All of the articles in this proceedings volume have been presented at the DAI 2023 during November 24–26 in Shanghai. These articles have been peer reviewed by the members of the Academic Committee Members and approved by the Editor-in-Chief, who affirms that this document is a truthful description of...

A stock trading strategy refers to a structured approach used to make informed decisions in buying, selling, or holding stocks in financial markets. These strategies play a crucial role in maximizing returns while managing risk. Over the years, trading strategies have transitioned from being expert-driven,...

Continuous systems are physical systems that can be stimulated by continuous and analog variables. The parameters or variables are within a range of values. An excellent continuous controlling policy enables the system to act appropriately and smoothly without much intervention, which can be useful in...

Population ageing has become a challenge faced by most developing countries in recent years, and for developing countries where agriculture is the supporting industry, the need for a large number of labourers to carry out agricultural operations is an inevitable requirement for the long-term stable development...

The electrical or mechanical translation of pictures of typed, handwritten, or printed text into machine-encoded text is known as optical character recognition (OCR). Pattern recognition, artificial intelligence, and computer vision are all areas of study in OCR. Early iterations operated on one typeface...

Due to their ability to automatically extract features, Deep Neural Networks (DNNS) have demonstrated performance never before seen. Due to this high degree of performance during the past ten years, a considerable number of DNN models have been combined with various Internet of Things (IoT) applications....

Sleep helps our body recover and wake up full of power. It is also the time when we are growing, both physical and mental. Unfortunately, sleep disorders can prevent individuals from getting adequate rest. 27% of the population in the world have sleep disorders. This can affect their daytime activities....

With the rapid development of science and technology, computers have been able to calculate faster than humans. For huge databases, machine learning can organize and analyze them faster than humans, and calculate them quickly through mathematical and physical models. Therefore, this study examines how...

As artificial intelligence and machine learning become more and more advanced nowadays, they have been used in vast fields. As a fundamental and mature topic, housing price prediction remains popular among machine learning workers and researchers. Housing price prediction can contribute a lot to the...

With the rapid development of sensor technology and machine learning, the performance and function of robots have been continuously improved, and then they have been applied in many fields. In the research of tracking robots, computer vision technology can be used to identify and track objects, helping...

Due to the rapid development and maturity of pipeline transportation systems in the oil and gas industry, in-pipe robots have become an important means of daily pipeline inspection and maintenance. Under the requirements of special transportation media and extremely serious accident consequences, the...

Welding defect detection is one of the research hotspots in the field of welding. Some researchers have found that in many welding processes, due to some uncontrollable factors, the weld will have different degrees of defects. These defects often cause great harm to production and life. This makes the...

Additive manufacturing (AM) is a new digital and environmentally friendly manufacturing technology developed in the past 30 years. It has the advantages of saving energy consumption, saving material consumption, rapid manufacturing of products with complex structures and the ability to produce small...

With the increasing automation and intelligence of welding robots, new requirements and higher precision standards have been put forward for the welding process of workpieces with complex structures in various welding environments. Robot vision sensing technology is an important foundation for developing...

With the arrival of Industry 4.0 era, traditional manufacturing industry has faced huge challenges. Compared to traditional industrial robots, a new type of industrial robot - collaborative robot - can better promote the development of traditional manufacturing towards automation. Among them, China’s...

For the past few years, with the development of smart grid and Industry 4.0 concepts, global industrial development has continued to accelerate, followed by a substantial increase in the demand for electricity by users. As a result, there is a sharp rise in the number of electrical equipment and electrical...

Reinforcement learning has emerged as a powerful approach for tackling complex continuous control tasks across various domains. This paper presents an extensive comparative analysis of two prominent reinforcement learning algorithms: the Deep Deterministic Policy Gradient (DDPG) algorithm and its advanced...

Reinforcement Learning is widely applied in the field of virtual agent training, enabling them to accomplish specific tasks. The agent is trained to navigate and collect yellow bananas in a large, square world that contains many yellow bananas and blue bananas. The goal is to allow agents to collect...

