In indoor fire rescue, swift and precise fire source localization and fire severity assessment are pivotal for firefighting strategic planning and casualty evacuation. However, existing solutions primarily focus on detecting fire presence, which do not offer insights into fire's localization and severity. In this paper, we propose UltraFlame, an accurate, user-friendly, and timely system for pinpointing fire sources and assessing fire severity based on acoustic sensing, which bridges significant gaps in fire safety and response. UltraFlame consists of a collocated commodity speaker and microphone pair, sensing fire by emitting inaudible sound waves. We conduct an in-depth investigation of sound propagation impacted by fire combustion, providing physically interpretable data for deep learning framework and enabling fire source localization even without any sound reflection by fire. We dedicatedly establish a correlation between fire severity and sound propagation delays, which serves as an effective indicator for estimating the heated region. Finally, an appropriate deep learning framework is employed to effectively extract temporal and spatial features from channel measurement. Extensive experiments demonstrate that 94% of the localization results have an error of less than 0.8m. Additionally, UltraFlame achieves an accuracy of 96.9% in fire severity assessment across diverse setups, providing real-time and reliable monitoring.

The precise classification of human activities through sensor data collection and analysis addresses the broad demands in healthcare, security surveillance, and smart home applications amidst the rapid development of IoT technology. However, achieving high efficiency and accuracy remains a significant challenge for HAR algorithms. This paper proposes a HAR algorithm based on Transformer and Random Forest (Transformer-RF). The algorithm extracts and integrates multimodal features in the time domain, frequency domain, and statistical metrics, constructing one-dimensional and two-dimensional feature sets through feature transformation. The Transformer component, leveraging self-attention mechanisms, captures long-range dependencies and extracts global contextual information. Concurrently, the Random Forest component randomly selects features and samples, enhancing model diversity and improving complex human activity recognization capabilities. Experimental results demonstrate that compared with state-of-the-art algorithms, the Transformer-RF model achieves superior performance on both one-dimensional and two-dimensional feature sets, with an accuracy of up to 94.17%. The primary contribution of this paper lies in the introduction of an innovative Transformer-RF human activity recognization method, which not only ensures high accuracy but also exhibits excellent generalization capability and practical application potential. This study provides new insights and technical solutions for the field of human activity recognization, offering significant theoretical and practical value.

Human Activity Recognition has been extensively applied to fulfill tasks such as fall detection, human-computer interaction, virtual reality, etc. Existing radio frequency-based HAR methods, although overcoming limitations of wearable-, visual-, and acoustic-based sensing technology, still suffer from high costs and low efficiency, which limits their pervasive use. In this paper, we propose LoDiHAR, a low-cost, distributed HAR system leveraging Radio Frequency Identification technology. LoDiHAR employs low-cost and fully programmable commercial wireless components, providing full access to the PHY samples of the backscattered signals, in which signal phases can be extracted to infer different activities. Different from COTS RFID systems that adopt a polling interrogation scheme, LoDiHAR supports a distributed sensing scheme, which profiles human activities more efficiently. LoDiHAR addresses a series of technical challenges such as accurate phase extraction from backscattered signals, asynchronous distributed RF data fusion and insufficient training data. A Conditional Generative Adversarial Network framework combined with a Transformer model is designed for accurate time-series activity classification. LoDiHAR demonstrates pro-ficiency in recognizing eight types of human activities across diverse environments, achieving an accuracy of up to 94.9% while only costing 10% of the mainstream COTS RFID systems.

As a promising way, controlling smart devices through gestures offers the benefits of non-contact interaction, efficiency and convenience. Previous researches on acoustic-based gesture recognition have mostly focused on near-field gestures within 1 meter and for a single user only. However, such a nearfield sensing scheme is inadequate to meet the growing demands for multi-person human-computer interaction in far-field spaces. In this paper, we present a novel acoustic-based room-scale gesture recognition system that is capable of recognizing gestures simultaneously performed by multi-user. Our approach achieves far-field sensing by examining the relationship between acoustic signal frame length and sensing range, and overcoming a series of practical challenges incurred by far-field sensing. To simultaneously detect and distinguish gestures of multiple persons, we divide the sensing area into multiple beamforming sub-scanning areas and apply binary search to detect multiple users, which allows for an efficient scanning process and facilitates real-time detection. Finally, we conduct a data augmentation scheme to enlarge the training data and apply a lightweight deep learning framework to classify different gestures. Extensive experiments confirm that our system enables multi-user gesture detection and can recognize nine gestures at a distance up to 7 meters.

In a fire emergency, timely and precise firefighting and emergency response significantly rely on rapid fire source location and fire severity assessment. Yet existing fire detection methods have limitations such as environmental interference, inaccurate fire source location, and inability to assess fire severity. We propose UltraFlame, an innovative acoustic fire sensing system that combines the functionality of fire detection, source localization, and fire severity estimation. Our approach utilizes high-frequency ultrasound waves (40kHz) and involves a Two-Stage Sector Beamforming (TSSB) method for real-time fire localization. Additionally, we develop a mathematical model linking fire source distance and severity, enabling real-time fire severity estimation with limited computational complexity. The experimental results suggest that UltraFlame will provide accurate fire source localization and fire severity assessment.

Recently, a major effort has been made to develop methods or tools for rock characterization and mineral content mapping. Light detection and ranging (LiDAR) is an efficient active remote sensing technique for collecting geometry information about rock surfaces. However, traditional LiDAR sensors work with a single-wavelength laser source, and it is unfeasible to obtain spectral information using one LiDAR sensor. The combination of hyperspectral imaging and LiDAR techniques is an emerging method for acquiring spatial and spectral information simultaneously that allows remote mapping of high-resolution mineral content and distributions and identifies subtle chemical variations. Unfortunately, spatial and spectral data registration, which introduces additional complicated data processing, is an inevitable and essential issue for this method. In this letter, first, we investigate the feasibility of ore classification applications with hyperspectral LiDAR (HSL). HSL consists of 17 spectral channels covering the visible–shortwave infrared (SWIR) spectral range. Spatial and spectral information about seven different ore samples is obtained under a controlled laboratory environment using HSL. The standard deviation of the distance measurements is less than 1.1 cm for different spectral channels, and the classification accuracy can reach 100% if all 17 spectral measurements are used. To optimize the system design with lower cost and system complexity, a spectral band selection criterion is built based on the feature contribution degree (FCD), which is calculated using the normalized variance of the reflectance values for different ore samples at each wavelength. Two different strategies of FCD selection are tested to generate vectors: ascending sequences and descending sequences. Feature vectors with descending sequences have better classification accuracy. In addition, the results show that the classification accuracy can reach 100% with the feature vector of the seven largest FCD values compared to 59.57% for the feature vector with the seven smallest FCD values. Moreover, we find that the channels with high FCD values are primarily centered in SWIR bands. This result could be a reference for optimizing the hardware design of HSL for ore classification or mineral identification.