Search

Early risk identification of an unexpected sudden cardiac death (SCD) in a person who is suffering malignant ventricular arrhythmias is highly significant for timely intervention and increasing the survival rate. For this purpose, we have presented an automated strategy for prediction of SCD with a high-level accuracy by using measurable arrhythmic markers in this paper. The set of arrhythmic parameters includes three repolarization interval ratios, such as TpTe/QT, JTp/JTe, and TpTe/JTp and two conduction-repolarization markers, such as TpTe/QRS and TpTe/(QT×QRS). Each of them is calculated directly from the detected QRS complex waves and T-wave of electrocradiogram (ECG) signals. Then, all calculated markers are used for the automatical classification of normal and SCD risk groups by employing machine learning classifiers, such as k-nearest neighbor (KNN), decision tree (DT), Naive Bayes (NB), support vector machine (SVM), and random forest (RF). The effectiveness and usefulness of the proposed method is evaluated using a database of measured ECG data acquired from 28 SCD and 18 normal patients. For the automated strategy, the set of five arrhythmic risk markers can predict SCD in less than one second with an average accuracy of 98.91% (KNN), 98.70% (SVM), 98.99% (DT), 97.46% (NB), and 99.49% (RF) for 30 minutes before the occurrence of SCD. Moreover, a practical and straightforward SCD index (SCDI) through a judicious integration of these markers is also proposed by using the Student's t-test. The obtained SCDIs are 1.2058 ± 0.0795 and 1.7619 ± 0.1902 for normal and SCD patients, respectively, which provide a sufficient discrimination degree with a p-value of 6.5061e-35. The present results show that both the automated classifier and the integrated SCDI can predict the SCD up to 30 minutes earlier, and that these predictions could be more practical and efficient if applied in portable smart devices with real-time requirements in hospital settings or at home.

Unmanned Aerial Vehicle (UAV) technology is more and more widely used in the field of civil and military information acquisition. GPS plays the most critical part of UAVs' navigation and positioning. However, since the communication channel of the GPS signals is open, attackers can disguise as real GPS signals to launch GPS spoofing attacks on civilian UAVs. At present, the detection schemes for GPS spoofing attacks can be divided into three categories respectively based on encryption and digital signatures, the characteristics of the GPS signal and various external characteristics of UAVs. However, there are some problems in these methods, such as low computing efficiency, difficulty in equipment upgrading, and limited application scenarios. To solve these problems, we propose a new GPS spoofing attack detection method based on Long Short-Term Memory (LSTM) which is a machine learning algorithm. In order to improve the detection ratio, after the machine learning algorithm, we let the UAVs fly according to the path of a specific shape to accurately detect GPS spoofing attacks. This is also the first time machine learning has been used to detect GPS spoofing attacks. According to our algorithm, we can detect GPS spoofing attacks accurately and quickly in a short time. This paper describes in detail the algorithm we proposed to resist GPS spoofing attacks, and the corresponding experiments are carried out in the simulation environment. The experimental results show that our method can quickly and accurately detect UAV GPS spoofing attacks without requiring upgrades to existing equipment.

Ground-based microwave radiometer could provide continuous thermodynamic profiles which are crucial to weather services. But further efforts should be made to improve the accuracy of measurements. In this study, quality control (QC) procedures have been applied to temperature and absolute humidity profiles obtained from a ground-based microwave radiometer (January 2012 to May 2014) at Shanghai Expo Station and thousands of doubtful profiles are flagged. Temporal distributions and possible causes of these doubtful profiles are further investigated. Results show that the doubtful profiles are closely related to specific weather conditions. The doubtful temperature profiles might be caused by various weather conditions, such as precipitation, frost, extreme high temperature, etc. The majority of doubtful humidity profiles are results of precipitation impacts.

In this paper, a fractional-order delay Logistic model with feedback control is presented and analyzed. We first study the local stability around the equilibrium point. Then global asymptotic stability are discussed by constructing suitable Lyapunov functional. Finally, numerical simulations are presented to support our theoretical results.

