A5101462600- Smart Agriculture and AI
- Underwater Vehicles and Communication Systems
- Geographic Information Systems Studies
- Big Data and Business Intelligence
- Flood Risk Assessment and Management
- Technology and Security Systems
- Hydrology and Watershed Management Studies
- Data Management and Algorithms
- Energy Load and Power Forecasting
- Data Quality and Management
- Underwater Acoustics Research
- Indoor and Outdoor Localization Technologies
- Hydrological Forecasting Using AI
- Stock Market Forecasting Methods
- Complex Systems and Time Series Analysis
Qingdao Agricultural University
2018-2024
To solve the problem where by available on-site input data are too scarce to predict level of groundwater, this paper proposes an algorithm make prediction called canonical correlation forest with a combination random features. assess effectiveness proposed algorithm, groundwater levels and meteorological for Daguhe River source field, in Qingdao, China, were used. First, results comparison among three regressors showed that is superior terms forecasting variations level. Second, experiments...
Predicting stock prices through historical data is a hot research topic. Stock price considered to be typical time series. Recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent units (GRU) have been commonly employed handle this type of data. However, most studies focus on the analysis individual stocks, thus ignoring correlation between similar stocks in entire market. This paper proposes clustering method for mining which combines morphological similarity...
Acquiring channel state information and mitigating multi-path interference are challenging for underwater acoustic communications under time-varying channels. We address the issues using a superimposed training (ST) scheme with least squares (LS) based estimation algorithm. The sequences small power linearly symbol sequences, signals transmitted over all time, resulting in enhanced tracking capability to deal channels at cost of only loss. To realize full potentials ST scheme, we develop LS...
Agricultural big data is growing rapidly and it faces many known unknown obstacles. This paper focuses on the need for managing farms effectively making decisions accurately. Using agricultural IoT technology, technology machine learning algorithms, application system established. Including collection, storage, analysis visualization management, we present a complete scheme. Through system, production cost reduced efficiency improved.
Semantic Spatial Trajectories are formed when trajectory locations with location or POI (point of interest) names and sentiment text attached to the POIs; these data a map behind as base. The release may violate privacy persons even anonymity for real aid in violating privacy. We consider releasing adjusted instead data, give how be adjusted, which can base choice assurance semantic spatial trajectories release.