The financial industry has always considered stock market forecasting to be vital. In recent years, the application of reinforcement learning techniques in stock market prediction has gained attention. This study aims to explore using Deep Q-Networks (DQN) and Double Deep Q-Network (DDQN) for stock market...

Sports image classification is a challenging task that involves multiple types of sports, with difficulties in feature recognition and suboptimal detection results. This study employs four pretrained models, namely Residual Network 50 (ResNet-50), EfficientNet B7, Densely Connected Convolutional Network...

The Lunar Lander problem presents a formidable challenge in the realm of reinforcement learning, necessitating the creation of autonomous spacecraft capable of safe landings on the lunar surface. In this study, three prominent reinforcement learning algorithms, namely Deep Q-Network (DQN), Double Deep...

The development of a stock trading strategy holds significant importance inside investing organizations. Investors can enhance their trading performance and attain their financial objectives by comprehending market behaviour, creating returns, effectively managing risk, and making well-informed judgments....

In this work, the performance of two value-based reinforcement learning algorithms is evaluated in the cliff walking problem, including State-Action-Reward-State-Action (SARSA) and Q-learning. This paper uses Python language and Numpy library to implement SARSA and Q-learning algorithms, and compares...

To solve problems involving sequential decision-making, Deep Reinforcement Learning (DRL) combines the advantages of Reinforcement Learning (RL) and Deep Learning (DL). These fusions are skilled at training agents for video games because they use neural networks to approximate nonlinear functions. The...

Reinforcement learning (RL) has made significant advancements in training artificial agents to play video games. Among various RL algorithms, the deep Q-network (DQN) based on Q-learning has shown outstanding performance in this domain. Recently, dueling DQN, as an enhancement to the standard DQN, has...

Reinforcement learning (RL) has recently gained significant attention due to the impressive successes of self-driving cars and human-like performance in games such as Go or StarCraft. However, approaching this subject can be intimidating. In this research, the author aims to explore how to train a RL...

As a matter of fact, the digital representation of musical instruments has long been a challenge for researchers, with the violin being one of the most complex due to its expressive nature and intricate timbre. This study delves into the synthesis of a digital violin, aiming to reproduce its rich sound...

Image matching holds fundamental significance in varieties of applications in CV (computer vision)., demanding methods that strike a balance between speed and robustness. This paper introduces an image matching approach built upon an improved version of the FAST (Features from Accelerated Segment Test)...

Forecasting oil prices is crucial for various industries and economic decision-making. This abstract explores the application of the fbprophet library for accurate and reliable oil price predictions. Fbprophet, developed by Facebook’s Core Data Science team, offers a user-friendly interface for time...

This paper provides a comprehensive review of the development, challenges, and future prospects of machine translation. It covers the evolution from rule-based systems to neural machine translation (NMT) models, using recurrent neural networks (RNNS) and convolutional neural networks (CNNS) as examples...

Target tracking is a crucial research area in computer vision, with increasing demand for real-time monitoring and intelligent interaction. Algorithms for target tracking have evolved from traditional feature matching methods to modern deep neural networks, reinforcement learning, and model-based approaches....

Sometimes people are unable to accurately express their views on a certain product, which may limit in accurately describing emotions. Facial emotion recognition can help solve the problem of people being unable to accurately express their opinions on products, by analyzing facial expressions to obtain...

With the upgrading of online shopping software, intelligent recommendation systems have emerged in various software and become the main recommendation engine of contemporary times. This article outlines the construction of an all-encompassing recommendation system, drawing inspiration from prior collaborative...

Recommendation systems are gaining increasing popularity in today’s society, aiming to cater to users’ potential preferences for the convenience of users and as part of businesses’ commercial strategies. Just as product recommendations have proven effective, location recommendations are also becoming...

In recent years, advances in image restoration have prominently featured Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs). Specifically, in seismic image denoising, the DnCNN model, rooted in CNN, employs residual learning combined with batch normalization for a streamlined...

