Current Issue

All articles published in this issue have undergone a thorough peer review process, and stringent checks for repetition rates have been implemented to ensure the integrity of the content.

Total number of articles in this issue: 13
Total number of pages in this issue: 126

For inquiries regarding the content of specific articles, please feel free to contact the respective authors via their provided email addresses. For questions related to the journal itself, please reach out directly to SUAS Press.

Year

2024

Volume

2

Number

6

Status

Archived

Published

2024 December 1

Articles

Open Access Research ArticlePublished 1 December 2024

Leveraging AI in Traffic Engineering to Enhance Bicycle Mobility in Urban Areas

Chang Che, Junchi Tian

More With the rise of AI-driven technologies, urban cycling is becoming more accessible and appealing to many due to benefits such as health improvement and cost efficiency. Governments worldwide are promoting cycling as a sustainable transportation option to address environmental challenges. Ensuring seamless bicycle mobility in cities is essential to incentivize cycling. AI-powered Traffic Engineering can significantly enhance the flow of bicycle traffic in urban areas by optimizing infrastructure and safety. This article explores the benefits of cycling and the rationale for investing in AI-integrated cycling infrastructure. It provides examples of smart solutions such as AI-based vehicle-cycle segregation (including London's Cycle Superhighways), protected intersections enhanced by machine learning algorithms, and Intelligent Transport Systems (ITS) that incorporate AI for dynamic traffic management. Their implementation and impact on cyclists and overall traffic flow are analyzed, demonstrating that these advanced systems reduce accidents, boost road efficiency, and make cycling more enjoyable. Quantitative data on these improvements is also presented. In conclusion, AI-enabled Traffic Engineering solutions play a vital role in enhancing bicycle mobility and safety in urban environments.

Disciplines:Artificial IntelligenceSubjects:Traffic EngineeringReferences:12

DOI10.70393/6a69656173.323039ARKark:/40704/JIEAS.v2n6a02
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Advances in Deep Reinforcement Learning for Computer Vision Applications

Zhengyang Li

Deep Reinforcement Learning (DRL) has become very popular for computer vision (CV), solving mostly visually complex environments with decision making and dynamic adaption to different situations. This article provides an introduction to the basic concepts of deep reinforcement learning with a special focus on their applications in computer vision tasks, including challenging problems and emerging solutions. It reviews various DRL algorithms such as Q-learning, policy gradient methods, and Actor-Critic models, explaining much of the modifications that are done to make it work on high-dimensional visual problems. Different applications of DRL in major CV applications like object detection, image segmentation, target tracking and image generation are reviewed to demonstrate the power as well as limitations of DRL in practice. More importantly, the novel paradigms such as hierarchical policy learning, adaptive reward design multi-task reinforcement learning and domain adaptation can be viewed as promising premises to improve model efficiency and generalizability in multiple scenarios. Finally, this paper mentions a few of the existing challenges like computational power cost and sample efficiency; as well as future paths for enhancing that can widen devout reinforcement learning in computer vision. Through this comprehensive overview, we aim to shed light on the promising synergies between DRL and CV, while identifying key areas for future research and application.

Disciplines:Computer ScienceSubjects:Computer VisionReferences:26

DOI10.70393/6a69656173.323234ARKark:/40704/JIEAS.v2n6a03
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Enhancing User Engagement and Behavior Change in Healthy Eating Apps: A Human-Computer Interaction Perspective

Yuxin Zhao, Jiawei Wu

Healthy eating apps have gained popularity as tools for promoting dietary improvements and supporting behavior change. Despite their potential, maintaining user engagement and achieving sustained behavior change remain significant challenges. This paper investigates how principles of Human-Computer Interaction (HCI) can be leveraged to address these challenges and enhance the effectiveness of healthy eating apps. By conducting a comprehensive review of relevant HCI methodologies and analyzing the functionalities of existing apps, the paper identifies key factors that influence user interaction and behavioral outcomes. The research highlights that incorporating HCI principles—such as personalized feedback, gamification, and social interaction—can lead to more engaging and effective apps. Personalized feedback helps users feel more understood and supported, while gamification elements increase motivation through rewards and challenges. Social interaction features foster community support and accountability, contributing to sustained engagement. The paper concludes with practical recommendations for app developers to integrate these HCI principles and outlines future research directions to further explore and refine strategies for enhancing user engagement and behavior change in healthy eating apps.

