A review and categorization of techniques on device-free human activity recognition

Wearable human machine interfaces (HMI) such as smart gloves have attracted considerable interest in recent years. The quality of the interactive experience with the real and virtual world using wearable HMI technologies depends on the intuitive two‐way haptic interfaces they offer and the real‐time touch‐based information they send and receive. Herein, various smart glove solutions and their application in interaction, rehabilitation, virtual (VR) and augmented reality (AR), and augmentative and alternative communication (AAC) tasks are reviewed. While the early variants of such systems were based on commercial touch sensors and displays integrated (e.g., stitched) on wearables, electronic skin (e‐skin)‐type technologies with multifunctional capabilities are being explored nowadays for rich user experience and comfort. In this regard, instead of using separate touch sensors and actuators, miniaturized integrated devices providing both touch sensing and vibrotactile actuation have also been reported recently. Such advances, the associated challenges, and the advantages they offer for users to enjoy the full characteristic benefits of VR/ARs for interaction, immersion, and imagination are discussed. Finally, the huge potential the smart‐glove‐type solutions hold for advances in various application areas such as robotics, health care, sensorial augmentation for nondisabled and tactile Internet is also discussed.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/aisy.202100091

Smart Tactile Gloves for Haptic Interaction, Communication, and Rehabilitation

Device free human gesture recognition using Wi-Fi CSI: A survey

Low-cost consumer radar integrated circuits combined with recent advances in machine learning have opened up a range of new possibilities in smart sensing. In this paper, we use a miniature radar sensor to capture Doppler signatures of 14 different hand gestures and train a deep convolutional neural network (DCNN) to classify these captured gestures. We utilize two receiving antennas of a continuous-wave Doppler radar capable of producing the in-phase and quadrature components of the beat signals. We map these two beat signals into three input channels of a DCNN as two spectrograms and an angle of arrival matrix. The classification results of the proposed architecture show a gesture classification accuracy exceeding 95% and a very low confusion between different gestures. This is almost 10% improvement over the single-channel Doppler methods reported in the literature.

Hand-Gesture Recognition Using Two-Antenna Doppler Radar With Deep Convolutional Neural Networks

The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a novel perspective revealing the two key factors in information utilization: class-relevance and redundancy. We derive a new information decomposition model where a novel concept called class-relevant redundancy is introduced. Subsequently a new algorithm called Conditional Informative Feature Extraction is formulated, which maximizes the joint class-relevant information by explicitly reducing the class-relevant redundancies among features. To address the computational difficulties in information-based optimization, we incorporate Parzen window estimation into the discrete approximation of the objective function and propose a Local Active Region method which substantially increases the optimization efficiency. To effectively utilize the extracted feature set, we propose a Bayesian MAP formulation for feature fusion, which unifies Laplacian Sparse Prior and Multivariate Logistic Regression to learn a fusion rule with good generalization capability. Realizing the inefficiency caused by separate treatment of the extraction stage and the fusion stage, we further develop an improved design of the framework to coordinate the two stages by introducing a feedback from the fusion stage to the extraction stage, which significantly enhances the learning efficiency. The results of the comparative experiments show remarkable improvements achieved by our framework.

Conditional Infomax Learning : An Integrated Framework for Feature Extraction and Fusion

