Transfer Learning in Smart Environments

Abstract

The knowledge embodied in cognitive models of smart environments, such as machine learning models, is commonly associated with time-consuming and costly processes such as large-scale data collection, data labeling, network training, and fine-tuning of models. Sharing and reuse of these elaborated resources between intelligent systems of different environments, which is known as transfer learning, would facilitate the adoption of cognitive services for the users and accelerate the uptake of intelligent systems in smart building and smart city applications. Currently, machine learning processes are commonly built for intra-organization purposes and tailored towards specific use cases with the assumption of integrated model repositories and feature pools. Transferring such services and models beyond organization boundaries is a challenging task that requires human intervention to find the matching models and evaluate them. This paper investigates the potential of communication and transfer learning between smart environments in order to empower a decentralized and peer-to-peer ecosystem for seamless and automatic transfer of services and machine learning models. To this end, we explore different knowledge types in the context of smart built environments and propose a collaboration framework based on knowledge graph principles for describing the machine learning models and their corresponding dependencies.

Blockchain as an Enabler for Transfer Learning in Smart Environments

“…As proof of concept, we have implemented a prototype based on the proposed methodology. In this section, we provide an overview of the technical architecture which is depicted in Figure 8 extends our previous implementation of ISL framework for knowledge sharing between smart environments [1].…”

“…Improvement of the energy performance of buildings is a major contributor for achieving the goals of the EU 2030 climate and energy framework 1 . By 2050 at least 75% of today's buildings will still exist and as a result, renovation of existing buildings and making them energy-efficient will have significant economic and environmental impacts.…”

“…In our previous work, we introduced the Inter-Space Learning Framework (ISL) [1] Which uses knowledge graph as an efficient medium for communicating the semantics of smart environments and bridging the information gap among IoT infrastructure, spaces, and machine learning processes.…”

“…In this research, we propose a decentralized and adaptive software framework based on blockchain and knowledge graph technologies for reliable and decentralized transfer of machine learning digital assets between AI-enabled smart environments such as smart buildings and smart city, in a transparent and trustworthy way. The proposed approach in this research follows the principles of Inter-Space Learning (ISL) framework [1] that was presented ion our previous work. Using ISL framework, smart environment resources are processed, aligned, and reconciled to create a uniform and interconnected information space that facilitates provisioning of the Inter-space learning.…”

Analysis and Simulation of Improved Seismic Data using Adaptive Processing by National Data Centre Iraq

“…By incorporating machine learning features, algorithms can better analyze and interpret complex data patterns, improving decision-making and problem-solving capabilities (Wang et al, 2021). These features can be derived from various sources, such as text mining tools, web indexing and search algorithms, social media inputs, and deep learning algorithms (Anjomshoaa & Curry, 2021).…”