Disciplines:Human-Computer InteractionSubjects:User Engagement and BehaviorReferences:49

DOI10.70393/6a69656173.323330ARKark:/40704/JIEAS.v2n6a04
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Exploring Multimodal Feedback Mechanisms for Improving User Interaction in Virtual Reality Environments

Yuxin Zhao, Zuen Cen

As Virtual Reality (VR) technology progresses, the need for intuitive and immersive interaction mechanisms becomes increasingly important. However, current VR systems primarily rely on visual and auditory feedback, often overlooking other sensory modalities, which limits the depth of user immersion. While visual and auditory inputs allow users to perceive virtual objects and sounds, the experience remains somewhat one-dimensional compared to real-world, multi-sensory interactions. To address this limitation, this paper explores the impact of multimodal feedback mechanisms, particularly through the incorporation of haptic (touch) and olfactory (smell) cues, on user experience in VR environments. By enriching the sensory inputs, these additional feedback mechanisms can significantly enhance the realism and intuitiveness of virtual interactions, making the experience more engaging and immersive.

Disciplines:Virtual RealitySubjects:Multimodal Feedback MechanismsReferences:40

DOI10.70393/6a69656173.323331ARKark:/40704/JIEAS.v2n6a05
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Automated Machine Learning: A Survey of Tools and Techniques

Junchi Tian, Chang Che

Automated Machine Learning (AutoML) has revolutionized the field of machine learning by automating complex and time-intensive tasks such as data preprocessing, model selection, and hyperparameter tuning. This study explores the capabilities, limitations, and practical applications of six widely used AutoML tools: Auto-sklearn, TPOT, H2O.ai, Google Cloud AutoML, Microsoft Azure AutoML, and Amazon SageMaker Autopilot. By evaluating these tools across diverse datasets—spanning tabular data, time series, image classification, and text sentiment analysis—the research highlights their predictive performance, computational efficiency, scalability, and explainability. Proprietary tools demonstrated superior scalability and efficiency through cloud integration, while open-source platforms provided more interpretability and flexibility. However, challenges such as lack of transparency in advanced neural architecture search mechanisms and ethical considerations, including bias mitigation, remain prevalent. This study concludes that while AutoML tools significantly lower the barrier to entry for machine learning, ongoing advancements are required to balance performance, usability, and ethical standards, making AutoML an integral solution for real-world applications.

Disciplines:Computer ScienceSubjects:Machine LearningReferences:22

DOI10.70393/6a69656173.323336ARKark:/40704/JIEAS.v2n6a08
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Interpretable Machine Learning: Explainability in Algorithm Design

Xueyi Cheng, Chang Che

In recent years, there is a high demand for transparency and accountability in machine learning models, especially in domains such as healthcare, finance and etc. In this paper, we delve into deep how to make machine learning models more interpretable, with focus on the importance of the explainability of the algorithm design. The main objective of this paper is to fill this gap and provide a comprehensive survey and analytical study towards AutoML. To that end, we first introduce the AutoML technology and review its various tools and techniques.

Disciplines:Computer ScienceSubjects:Machine LearningReferences:22

DOI10.70393/6a69656173.323337ARKark:/40704/JIEAS.v2n6a07
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Adaptive Hybrid Optimized LSTM Models: A Novel Computational Framework for Algorithmic Financial Trading System

Pei-chiang Su

In our modern society, with the development of Internet and information system, pre-programing algorithmic trading strategies for online automatic trading has also flourished, especially in the rapidly fluctuating trading market. Using quantitative trading programs that can automatically trade in response to market conditions has attracted the attention of major financial institutions and governments in the financial market. How to use self-adaptive programs to automatically trade in the ever-changing financial market has become a popular research topic for the development and pursuit of all financial markets in recent years. This research proposes an online self-adaptive trading algorithm that can be applied to financial markets such as stock market, currency markets, cryptocurrency markets, futures markets, etc. In the first part of the algorithm, the simplified swarm optimization will be used to optimize the parameters of the newly proposed flexible grid in this research. Then the data will be imported into the artificial neural network model for training in the latter part, helping the trading model automatically select the appropriate parameters for construction flexible grid corresponding to the market conditions. The greatest contribution of the research is to provide a whole new trading algorithm that can adapt to the dynamic trading market, automatically make suitable adjustments to current trading strategy and place real-time orders. The algorithm controlling both profit and risk, which can seem like a balanced trading algorithm that are robust and profitable.

