Search

In this paper, we used electroencephalography (EEG)-eye movement (EM) synchronization acquisition network to simultaneously record both EEG and EM physiological signals of the mild depression and normal controls during free viewing. Then, we consider a multimodal feature fusion method that can best discriminate between mild depression and normal control subjects as a step toward achieving our long-term aim of developing an objective and effective multimodal system that assists doctors during diagnosis and monitoring of mild depression. Based on the multimodal denoising autoencoder, we use two feature fusion strategies (feature fusion and hidden layer fusion) for fusion of the EEG and EM signals to improve the recognition performance of classifiers for mild depression. Our experimental results indicate that the EEG-EM synchronization acquisition network ensures that the recorded EM and EEG data require that both the data streams are synchronized with millisecond precision, and both fusion methods can improve the mild depression recognition accuracy, thus demonstrating the complementary nature of the modalities. Compared with the unimodal classification approach that uses only EEG or EM, the feature fusion method slightly improved the recognition accuracy by 1.88%, while the hidden layer fusion method significantly improved the classification rate by up to 7.36%. In particular, the highest classification accuracy achieved in this paper was 83.42%. These results indicate that the multimodal deep learning approaches with input data using a combination of EEG and EM signals are promising in achieving real-time monitoring and identification of mild depression.

Hypertension detection is an important global health challenge, in which there exists a large population of hypertensive people, yet a great portion of them remain undiagnosed. Recently, studies have indicated a strong correlation between early obstructive sleep apnea and the development of hypertension. Based on the relationship, we propose the smartphone hypertension detector which can detect hypertensive users by automatically monitoring user's overnight sleep behavior. The portable mobile application can serve as a premonitory detection method complementary to traditional medical detection methods. Experiments of smartphone hypertension detector have demonstrated its desired functionality and practicality for real-world deployment.

In the big data era, thousands of hundreds of devices play the role of data producer as well as data consumer. However, wireless devices bear the power exhausted problem in various situations. How to balance the trade-off between data processing speed and power efficiency is meaningful to be researched. In this study, we propose a Sleep Data Fusion Networks module (SFDN) which has a star topology Bluetooth network to fuse data of sleep-aware applications basing on our designed application protocol. In the network, a center Bluetooth device fuses data generated from target node Bluetooth devices. Due to the low power consumption of Bluetooth as well as connection safety, our method is a better choice for a long lifetime and non-real time sleep data processing and fusion tasks then the Wi-Fi-based approach used in EAST and Smart-Alarm sleep-aware applications.

As the challenge of depression problems increases today, it is important to effective and timely detect for patients' treatments and depression prevention. Current methods of automated depression diagnosis depend almost entirely on audio, video, and Electroencephalogram (EEG) etc. In this paper, we propose a novel method to detect depression using gait data that is collected by Kinect camera. Its key components include a camera rectification method and a rigid-body representation of the human body. The camera rectification method achieves the purpose of improving data processing accuracy by changing the camera angle. The rigid-body representation can not only improve the robustness of detecting depression patients with noisy input, but also can reduce the classification time. We evaluate our method on the depression gait dataset in postgraduate students. The proposed method has an outstanding performance in classic machine learning algorithms, and the best accuracy can achieve 88.89%. Our solution provides a new method for automatic depression detection (ADD) that has exciting implications in clinical theory and practice, and has the advantages of high accuracy, inexpensive, low time cost, and no-contact.

Human action recognition plays an important role in e-health applications, such as surgical skill analysis, patient monitoring, and automatic nursing systems. Recently, skeleton-based action recognition gains massive attention. It is an essential yet challenging task that requires effectively modeling the intra-frame skeleton representation and inter-frame temporal dynamics. Traditional Long Short-Term Memory (LSTM) based methods mainly capture long-term action context information from global level, yet they cannot fully model the relationship between different joints or persons to mine crucial co-occurrence features from different levels. To overcome this drawback, we propose a general end-to-end Multi-level Co-occurrence Graph Convolutional LSTM (MCGC-LSTM). By incorporating graph convolutional networks (GCN) into LSTM, our model can not only better exploit body structural information from skeletons but also enhance the multi-level co-occurrence feature learning. Specifically, we first devise multi-level co-occurrence (MC) memory units coupled with GCN to automatically model the spatial relationship between joints, and simultaneously capture the co-occurrence features from different joints, persons, and frames. Then we construct aggregated features of multi-level co-occurrences (AFMC) from MC memory units to better represent the intra-frame action context encoding, and leverage a concurrent LSTM (Co-LSTM) to further model their temporal dynamics for action recognition. Experiments show that our proposed model significantly outperforms mainstream methods on NTU RGB+D 120 dataset and Northwestern-UCLA dataset.

