All of the articles in this proceedings volume have been presented at the ICIAAI 2024 during August 9-11 in Singapore. 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...

In the current field of medical research, identifying and evaluating the key factors affecting the onset of cancer and especially the lung cancer’s onset is of great significance to improve the early management and diagnosis of lung cancer. This study employed a comprehensive approach, utilizing both...

Precise forecasting of lung cancer is crucial due to its high mortality rate. Integrating Artificial Intelligence (AI) into medical diagnostics offers significant potential to enhance prediction accuracy and early detection. This study utilized a dataset from Kaggle, consisting of approximately 1000...

As one of the most common types of cancer in women in the world and early diagnosis of breast cancer is crucial to improve the survival rate and quality of life of patients worldwide. Therefore, it is of great significance to develop efficient and accurate breast cancer prediction methods for the medical...

In recent years, credit card fraud has become increasingly rampant, posing a major threat to financial security. To effectively detect and prevent credit card fraud, this study combines three machine learning algorithms, namely Random Forest (RS), Support Vector Machine (SVM), and Logistic Regression...

Based on machine learning methods, this paper explores the potential of decision time and Multilayer Perceptron (MLP) in predicting trends in Amyotrophic Lateral Sclerosis(ALS), and introduces a prediction model based on decision trees and multi-layer perceptrons (MLPS). The paper first analyzes the...

Nowadays many people are suffering from diabetes. This disease poses significant health risks and economic burdens. This research addresses the increasing incidence of diabetes by investigating the use of machine learning to improve diabetes treatment, diagnosis, and prediction. The research shows how...

In recent years, lung cancer has the highest number of confirmed cases and a high mortality rate among all types of cancer, thus, it is vital to make timely and accurate lung cancer predictions. To alleviate this situation, this paper experimented with lung cancer classification prediction based on historical...

Breast cancer is a malignant tumor that develops from the cells of breast tissue, typically from the ducts or glands. Artificial Intelligence (AI) technology has become a viable option for the automated detection of breast cancer. The study aims to provide a comprehensive review about the application...

Stock market aids investors in making wiser choices. However, the complexity and uncertainty of the financial market result in existing prediction models falling short of expectations. Existing Long Short-Term Memory (LSTM) models commonly suffer from lagging issues, while Support Vector Regression (SVR)...

Due to the rapid development of the internet and the financial industry, stock price prediction has become a widely discussed topic. Government departments and regulatory agencies use stock price forecasts to understand the market’s health, which helps formulate economic strategies and prevent systemic...

Strokes significantly affect global public health and economic stability, with over 12.2 million new cases annually and being a leading cause of death worldwide. This essay takes a dataset containing 15000 entries and 22 features as an example to analyze its preprocessing, feature engineering, and algorithm...

Deep learning is a branch of artificial intelligence. Deep learning can make learning predictions by simulating the working principles between neurons in the human brain. Lung cancer is a major problem in the medical field, and the prediction of lung cancer based on deep learning is of great significance....

As blockchain, virtual reality, and artificial intelligence rapidly advance, the Metaverse is shifting from sci-fi to actuality. This evolution not only promises to transform human existence but also stands to profoundly influence financial transactions. Representing the next-gen Internet, the Metaverse...

In addressing the growing cyber threats prevalent in the digital age, this research presents Machine Intrusion Detection System Based on Learning (MLIDS), an innovative system for detecting intrusions that harnesses the power of deep learning through the integration of a Multi-Layer Perceptron (MLP)....

The popularity of video games such as Pokémon has led to victory prediction receiving increasing attention from researchers and the eSports industry. This study used a dataset containing a variety of Pokémon attributes (including type, attack, defence, speed, and special abilities) and machine learning...

Survival in natural disasters and major accidents is difficult to predict, and in many cases, it is difficult to extrapolate. In this paper, and the probability of survival of the Titanic tourists is discussed. First of all, the characteristics of the passengers in the Titanic data collection from the...

In a 100-meter race, segmented data every 10 meters is crucial for studying an athlete’s performance. Although there are currently two ways - official provision and video analysis - to obtain segmented data, both have significant drawbacks, making it very difficult to obtain segmented data at present....

Weather forecasting is paramount for various sectors, fueling growing interest in leveraging machine learning for predictive weather analysis. The model proposed in this paper represents a significant advancement in this domain by integrating Long Short-Term Memory (LSTM) to augment the capabilities...

The challenging employment landscape is characterized by a significant disparity between high job expectations and intense competition, often resulting in a discrepancy between applicants’ self-assessment and enterprise standards. Within the vast array of job information available, salary emerges as...

