EAI Endorsed Transactions on Scalable Information Systems

INTRODUCTION: With the development of digital technology and computer technology, the theory of digital economy has also had far-reaching development, but at present, the digital economy is still not able to clearly define whether the digital economy is good or bad for the high-quality development of China's economy. Therefore, it is necessary to research the spillover effect of the digital economy and the high-quality development of the economy with the help of embedded system technology.OBJECTIVES: To solve the issue of the poor coupling between the digital economy and high-quality development, to raise the degree of China's digital economic development, to improve the high energy consumption in the course of China's economic high-quality development, and to improve the application level of system technology in the study of China's economic development.METHODS: The digital economy model is established using the entropy weight method; its efficiency is evaluated using embedded system technology; the spillover effect analysis of high-quality development is then conducted using the digital economy index; and lastly, the overall assessment of the spillover effect is conducted using the comprehensive evaluation results of the entropy weight method.RESULTS: Embedded system technology has a noticeable promotion effect on the development of the digital economy; although the development of the digital economy and economic high-quality development are poorly coupled, their promotion effect is more significant; embedded system technology can indirectly promote the development of economic high-quality development through the digital economy.CONCLUSION: China should vigorously develop embedded system technology to promote the application of new technology in the economy and should further standardize the market economic order to maintain the orderly development of the digital economy.

Jian Gao

ICST Transactions on Scalable Information Systems

Embedded System Technology Spillover Effects of Digital Economy and High-Quality Economic Development

数字经济与高质量发展背景下的嵌入式系统技术溢出效应

INTRODUCTION: Deep learning algorithms have advantages in extracting key features for detecting fake news. However, the existing multi-modal fake news detection models only fuse the visual and textual features after the encoder, failing to effectively utilize the multi-modal contextual relationships and resulting in insufficient feature fusion. Moreover, most fake news detection algorithms focus on mining news content and overlook the users' preferences whether to spread fake news. OBJECTIVES: The model uses the multi-modal context relationship when extracting model features, and combines with user features to assist in mining multi-modal information to improve the performance of fake news detection. METHODS: A fake news detection model called MFUIE (Multimodal Feature and User Information Enhancement) is proposed, which utilizes multi-modal features and user information enhancement. Firstly, for news content, we utilize the pre-trained language model BERT to encode sentences. At the same time, we use the Swin Transformer model as the main framework and introduce textual features during the early visual feature encoding to enhance semantic interactions. Additionally, we employ InceptionNetV3 as the image pattern analyser. Secondly, for user's historical posts, we use the same model as the news text to encode them, and introduce GAT (Graph Attention Network) to enhance information interaction between post nodes, capturing user-specific features. Finally, we fuse the obtained user features with the multi-modal features and validate the performance of the model. RESULTS: The proposed model's performance is compared with those of existing methods. MFUIE model achieves an accuracy of 0.926 and 0.935 on the Weibo dataset and Weibo-21 dataset, respectively. F1 on Weibo is 0.926, 0.017 greater than SOAT model BRM; while F1 on Weibo-21 is 0.935, 0.009 greater than that of BRM. CONCLUSION: Experimental results demonstrate that MFUIE can improve the fake news recognition in some degree.

Xiulan Hao

Wenjing Xu

Xu Huang

Zhenzhen Sheng

Huayun Yan

MFUIE: A Fake News Detection Model Based on Multimodal Features and User Information Enhancement

MFUIE：一种基于多模态特征和用户信息增强的虚假新闻检测模型

This study examines the influence of title length and the number of words in titles on the view counts of YouTube videos, with a focus on optimizing title characteristics to enhance viewer engagement. Using a dataset of 12,466 Microsoft Excel tutorial videos published between January 2006 and November 2023, the analysis identifies significant patterns in title characteristics that affect viewership. The results reveal a bell-shaped relationship, with both mean and median view counts peaking at specific title lengths and word counts, emphasizing the importance of striking a balance between informativeness and brevity. Furthermore, the study highlights the critical role of visual information (character count) compared to semantic information (word count) in driving video engagement. By providing actionable insights, this research offers practical, cost-efficient guidelines for creators to optimize their video titles, ultimately contributing to more effective content strategies on digital platforms.

Tomohiro Kawata

Takumi Kato

Kazuhiko Tsuda

Effect of Title Length and Word Count on Views: Evidence from Microsoft Excel videos on YouTube

标题长度和字数对观看次数的影响：来自YouTube上Microsoft Excel视频的证据

INTRODUCTION: The contemporary business world is witnessing a proliferation of startups, each striving to carve its niche amidst fierce competition and rapid technological advancements. In this landscape, the ability to innovate and adapt swiftly is paramount for startup survival and growth. This introductory section sets the stage by highlighting the importance of innovation in today's entrepreneurial endeavors. OBJECTIVES: This paper aims to examine the current trends driving startup innovation and explore innovative tactics employed by startups. METHODS: To fulfill the objectives of this study, a comprehensive research methodology was employed. Leveraging techniques derived from social network analysis, qualitative interviews, and extensive literature review, this research endeavors to provide a holistic understanding of the dynamics of startup innovation. By employing a multidisciplinary approach, this study aims to capture the nuanced interplay of factors influencing innovation in the startup ecosystem. RESULTS: Key findings include the prominence of sustainability, remote work integration, and the pivotal role of AI and machine learning in startup strategies. CONCLUSION: This paper concludes by consolidating insights and offering guidance for navigating the dynamic terrain of startup innovation.