With the expansion of the IoT, it is important to optimize available bandwidth to reliably support edge to device communications. Thus we propose a wireless network where each edge server communicates with its end devices using its wireless band as a primary channel, assisted by a secondary edge server that can relay communications via its own wireless band as a secondary channel. The network can optimize capacity by balancing load between primary and secondary wireless bands, and we analyze the geometry of achievable rate regions, depending on the state of bands modeled as Rayleigh fading channels. The allocation of a connection to the primary or secondary band is formulated as an optimization problem which is then solved, and illustrated with numerical examples.

Alzheimer's disease(AD) is a neurodegenerative disease that progresses slowly but worsens gradually, also, the most common kinds of dementia. Clinically, the diagnosis of AD is mainly based on rating scales and neuroimaging technology which is invasive, costly and time-consuming. Other than that, the clinical pathology has become irreversible when neuroimaging characteristics appear. It is imperative to develop new noninvasive methods for early diagnosis of AD. Several studies indicated the probable association of cognitive decline with gait changes might shed light on potential features for distinction of AD. This paper aims to exploit the feasibility of gait features for early diagnosis of mild cognitive impairment(MCI) and AD by using machine learning methods. A device-free AD detection system is built, with a natural undisturbed gait collecting system and a well-performed Long Short-Term Memory(LSTM) based model, in this article. Moreover, it can serve as a simplified, non-invasive, and highly accurate clinical auxiliary tool for early diagnosis and distinction of AD. Experimental results showed a 90.48%, 92.00%, and 88.24% in accuracy, sensitivity, and specificity respectively for distinguishing AD by using the method with LSTM based model. Furthermore, the gait cycle and stride length in MCI or AD were more variable than in healthy controls through redefining and calculating the gait features with skeleton data obtained by Kinect devices.

Generalized anxiety disorder (GAD), as one of the most common chronic anxiety disorders, faces difficulties in clinical diagnosis. With the rapid development and wide application of smartphones in recent years, smartphones have a vivid application prospect in the field of mental disease monitoring and diagnosis. Based on WeChat applet platform on smartphones, an APP that integrates scale testing and inertial sensor data collection is developed to study the detection of subjects with GAD in task state. A behavior patterns extraction method is proposed using sliding windows to split behavior data, and processing data segments for clustering. Distribution information are extracted from the subjects' behavior patterns and are combined with the descriptive statistical features of the sample to identify GAD. The results show that this method has an accuracy of 66.44% for female subjects and 71.43% for male subjects in GAD recognition.

Visual-inertial simultaneous localization and mapping (SLAM) shows significant progress in recent years due to the complementary nature of the visual and inertial sensor but still, challenges remain for low-light environments. Recent visual-inertial SLAMs often drift or even fail in low-light conditions due to insufficient 3D-2D correspondences for bundle adjustment. To address the issue, this paper performs image preprocessing firstly with a united image enhancement method involving adaptive gamma correction and contrast limited adaptive histogram equalization, which could ameliorate the brightness and contrast of the image greatly. Moreover, we track features using optical flow for adequate point correspondences in dim-light environments, and supplement the corresponding map points continually by insert keyframe and triangulation to keep tracking. Finally, we construct a tightly-coupled nonlinear optimization model, which combines a feature reprojection error on point correspondences and IMU measurement by pre-integration to constrain and compensate each other for more accurate pose estimation. We validate the performance of our algorithm on public dataset and real-word experiments with a mobile robot, including dark laboratory, etc., and compare against existing state-of-the-art visual-inertial algorithms. Experimental results indicate our algorithm outperforms other state-of-the-art SLAMs in accuracy and robustness, and works reliably well for both general and low-light environments.

