The application of construction robots is crucial to mitigate challenges faced by the construction industry, such as labor shortages and low productivity. Reinforcement learning (RL) enables robots to take actions based on observed states, improving ...

We propose TEA-bot (Thermography Enabled Autonomous Robot) to address the problem of labor-intensive manual inspections of thermal leaks in Heating Ventilation and Air Conditioning (HVAC) systems while avoiding installation of sensor networks, which can ...

The competition among Chinese coastal ports is becoming increasingly fierce, but the means of low-price competition is not conducive to the healthy and sustainable development of ports. It is necessary to improve the level of customer relationship ...

Semantic segmentation of remote sensing (RS) images plays a vital role in a variety of fields, involving urban planning, natural disaster monitoring, and land resource management. Due to the complexity and low resolution of RS images, many approaches have ...

Deep learning is the most popular method in the field of artificial intelligence, and a faster way to study deep learning is to generate admissible neural network. The generative adversarial network is a learning network which is composed of the ...

Aiming at the problem of high computational complexity and accuracy of dynamic gesture recognition, this paper proposes a multi-feature fusion dynamic gesture recognition based on improved EfficientNet[1] model. Firstly, for each video data set, video ...

Kronecker-factored Approximate Curvature (K-FAC) has recently been shown to converge faster in deep neural network (DNN) training than stochastic gradient descent (SGD); however, K-FAC's larger memory footprint hinders its applicability to large models. ...

The routing-by-agreement mechanism in capsule networks (CapsNets) is used to build visual hierarchical relationships with a characteristic of assigning parts to wholes. The connections between capsules of different layers become sparser with more ...

Since 2019, China's urbanization rate has exceeded 60%. Cities are densely populated, economically developed, and highly concentrated areas of social wealth. With global warming, the frequency of extreme weather impacts on cities has increased. For the ...

The one-way running time of the bus has been paid a lot of attention especially for passengers to decide their travels and for bus companies to make schedules. Recent research provide some machine learning algorithms for the prediction of similar topics,...

Blockchain technology is characterized by decentralization, traceability and tamper resistance. A decentralized application (Dapp) refers to a blockchain-based application deployed on Ethereum platform, with the aim to facilitate decentralized smart ...

While the computational power of modern supercomputers has risen tremendously in recent years, user’s I/O work (read, write, open, close, etc.) has increased correspondingly. As a result of the high I/O load, these jobs often overwhelm the ...

With the increasing adoption of containerization among HPC applications and workflows to achieve the ever-increasing demand in portability, flexibility, and customizability, the IO pattern and workload from such an isolated environment have evolved ...

Academic social networks are profoundly influencing and changing the way researchers connect with each other, share information and collaborate during innovation. Their value is becoming more and more obvious. However, research on academic social ...

User mobility is an intrinsic trait of many MEC applications, which has posed significant challenges for realizing reliable computing. However, existing works studying this problem mainly focus on the movements of users while another high-dynamic ...

This paper addresses the problem of authenticating the transmitter device in wirelessly powered communications networks (WPCNs). We proposed a physical-layer authentication scheme for a WPCN. In comparison with upper-layer authentication schemes, the ...

The forecast of port throughput can not only provide a basis for the business plan of the enterprise, but also provide a reference for the construction of transportation facilities in the city where the port is located. Gated Recurrent Unit (GRU), as ...

Training neural networks with many processors can reduce time-to-solution; however, it is challenging to maintain convergence and efficiency at large scales. The Kronecker-factored Approximate Curvature (K-FAC) was recently proposed as an approximation ...

Person re-identification (ReID) has recently received extensive research interests due to its diverse applications in multimedia analysis and computer vision. However, the majority of existing works focus on improving matching accuracy, while ignoring ...

Due to the popularity of electric vehicles and the "range anxiety" problem caused by insufficient range of electric vehicles, accurate range estimation of electric vehicles is of great significance. This paper proposes a fusion method for range ...