Disciplines:Computational ScienceSubjects:Intelligent ComputingReferences:53

DOI10.70393/6a69656173.323338ARKark:/40704/JIEAS.v2n6a06
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

The Application of Generative AI in Virtual Reality and Augmented Reality

Shijie Lyu

This study explores the historical development of Virtual Reality (VR) and Augmented Reality (AR) technologies and their applications in various fields, such as education, tourism, and consumer experiences. Through a review of relevant literature, the paper analyzes how VR and AR enhance user engagement and satisfaction by providing immersive and interactive experiences. In education, VR and AR are used to create vivid learning environments, promoting students' understanding and interest; in the tourism industry, these technologies enhance visitors' exploration and experience of destinations; in business, AR applications improve consumer shopping experiences and brand loyalty. Despite the widespread application of these technologies facing challenges such as high costs and user adaptability issues, research shows their potential remains significant. Future research should focus on optimizing user experience, lowering technological barriers, and expanding application scenarios. In conclusion, the development of VR and AR technologies will drive innovation and transformation across industries, offering richer experiences in daily life.

Disciplines:Computer ScienceSubjects:Generative AIReferences:47

DOI10.70393/6a69656173.323339ARKark:/40704/JIEAS.v2n6a01
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Anomaly Pattern Detection in High-Frequency Trading Using Graph Neural Networks

Maoxi Li, Mengying Shu, Tianyu Lu

This paper presents a new method for detecting abnormal patterns in high-frequency trading (HFT) using graph neural networks (GNNs). The increasing sophistication of trading algorithms and the large volume of data have often created unprecedented challenges for traditional market analysis. Our framework addresses these challenges by introducing a GNN-based architecture that takes advantage of the physical and structural properties of business data. The proposed method transforms HFT data into graphical models where the nodes represent market conditions and the edges capture their physical and price relationships. A specialized GNN architecture, incorporating attention mechanisms and temporal convolution modules, is developed to learn complex trading patterns and identify potential anomalies. The model is evaluated on high-frequency trading data from five major stocks listed on NASDAQ, spanning six months of trading activity with over 10 million events. Experimental results demonstrate superior performance compared to existing approaches, achieving a 15% improvement in detection accuracy and maintaining robust performance across different market conditions. The framework exhibits particular strength in identifying complex manipulation patterns while maintaining low false positive rates. Our approach processes large volumes of trading data in real time with significantly reduced computational requirements compared to traditional methods. This research contributes to the development of more effective market surveillance systems and provides valuable insights for regulatory authorities in maintaining market integrity.

Disciplines:Artificial Intelligence TechnologySubjects:Machine LearningReferences:20

DOI10.70393/6a69656173.323430ARKark:/40704/JIEAS.v2n6a09
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Real-time Detection of Abnormal Financial Transactions Using Generative Adversarial Networks: An Enterprise Application

Shuaiqi Zheng, Maoxi Li, Wenyu Bi, Yining Zhang

This paper presents a novel real-time financial fraud detection framework utilizing Generative Adversarial Networks (GANs) for enterprise applications. The proposed system addresses critical challenges in fraud detection, including class imbalance, real-time processing requirements, and enterprise scalability. Implementing a sophisticated multi-layered architecture, the system integrates advanced preprocessing techniques with an optimized GAN model explicitly designed for fraud pattern recognition. The framework incorporates parallel processing capabilities and adaptive batch processing mechanisms to maintain high throughput while ensuring sub-second latency. The experimental evaluation uses a subset of the European Credit Card Transaction dataset, comprising 50,000 transactions with a balanced representation achieved through strategic sampling and SMOTE technique. The proposed model achieves 97.8% accuracy, 96.5% precision, and 95.8% recall, demonstrating competitive performance compared to traditional machine learning approaches. Real-time performance analysis shows consistent sub-100ms latency while maintaining robust performance under varying load conditions. The system demonstrates linear scalability up to 32 nodes, with high availability and failover capabilities. The comprehensive assessment validates the framework's effectiveness in enterprise environments, providing practical solutions for financial institutions facing evolving fraud challenges. This research contributes to the advancement of financial security technology through the innovative application of adversarial learning in fraud detection.