Aiming to effective early detection of breast cancer, automatic tumor segmentation based on breast Magnetic Resonance Imaging (MRI) is concentrated by more and more researchers. This paper proposes a dense encoder-decoder network based on two-level context enhanced residual attention mechanism (TLCRAM-DED). With respect to TLCRAM-DED, we design the encoding structure combining two-level residual attention structure with dense block to extract and refine the features of different layers. Meanwhile, a dense multi-scale atrous convolution is used at the end of the encoder to obtain a larger receptive field and enrich the extracted semantic information. Moreover, residual attention structure (RAS) is also used for the refinement during decoding stage, while a long connection formed with the encoder RAS output is applied to supplement the features and to gradually recover the segmentation details. We validated prosed model in the DCE sequence of challenging breast cancer MRI dataset. The average Dice coefficient is up to 81.04%, which outperforms compared state-of-the-arts.

Due to the dynamic characteristics of mobile wireless ad hoc networks, a node may join or leave/fail at any time, and links are usually intermittently unavailable. The destruction of the network connectivity would dramatically degrade the performance. To resolve this challenge, topology control is an efficient way to maintain network connectivity, which focuses on the adjustment of node transmit power in the past few decades. However, the adjustment of node movement has not been adequately addressed to restore the connectivity in mobile wireless ad hoc networks. In this paper, we propose three hybrid recovering algorithms, namely, cascade movement based on nearest nodes, cascade movement based on connected dominating set, and cascade movement based on critical nodes. With the adoption of Kalman filter, all these schemes can predict the movement of nodes so as to identify and maintain connectivity of mobile wireless ad hoc networks. Meanwhile, once a node fails or a link breaks down, they can also recover the connectivity immediately. We conduct extensive simulations on the metrics of the average number of participating nodes, the deviation from original direction, and the ratio of cascade movement for the three proposed algorithms, and the algorithm of cascade movement based on critical nodes achieves the best results.

In this paper, we proposed a practical and efficient algorithm based on conventional semi-direct monocular visual odometry (SVO) algorithm, which mainly aims at the future application of the Simultaneous Localization and Mapping (SLAM) for embedded or mobile platforms such as robots and wearable devices. By applying the velocity momentum during the initial pose estimation, we present a novel algorithm for obtaining the initial pose, which is closer to the true value and more effective to solving the limitation of non-convergence in most existing approaches. A sparse image alignment module is also proposed to rectify the pose offset occurred at the corner, by elaborately resetting the relative pose at the location with large photometric error. The proposed lifted semi-direct monocular visual odometry has been extensively evaluated on benchmark dataset. The experimental result demonstrates that our method can explicitly generate the accurate initial poses without reducing the speed.

In many people's daily life, alarm sounds play an important role, which reflects the fast paced life in the modern society. On most occasions, people uses alarm sounds to wake them up in the morning. Improper alarm sounds could make people feel terrible. In this paper, we mainly propose a smart alarm sound recommendation system and construct an application to study how alarm sounds can impact human emotions. The recommendation system is deployed on the cloud, working with smartphones to deliver smart alarm sounds by considering not only sleep patterns, but also context information such as weather. The designed system can recommend smart alarm sounds to users, orchestrate sensing data collected by multiple sensors on smartphones, and collaborate with cloud computing to recommend preferable alarm sounds. An application is developed to demonstrate system effectiveness, which consists of the fore-end on Android OS and the back-end on the cloud. Experiments demonstrate that our system can recommend smart alarm sounds to wake participants up in the morning and the participants give feedback about their emotional states. The results show the system can improve people's emotion states by about 14.57%, compared to traditional alarm sound delivery.

