counting of rice light-trap pests are important to monitor pest population dynamics make forecast. manually is time-consuming, leads fatigue an increase in the error rate. A insect imaging system developed automate identification. This can capture top bottom images each by two cameras obtain more image features. method proposed for removing background color difference with non-pests. 156 features including color, shape texture extracted into support vector machine (SVM)...
A quantitative survey of rice planthoppers in paddy fields is important to assess the population density and make forecasting decisions. Manual planthopper methods are time-consuming, fatiguing tedious. This paper describes a handheld device for easily capturing images on stems an automatic method counting based image processing. The consists digital camera with WiFi, smartphone extrendable pole. surveyor can use control camera, which fixed front pole by photograph stems. For stems, we adopt...
This paper proposes an audio depression recognition method based on convolution neural network and generative antagonism model. First of all, preprocess the data set, remove long-term mute segments in splice rest into a new file. Then, features speech signal, such as Mel-scale Frequency Cepstral Coefficients (MFCCs), short-term energy spectral entropy, are extracted difference normalization algorithm. The matrix vector feature data, which represents unique attributes subjects' own voice, is...