ICDLT

The convolutional neural network is relied upon by the mainstream image classification model to be achieved, but the convolutional neural network itself has defects such as easy loss of data. At the same time, deep learning models are vulnerable to ...

Transformer network has been widely applied in the field of computer vision. Thanks to the application of self-attention mechanism, Transformer can extract and pay attention to features at each position in the image, capturing details more accurately. ...

In this paper, with the research objective of detecting the degree of sports injury recovery with high accuracy and efficiency, an infrared thermography-based recovery detection method for sports injury is proposed. The temperature at the sports injury ...

Cracks are a typical disease form of airport pavement and highway pavement, mainly caused by heavy traffic load, complex external environment, and performance decay of road infrastructure. Pavement crack recognition technology is transitioning from ...

Accurate detection and discovery of early lung cancer is the most effective measure to reduce lung cancer mortality with high clinical value. However, existing common object detectors show unsatisfactory detection accuracy for pulmonary nodule ...

Many lightweight approaches for image super-resolution are currently unsatisfactory in their performance. To address this issue, we propose an efficient attention fusion feature extraction network (EAFFEN) for lightweight image super-resolution model. ...

Solar panels are susceptible to defects such as hot patches and cracks due to environmental and human factors, which can directly affect energy management and power generation quality if not maintained in a timely manner. Computer vision technology ...

The visual detection of transmission lines is a key component to reduce the safety hazards in energy transmission tasks. However, due to the complex background of the defect target, the small size of the target, and the slight difference between the ...

In recent years, with the introduction of graph neural networks in recommendation systems, collaborative filtering has been significantly improved, especially in handling large-scale, high-dimensional, and sparse user behavior data. Graph neural ...

In order to solve the problems of traditional ankle joint safety angle control systems, such as poor stability of the PWM control unit and low accuracy of ankle joint angle control, this paper designs the human ankle joint's safety angle optimization ...

At present, the situation of cybersecurity is becoming increasingly serious, and the study of Named Entity Recognition (NER) in the field of cybersecurity is helpful to automatically extract cybersecurity entities. It is of great significance for the ...

The VHF data exchange system is a new maritime communication system in the e-navigation strategy led by the International Maritime Organization. Among them, VDE-TER designs multiple service logical channels with different combinations of data modulation ...

Internet rumors are prevalent and harmful to society. Hence, automatic rumor detection is essential. However, supervised learning methods are impractical due to the high cost of data labeling in the early stage of rumor propagation. Moreover, rumors can ...

The data collected in current practical applications in various fields is gradually developing towards the direction of ultra-high-dimensional and large-scale, and a considerable portion of traditional analysis methods significantly reduce the ...

Stock price prediction has always been a difficult problem for investors. In the past, investors used traditional analysis methods such as candlestick charts and cross lines to predict stock trends. However, with the progress of technology and the ...

Accurately predicting the remaining useful life (RUL) of lithium-ion batteries can help us better understand and manage battery health. With the continuous development of computer technology, deep learning has gradually been applied to this field. In ...