Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Annals of Computer Science and Information Systems

2 Bosse Stefan

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

IoT and Edge Computing using virtualized low-resource integer Machine Learning with support for CNN, ANN, and Decision Trees

Bosse Stefan

Annals of Computer Science and Information Systems

2023

Vol. 35

367--376

Tiny Machine Learning is a new approach that is being used for data-driven prediction classification and regression on microcontrollers using local sensor data. The models are typically learned off-line and sent to the microcontroller for use as binary objects or frozen and converted static data. This approach is not universal or flexible. The REXA VM introduced in this work, which can virtualize embedded systems and sensor nodes and includes a general machine learning framework that supports arbitrary dynamic ANN and decision tree (DT) models, is introduced in this study. The models are delivered as text files with highly compressed program code that are enclosed in code frames with embedded data (model parameters). The VM offers fundamental computations for ANN and DT models (Microservices). Using a decompiler, models can be updated (retrained) and sent to other nodes (mobile models). It can be demonstrated that virtualization using a bytecode machine and just-in-time compiler is still appropriate and effective for extremely low-resource processors.

Wireless Agent-based Distributed Sensor Tuple Spaces using Bluetooth and IP Broadcasting

Bosse Stefan

Annals of Computer Science and Information Systems

2022

Vol. 30

601--604

Most Internet-of-Things (IoT) devices and smart sensors are connected via the Internet using IP communication directly collected by a server periodically or event-based. Although, Internet access is widely available, there are places that are not covered and WLAN and mobile cell communication requires a descent amount of power not always available. Finally, the spatial context with respect to data and communication is not reflected accurately by Internet connectivity. In this work, devices communicate connectionless and ad-hoc by using low-energy Bluetooth broadcasting available in any smartphone and in most embedded computers, e.g., the Raspberry PI devices. Bi-directional connectionless communication is established via the advertisements and scanning modes. The communication nodes can exchange data via functional tuples using a tuple space service on each node. Tuple space access and routing is performed by simple event-based agents. Mobile devices act as tuple carriers that can carry tuples between different locations. Additionally, UDP-based Intranet communication can be used to access tuple spaces on a wider spatial range. The Bluetooth Low Energy Tuple Space (BeeTS) service enables opportunistic, ad-hoc and loosely coupled agent-based device communication with a spatial context.