The Cyber-Physical System (CPS) concept is now attracting attention in systems engineering, and it is being applied to a fully automated factory control in processes such as semiconductor fabrication. In this paper, we propose a novel control decision structure for process manufacturing, designated as the 3D Optical Network-on-Chip (ONoC) multi-core system, based on the cloud-supported CPS concept. We first construct a task graph — which includes interconnected Virtual Machines (VMs)—to represent the interaction between industrial-physical processes and cyber states. Given the task graph, the control decision process becomes into the problem of the on-chip VM placement. We then design a highly reliable on-chip VM placement scheduling to find the optimal control strategy while guaranteeing the reliability of the 3D ONoC structure. The simulation results demonstrate that our scheme achieves a higher reliability of the 3D ONoC structure when we make the control decision for process manufacturing.

Vision-based object detection is one of the fundamental functions in numerous traffic scene applications such as self-driving vehicle systems and advance driver assistance systems (ADAS). Meanwhile, it also poses to be a demanding task due to the diversity of traffic scenes and resource limitations of the platforms for traffic scene applications. To address these issues, we present a generalized Haar filter based CNN (Convolutional Neural Network) which is suitable for the object detection tasks in traffic scenes. In this approach, we first decompose an object detection task into multiple local regression tasks. Thereafter, we handle these local regression tasks using several light and efficient networks which simultaneously output the bounding boxes, categories and confidence scores of detected objects. To reduce the consumption of storage and computing resources, the weights of these deep networks are constrained to the form of generalized Haar filters. Finally, we carry out various experiments to evaluate the performance of our proposed approach in traffic scene datasets. Experimental results demonstrate that our object detection system is light and effective in comparison with the state-of-the-art.

Software defined networking (SDN) has the potential to meet the requirements of the next generation traffic and service requirements. It is especially feasible and flexible when combining with small cell networks, which emerges into a software defined small cell networking (SDSCN) framework. SDSCN stands a chance to play a fundamental role in developing future 5G networks. It is particularly a challenging task to deploy dense small cell networks in the presence of dynamic traffic patterns and severe co-channel interference. Based on the SDSCN framework, in this paper, we propose a traffic clustering method to obtain all traffic patterns in a given area and an energy-efficient scheme to deploy and switch on/off small cell base stations (s-BSs) according to the prevailing traffic pattern. The simulation results indicate that our scheme can meet dynamic traffic demands with optimized deployment of small cells and enhance the energy efficiency of the system without compromising on the spectrum efficiency and quality-of-service (QoS) requirements. In addition, our scheme can achieve very close performance compared with the leading optimization solver CPLEX and find solutions in much less computational times than CPLEX.

The automotive Internet of Things (IoT) is an emerging research field by applying the IoT into the intelligent transportation system. Information sharing among objects such as smart mobile devices and vehicles' sensors plays an important role in strengthening their partnership in the vehicular environment. In this paper, we first consider message trading and propose a community-based information sharing (CIS) mechanism to motivate all objects to engage in sharing traffic events with each other. Specifically, a message processing algorithm and a message generating algorithm are proposed to handle incoming messages originated from other objects and to share new traffic events with others, respectively. Since CIS only uses private information, e.g., location data, locally, the proposed mechanism also ensures the privacy of all objects during information sharing. Simulation results demonstrate that the proposed mechanism can effectively improve the quality of experience of human-beings in terms of the average arriving delay.

Millions of people are severely injured or killed in road accidents every year and most of these accidents are caused by human error. Fatigue and negative emotions such as anger adversely affect driver performance, thereby increasing the risk involved in driving. Research has shown that listening to the right kind of music in these situations can ameliorate driver performance and improve road safety. Context-aware music delivery systems succeed in delivering suitable music according to the situation through the process of music mood-mapping which identifies the mood of a song. Additionally, we can leverage the power of the cloud to enable crowd sensing of the mood-mapping of various songs and enhance the effectiveness of situation-aware music delivery for drivers. The cloud can be used to aggregate the crowd sensed music mood-mapping data and improve the effectiveness of music delivery by providing accurate mood-mappings from the aggregated data. Currently, context-aware music delivery systems consider only features from the song for music mood-mapping. In this paper, we propose a novel approach to music mood-mapping for drivers which also incorporates the social context of a driver including age, gender and cultural background to enhance the effectiveness of music delivery in context-aware music recommendation systems for drivers.

