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.

Human activity recognition (HAR) utilizing wearable sensors is a prominent topic in academia, and has been widely used in health monitoring, medical treatment, motion analysis, and other fields. Although HAR technology based on deep learning has made some progress, there are still some problems such as incomplete feature extraction and low utilization rate of features, which may result in false recognition. To settle the problems, we propose a novel deep multi-feature extraction framework based on attention mechanism (DMEFAM), which includes the temporal attention feature extraction layer (TAFEL), the channel and spatial attention feature extraction layer (CSAFEL), and the output layer. The TAFEL is comprised of bidirectional gated recurrent units (Bi-GRU) and self-attention (SA) mechanism, and the CSAFEL is comprised of convolutional block attention module (CBAM) and residual network-18 (ResNet-18). In this framework, the combination of deep learning neural networks, SA mechanism, and CBAM assigns different important degrees to features, increases the diversities of feature extraction, and improves the accuracy of HAR. To improve the practicability of the proposed framework, a daily and aggressive activity dataset (DAAD) is collected by our laboratory for performance evaluation. The experiments are conducted on the wireless sensor data mining laboratory (WISDM) dataset, the University of California Irvine-HAR (UCI-HAR) dataset, and the collected DAAD dataset. The results show that the proposed DMEFAM can upgrade the recognition performance effectually, compared to other advanced HAR frameworks, with recognition accuracies of 97.9%, 96.0% and 99.2% on the WISDM dataset, the UCI-HAR dataset, and the DAAD dataset, respectively.

Source camera identification has long been a hot topic in the field of image forensics. Besides conventional feature engineering algorithms developed based on studying the traces left upon shooting, several deep-learning-based methods have also emerged recently. However, identification performance is susceptible to image content and is far from satisfactory for small image patches in real demanding applications. In this paper, an efficient patch-level source camera identification method is proposed based on a convolutional neural network. First, in order to obtain improved robustness with reduced training cost, representative patches are selected according to multiple criteria for enhanced diversity in training data. Second, a fine-grained multiscale deep residual prediction module is proposed to reduce the impact of scene content. Finally, a modified VGG network is proposed for source camera identification at brand, model, and instance levels. A more critical patch-level evaluation protocol is also proposed for fair performance comparison. Abundant experimental results show that the proposed method achieves better results as compared with the state-of-the-art algorithms.

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.