The rapid advancement of machine learning (ML) technologies offers unprecedented opportunities to enhance healthcare diagnostics and treatment, particularly in the face of global challenges such as aging populations and the rise of chronic diseases. This paper explores the transformative impact of ML...

Diabetes mellitus (DM) is a major worldwide health problem since it is characterised by persistently elevated blood sugar levels. Predictive analysis of DM is crucial for early detection and prevention, optimal resource allocation, development of personalized treatment plans, cost reduction, and formulation...

Cardiovascular diseases (CVDs) are responsible for a significant number of deaths worldwide and are one of the leading causes of mortality. The main types of CVDs include coronary heart disease, rheumatic heart disease, and congenital heart disease. This article employs logistic regression to investigate...

This paper explores the integration of artificial intelligence technologies in finance, specifically through machine learning and deep learning approaches, across three critical areas: stock price prediction, credit score prediction, and customer churn prediction. It details the methods and workflows...

Blockchain technology is rapidly evolving and widely adopted across various domains, owing to its fundamental characteristics of decentralization, transparency, autonomy, and immutability. This study introduces a blockchain-based pseudo-random number generation method applied to the popular game Monopoly....

As the frequency of extreme weather in the world increases, so does the impact on the insurance industry, making the study of extreme weather on the sustainability of insurance properties particularly important. First, it collected some data on extreme weather occurrences from official databases in the...

With the maturation and widespread adoption of technologies such as peer-to-peer networks (P2P), asymmetric encryption, and distributed storage, blockchain technology has surged to prominence, capturing the interest of scholars across diverse disciplines. This paper provides a historical overview of...

Over the past decade, blockchain technology has undergone remarkable growth, largely driven by its versatility across various applications, which has garnered significant attention from multiple sectors. This technology has facilitated the shift from traditional, centralized ledgers controlled by single...

As information technology advances rapidly, blockchain has risen as a transformative decentralized cryptographic system, celebrated for its robust security features and immutability. This paper offers a succinct overview of the various blockchain types, articulating their structures and functions. It...

Currently, blockchain technology is finding applications across a broad range of industries beyond its traditional role as a decentralized ledger. A notable area of expansion is in blockchain gaming, which leverages the core attributes of blockchain—transparency, immutability, and decentralization—to...

In recent years, the rise of blockchain technology has sparked significant interest in both cybersecurity and financial investment sectors. Blockchains, categorized into permissioned and permissionless types based on their unique attributes, have shown varied applications. Notably, permissioned blockchains...

Sectors including industry and academia. Central to Bitcoin’s innovation is blockchain technology, which has sparked extensive research into its potential beyond simple financial transactions. This paper delves into blockchain technology, examining its historical development, the nuanced trade-offs inherent...

Blockchain technology, introduced by Satoshi Nakamoto in 2008, has undergone significant evolution from its origins in decentralized transaction documentation. Known for its transparency, robustness, and decentralization, blockchain now permeates various sectors, including finance, healthcare, supply...

The essence of blockchain technology lies in the consensus algorithm, which ensures data consistency among network nodes and secures the blockchain system. As blockchain technology rapidly evolves and finds widespread application, a diverse array of consensus algorithms has emerged, each tailored to...

News is an important way to understand the information of contemporary society, and it is necessary to quickly categorize and identify a large amount of news information. In this report, a classification task was performed on Chinese news headlines based on the Bidirectional Encoder Representations from...

As technology advances, both institutions and individuals are increasingly prioritizing information security. Consequently, many enterprises and institutions are turning to distributed technologies that offer enhanced security for data storage and sharing, with blockchain technology emerging as a critical...

Smart contracts, pivotal to blockchain technology, are rapidly proving their worth across the digital economy. Yet, as their application widens, issues concerning their security and scalability have emerged as major industry concerns. This paper provides a comprehensive analysis of these challenges,...

Measuring dependencies between two variables in an extremely large data set is an increasingly important problem, naturally then the methods to solve such problems warrants equal if not greater attention. This paper aims to overview an effective measure of dependence, the MIC. This statistical measure...

In recent years, people’s technological advancement has led to the rapid development of drone technology, but there is still a long way to go before the realisation of drone technology that does not require a human to operate it. Currently, people’s drone technology is at the stage where it does not...

The freshwater available for direct human use is extremely scarce compared to the total amount of water on Earth. Most of this freshwater is located in freshwater lakes. As human civilization progresses, the ecological destruction of freshwater lakes has become increasingly common. Drones have become...

