A5100613787- Reinforcement Learning in Robotics
- High-Voltage Power Transmission Systems
- Advanced Sensor and Control Systems
- Wheat and Barley Genetics and Pathology
- Robotics and Automated Systems
- Vacuum and Plasma Arcs
- Industrial Technology and Control Systems
- Smart Grid and Power Systems
- Neural Networks and Applications
- Advanced Manufacturing and Logistics Optimization
- Human Pose and Action Recognition
- Genetic Mapping and Diversity in Plants and Animals
- Evolutionary Algorithms and Applications
- Domain Adaptation and Few-Shot Learning
- Image Processing Techniques and Applications
- Advanced Wireless Communication Technologies
- Transportation and Mobility Innovations
- Assembly Line Balancing Optimization
- Power Systems Fault Detection
- Grouting, Rheology, and Soil Mechanics
- Advanced Algorithms and Applications
- Robotic Locomotion and Control
- Cognitive Computing and Networks
- Technology and Security Systems
- Electrical Contact Performance and Analysis
Northwestern Polytechnical University
2023-2024
Fujian Medical University
2024
Anhui University of Finance and Economics
2024
Nanjing Agricultural University
2022-2023
China Electric Power Research Institute
2019-2022
North China Electric Power University
2019-2022
Beijing Normal University - Hong Kong Baptist University United International College
2022
Jinan University
2022
Chang'an University
2022
Western University
2022
Effective communication plays a crucial role in coordinating the actions of multiple agents. Within realm multi-agent reinforcement learning, agents have ability to share information with one another through channels, leading enhanced learning outcomes and successful goal attainment. Agents are limited by their observations ranges due increasingly complex location arrangements, making collaboration based on difficult. In this article, for some partially observable scenarios, we propose...
Structural chromosome variations (SCVs) are large-scale genomic that can be detected by fluorescence in situ hybridization (FISH). SCVs have played important roles the genome evolution of wheat (Triticum aestivum L.), but little is known about their genetic effects. In this study, a total 543 accessions from Chinese mini-core collection and Shanxi Province were used for analysis using oligonucleotide probe multiplex FISH. A 139 including translocations, pericentric inversions,...
Fhb7 is a major gene that was transferred from Thinopyrum ponticum to chromosome 7D of wheat (Triticum aestivum) and confers resistance both Fusarium head blight (FHB) crown rot (FCR). However, tightly linked the PSY-E2 gene, which causes yellow flour, limiting its application in breeding. To break this linkage, marker K-PSY developed for tagging used with markers identify recombination between two genes. Screening 21,000 BC1F2 backcross progeny (Chinese Spring ph1bph1b*2/SDAU 2028) revealed...
This paper is concerned with complex reinforcement learning tasks whose observations are difficult to characterize as appropriate inputs for policy mapping. The representation technique leveraged extract the features from optimal action generation. In literature, vector, which consists of actions in each dimension, usually learned full features. However, we find empirically that different may be only highly related small part and weakly depend on rest. Therefore, this unified strategy lead...
Electric Vehicles (EV) are environment-friendly with lower CO2 emissions, and financial affordability (in term of battery based refuel) benefits. Here, when where to recharge sensitive factors significantly impacting the environmental gains, these still challenges be tackled. In this paper, we propose a sustainable smart EV charging scheme enables preemptive functions for heterogeneous EVs equipped various capabilities brands. Our intents address problems ownerships priority, in related...
Federated learning enables a large number of clients (such as edge computing devices) to learn model jointly without data sharing. However, the high amount communication federated aggregation algorithm hinders realisation artificial intelligence in last mile. Although FederatedAveraging (FedAvg) is leading algorithm, its cost still high. The method delay and gradient sparse can reduce cost, but there no previous work analyse relationship common effects these two dimensions. Aiming at...
Dasypyrum villosum (2n = 2x 14) harbours potentially beneficial genes for hexaploid and tetraploid wheat improvement. Highly diversified chromosome variation exists among within accessions due to its open-pollination nature. The wheat-D. T6VS·6AL translocation was widely used in breeding mainly because gene Pm21 the 6VS segment conferred high lasting powdery mildew resistance. However, widespread use of this may narrow genetic base wheat. A better solution is utilize D. as source breeding....
The original red clay can be used as a construction material after being stabilized. use of the Consolid system for reinforcement has advantages green, convenient, and fast. improvement on mechanical properties durability performance was investigated enhancement mechanism revealed in terms micromorphology, pore structure, soil-water characteristics, water repellency. effects were also compared with those traditional lime cement stabilization. results show that significantly enhance clay, far...
Equivalent capacitance of thyristor used in valve the controlled metal oxide arrester (CMOA, shortly), C <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</inf> , changes with terminal voltage, ϕ . When voltage distribution CMOA is calculated, such characteristic should be considered. Combining field-circuit combination method and variable rule CT a calculation program was put forward. Firstly, electric field numerical models MOA1, MOA2 MOR were...
Machines that simultaneously process jobs in a batch and sequentially handle batches are widely used additive manufacturing such as 3D printing. This paper is concerned with the job packing scheduling problem of single-batch-processing machine under two-dimensional geometric constraints (2D-SBPM). Existing researches for 2D-SBPM based on heuristic methods, which have unsatisfactory solution quality because repeated evaluations during habitual use original rules packing. To improve...
Due to the strong cyclical and seasonal special training of vegetable products in sales process, it is very necessary develop flexible pricing marketing strategies for consumers. This paper mainly studies formulation reasonable replenishment strategy, establishes model products, reduce loss supermarket bring higher profits. Firstly, after descriptive statistics six dishes, correlation obtained by gray analysis, model, nonlinear function total cost-plus determined, LSTM predicted change,...
Abstract This study presents an innovative machine learning approach for predicting the operating stress level as a percentage of Specified Minimum Yield Strength (% SMYS) when primary pipeline properties such grade and wall thickness in steel pipelines were incomplete. becomes particularly vital where data is missing, common challenge integrity management. The parameter, % SMYS, essential classifying segments into management regulatory categories Distribution Transmission. However, missing...
The technique of behavior cloning is to equip a robot with the capability learning control skills through observation, which can naturally perform human–robot interaction. Despite many related studies in context humanoid cloning, problems unnecessary recording similar actions and more efficient storage forms than by joint angles or motor counts are still worth discussing. To reduce burden on robots, we implemented an end-to-end system, consists three modules, namely action emulation,...