Scholarlink

<p>Edge computing and artificial intelligence gradually intersect to build a novel concept. Edge systems are now equipped with artificial intelligence solutions to deliver faster insights closer to where data is generated, reducing communication latency and avoiding fog or cloud interactions. Within the spectrum of applications demanding EdgeAI, anomaly detection is a pivotal research domain. Here, conventional statistical methods often prove inadequate for identifying anomalies across various scenarios. Therefore, more sophisticated techniques, such as machine learning methods, are required to handle the high dimensionality, nonlinearity, and nonstationarity of the data. Given the state of the art, the literature offers limited references in this field and lacks a clear, up-to-date overview of academic and market initiatives. In this way, the present survey aims to investigate the main concerns of anomaly detection, addressing the opportunity outlined above. We have analyzed 4,075 articles and 10 market players in the field of anomaly detection. Our study presents an updated overview of anomaly detection in EdgeAI, integrating academic and industry perspectives. It encompasses AI libraries, algorithms, hardware, communication technologies, and cost–benefit considerations. Furthermore, we introduce a novel taxonomy that categorizes these approaches by algorithmic features, communication methods, hardware capabilities, energy efficiency, and financial impact.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Looking at anomaly detection in EdgeAI through the up-to-date lens of academic and market perspectives

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月15日

查看全文
  • Alberth dos Santos Oliveira,
  • Fernanda Schäfer Tesch da Silva,
  • Daniel Lopes Ferreira,
  • Mateus Roveda,
  • Cristiano André da Costa,
  • Gabriel de Oliveira Ramos,
  • Rodrigo da Rosa Righi

摘要

Edge computing and artificial intelligence gradually intersect to build a novel concept. Edge systems are now equipped with artificial intelligence solutions to deliver faster insights closer to where data is generated, reducing communication latency and avoiding fog or cloud interactions. Within the spectrum of applications demanding EdgeAI, anomaly detection is a pivotal research domain. Here, conventional statistical methods often prove inadequate for identifying anomalies across various scenarios. Therefore, more sophisticated techniques, such as machine learning methods, are required to handle the high dimensionality, nonlinearity, and nonstationarity of the data. Given the state of the art, the literature offers limited references in this field and lacks a clear, up-to-date overview of academic and market initiatives. In this way, the present survey aims to investigate the main concerns of anomaly detection, addressing the opportunity outlined above. We have analyzed 4,075 articles and 10 market players in the field of anomaly detection. Our study presents an updated overview of anomaly detection in EdgeAI, integrating academic and industry perspectives. It encompasses AI libraries, algorithms, hardware, communication technologies, and cost–benefit considerations. Furthermore, we introduce a novel taxonomy that categorizes these approaches by algorithmic features, communication methods, hardware capabilities, energy efficiency, and financial impact.