Search

In this paper, 1,538 papers retrieved with the keywords "sports artificial intelligence (AI)" on the Web of Science database since 2007 were taken as the data source, and the Cite Space V software was used to visualize and analyze them. A visual knowledge graph was used to streamline the countries, institutions and authors conducting sports AI research, discipline distribution, research hotspots and development trends in the past 15 years. Subsequently, its development direction and research progress were discussed. Sports AI was widely distributed, with the US, China and the UK leading the way. The most prolific authors and teams in research on sports AI were concentrated in American universities. Their main research direction is to develop and improve smart wearable devices based on machine learning and deep learning technologies for different groups of people. Research on sports AI involved multiple disciplines, which mainly applied and referred to research methodologies and theories on engineering, computer science and sports science. It could be seen from the frequency and centrality of keywords that in the current field of sports AI, machine learning is the main direction, artificial neural networks is the main algorithm, and practical and empirical research based on data mining is the focus. The research hotspots were divided into three major clusters: physical health promotion, sports injury prevention and control, and athletic performance enhancement. How to introduce intelligent technology into sports for a perfect integration still has an arduous and long way to go. Future development requires joint efforts and participation of scientific researchers, professionals and common people. [ABSTRACT FROM AUTHOR]

As the presentation form of the web, web pages contain a lot of important information in web design. As many information carriers, such as sound, graphics, and text, web pages have been integrated and have played a good role in visual transmission. It inherits many features of traditional graphic design, it can be said that it extends graphic design, and web design is richer in visual performance. At present, the research on web design in China is mainly background research. There is little research on the front-end aspects of web pages, especially in the aspect of plane vision. The lack of research in this area limits the development of web design. This paper introduces the relevant situation of web design and then analyzes the relevant elements in web design, such as visual elements, and their innovative applications. In addition, it focuses on the presentation form of visual elements in web design and summarizes the development trend of visual elements in contemporary web interface design. It proposes the strategy of innovation and application of visual elements in web design. The author hopes that, through the research of this paper, it will lay a theoretical foundation for the development of web design in the future. At the same time, this paper uses the NCMF algorithm in artificial intelligence to identify the visual elements of web pages, thereby improving the efficiency of web page design. Experiments show that the Chaos accuracy rate of the NCMF algorithm in the CETD dataset is 73.3482%. [ABSTRACT FROM AUTHOR]

With the rapid development of China's economy and the continuous optimization and improvement of Internet information technology, a new thing, new media, has emerged. On this basis, a kind of artistic behavior of creating, carrying, spreading, and appreciating is also called new media art. New media art has developed for a long time in foreign countries, but its development and popularization are relatively late in China, and it is still in a stage of improvement. As far as visual communication design is concerned, the emergence and development of new media have strongly promoted the development of its work and the dissemination of various works. Developing visual communication design based on new media art has become a key issue for all visual communication designers. Nowadays, deep learning is widely used in different fields in different ways, and image art representation is a hot research field in computer vision. Therefore, this paper mainly studies and analyzes the symbolism of new media art expression forms and proposes a new media art symbolism model based on artificial intelligence big data. In order to provide a method of real-time representation of art images, the deep learning method is used to model the artistic expression of images, and spatial reorganization of content features and style features is carried out. This paper designs simulation experiments to verify the effectiveness of the model, which can provide some help for the development and improvement of new media art in China. We compared the results of our model with a number of other models to test its effectiveness. We achieved a matching accuracy of 98.4% which is higher than or equal to the results of the existing models. [ABSTRACT FROM AUTHOR]

In this work, we introduce our project on Dunhuang cultural heritage protection using artificial intelligence. The Dunhuang Mogao Grottoes in China, also known as the Grottoes of the Thousand Buddhas, is a religious and cultural heritage located on the Silk Road. The grottoes were built from the 4th century to the 14th century. After thousands of years, the in grottoes decaying is serious. In addition, numerous historical records were destroyed throughout the years, making it difficult for archaeologists to reconstruct history. We aim to use modern computer vision and machine learning technologies to solve such challenges. First, we propose to use deep networks to automatically perform the restoration. Through out experiments, we find the automated restoration can provide comparable quality as those manually restored from an archaeologist. This can significantly speed up the restoration given the enormous size of the historical paintings. Second, we propose to use detection and retrieval for further analyzing the tremendously large amount of objects because it is unreasonable to manually label and analyze them. Several state-of-the-art methods are rigorously tested and quantitatively compared in different criteria and categorically. In this work, we created a new dataset, namely, AI for Dunhuang, to facilitate the research. Version v1.0 of the dataset comprises of data and label for the restoration, style transfer, detection, and retrieval. Specifically, the dataset has 10,000 images for restoration, 3455 for style transfer, and 6147 for property retrieval. Lastly, we propose to use style transfer to link and analyze the styles over time, given that the grottoes were build over 1000 years by numerous artists. This enables the possibly to analyze and study the art styles over 1000 years and further enable future researches on cross-era style analysis. We benchmark representative methods and conduct a comparative study on the results for our solution. The dataset will be publicly available along with this paper. [ABSTRACT FROM AUTHOR]