This paper proposes a novel power management solution for resource-constrained devices in the context of Internet of Things (IoT). We focus on smartphones in the IoT, as they are getting increasingly popular and equipped with strong sensing capabilities. Smartphones have complex and asynchronous power consumption incurred by heterogeneous components including their on-board sensors. Their interaction with the cloud allows them to offload computation tasks and access remote data storage. In this work, we aim at monitoring the power consumption behaviours of the smartphones, profiling both individual applications and the system as a whole, to make better decisions in power management. We design a cloud orchestration architecture as an epic predictor of behaviours of smart devices by extracting their application characteristics and resource utilization. We design and implement this architecture to perform energy profiling and data analysis on massive data logs. This cloud orchestration architecture coordinates a number of cloud-based services and supports dynamic workflows between service components, which can reduce energy consumption in the energy profiling process itself. Experimental results showed that small portion of applications dominate the energy consumption of smartphones. Heuristic profiling can effectively reduce energy consumption in data logging and communications without scarifying the accuracy of power monitoring.

In this paper, we present a mobility cloud platform called CarCloud that has been designed to facilitate the real-world deployment of ubiquitous mobile telematic applications to promote smart transportation. CarCloud leverages the mobility, sensing and communication capacities of mobile devices, and collaborates with sensors embedded in vehicles (e.g., accessed via OBD-II) and cloud services to form a seamless platform. This platform orchestrates different mobility data in transportations to REST web service based mobility services that could be used for different mobile telematic applications (e.g., enabling traffic managers to monitor the behaviors of drivers) in intelligent transportation systems (ITS). Prototype implementation and preliminary experiments demonstrate the desired functionality of CarCloud for ITS and its feasibility for real-world deployment.

Driving is an integral part of our everyday lives, and the average driving time of people globally is increasing to 84 minutes everyday, which is a time when people are uniquely vulnerable. A number of research works have identified that mobile crowd sensing in vehicular social networks (VSNs) can be effectively used for many purposes and bring huge economic benefits, e.g., safety improvement and traffic management. This paper presents our effort that toward context-aware mobile crowd sensing in VSNs. First, we introduce a novel application-oriented service collaboration (ASCM) model which can automatically match multiple users with multiple mobile crowd sensing tasks in VSNs in an efficient manner. After that, for users' dynamic contexts of VSNs, we proposes a context information management model, that aims to enable the mobile crowd sensing applications to autonomously match appropriate service and information with different users (requesters and participants) in crowdsensing.

In smart cities, cellular network plays a crucial role to support connectivity anywhere and anytime. However, the communication demand brought by applications and services is hard to predict. Traffic in cellular networks might fluctuate heavily over time to time, which causes burden and waste under different traffic states. Recently, small cell was proposed to enhance spectrum efficiency and energy efficiency in cellular networks. However, how green the small cell network can be is still a question because of the accompanying interference. To meet this challenge, new green technologies should be developed. In this paper, we propose a green small cell planning scheme considering dynamic traffic states. First, we predefine a set of candidate locations for base stations (BSs) in a geographical area and generate a connection graph which contains all possible connections between BSs and user equipments (UEs). Then we adopt a heuristic to switch off small cell BSs (s-BSs) and update BS-UE connections iteratively. Finally we obtain a cell planning solution with energy efficiency without reducing spectrum efficiency and quality-ofservice (QoS) requirements. The simulation results show that our dynamic small cell planning scheme has low computational complexity and achieves a significant improvement in energy efficiency comparing with the static cell planning scheme.

This paper proposes Health Drive, a novel mobile healthcare platform with context-aware multiple-sensor integration to promote safe driving. Health Drive employs a multi-tier vehicular social network (M-VSN) architecture that consists of three tiers: network tier, mobile device tier and cloud tier. The network tier provides communication supports, and the mobile device tier works in parallel with the cloud tier to integrate and interpret diverse sensing data. The three tiers work together to provide a seamless solution that can efficiently collect and interpret diverse sensing data in the heterogeneous environments found in vehicular networks, to deliver personalized service to drivers for safety improvement in real-time. We evaluate the system performance of Health Drive and provide results of practical experiments to show the desired functionality and feasibility of Health Drive in the real-world for safety improvement in transportation.