The increasing use of Unmanned Aerial Vehicles (UAVs) in various sectors like agriculture, surveying, logistics, and environmental monitoring has created a pressing need for the ability to gather and process positioning sensor data. The precision of positioning, equipment performance, and data processing...

This paper proposes a new Pan-Tilt-Zoom PTZ UAV loading system, which uses the PTZ to connect with the loading mechanism to protect the cargo in the UAV transportation process. PTZ can eliminate the shaking of the cargo box caused by the movement of the drone, and the cargo box below can provide a relatively...

With the wide application of UAVs in various fields of society, some shortcomings of UAVs are gradually exposed, especially the shortcomings of power sources make the endurance range and time limits of UAVs, which seriously restricts the development of UAVs industry. Through careful comparative study,...

In recent years, the technology of remote sensing has achieved rapid development in UAV. In addition, the global reduction of arable land has led to increased food security challenges, and the demand for precision agriculture is increasing, and more and more drones are being used in this area. Compared...

In recent years, drones have been widely used in various industries and have played a significant role. However, with the popularization of civilian drones, the safety issues brought about by drone “black flying” should also be given sufficient attention. Good drone signal detection technology is a prerequisite...

In the realm of autonomous driving technology, significant strides have been made, yet challenges persist. This paper aims to explore the effectiveness of applying a Model Predictive Path Integral (MPPI) controller in autonomous driving technology. The advancement of autonomous driving technology has...

With the increasing global demand and expanding application fields of drones, the safety and durability of drones during flight has become particularly important in commercial competition. This study focuses on designing a protective shield specifically tailored for both commercial and personal drone...

Quadcopter Unmanned Aerial Vehicles (UAVs) have seen widespread use in many industries recent years because of their versatility and efficiency in various applications. Integral components of the flight control system, such as PID (Proportional-Integral-Derivative) control and SMC (Sliding Mode Control)...

As their application scenarios become more diverse, the demand for control methods that can resist interference is also growing. This is particularly important for UAVs operating in some scene happened in complex environments, where they may be susceptible to various external interference factors, such...

In recent years, with the development of economy and science and technology, establishing a more intelligent transportation system is an effective way to solve the frequent traffic problems. Drones are widely used in intelligent transportation because of their compactness and flexibility, wide aerial...

Based on the gradual popularization of UAV and the development trend of UAV application, the application of UAV sensors for target recognition and information fusion analysis has become one of the key topics of today’s research. Researchers have made progress in UAV target recognition by adopting wireless...

With the rapid development of Unmanned Aerial Vehicles (UAV) technology, their applications in agricultural monitoring, search and rescue, environmental monitoring and other fields are increasing. These application scenarios put forward higher requirements for the autonomous navigation and path planning...

With the development of automatic control technology, quadcopter UAVs based on PID controllers are widely used in many fields such as exploration, aerial photography, monitoring patrols, etc. Due to the fact that the controlled object has a certain nonlinearity in complex environments, there exists the...

Machine learning has found widespread application in contemporary society, yet it remains vulnerable to the corrosive effects of adversarial samples. These refer to input data that has been deliberately modified in a certain way to mislead machine learning models. While these modifications may be undetectable...

Since ancient times, language has been a fundamental medium for human communication and the expression of thoughts. The advancement of speech recognition technology has significantly enhanced the efficiency of generating, transmitting, storing, and acquiring speech information, thereby facilitating more...

A serious brain condition with a high death rate, intracranial hemorrhage (ICH) requires a precise and timely diagnosis. While Computed Tomography (CT) is commonly used for its speed and accessibility, its diagnostic accuracy is limited compared to Magnetic Resonance Imaging (MRI). However, the latter...

With the increasing popularity of video social platforms, recommendation systems play a crucial role on these platforms. They can recommend content of interest to users based on their interests and preferences, greatly improving their content browsing experience. This article provides an in-depth analysis...

As the Internet of Things (IoT) proliferates, securing these interconnected devices has become a critical concern. Trusted Execution Environments (TEEs) offer a crucial mechanism for bolstering IoT device security. This paper delves deeply into the application of TEEs within the IoT ecosystem to protect...

Stroke is a major global health challenge, significantly contributing to disability and death worldwide. Due to the rapid progress of deep learning, the challenges in this field have the potential to be solved. This article offers a comprehensive examination of the uses of deep learning in stroke segmentation....

Ischemic stroke has a devastating impact on global health, causing both death and disability. Automatic, accurate segmentation of these stoke areas, or infarctions, from Magnetic Resonance Imaging (MRI), can aid clinicians in personalized therapeutic strategies. Recent advances in merging fully convolutional...

