Meta-learning meets the Internet of Things: Graph prototypical models for sensor-based human activity recognition

TL;DR: In this paper , a multi-level feature fusion technique for multimodal human activity recognition using multi-head CNN with Convolution Block Attention Module (CBAM) to process the visual data and Convolutional Long Short Term Memory (ConvLSTM) for dealing with the time-sensitive multi-source sensor information.

TL;DR: A novel FSOD taxonomy method is proposed and the plentifully remarkable FSOD algorithms are surveyed based on this fact to report a comprehensive overview that facilitates a deeper understanding of the FSOD problem and the development of innovative solutions.

TL;DR: In this paper , the authors proposed a novel device-free method based on Time-Streaming Multiscale Transformer (TransTM), which leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.

TL;DR: The motive of the proposed concept is to address limitations by connecting the sensors with an Internet of Things network and cloud platform for remote recording and monitoring purposes by utilizing the Blynk IoT application and cloud server for the analytics.

TL;DR: The Screenkhorn algorithm, a novel strategy for efficiently approximating the Sinkhorn distance between two discrete measures, is introduced, based on a new formulation of dual of Sinkinghorn divergence problem and on the KKT optimality conditions of this problem, which enable identification of dual components to be screened.

TL;DR: A novel semi-supervised classifier (OSC) that works together with a novel Bayesian stream-based active learning (BSAL) strategy to selectively query the user/resident about the label of particular activities in order to improve the model accuracy is proposed.

Abstract: Human activity recognition is commonly used in several Internet of Things applications to recognize different contexts and respond to them. Deep learning has gained momentum for identifying activities through sensors, smartphones or even surveillance cameras. However, it is often difficult to train deep learning models on constrained IoT devices. The focus of this paper is to propose an alternative model by constructing a Deep Learning-based Human Activity Recognition framework for edge computing, which we call DL-HAR. The goal of this framework is to exploit the capabilities of cloud computing to train a deep learning model and deploy it on lesspowerful edge devices for recognition. The idea is to conduct the training of the model in the Cloud and distribute it to the edge nodes. We demonstrate how the DL-HAR can perform human activity recognition at the edge while improving efficiency and accuracy. In order to evaluate the proposed framework, we conducted a comprehensive set of experiments to validate the applicability of DL-HAR. Experimental results on the benchmark dataset show a significant increase in performance compared with the stateof-the-art models.

TL;DR: This paper proposes an adaptive task sampling method, which selects difficult tasks according to class-pair potentials and achieves consistent improvements across different feature backbones, meta-learning algorithms and datasets.