Mitra Madanchian

Hamed Taherdoost

Navigating the New Frontier: Exploring Emerging Trends and Strategies in Startup Innovation

探索新前沿：探索初创企业创新的新兴趋势与策略

Deep neural networks (DNNs) have achieved state-of-the-art performance in classification tasks; however, they are susceptible to small perturbations that are seemingly imperceptible to the human eye but are enough to fool the network into misclassifying images. To develop more robust DNNs against adversarial attacks, research methods have focused on exploring the interaction between a machine learning classifier and a single adversary. However, these methods do not adequately model the real-world scenarios in which these classifiers are deployed. In this research paper, we address this gap and propose an adversarial learning algorithm with multiple adversaries using Bayesian Stackelberg games to model the interaction between the learner and multiple adversaries. We conclude that the nested Bayesian Stackelberg method is a useful strategy for developing adversarial learning algorithms to improve the robustness of DNNs. This strategy can serve as a benchmark in future defense attempts to create DNNs that resist adversarial attacks.

Hakeem Quadri

Mixed Bayesian Stackelberg Strategies for Robust Adversarial Classifiers

混合贝叶斯斯坦克尔伯格策略用于鲁棒对抗分类器

INTRODUCTION: A stroke, a sudden interruption of blood flow to the brain, is a leading cause of disability and death. Early diagnosis is paramount for minimizing brain damage and maximizing treatment effectiveness.OBJECTIVES: Traditional diagnostic methods can be time-consuming and have limited Accuracy. METHODS: This study investigates the efficacy of various machine-learning models for stroke prediction. Specifically, it compares established models like K-Nearest Neighbor, Artificial Neural Network, Long Short Term Memory (LSTM), and stacked LSTM with a newly proposed Transformer Convolutional Neural Network (TCNN) architecture, which fuses Transformer and Convolutional neural network (CNN) models.RESULTS: The TCNN demonstrates significant promise, achieving a superior accuracy of 98% when optimized with the AMSGrad optimizer.CONCLUSION: These findings suggest that the TCNN architecture has the potential to revolutionize stroke prediction accuracy compared to existing methods, potentially leading to improved patient outcomes.

R. Bhuvanya

T. Kujani

K. Sivakumar

Fusing Attention and Convolution: A Hybrid Model for Brain Stroke Prediction

融合注意力机制与卷积：一种用于脑卒中预测的混合模型

This paper presents a critical analysis of the role of Artificial Intelligence (AI) in defending against spear phishing attacks, which continue to be a significant cybersecurity threat. By examining 30 seminal studies, we provide an in-depth evaluation of current AI techniques, such as machine learning, natural language processing, and behavioural analytics, which are utilized to detect and mitigate sophisticated email threats. Our review uncovers that AI not only significantly enhances the detection capabilities against these tar-geted attacks but also faces challenges like adaptability and false positives. These findings highlight the continuous evolution of AI strategies in spear phishing defense and the need for ongoing innovation to keep pace with ad-vanced threat tactics. This paper aims to guide future research by proposing integrated AI solutions that enhance both detection capabilities and respon-siveness to new threats, thereby strengthening cybersecurity defenses in an increasingly digital world.

Nachaat Mohamed

Enhancing Spear Phishing Defense with AI: A Comprehensive Review and Future Directions

用AI增强钓鱼邮件防御：综合评述与未来方向

短名	EAI Endorsed Scal Inf Syst
Journal Impact	1.14
国际分区	COMPUTER SCIENCE, INFORMATION SYSTEMS(Q4)

ISSN	2032-9407
h-index	15

涉及主题	计算机科学人工智能数学操作系统工程类机器学习哲学物理程序设计语言计算机网络心理学生物经济计算机安全计算机视觉语言学地理数据挖掘
出版信息	出版商: European Alliance for Innovation，出版周期: ，期刊类型: journal，开源期刊: 是
基本数据	创刊年份: 2014，原创研究文献占比: 100.00%，自引率:18.20%， Gold OA占比: 99.27%
平均审稿周期	网友分享经验：10 Weeks

EAI Endorsed Transactions on Scalable Information Systems

期刊引文格式

有 1 位以上作者的期刊

有 2 位作者的期刊

有 3 位作者的期刊

有 5 位以上作者的期刊

书籍引用格式

学位论文引用格式

网页引用格式

专利引用格式

手工熬夜修改参考文献？研飞自动匹配期刊，一键轻松成稿，支持 Word/WPS

投稿经验分享

Embedded System Technology Spillover Effects of Digital Economy and High-Quality Economic Development

MFUIE: A Fake News Detection Model Based on Multimodal Features and User Information Enhancement

Effect of Title Length and Word Count on Views: Evidence from Microsoft Excel videos on YouTube

Navigating the New Frontier: Exploring Emerging Trends and Strategies in Startup Innovation

Mixed Bayesian Stackelberg Strategies for Robust Adversarial Classifiers

Navigating the New Frontier: Exploring Emerging Trends and Strategies in Startup Innovation

Effect of Title Length and Word Count on Views: Evidence from Microsoft Excel videos on YouTube

MFUIE: A Fake News Detection Model Based on Multimodal Features and User Information Enhancement

Fusing Attention and Convolution: A Hybrid Model for Brain Stroke Prediction

Enhancing Spear Phishing Defense with AI: A Comprehensive Review and Future Directions