COVID-19 is a contagious disease, with tens of millions of people worldwide infected. Taking Chest X-Ray (CXR) images is an important step during clinical diagnosis, because doctors could monitor the lung status directly by this way. In this paper, we deploy three models: pretrained ResNet152, Linear...

With the increasing popularity of sports competitions, the recognition of number plate images has become a label for athletes in order to make it easier to monitor their progress and status in real time. This paper proposes a comprehensive deep convolutional neural network model for number plate recognition....

Vision, one of humanity’s paramount senses, plays a pivotal role in our lives and learning. Maintaining a pair of healthy eyes is of utmost significance. Conventional vision assessments typically necessitate the expertise of ophthalmologists or optometrists to diagnose myopia. Unfortunately, this approach...

Since the traditional method of English character recognition had already reach its limit, there’s a need of a new pattern which can deal with various problems such as noises, distorted words, obstacles and more. Deep learning is a way out. The unique neural network structure of deep learning determines...

With the development of the Internet, a large number of conceptual art pieces have been created in the form of digital images and uploaded to the internet, giving rise to a diverse range of digital image resources that cater to the needs of contemporary youth subcultures. Therefore, categorizing these...

The human body’s structural details can be more clearly seen in high-resolution MRI and CT pictures, which can also aid in the early identification of disorders. However, due to the limits of imaging technologies, imaging surroundings, and human variables, clean high-resolution photographs are challenging...

Today, there are many disadvantages to using manual sorting for refuse classification. How can we solve the problem of garbage classification efficiently and correctly? It is necessary to solve it at present. In order to solve this problem, researchers have begun to use deep learning technology to sort...

With the development of artificial intelligence and the upgrading of traditional cars, artificial neural networks have great potential in unmanned driving technology. Academics are paying increasingly close attention to computer vision research, and applications based on artificial neural networks are...

The video game industry has seen remarkable growth in recent years, accompanied by an escalating demand for high-quality graphics and realistic character rendering. Unity, a leading game development engine, offers an extensive toolkit for asset creation and optimization, including shaders, which are...

Video games have evolved into intricate mediums, allowing players to engage with profound philosophical concepts. However, the relationship between philosophical themes and gameplay mechanics remains under-explored. Despite the rise of narrative-driven games, there is a lack of comprehensive studies...

E-commerce has transformed the retail industry due to its convenience in customization and scalability. Researchers and analysts are deploying machine learning and especially image processing onto E-commerce to visually satisfy customers. This paper explains the most significant application of image...

In recent years, the field of virtual reality (VR) technology has undergone rapid development, leading to notable advancements in VR games. The market has witnessed the emergence of numerous VR games since 2016, among which Gal Game has gained prominence with its adaptation for VR devices. This paper...

Since 2010, the computer has been developing continuously in the field of speech conversion, and now the speech-to-text technology has become mature, but the development of timbre conversion and imitation is not perfect. Recently a new tone imitation program has become a focus, but this program model...

At present, virtual reality (VR) technology is being used more and more widely and deeply used in the field of games, playing a role in different types of games, and generally improving the user experience. This paper summarizes the application of VR technology in different types of games, including...

In recent years, the rapid evolution of Three Dimensional (3D) technology has led to the exploration of its broader applications, particularly in the realm of visual representation, making it a new medium for cultural display. This research paper aims to provide a comprehensive description of the entire...

Modeling techniques are increasingly used in various industries, while the areas of model interpretability, automated modeling, and small-sample learning have received significant attention, contributing significantly to building a smarter and more efficient society. Meanwhile, virtual reality (VR) and...

In recent times, Three-dimensional(3D) technology has gained significant popularity across various industries including gaming, movies, medicine, and architecture, primarily due to advancements in computer graphics technology. However, the requirements for modeling tools and functionalities vary across...

With the continuous development of modern computer graphics technology, its scope of application is becoming increasingly broad. This also has a positive impact on the preservation of traditional culture, as modern modeling techniques can digitally recreate many traditional buildings and objects. This...

