Recent advances in mobile devices have made profound changes in people's daily lives. In particular, the impact of easy access of information by the smartphone has been tremendous. However, the impact of mobile devices on healthcare has been limited. Diagnosis and treatment of diseases are still initiated by occurrences of symptoms, and technologies and devices that emphasize on disease prevention and early detection outside hospitals are under-developed. Besides healthcare, mobile devices have not yet been designed to fully benefit people with special needs, such as the elderly and those suffering from certain disabilities, such blindness. In this paper, an overview of our research on a new wearable computer called eButton is presented. The concepts of its design and electronic implementation are described. Several applications of the eButton are described, including evaluating diet and physical activity, studying sedentary behavior, assisting the blind and visually impaired people, and monitoring older adults suffering from dementia.

Semantic segmentation is a key step in scene understanding for autonomous driving. Although deep learning has significantly improved the segmentation accuracy, current highquality models such as PSPNet and DeepLabV3 are inefficient given their complex architectures and reliance on multi-scale inputs. Thus, it is difficult to apply them to real-time or practical applications. On the other hand, existing real-time methods cannot yet produce satisfactory results on small objects such as traffic lights, which are imperative to safe autonomous driving. In this paper, we improve the performance of real-time semantic segmentation from two perspectives, methodology and data. Specifically, we propose a real-time segmentation model coined Narrow Deep Network (NDNet) and build a synthetic dataset by inserting additional small objects into the training images. The proposed method achieves 65.7% mean intersection over union (mIoU) on the Cityscapes test set with only 8.4G floatingpoint operations (FLOPs) on 1024×2048 inputs. Furthermore, by re-training the existing PSPNet and DeepLabV3 models on our synthetic dataset, we obtained an average 2% mIoU improvement on small objects.

It has been reported that the pulse transit time (PTT), the interval between the peak of the R-wave in electrocardiogram (ECG) and the fingertip photoplethysmogram (PPG), is related to arterial stiffness, and can be used to estimate the systolic blood pressure (SBP) and diastolic blood pressure (DBP). This phenomenon has been used as the basis to design portable systems for continuously cuff-less blood pressure measurement, benefiting numerous people with heart conditions. However, the PTT-based blood pressure estimation may not be sufficiently accurate because the regulation of blood pressure within the human body is a complex, multivariate physiological process. Considering the negative feedback mechanism in the blood pressure control, we introduce the heart rate (HR) and the blood pressure estimate in the previous step to obtain the current estimate. We validate this method using a clinical database. Our results show that the PTT, HR and previous estimate reduce the estimated error significantly when compared to the conventional PTT estimation approach (p<;0.05).

This paper studies the behavior of recurrent neural networks with lateral inhibition. Such network architecture is important in biological neural systems. General conditions determining the existence, number, and stability of network equilibria are derived. The manner in which these features depend upon steepness of neuronal activation functions and the strength of lateral inhibition is demonstrated for a broad range of nondecreasing activation functions including the discontinuous threshold function which represents the infinite gain limit. For uniform lateral inhibitory networks, the lateral inhibition is shown to sharpen neuron output patterns by increasing separation of suprathreshold activity levels of competing neurons. This results in the tendency of one neuron's output to dominate those of the others which can afford a "winner-take-all" (WTA) mechanism. Importantly, multiple stable equilibria may exist and shifts in inputs levels may yield network state transitions that exhibit hysteresis. A limitation of using lateral inhibition to implement WTA is further demonstrated. The possible significance of these identified network dynamics to physiology and pathophysiology of the striatum (particularly in Parkinsonian rest tremor) is discussed

Polyphase permanent magnet synchronous motors exhibit outstanding advantages over the traditional three-phase traction motors in electrified transportation applications. This manuscript introduces a novel direct-torque model predictive control technique aiming at developing a highly reliable, loss-minimizing and energy efficient five-phase permanent magnet synchronous motor drive. Leveraging the underlying constrained optimization process, the direct torque model predictive control approach optimizes the torque delivery and speed regulation quality, improves the flux and torque ripples, reduces higher-order current harmonics, minimizes motor drive losses, and boosts power efficiency of the electric powertrain. dSPACE DS1104 hardware-in-the-loop and computer simulation studies are jointly utilized to verify the effectiveness and robustness of the proposed direct torque model predictive control approach in polyphase permanent magnet synchronous motor drive applications.

The rapid development of autonomous driving in recent years presents many challenges for scene understanding. As an essential step towards scene understanding, semantic segmentation has received increased attention in the past few years. Although deep learning based approaches have achieved great success in improving the segmentation accuracy, most of them suffer from an inefficiency problem and can hardly be applied to real-time applications. In this paper, we analyze the computational cost of Convolutional Neural Network (CNN) and find that the inefficiency of CNNs is mainly caused by their wide structure rather than deep structure. In addition, the success of pruning based model compression methods proves that there are many redundant channels in CNNs. Thus, we design a narrow while deep backbone network to improve the efficiency of semantic segmentation. By casting our network to fully convolutional network (FCN32) segmentation architecture, the basic structure of most segmentation methods, we achieve 61.5% mIoU on Cityscapes validation dataset with only 4.2G floating-point operations (FLOPs) on 1024x2048 inputs, which already outperforms one of the earliest real-time deep learning based segmentation methods: ENet (58.3% mIoU, 3.8G FLOPs on 640x360 inputs). By further refining the output resolution of our network to the 1/8 of the input resolution with a simple encoder-decoder structure, we achieve 65.3% mIoU on Cityscapes test set with 14.0G FLOPs and 39.9 frames per second (FPS) on Titan X card. We have made our model publicly available at https://github.com/zgyang-hnu/NDNet.