North China University of Technology

Due to the implementation of information management in colleges, a large number of data related to student behavior are generated. How to combine the data of students' daily life to predict and classify the students as is a challenge faced by ...

With the development of computer technology, traditional computing architectures face efficiency bottlenecks when dealing with big data and complex algorithms, and amnesia shows great potential in the field of neuromorphic computing due to its unique non-...

Image super-resolution (SR) plays a vital role in vision tasks, in which Transformer-based methods outperform conventional convolutional neural networks. Existing work usually uses residual linking to improve the performance, but this type of ...

The paper proposes a novel optimal scheduling strategy for urban power grids based on the stackelberg game. The strategy can improve the utilisation efficiency of new energy generation and coordinate the balance of interests of each participant. Firstly, ...

This paper addresses the comprehensive risk measurement of new urban power grids under extreme conditions. It explores the integration of renewable energy sources like wind and solar power into urban power grids, focusing on their impact on grid stability ...

To address the issues of large voltage fluctuations and high local voltages caused by reverse power flow, due to large-scale integration of distributed renewable energy sources, like wind and solar power, into the urban distribution network, this paper ...

Inverters are the key to connecting the grid to new energy systems. Microgrid units controlled using a virtual synchronous generator (VSG) can switch between grid-connected and island modes for increased flexibility and reliability. When the big grid ...

In response to situations such as grid line faults or disconnection of distributed generator (DG).This requires that during isolated microgrid operation, frequency and voltage variations are controlled within acceptable ranges, and power is allocated ...

In order to solve the problem of image classification under different data distribution, this paper introduces a novel Principle Invariant Gradient Fusion Loss function aimed at enhancing domain generalization. By incorporating foundational principles and ...

Coronary heart disease (CHD) is one of the most prevalent cardiovascular diseases, and its its prevalent has been rising year by year. The theories of Traditional Chinese Medicine (TCM) believes that tongue image is closely related to changes in internal ...

Visual language pre-training empowers image captioning models with the capacity to describe open-world scenarios. However, this capacity is often limited, as manifested in the models’ poor performance on out-domain datasets. Since advanced models ...

In this paper, an enhanced model-free adaptive control algorithm considering time delay is proposed for the path tracking problem of autonomous vehicles. First, a path tracking mechanism based on the preview-deviation-yaw angle is proposed, which ...

Compared to traditional feature extraction methods like MFCC and FBank, self-supervised learning (SSL) based pre-trained models in automatic speech recognition (ASR) can capture deeper speech patterns and contextual information, thereby improving ...

Neural Radiance Fields (NeRF) utilizes neural networks to generate high-quality novel view images, but their rendering speed is slow. Reducing the resolution of input images can accelerate the rendering process, but it affects the quality of the ...

Aluminum electrolysis is a complex production process, and current efficiency is crucial. This paper proposes a Multi-Strategy Improved Dung Beetle Optimization Algorithm (MSIDBO) to optimize the current efficiency of aluminum electrolysis, addressing the ...

Traditional TCP congestion control algorithms, such as TCP Reno and TCP New Reno, mainly rely on packet loss signals to adjust the congestion window, which will lead to low utilization of network resources to a certain extent, especially in the network ...

When applied to nighttime driving scenarios, object detection models often experience significant performance degradation due to insufficient illumination. Existing mainstream nighttime object detection techniques either cascade multiple image ...

This study revives the Turtle Trading Rule, offering new parameters and a more stable strategy for increased profit opportunities. Proposed in the 1980s, the Turtle Trading method is a classic trend trading strategy crucial to automated systems. This ...

The planar Turán number of a graph H, denoted by e x P ( n , H ), is the maximum number of edges in an n-vertex H-free planar graph. Recently, D. Ghosh, et al. initiated the topic of double stars and prove that e x P ( n , S 2 , 5 ) ≤ 20 7 n. In ...

The fusion of LiDAR and camera sensors is extensively applied in the field of 3D reconstruction. LiDAR provides high-accuracy measurements and strong anti-interference capabilities, while cameras offer rich color and texture information. This paper ...