DF-WiSLR: Device-Free Wi-Fi-based Sign Language Recognition

Device-free human gesture recognition (HGR) using commercial off the shelf (COTS) Wi-Fi devices has gained attention with recent advances in wireless technology. HGR recognizes the human activity performed, by capturing the reflections of Wi-Fi signals from moving humans and storing them as raw channel state information (CSI) traces. Existing work on HGR applies noise reduction and transformation to pre-process the raw CSI traces. However, these methods fail to capture the non-Gaussian information in the raw CSI data due to its limitation to deal with linear signal representation alone. The proposed higher order statistics-based recognition (HOS-Re) model extracts higher order statistical (HOS) features from raw CSI traces and selects a robust feature subset for the recognition task. HOS-Re addresses the limitations in the existing methods, by extracting third order cumulant features that maximizes the recognition accuracy. Subsequently, feature selection methods derived from information theory construct a robust and highly informative feature subset, fed as input to the multilevel support vector machine (SVM) classifier in order to measure the performance. The proposed methodology is validated using a public database SignFi, consisting of 276 gestures with 8280 gesture instances, out of which 5520 are from the laboratory and 2760 from the home environment using a 10 × 5 cross-validation. HOS-Re achieved an average recognition accuracy of 97.84%, 98.26% and 96.34% for the lab, home and lab + home environment respectively. The average recognition accuracy for 150 sign gestures with 7500 instances, collected from five different users was 96.23% in the laboratory environment.

https://www.mdpi.com/1424-8220/19/13/2959/pdf

Higher Order Feature Extraction and Selection for Robust Human Gesture Recognition using CSI of COTS Wi-Fi Devices

Today, blockchain is becoming more popular in academia and industry because it is a distributed, decentralised technology which is changing many industries in terms of security, building trust, etc. A few blockchain applications are banking, insurance, logistics, transportation, etc. Many insurance companies have been thinking about how blockchain could help them be more efficient. There is still a lot of hype about this immutable technology, even though it has not been utilised to its full potential. Insurers have to decide whether or not to use blockchain, just like many other businesses do. This technology keeps a distributed ledger on each blockchain node, making it more secure and transparent. The blockchain network can operate smart contracts and convince others to agree, so criminals cannot make mistakes. On another side, the Internet of Things (IoT) might make a real-time application work faster through its automation. With the integration of blockchain and IoT, there will always be a problem with technology regarding IoT devices and mining the blockchain. This paper gives a real-time view of blockchain—IoT-based applications for Industry 4.0 and Society 5.0. The last few sections discuss essential topics such as open issues, challenges, and research opportunities for future researchers to expand research in blockchain—IoT-based applications.

/pdf/blockchain-internet-of-things-applications-opportunities-and-2d2yhrd4.pdf

Blockchain—Internet of Things Applications: Opportunities and Challenges for Industry 4.0 and Society 5.0

Wildfire early detection and prevention had become a priority. Detection using Internet of Things (IoT) sensors, however, is expensive in practical situations. The majority of present wildfire detection research focuses on segmentation and detection. The developed machine learning models deploy appropriate image processing techniques to enhance the detection outputs. As a result, the time necessary for data processing is drastically reduced, as the time required rises exponentially with the size of the captured pictures. In a real-time fire emergency, it is critical to notice the fire pixels and warn the firemen as soon as possible to handle the problem more quickly. The present study addresses the challenge mentioned above by implementing an on-site detection system that detects fire pixels in real-time in the given scenario. The proposed approach is accomplished using Deeplabv3+, a deep learning architecture that is an enhanced version of an existing model. However, present work fine-tuned the Deeplabv3 model through various experimental trials that have resulted in improved performance. Two public aerial datasets, the Corsican dataset and FLAME, and one private dataset, Firefront Gestosa, were used for experimental trials in this work with different backbones. To conclude, the selected model trained with ResNet-50 and Dice loss attains a global accuracy of 98.70%, a mean accuracy of 89.54%, a mean IoU 86.38%, a weighted IoU of 97.51%, and a mean BF score of 93.86%.

/pdf/assessing-the-impact-of-the-loss-function-and-encoder-gha45x56.pdf

Hasmath Farhana Thariq Ahmed

Papers

Device free human gesture recognition using Wi-Fi CSI: A survey

DF-WiSLR: Device-Free Wi-Fi-based Sign Language Recognition

Higher Order Feature Extraction and Selection for Robust Human Gesture Recognition using CSI of COTS Wi-Fi Devices

Blockchain—Internet of Things Applications: Opportunities and Challenges for Industry 4.0 and Society 5.0

Assessing the Impact of the Loss Function and Encoder Architecture for Fire Aerial Images Segmentation Using Deeplabv3+