Timely calls for help can really make a difference for elders who suffer from falls, particularly in private locations. Considering privacy protection and convenience for the users, in this paper, we approach the problem by using impulse–radio ultra-wideband (IR-UWB) monostatic radar and propose a learning model that combines convolutional layers and convolutional long short term memory (ConvLSTM) to extract robust spatiotemporal features for fall detection. The performance of the proposed scheme was evaluated in terms of accuracy, sensitivity, and specificity. The results show that the proposed method outperforms convolutional neural network (CNN)-based methods. Of the six activities we investigated, the proposed method can achieve a sensitivity of 95% and a specificity of 92.6% at a range of 8 meters. Further tests in a heavily furnished lounge environment showed that the model can detect falls with more than 90% sensitivity, even without re-training effort. The proposed method can detect falls without exposing the identity of the users. Thus, the proposed method is ideal for room-level fall detection in privacy-prioritized scenarios.

Passive indoor localization has gained much attention recently. Numerous applications including storage management and somatosensory systems would benefit from accurate passive indoor localization. As a potential technology for the internet of things, radio frequency identification (RFID) has many advantages for indoor localization, such as low cost, parallel processing, and low complexity. In this paper, a passive indoor localization system, named Lobain, was proposed based on interference of ultrahigh frequency RFID tags. Using commercial off-the-shelf reader, antenna, and tags, this system, functions for tagged and tag-free item localization in 2-D and 3-D indoor environments. Small numbers of reference tags were used as sensors to improve performance and reduce cost. Unlike traditional methods, an improved propagation model and an innovative method were presented to extract a target's channel information from a complicated received signal. A relative phase wrapping integer method was presented to solve the phase wrapping problem of reference tags, and the least-squares method was used to optimize the tradeoff between number of reference tags and accuracy. A tag and tag-free items including shrimp chips, cola, and instant noodles were localized as single target in the evaluation experiments. The prototype achieved mean 2-D median localization errors of 5.9 (x-axis) and 8.2 cm (y-axis), and achieved mean 3-D median errors of 9 (x-axis), 6.7 (y-axis), and 13.3 cm (z-axis).

Automatic modulation classification (AMC) is the premise for signal detection and demodulation applications, especially in non-cooperative communication scenarios. It has been a popular topic for decades and has gained significant progress with the development of deep learning methods. To further improve classification accuracy, a hierarchical multifeature fusion (HMF) based on a multidimensional convolutional neural network (CNN)-long short-term memory (LSTM) network is proposed in this paper. First, a multidimensional CNN module (MD-CNN) is proposed for feature compensation between interactive features extracted by two-dimensional convolutional filters and respective features extracted by one-dimensional filters. Second, learnt features of the MD-CNN module are fed into an LSTM layer for further exploitation of temporal features. Finally, classification results are obtained by the Softmax classifier. The effectiveness of the proposed method is verified by abundant experimental results on two public datasets, RadioML.2016.10a and RadioML.2016.10b. Satisfying results are obtained as compared with state-of-the-art methods.