A5100767955- Air Quality Monitoring and Forecasting
- Solar Radiation and Photovoltaics
- Air Quality and Health Impacts
- Energy Load and Power Forecasting
- Soil and Unsaturated Flow
- Vehicle emissions and performance
- Machine Learning and ELM
- Traffic control and management
- Transportation Planning and Optimization
- Neural Networks Stability and Synchronization
- Traffic Prediction and Management Techniques
- Distributed Control Multi-Agent Systems
- Hydrology and Drought Analysis
- Ecosystem dynamics and resilience
- Plant Water Relations and Carbon Dynamics
- Advanced Memory and Neural Computing
- Soil Moisture and Remote Sensing
- Complex Systems and Time Series Analysis
- Electric Power System Optimization
Zhongnan University of Economics and Law
2019-2023
Jiangsu University
2018
To solve the missed and wrong detection problems of object model in identifying soybean companion weeds, this paper proposes an enhanced multi-scale channel feature based on RT-DETR (EMCF-RTDETR). First, we designed a lightweight hybrid-channel extraction backbone network, which consists CGF-Block module FasterNet-Block working together, aiming to reduce amount computation number parameters while improving efficiency extraction. Second, constructed EA-AIFI module. This enhances detailed...
There is an important significance for human health in predicting atmospheric concentration precisely. However, due to the complexity and influence of contingency, prediction a challenging topic. In this paper, we propose novel hybrid learning method make point interval predictions PM2.5 simultaneously. Firstly, optimize Sparrow Search Algorithm (SSA) by opposition-based learning, fitness-based Lévy flight. The experiments show that improved (FOSSA) outperforms SSA-based algorithms....
The randomness, nonstationarity and irregularity of air pollutant data bring difficulties to forecasting. To improve the forecast accuracy, we propose a novel hybrid approach based on two-stage decomposition embedded sample entropy, group teaching optimization algorithm (GTOA), extreme learning machine (ELM) concentration particulate matter (PM10 PM2.5). First, improvement complementary ensemble empirical mode with adaptive noise (ICEEMDAN) is employed decompose PM10 PM2.5 into set intrinsic...
In this paper, a data-driven voltage collapse predicting method is proposed based on the critical slowing down phenomenon of dynamic systems. First, model power systems with fluctuations established using stochastic differential algebraic equations. The system used to simulate operating data systems, and does not rely detailed model. Second, introduced, statistical indicators such as variance autocorrelation state variables are designed. Third, machine learning predict indicators. Finally,...
In order to explore the influence of sloping tea fields on soil water migration, this paper studied characteristics transport in moisture infiltration and redistribution under different slope gradients (0°, 5° 15°) with or without plants (Camellia Sinensis L). The results experiment showed that process infiltration, time required for infiltrate same depth varies plants. absence plants, increased first then decreased increase slope. When were planted, increasing redistribution, slope,...
This paper mainly researches the synchronization issue of discrete-time recurrent neural networks (DTRNNs) with time-varying delay based on event-triggered control (ETC). ETC can effectively decrease quantity controller updates performed and utilization communication resources. By using Lyapunov–Krasovskii functional (LKF), Schur complement lemma, discrete time free weight matrix method, linear inequalities (LMIs) other analytical methods, stability conditions error system are deduced....