Disciplines:Artificial Intelligence TechnologySubjects:Machine LearningReferences:36

DOI10.70393/6a69656173.323431ARKark:/40704/JIEAS.v2n6a10
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Multi-modal Market Manipulation Detection in High-Frequency Trading Using Graph Neural Networks

Yuexing Chen, Maoxi Li, Mengying Shu, Wenyu Bi, Siwei Xia

This paper proposes a novel multi-modal graph neural network framework for detecting market manipulation in high-frequency trading environments. The framework integrates diverse data sources through sophisticated fusion mechanisms and employs attention-based graph neural networks to capture complex trading patterns. Our approach constructs dynamic trading networks that encode temporal and structural dependencies, enabling the detection of subtle manipulation strategies. The model architecture incorporates multiple attention layers for feature selection and cross-modal information fusion, achieving superior detection performance compared to traditional methods. Experimental results on real-world high-frequency trading data from major exchanges demonstrate the framework's effectiveness, reaching 98.7% accuracy in manipulation detection while maintaining low latency (8.3ms average processing time). The model exhibits robust performance across various market conditions and manipulation patterns, with precision and recall rates exceeding 97%. Through comprehensive case studies and interpretability analysis, we validate the framework's ability to identify and explain complex manipulation strategies while providing insights for regulatory compliance. The proposed approach advances state-of-the-art market surveillance technology, offering a scalable solution for real-time manipulation detection in modern financial markets.

Disciplines:Artificial Intelligence TechnologySubjects:Machine LearningReferences:24

DOI10.70393/6a69656173.323432ARKark:/40704/JIEAS.v2n6a12
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

FSMM: Food System Monitoring Model for Re-optimization

Wenjun Wu, Dong Liu, Lai Jiang, Kai Guo

The unstability of global food system have aroused growing attention worldwide. Althrough there is sufficient food produced to feed every person, many people in the world are suffering from hunger. Moreover, the current food system is harmful to the environment. As our global population continues to rise, the ability to produce more food while sustaining, and even improving, the health of our environment counts. The FSMM(Food System Monitoring Model) provides score rank using entropy weight and subjective weight to evaluate the current state of the food system for most countries in the world. It contains 9 individual features to measure multiple aspects, including efficiency, profitability, sustainability and equity. Considering the future trend of the food system, we apply Gray Forecast Model to forecast the next 5 years of the development of the food system to figure out the time for each country to change into equity and sustainability. To find out the relation between external factors and food system, The FSMM uses Boosting Regression Model to find the correlation between the scores and 10 indicators which represent the influences of energy use, government, agriculture, social factors and population ratio. The FSMM fits the data from 178 countries from 2000 to 2019. After simulating and adjusting the parameters to decrease the loss of the model, we gets the importance rate of each indicator. We find the indicators whose importance rate change significantly when the food system is optimized for equity and sustainability. And we use these indicatos as dependent variable and apply Linear Regression to fit by using the yields of the wheat, meat and vegetables as independent variable. By doing this, We find out the direct impact of re-optimization on the food system. We finally get the importance rate and the coefficient of two regression model and analyze the specific influence of various factors on the food system and compare the differences between the influence on developing and developed countries. After the overall analysis of the influence on developed and developing countries, we pick some specific developing and developed countries to analyze and discuss the scalability and adaptability of the model.

Disciplines:Applied MathematicsSubjects:Mathematical ModelingReferences:28

DOI10.70393/6a69656173.323433ARKark:/40704/JIEAS.v2n6a11
View ArticleDownload PDFScholar

Open Access Research ArticlePublished 1 December 2024

Deep Reinforcement Learning-Enhanced Multi-Stage Stochastic Programming for Real-Time Decision-Making in Centralized Seed Packaging Systems

Yuqun Zhou

The centralized seed packaging system faces significant challenges in dynamic decision-making due to stochastic demand fluctuations and operational constraints. This paper presents a novel hybrid approach integrating deep reinforcement learning (DRL) with multi-stage stochastic programming (MSP) to optimize decision-making processes. Our method leverages DRL for adaptive learning and MSP for uncertainty modeling, enabling real-time adjustments. Results from case studies demonstrate improved efficiency, reduced costs, and enhanced robustness compared to traditional approaches.

Disciplines:Artificial Intelligence TechnologySubjects:Machine LearningReferences:5

DOI10.70393/6a69656173.323435ARKark:/40704/JIEAS.v2n6a13
View ArticleDownload PDFScholar

Copyright © 2026 The Author(s). Published by Southern United Academy of Sciences.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Journal of Industrial Engineering and Applied Science (JIEAS)
Published by Southern United Academy of Sciences Limited ISNI: 0000000512776460, operated by the Publications Division.