Search

Radar-based fall detection technology has attracted much attention for its high accuracy, robustness, and privacy preservation potential. Detection of “Soft Fall,” i.e., high-freedom fall, is the key to practical application. This letter proposes a novel height-tracking method based on a multiple-input multiple-output (MIMO) radar system to address this problem. First, the received signal was segmented into a time sequence with a sliding window along slow time. Next, fast Fourier transform (FFT) and multiple signal classification (MUSIC) algorithms were applied to estimate the general trend of the human body’s time-varying range and pitch angle information. Then, they were fused with a geometrical relationship to describe height changes during fall motions using a height trajectory map. Two height-based features were extracted as input to support vector machine (SVM) to distinguish soft fall and fall-similar motions. Finally, experiments, including four soft fall and five typical fall-similar motions, were conducted to demonstrate its feasibility and superiority. [ABSTRACT FROM AUTHOR]

Cancelable biometrics is a powerful remedy for information leakage caused by the extensive usage of unprotected biometric data. Current measures usually suffer from deteriorated accuracy, which is known as the security–performance tradeoff. Motivated by these concerns, in this article, a novel cancelable fingerprint approach, i.e., Indexing-Min–Max (IMM) hashing, is proposed to securely transform a fixed-length fingerprint feature vector to a discrete index hashed code. IMM hashing is essentially established upon the min–max hash and further strengthened by the integration of the partial Hadamard transform, which alleviates performance deterioration while maintaining a high security level. Extensive experiments on FVC2002 and FVC2004 fingerprint datasets coupled with comprehensive theoretical analyses demonstrate the favorable accuracy and strong anti-attack resilience of the proposed method. Besides, compared to the unprotected counterpart, the matching precision of the protected templates yields little accuracy loss or even improved performance, which means the security–performance tradeoff is well handled. Furthermore, IMM hashing also meets the unlinkability and revocability requisites of cancelable biometrics. [ABSTRACT FROM AUTHOR]

Visual food recognition on mobile devices has attracted increasing attention in recent years due to its roles in individual diet monitoring and social health management and analysis. Existing visual food recognition approaches usually use large server-based networks to achieve high accuracy. However, these networks are not compact enough to be deployed on mobile devices. Even though some compact architectures have been proposed, most of them are unable to obtain the performance of full-size networks. In view of this, this paper proposes a Joint-learning Distilled Network (JDNet) that targets to achieve a high food recognition accuracy of a compact student network by learning from a large teacher network, while retaining a compact network size. Compared to the conventional one-directional knowledge distillation methods, the proposed JDNet has a novel joint-learning framework where the large teacher network and the small student network are trained simultaneously, by leveraging on different intermediate layer features in both network. JDNet introduces a new Multi-Stage Knowledge Distillation (MSKD) for simultaneous student-teacher training at different levels of abstraction. A new Instance Activation Learning (IAL) is also proposed to jointly train student and teacher on instance activation map of each training sample. Experimental results show that the trained student model is able to achieve a state-of-the-art Top-1 recognition accuracy on the benchmark UECFood-256 and Food-101 datasets at 84.0% and 91.2%, respectively, and retaining a 4x smaller network size for mobile deployment. [ABSTRACT FROM AUTHOR]

This article covers radar signal processing for sensing in the context of assisted living (AL). This is presented through three example applications: human activity recognition (HAR) for activities of daily living (ADL), respiratory disorders, and sleep stages (SSs) classification. The common challenge of classification is discussed within a framework of measurements/preprocessing, feature extraction, and classification algorithms for supervised learning. Then, the specific challenges of the three applications from a signal processing standpoint are detailed in their specific data processing and ad hoc classification strategies. Here, the focus is on recent trends in the field of activity recognition (multidomain, multimodal, and fusion), health-care applications based on vital signs (superresolution techniques), and comments related to outstanding challenges. Finally, this article explores challenges associated with the real-time implementation of signal processing/classification algorithms. [ABSTRACT FROM AUTHOR]

Personal videos often contain visual distractors, which are objects that are accidentally captured and can distract viewers from focusing on the main subjects. We propose a method to automatically detect and localize these distractors through learning from a manually labeled dataset. To achieve spatially and temporally coherent detection, we propose extracting features at the temporal-superpixel level using a traditional supporting vector machine based learning framework. We also experiment with end-to-end learning using convolutional neural networks, which achieves slightly higher performance than other methods. The classification result is further refined in a postprocessing step based on graph-cut optimization. Experimental results show that our method achieves an accuracy of 81% and a recall of 86%. We demonstrate several ways of removing the detected distractors to improve the video quality, including video hole filling, video frame replacement, and camera path replanning. The user study results show that our method can significantly improve the aesthetic quality of videos. [ABSTRACT FROM AUTHOR]

The ability to identify electric shock in the human body is a crucial consideration in the design of touch/leakage protective devices. In this paper, the $\alpha$ -dispersion characteristics of electrical impedance in the human body are investigated based on the Cole–Cole model. An improved electric shock identification method is proposed accordingly. The effects of various factors (e.g., transition resistance and feeder reactance) on the accuracy and reliability are analyzed. Feasibility and effectiveness of the method are verified via numerical simulation. The results indicate that 1) $\alpha$-dispersion is an effective feature for distinguishing living or nonliving organisms; 2) the proposed method is robust and unaffected by transition resistance; and 3) the computational cost is low to satisfy standard leakage current protective device requirements. This paper provides a solution to the dead-zone problem as well as a set of workable guidelines for protective device design. [ABSTRACT FROM AUTHOR]