Applied AI Solutions on Edge Devices
The new issue is opened. Welcome to submit your work under defined topics. Deadline of submission is 30.06.2023.Read more about Applied AI Solutions on Edge Devices
The new issue is opened. Welcome to submit your work under defined topics. Deadline of submission is 30.06.2023.Read More Read more about Applied AI Solutions on Edge Devices
Traditionally, AI solutions were cloud- or high-performance computing platform-driven and demanded powerful hardware to perform deep-learning / machine learning computational tasks and scale resources effortlessly. However, this involved offloading data to external computing systems for additional computations, which degraded latency, led to higher communication costs, boosted energy consumption, and triggered privacy concerns. Moreover, Inference is a comparatively less computationally demanding task than training, in which latency is more significant in delivering real-time results for a model. The majority of inference is still performed in the cloud or on a dedicated server, but through the increasing diversity of AI applications, the centralized training and inference paradigm is being challenged.
The Journal of Embedded Selforganising Systems is an online, multi-media, academic journal that adheres to the highest standards of peer review and engages established and emerging scholars from anywhere in the world. The Journal of Embedded Selforganising Systems is an interdisciplinary journal that, while centered in computer engineering, is open and welcoming to contributions from the many disciplines and approaches that meet at the crossroads that is embedded system study.
This peer-reviewed journal aims to be a high quality scientific publication that will be of interest to researchers in all disciplines involved in embedded systems. The journal will be published electronically with free and open access via the internet. We aim for a fast review and publication process, so that papers could be published fast.
We take advantage of the greater exiblity and agility an e-journal can provide in comparison to the traditional print journal: Instead imitating the classical creation process of a journal with fix issuses we use the "sliding issue" model. Each issue of the Embedded Selforganising System Journal starts with an editorial that also serves as a kind of call contributions. Any contribution that is reviewed and accepted will be published as soon as the final version is received by the editorial board. In this way, an issue is "growing"until the editors decide to close it. With other words, you can already read articles while other articles are still in the process of preparation. In addition, there may exist other topic-specific issues in parallel.