ICIAI

As the use of manual inspection of the power system is time-consuming and laborious, the use of UAV to patrol the power system also arises at the historic moment. However, the UAV inspection system is easy to deviate from the preset route due to ...

With the continuous development of artificial intelligence, autonomous driving technology is becoming more and more mature. The accuracy and real-time judgment of road conditions in autonomous driving technology are very important. In autonomous driving,...

Directly benefiting from the deep neural network, object detection algorithm has played a key role in industrial automation in recent years. Computer motherboard component detection is essential in the industrial automation of computer assembly or ...

Printed circuit boards are an important part of electronic products. Ensuring the quality of printed circuit boards is an important task. Traditional target detection methods require cropping of the image, which leads to poor real-time detection and ...

While object detection has made substantial progress in medical image anomaly identification, the deep learning method fails to extract breast cancer images' hidden features. We thus applied traditional image processing techniques, such as high-boost ...

In order to realize efficient fault recognition and utilization of the high-speed train (EMU) undercarriage image obtained by detection robot, image alignment technology play an important role. Firstly, research the original image data collection ...

In low-light conditions, images captured by marine imaging equipment suffer from degradation problems like low brightness and colour distortion. Most existing low light enhancement methods are not well to restore detailed information. To address this ...

Recent developments of deep neural networks based image classification have attracted much attention because of their top performance. However, the volume of data for training seriously affected the classification effect of neural networks, thus it ...

We present a spectrum-based framework, utilizing low and high spectral latent features, to colorize the grayscale image. Current image colorization algorithms, despite significant achievements, constantly struggle with color bleeding and low color ...

Due to the existence of atmospheric particles in the air (such as dust, colloids, raindrops, etc.), the quality of images taken in outdoor scenes is usually poor, and the visual effect will decline a lot. The phenomena caused by the absorption and ...

Aiming at the problem that the LDA model is not effective for short text topic extraction, this paper proposes a topic detection method based on BERT and seed LDA clustering model. Firstly, the seed LDA model (sLDA) is designed for optimize the LDA ...

In the background of low carbon power, accurate prediction of carbon emission intensity and carbon emission source percentage of the power system can provide data support for carbon emission optimization strategy to achieve effective reduction of carbon ...

Even though sophisticated deep learning methods are getting better and better day by day, still they rely on a large number of datasets. But it is not always possible to acquire large datasets for all kinds of problems. Though diffusion models are now ...

The Chinese Named Entity Recognition (CNER) is difficult to classify words accurately because of the lack of natural separators. Character embedding can effectively avoid the cumulative errors caused by word division, but carries relatively insufficient ...

In this paper, we use the Apriori algorithm as the core idea to establish a highly reusable and high-degree-of-freedom human factor correlation analysis model to better guide the development of the ice and snow sports market. We first normalized the ...

With the gradual advancement of Internet technology, green and intelligent furniture is produced which makes people's living standard improve gradually, and people gradually start to use smart home products, and the market scale of smart home is ...

Based on the problem that the value of enterprise evaluation index fluctuates greatly at present, this paper uses LSTM neural network combined with data analysis to analyze and calculate the data according to the provided data sets of different ...

In recent years, global warming and the frequent occurrence of extreme weather have raised concerns about global climate change. With the advent of big data and information technology era, it has improved more scientific technical support for ...

The application of Train of EMU failures Detection System (TEDS) ensures the running safety of EMU. In order to reduce the manual workload and meet the requirements of fine classification monitoring, we researched the automatic classification technology,...

In the last few years, there has been growing recognition of the vital links between visual tracking and unmanned aerial vehicle (UAV). Questions have been raised about the feasibility of CNN-based and transformer-based trackers on UAVs. However, deep ...

Reasonably arranging the operation scheme of EMU maintenance line is the key link in the operation organization of EMU Depot. Considering the characteristics of the maintenance line utilization, on the premise that the time of EMU occupying the ...

Spiking neural networks (SNNs) obtain impressive good performance on various applications due to their powerful computing capacity for encoding spatio-temporal information. However, most existing spiking neural networks remain shallow structures, ...

The main research of this paper is to design a multi-sensor fusion-based vehicle localisation algorithm. In order to achieve long-term robust and drift-free attitude estimation in autonomous driving, this paper proposes a method to fuse global position ...

The flight and take-off mechanism of pterosaurs remains a mystery. Currently, the flight mechanism of pterosaurs exists only in the imaginary stage. To study the flight mechanism of pterosaurs, a dynamic model of pterosaur flight was developed to ...

Joint entity and relation extraction is an important research topic in natural language processing. However, the current work cannot clearly identify the boundaries of entity and relation when solving the triple overlapping problem where triple share ...

End-to-End speech translation means that using a model to translate speech in one language into text in another language. Currently, the main challenge in the field of speech translation is data scarcity. Existing works solve this problem by using text ...

Biomedical Named Entity Recognition (BioNER) is one of the basic tasks of biomedical text mining. In reality, the labeled biomedical data is relatively limited, there is a lack of large enough training data to train a strong model, and manual labeling ...

Offline reinforcement learning, also known as batch RL, promises to learn policies effectively from previously collected datasets without exploration. But lack of interaction with the environment continually brings the distribution shift between the ...

As the problem of marine pollution is becoming more and more serious, this paper starts from the problem of marine floating debris treatment and aims at the problem of path planning for the treatment area and proposes a marine floating debris treatment ...