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: In this paper, the authors consider the problem of human activity recognition using triaxial accelerometers and deep learning paradigms and show that deep activity recognition models can provide better recognition accuracy of human activities, avoid the expensive design of handcrafted features in existing systems, and utilize the massive unlabeled acceleration samples for unsupervised feature extraction.

TL;DR: In this article, a deep learning-based multimodal fusion architecture for classification tasks is proposed, which guarantees compatibility with any kind of learning models, deals with cross-modal information carefully, and prevents performance degradation due to partial absence of data.

TL;DR: In this article, an ensemble of deep Long Short Term Memory (LSTM) networks is proposed for real-life applications of human activity recognition using wearable devices. And the ensemble of LSTM networks outperforms individual LSTMs.

TL;DR: In this paper, a category traversal module is proposed to identify task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space, which can be inserted as a plug-and-play module into most metric-learning based few-shot learners.