AITIA: Embedded AI Techniques for Embedded Industrial Applications

M. Hübner M. Veleski B. Silva + 10 lainnya

1 Agustus 2021

Motivated by an increasing interest from startups in embedded Artificial Intelligence (AI) and by their limited expertise, the AITIA Project targets the development of embedded AI techniques for industrial applications. This extended abstract presents the motivation and the solutions being developed towards four use cases: smart sensors, network intrusion detection, driver-assistance systems, and Industry 4.0.

K. Seng L. Ang

2022

Recent years have seen deployments of increasingly complex artificial intelligent (AI) and machine learning techniques being implemented on cloud server architectures and embedded into edge computing devices for supporting Internet of Things (IoT) and mobile applications. It is important to note that these embedded intelligence (EI) deployments on edge devices and cloud servers have significant differences in terms of objectives, models, platforms and research challenges. This paper presents a comprehensive survey on EI from four aspects: (1) First, the state-of-the-art for EI using a set of evaluation criteria is proposed and reviewed; (2) Second, EI for both cloud server accelerators and low-complexity edge devices are discussed; (3) Third, the various techniques for EI are categorized and discussed from the system, algorithm, architecture and technology levels; and (4) The paper concludes with the lessons learned and the future prospects are discussed in terms of the key role EI is likely to play in emerging technologies and applications such as Industry 4.0. This paper aims to give useful insights and future prospects for the developments in this area of study and highlight the challenges for practical deployments.

Jingpeng Li Zhaoyun Zhang

22 April 2023

Advancements in artificial intelligence algorithms and models, along with embedded device support, have resulted in the issue of high energy consumption and poor compatibility when deploying artificial intelligence models and networks on embedded devices becoming solvable. In response to these problems, this paper introduces three aspects of methods and applications for deploying artificial intelligence technologies on embedded devices, including artificial intelligence algorithms and models on resource-constrained hardware, acceleration methods for embedded devices, neural network compression, and current application models of embedded AI. This paper compares relevant literature, highlights the strengths and weaknesses, and concludes with future directions for embedded AI and a summary of the article.

Kiran Mehmood Usama Latif Saad Wazir + 2 lainnya

2 September 2020

The use of Deep Learning and Machine Learning is becoming pervasive day by day which is opening doors to new opportunities in every aspect of technology. Its application Ranges from Health-care to Self-driving Cars, Home Automation to Smart-agriculture, and Industry 4.0. Traditionally the majority of the processing for IoT applications is being done on a central cloud but that has its issues; which include latency, security, bandwidth, and privacy, etc. It is estimated that there will be around 20 Million IoT devices by 2020 which will increase problems with sending data to the cloud and doing the processing there. A new trend of processing the data on the edge of the network is emerging. The idea is to do processing as near the point of data production as possible. Doing processing on the nodes generating the data is called Edge Computing and doing processing on a layer between the cloud and the point of data production is called Fog computing. There are no standard definitions for any of these, hence they are usually used interchangeably. In this paper, we have reviewed the development boards available for running Artificial Intelligence algorithms on the Edge

Matteo Francobaldi A. D. Filippo N. Pizurica + 4 lainnya

8 Mei 2023

Artificial Intelligence (AI) is becoming increasingly important and pervasive in the modern world. The widespread adoption of AI algorithms is reflected in the extensive range of HW devices on which they can be deployed, from high-performance computing nodes to low-power embedded devices. Given the large set of heterogeneous resources where AI algorithms can be deployed, finding the most suitable device and its con- figuration is challenging, even for experts. We propose a data-driven approach to assist AI adopters and developers in choosing the optimal HW resource. Our approach is based on three key elements: i) fair benchmarking of target AI algorithms on a set of hetero- geneous platforms, ii) creation of ML models to learn the behaviour of these AI algorithms, and iii) support guidelines to help identify the best deployment option for a given AI algorithm. We demonstrate our approach on a specific (and relevant) use case: Deep Neural Net- work (DNN) inference on embedded devices.