With the continuous development of China's economy and the improvement of residents' living standards, it also brings increasing costs of labor and rent. In addition, the impact of the pandemic on the entity industry has brought opportunities for the development of new retail models. Based on the booming development of artificial intelligence, big data, and mobile payment in the new era, the new retail industry using artificial intelligence technology has shown outstanding performance in the market. Among them, intelligent vending machines have emerged in the new retail model. In order to provide users with a good shopping experience, the product detection speed and accuracy of intelligent vending machines must be high enough. We adopt Faster R-CNN, a mature object detection algorithm in deep learning, to solve the commodity settlement scenario of intelligent vending machines. [ABSTRACT FROM AUTHOR]

The world's population has reached 8 billion and is projected to reach 9.7 billion by 2050, increasing the demand for food production. Artificial intelligence (AI) technologies that optimize resources and increase productivity are vital in an environment that has tensions in the supply chain and increasingly frequent weather events. This study performed a systemic review of the literature using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology on artificial intelligence technologies applied to agriculture. It retrieved 906 relevant studies from five electronic databases and selected 176 studies for bibliometric analysis. The quality appraisal step selected 17 studies for the analysis of the benefits, challenges, and trends of AI technologies used in agriculture. This work showed an evolution in the area with increased publications over the last five years, with more than 20 different AI techniques applied in the 176 studies analyzed, with machine learning, convolutional neural networks, IoT, big data, robotics, and computer vision being the most used technologies. Considering a worldwide scope, the countries highlighted were India, China, and the USA. Agricultural sectors included crop management and prediction and disease and pest management. Finally, it presented challenges and trends that are promising when considering the future directions in AI for agriculture. [ABSTRACT FROM AUTHOR]

In recent years, the issue of governance of the ecological environment has been a subject of high of social concern, and the challenges in the governance of smog is even more remarkable. China has accumulated a vast real-time monitoring system, which mainly obtains pollution data through national monitoring stations, providing a strong foundation for atmospheric governance. However, there are still several challenges in obtaining data from national monitoring stations, such as high cost and difficulty in comprehensive coverage. In the internet world, big data, cloud computing and other technologies are rapidly developing. It is imperative that new countermeasures counterfeit, falsify, and establish a sound long-term supervision mechanism. It is a popular research issue in academia and a policy difficulty faced by government departments. In terms of statistical models, various deep learning methods that have made major breakthroughs in the field of computer vision are used to try to obtain standardized estimates of concentration based on picture data. In general, based on the collection and arrangement of a large amount of image data over the past three years, 7 types of deep learning models have been constructed, which can achieve fast reading and accurate estimation of PM2.5 concentrations. Based on this model, we have put forward practical policy recommendations with a view to helping the early realization of smart monitoring to reduce concentration. For the standardized PM2.5 data, the minimum estimate error can reach 0.42. On this basis, we also put forward policy recommendations with practical value, with a view to helping the early realization of smart monitoring of pollutant concentrations. [ABSTRACT FROM AUTHOR]

Apical periodontitis (AP) is one of the most prevalent disorders in dentistry. However, it can be underdiagnosed in asymptomatic patients. In addition, the perioperative evaluation of 3-dimensional (3D) lesion volume is of great clinical relevance, but the required slice-by-slice manual delineation method is time- and labor-intensive. Here, for quickly and accurately detecting and segmenting periapical lesions (PALs) associated with AP on cone beam computed tomography (CBCT) images, we proposed and geographically validated a novel 3D deep convolutional neural network algorithm, named PAL-Net. On the internal 5-fold cross-validation set, our PAL-Net achieved an area under the receiver operating characteristic curve (AUC) of 0.98. The algorithm also improved the diagnostic performance of dentists with varying levels of experience, as evidenced by their enhanced average AUC values (junior dentists: 0.89–0.94; senior dentists: 0.91–0.93), and significantly reduced the diagnostic time (junior dentists: 69.3 min faster; senior dentists: 32.4 min faster). Moreover, our PAL-Net achieved an average Dice similarity coefficient over 0.87 (0.85–0.88), which is superior or comparable to that of other existing state-of-the-art PAL segmentation algorithms. Furthermore, we validated the generalizability of the PAL-Net system using multiple external data sets from Central, East, and North China, showing that our PAL-Net has strong robustness. Our PAL-Net can help improve the diagnostic performance and speed of dentists working from CBCT images, provide clinically relevant volume information to dentists, and can potentially be applied in dental clinics, especially without expert-level dentists or radiologists. [ABSTRACT FROM AUTHOR]