As computer graphics and three-dimensional (3D) modeling continue to advance, their applications have become ubiquitous in everyone’s lives. However, traditional Chinese lanterns, a revered handcraft, have been largely untouched by these digital innovations. This is partly due to a lack of digitalization...

Just as in many other fields, the application of machine learning methods has become a prominent topic in the realm of computer graphics. This paper reviews and summarizes some ongoing applications of machine learning in both the academic and industrial aspects of computer graphics, along with certain...

With the speedy improvement of the gaming industry, the connection among recreation builders and players has end up increasingly more complex. Within the past, recreation developers regularly faced challenges in rewriting code to ensure compatibility. However, with technological advancements, the growing...

With the advancement of computer software and hardware technology, artificial intelligence (AI) has significantly enhanced gameplay in the gaming industry and has become a crucial determinant of a game’s success or failure. This article provides an overview of the current applications and associated...

Despite the long-standing presence of the internet in our lives, there remains a significant portion of the population unaware of how their data is transmitted, the speed of their connections, and the security of their online activities. It is essential to consolidate knowledge in this field, enabling...

This study explored the development and application of a random number generator following the Bernoulli distribution, emphasizing its significance in various fields such as simulation experiments, probability analysis, optimization algorithms, and machine learning. The generator’s versatility in generating...

Facial Expression Recognition (FER) refers to the classification of facial expressions based on facial expressions in images by using classification algorithms, which are usually classified into 6 categories. Given the large number of students in a classroom, researchers have employed facial expression...

People constantly receive personalized information recommendations, and movie recommendation is one of the most recognized applications. Effective algorithms support the analysis of users’ behavior, which helps to improve the rating system. Content-based filtering (CBF) is a major technique in recommender...

In the contemporary data-centric era, recommendation systems play an essential role in enhancing the digital user experience by converting the vast expanse of information into tailored streams aligned with individual preferences. This research delves deep into the nuanced mechanisms anchoring these systems,...

Based on the rapid development of the real estate market, real estate prices in various regions of the world fluctuate greatly and are unstable, and we need to make some predictions for real estate prices. However, in reality, we pay too much attention to the relationship between past property prices...

This research focuses on exploring the robustness of the reinforcement learning algorithm Twin Delayed Deep Deterministic Policy Gradients (TD3), especially in terms of its performance in the face of uncertainty, noise, and attacks. Reinforcement learning is a machine learning paradigm in which an agent...

Nowadays, the concept of artificial intelligence is widely popularized and attracting more and more attention. Computer vision is a hot field of artificial intelligence, and semantic segmentation in computer vision has been a worthwhile research direction in recent years. Not only does it play a crucial...

Multiple factors contribute in a non-linear manner, making the field more attractive. The wide availability of educational datasets further fuels this interest. The potential application of data processing models in the field of education is: Data analytics help teachers to understand the learning abilities...

Changes in the world's population are a constant problem, such as the aging crescent, declining fertility and so on. Having an accurate forecast can chart a better and more useful plan for future development. The accuracy of the python prediction is obtained by computing the standard deviation of...

This paper is mainly about using machine learning methods to predict cardiovascular disease. Because cardiovascular disease now ranks first in mortality and the methods and costs of curing heart disease are very small and expensive, so why not take a step earlier? As for discovering diseases, there are...

Now, the continuous advancement of astronomical observation equipment has led to a steady rise in the quantity of identified exoplanets. Hence, there is a pressing need for the development of an efficient and practical approach to forecasting the livability indices of these exoplanets. The objective...

House price prediction is a challenging task, and for home buyers, it is difficult to accurately predict house prices due to the complexity and dynamics of the real estate market. Secondly, as far as the data is concerned, house price prediction is affected by several indicators and it has a great deal...

Parkinson’s disease is a progressive neurological disorder that has a significant impact on the quality of life of millions worldwide. Despite well-defined symptoms and known pathophysiological mechanisms, early diagnosis and effective treatment of Parkinson’s disease remain considerable challenges....