This empirical study investigated the impact of face occupancy on the generalization performance of Convolutional Neural Networks (CNNs), specifically focusing on three widely-used architectures: ResNet50, VGG16, and MobileNetV2. The face occupancy ratio, defined as the proportion of the image occupied...

Facial expression recognition is an essential domain within computer vision, focused on interpreting human emotions through facial cues for enhanced human-computer interaction. This study examines the current state and challenges in facial expression recognition, emphasizing the role of deep learning...

Brain tumor is a serious disease that affects lots of people. Traditional methods of tumor detection are time-consuming and subjective. Many studies have demonstrated Convolutional Neural Networks (CNNs) can classify brain tumors with a high accuracy, but they did not focus on the generalization of the...

Irony is a figure of speech in which the words are employed with an intended meaning that differs from their literal meaning. The ability to recognize and interpret ironic sentences can prevent misunderstandings in conversations and enhance effective communication. With the continuous improvement of...

This article comprehensively describes natural language processing (NLP) and its relationship to adversarial attacks. As an interdisciplinary field involving computer science, artificial intelligence, and linguistics, the NLP has great potential to transform all walks of life. Deep learning, as the main...

Spam is one of the significant threats to cyber security by not only sending unwanted messages but also by potentially carrying viruses. Conventional spam detection methods, such as keyword matching and rule-based filtering, are less effective since spammers could advance their method to bypass these...

Indoor mobile robots are now widely used in restaurants for delivery services to improve delivery efficiency and reduce labor costs. Simultaneous visual localization and mapping (SLAM) and path planning are the basis for restaurant service robots to navigate and deliver food. Therefore, it is useful...

With machine learning has been widely used in face recognition, natural speech processing, automatic driving and medical systems, attacks against machine learning are also accompanied, which may bring serious safety risks to biometric certification systems or automobiles. Incorrect classification of...

Traditional natural language processing models often find it difficult to distinguish between sentences with “similar structure and different semantics” and sentences with “different structure and similar semantics”. Based on the all-MiniLM-L6-v2 and Bidirectional Encoder Representations from Transformers...

With the widespread adoption of digital communication platforms, emojis have become an integral part of conveying subtle emotions and expressions within written content. This paper delves into the application of BERT and its foundational Transformer technology in processing texts enriched with emojis,...

In recent years, Chinese college students have generally faced social problems such as fierce competition for employment and rising youth unemployment. Sentiment analysis of college students’ employment attitudes helps them recognize the situation, accurately position themselves, and rationally arrange...

Image stitching is a popular research area in the fields of computer vision and computer graphics. The feature points of images provide crucial information for this process. The accurate extraction of these features is essential to minimize misalignment and defects in the final stitched image. This paper...

This paper explores the enhancement of security and robustness in the field of facial recognition by investigating adversarial example attacks. The author not only introduces an advanced adversarial example generation technique by utilizing key facial landmarks, but also investigates universal mask-based...

With the increasing complexity and diversity of traffic environments, accurate identification of traffic signs becomes a necessary aspect for the development of assisted driving and autonomous driving technologies. Traffic sign recognition approaches exploiting deep learning have demonstrated significant...

Panoramic image stitching technology has penetrated into every field of modern life. As an important part of the stitching process, image feature matching directly affects the quality and speed of the stitching. In this paper, photos taken in daily life are used for experiments, and the precision and...

This paper delves into the realm of three-dimensional (3D) reconstruction technology, specifically examining the principles underlying Multi-View Stereo (MVS) techniques, encompassing pose calculation, dense reconstruction, surface reconstruction, and texture mapping. It scrutinizes the application of...

Due to factors such as perspective and lighting, traditional stitching such as perspective and lighting algorithms find it difficult to achieve high-quality stitching results. Therefore, how to effectively improve the image stitching effect has become a hot research topic. The traditional image stitching...

In the field of image stitching, generating multiple panoramas from a large set of images is a challenging task. Traditional methods often require complex pairwise comparisons, leading to time-consuming operations that may affect accuracy and efficiency. To address this issue, this paper presents an...

In the field of computer vision, planar homography plays a pivotal role in our research process. The homography matrix is capable of performing a variety of functions such as image warping, stitching, and video stitching. Within the realm of epipolar-geometry, it enables the execution of numerous tasks,...

Given how quickly augmented reality (AR) and virtual reality (VR) technologies are developing, panoramic image stitching technology is playing an increasingly important role in providing immersive experiences. Especially in complex scenes where natural and urban environments are interwoven, high-quality...