The powerful data storage and data processing abilities of cloud computing (CC) and the ubiquitous data gathering capability of wireless sensor network (WSN) complement each other in CC-WSN integration, which is attracting growing interest from both academia and industry. However, job scheduling for CC integrated with WSN is a critical and unexplored topic. To fill this gap, this paper first analyzes the characteristics of job scheduling with respect to CC-WSN integration and then studies two traditional and popular job scheduling algorithms (i.e., Min-Min and Max-Min). Further, two novel job scheduling algorithms, namely priority-based two phase Min-Min (PTMM) and priority-based two phase Max-Min (PTAM), are proposed for CC integrated with WSN. Extensive experimental results show that PTMM and PTAM achieve shorter expected completion time than Min-Min and Max-Min, for CC integrated with WSN.

Mobile cloud computing (MCC) is a very hot research focus of both academia and industries, since it can greatly relieve the hardware limitation of mobile devices as well as create new fascinating mobile services with its tremendous storage and processing ability. Moreover, wireless sensor networks (WSNs) have been attracting attention for about two decades, because of its powerful capability to detect physical or environmental conditions. Motivated by incorporating the advantages of both MCC and WSNs, a lot of schemes which integrate MCC with WSNs have been proposed for exploiting the cloud to share the data gathered by WSNs to mobile users. Particularly, all current integration frameworks utilize the always-on WSNs to collect sensory data for cloud clients, since the data requests of mobile users generally require being responded in real-time. However, these MCC and WSNs integration schemes ignore the following two observations: 1) the specific data cloud clients request usually depends on the current location of cloud clients 2) most sensors are usually equipped with non-rechargeable batteries with limited energy. In this paper, motivated by the above two issues, we present two novel collaborative location-based sleep scheduling (CLSS) schemes for WSNs to integrate with MCC. Based on the location of mobile user, CLSS dynamically determines the awake or asleep status of each sensor node to save energy consumption of WSNs. Theoretical and simulation results show that the proposed scheme can achieve a prolonged network lifetime of WSNs while still satisfy the data requests of mobile users.

Recently, the arising of cloud computing (CC) concept and explosive growth of mobile applications induce a novel technology, i.e., mobile cloud computing (MCC). By integrating CC into mobile environment, MCC alleviates limitations of mobile devices and proliferates a variety of new fascinating mobile services. The key to enable MCC is to equip mobile users with the data processing and storage abilities in the clouds via wireless networks. In this paper, aiming at facilitating the research of MCC and inducing more research topics regarding MCC, we offer a review of the key issues that concern the feasibility of MCC and identify the corresponding novel techniques to mitigate these key issues. Moreover, we propose a potential framework to enhance the robustness of MCC incorporating these novel techniques.

This paper proposes a novel service-oriented mobile social networking platform called MS2A for disaster situations. MS2A consists of two layers: service layer and application layer. The service layer is implemented based on the service-oriented architecture (SOA) to ease application developments. By extending and composing the web services at this layer, application developers can efficiently and flexibly develop different new functions or applications for mobile disaster rescue and recovery applications. The application layer is oriented to mobile users and it integrates with functions of mobile social networks. With dynamic and automatic service collaboration support, it enables people to easily collaborate and help each other through their mobile devices in disaster situations. The results of our experiments and demonstration examples given in the paper show the feasibility and desired functionality of MS2A for relieving disaster situations with mobile devices.

One of the main threats to wireless multi-hop networks is Denial-of-Service (DoS), which either aims to bring down network performance or tends to rapidly consume resources of a particular node. Different from traditional DoS which provokes sudden changes in network traffic, routing protocol misuse that exploits vulnerabilities of routing protocols would reduce the overall performance without triggering alarms from existing detection methods based on rapid changes in network traffic. In order to overcome the weakness of traffic burst based detection methods, this paper proposes an enhanced anomaly detection and restoration scheme to defeat low-rate DoS launched by rogue nodes. Meanwhile, an exponential backoff restoration (EBR) algorithm is proposed to reduce performance degradation. Simulation results validate that the proposed scheme is able to maintain the overall network performance under low-rate DoS.