Abstract
The application of Artificial Intelligence to the industrial world and its appliances has recently grown in popularity. Indeed, AI techniques are now becoming the de-facto technology for the resolution of complex tasks concerning computer vision, natural language processing and many other areas. In the last years, most of the the research community efforts have focused on increasing the performance of most common AI techniques—e.g., Neural Networks, etc.—at the expenses of their complexity. Indeed, many works in the AI field identify and propose hyper-efficient techniques, targeting high-end devices. However, the application of such AI techniques to devices and appliances which are characterised by limited computational capabilities, remains an open research issue. In the industrial world, this problem heavily targets low-end appliances, which are developed focusing on saving costs and relying on—computationally—constrained components. While some efforts have been made in this area through the proposal of AI-simplification and AI-compression techniques, it is still relevant to study which available AI techniques can be used in modern constrained devices. Therefore, in this paper we propose a load classification task as a case study to analyse which state-of-the-art NN solutions can be embedded successfully into constrained industrial devices. The presented case study is tested on a simple microcontroller, characterised by very poor computational performances—i.e., FLOPS –, to mirror faithfully the design process of low-end appliances. A handful of NN models are tested, showing positive outcomes and possible limitations, and highlighting the complexity of AI embedding.
Highlights
The emerging trend of products smartness is becoming a minimum requirement that each commercial appliance should satisfy
The relevance of our work is two-folded: (i) we present a realistic case study for embedding Artificial Intelligence (AI) techniques into constrained devices; (ii) we apply such case study over hyper-constrained devices, analysing how available state-of-the-art techniques can be leveraged on such devices
In order to measure the performance of state-of-the-art Neural Networks (NNs) architectures and show their limitations on hyper-constrained devices, we start our experiments considering wellknown NN architectures
Summary
The emerging trend of products smartness is becoming a minimum requirement that each commercial appliance should satisfy. Users who once were surprised by simple smart features of commercial products are expecting devices to perform highly complex tasks such as object detection [1], language processing [2], and many others [3]. It is a common trend of industries and manufacturers to introduce processors and controllers in modern commercial products, aiming at satisfying customers requests and transforming once-dumb devices into smart appliances. The introduction of costly components like GPUs or powerful processors just to tackle intelligent tasks would produce an undesirable increase of the final product cost, leading to possible negative outcomes on the market
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