As global population growth poses an increasing challenge to agriculture, the importance of crop pest management has increased. At present, most pest problems are solved by traditional manual methods, which are becoming increasingly inefficient in the face of increasing production capacity, so automated...

With the rapid advancements in computer vision and image processing technologies, three-dimensional (3D) reconstruction from a single image has emerged as a significant area of research within the field of computer vision. However, due to the inherent lack of depth information in single images, 3D reconstruction...

The prevalence of short text comments in the comment sections of social media platforms accelerates the rate of information dissemination. The diversity and unpredictability of comment content can affect the sentiments of viewers and their judgment of topics and interfere with social media platforms’...

Emotion recognition stands as a cornerstone across various domains, propelling the evolution of artificial intelligence. This paper introduces a pioneering approach to emotion recognition, employing a Bi-directional Long Short-Term Memory (Bi-LSTM) neural network fused with an attention mechanism (Att)....

Fueled by the swift advancements in artificial intelligence, computer vision technology has found extensive applications across various domains. This article will focus on how to use the You Only Look Once version 5 (YOLOv5) to enhance the accuracy and efficiency of pedestrian detection. It begins by...

This study delves into the realm of anime face generation with the aim of empowering individuals to create their own anime characters and easing the burden on artists. Employing Deep Convolutional Generative Adversarial Networks (DCGAN), the research focuses on generating anime face images. The DCGAN...

Precise and efficient detection of water bodies in satellite pictures is essential for diverse applications, like environmental surveillance, urban development, and disaster response. This study investigates the effectiveness of utilizing the U-shaped network (U-Net) models with input shapes of 128x128...

The study solved the imbalanced Magnetic resonance imaging (MRI) dataset problem by choosing different loss functions to achieve a higher stroke lesion area segmentation accuracy. It is helpful for doctors to treat patients efficiently by segmenting the stroke areas quickly with the machine learning...

This paper aims to explore the effect of parameter adjustment in classification layers of VGGNet. It provides suitable amounts of parameters for VGGNet with FC and FCN layers, which are available for reference. In the research, FER13 dataset, which contains gray-scaled images with shape of 48 x 48 with...

Due to the mortality and disabilities caused by ischemic stroke, it is of great significance to provide accurate segmentation during the treatment of ischemic stroke. In this study, pre-trained UNets were utilized to save the computational resource and provide accurate prediction of lesion area caused...

Due to the surge of depression among netizens in China’s online society, the problem of social depression has developed seriously. The purpose of this paper is to detect and remind Internet negative emotions through natural language processing technology. In this paper, the Bidirectional Encoder Representations...

Lacking sufficient data has become a serious problem in the field of Facial Expression Recognition (FER), since the cost of collecting a large amount of facial expression images is huge and training a new FER model from the beginning is time-consuming. In this paper, the author trained a FER model based...

Traditionally, medical image classification and denoising tasks are conducted and evaluated separately, which may waste computational resources and incur excessive expenses. Besides, the features extracted by different models cannot be shared and utilized effectively. Therefore, an end-to-end multimodal...

Artificial Intelligence (AI) has become a driver of innovation in a rapidly evolving technological landscape across a wide range of industries, and the gaming industry is at the forefront of these advances. The aim of this paper is to explore the wide range of applications and potential uses of AI in...

One of the core tasks of computer vision is image classification, which aims to distinguish different types of images based on various features. However, traditional image classification methods often rely on a large amount of labeled data to support them and obtaining large-scale, high-quality labeled...

Since 2010, with the rapid emergence of deep learning, Convolutional Neural Networks (CNNs) have made significant progress across various domains. In particular, advancements in CNNs have profoundly impacted the field of computer vision, resulting in substantial improvements in tasks such as image classification,...

In the context of current technological development, large language models (LLMs) have become a core component of artificial intelligence. This report provides an in-depth discussion of various advanced strategies and techniques to improve the processing and computational efficiency of LLMs. First, the...

Researchers in the domain of computer vision have increasingly turned their attention towards harnessing the power of Transformer models for visual tasks. This paradigm shift has led to the emergence of pioneering models such as Detection Transformer (DETR) and Vision Transformer (ViT), opening up new...

Facial expression recognition has emerged as a pivotal aspect of human-computer interaction and psychological research, drawing extensive attention in computer vision. The essay aims to improve the facial expression recognition performance of Convolutional Neural Networks (CNN) under different imaging...

Artificial intelligence-based approaches, such as Convolutional Neural Networks (CNN), hold significant promise for emotion detection, particularly in facial expression recognition, offering invaluable insights for various sectors including business, medicine, and psychology. This paper explores the...