Malignant ventricular arrhythmia (especially ventricular fibrillation (VF)) is the main reason which causes sudden cardiac death (SCD). This paper presents an automatic SCD-patient classifier we developed to identify patients with unexpected VF using 60-minutes continuous single-lead electrocardiograms (ECG) signals before that. Patients are classified as having SCD if the majority of their recorded ventricular repolarization (VR) is recognized as characteristic of unexpected VF. Thus, the classifier's underlying task is to recognize individual VR delineated from single-lead ECG signals as SCD VR, where VR from non-SCD patients are used as controls. With the reported clinical practices of SCD, we extracted five morphological and temporal features (both commonly used and newly developed ones) from ECG signals for VR classification. To evaluate classification performance, we trained and tested k nearest neighbor classifier, a decision tree classifier, and a Naïve Bayes classifier using five-fold cross validation on 36 one-hour ECG signals (18 from patients at risk of SCD and 18 from control people). We compared the performance of these three classifiers, and the patient-classification sensitivity is approximately 98.02-99.51%. Moreover, the k nearest neighbor with a higher accuracy (98.89%) and specificity (98.27%) performed better than the other two. Importantly, the results show obvious superiorities of performance over that in the same duration and of usefulness over several minutes given by related works.Clinical Relevance- This could be integrated into a real-time, long-term out-of-hospital SCD predictor to improve the warning veracity and bring forward the warning time, especially for patients with implantable cardiac defibrillators or pacemakers, etc..

In this paper, a fractional-order vector-bias model on malaria transmission is presented and analyzed. First, the basic reproduction number R 0 and the existence of equilibria are obtained. Further, the stability of the disease free equilibrium points and endemic equilibrium points are investigated. Then, Hopf bifurcation are proposed by choosing the fractional-order q 1 as the bifurcation parameter. Finally, numerical simulations are presented to illustrate our theoretical results.

Inverse-designed digital nanophotonic devices have been widely and successfully used due to their simple brute-force design methods, compact footprint, flexibly-designed functions and high performance in various applications. Unfortunately, the number of 3D FDTD simulations in brute-force methods will increase exponentially with the "pixel" number in a digital pattern, which may drastically limit the inverse design capability of digital nanophotonic devices. In this work, we propose and demonstrate a modified adjoint method for efficient inverse design of compact digital nanophotonic power dividers with arbitrary power ratios.

Action recognition plays an important character for numerous tasks of video area. Although previous works often learn the appearance and motion information with Convolutional Neural Networks (CNNs), they ignore the corresponding space structures of video representation. In this work, we address action recognition task with a Spatial-Temporal representation analysis algorithm Across Grassmannian manifold and Euclidean space (ST-AGE), which considers the appearance and motion information of video samples in an unified framework. For each video sample, we extract temporal features with classical CNNs (e.g., ConvNet, VGG, ResNet) and motion representation with the trajectory tracking method. Both spatial and temporal information can be then analyzed by embedding them on the Grassmannian manifold and Euclidean space, and an appropriate multi-kernel SVM is further conducted. Comprehensive evaluations on HMDB-51 and UCF-101 datasets demonstrate the significant superiority of STAGE over other state-of-the-art for human action recognition.

In cloud computing environments, data centers can provide high-performance computing resources and distributed storage space. Scientific workflows often need to be implemented across multiple data centers, where copious amounts of application data are stored. Moving data across geographically distributed data centers leads to intolerable delays and hinders the efficient execution of scientific workflows, which are large-scale data-intensive. Reasonable data placement can reduce data scheduling between the data centers effectively. In this paper, an adaptive discrete particle swarm optimization (PSO) algorithm based on genetic algorithm has been proposed to decrease the number of data transmissions across data centers. The algorithm overcame the premature convergence defect of PSO by introducing the mutation and crossover of genetic algorithm. Moreover, it effectively improved the diversity in the process of population evolution. Compared with the previous work, the simulation results showed that the proposed strategy greatly reduced the volume of data transfer while reducing the number of data movement across data centers.

Smart home is an important application area of the Internet of things (IoT). However, the diversification of smart home application scenarios increases the difficulty of understanding the scenarios for developers. And the heterogeneity of the programming interfaces of smart devices as well as the close coupling of the code to the underlying systems is still an important work for the developers. Furthermore, the complexity and variability of business requirements poses a great challenge to the development of applications logic. In this paper, we present a runtime knowledge graph based approach to smart home application development. First, a conceptual model describing the smart home scenarios is defined. Second, the manageability of smart devices is abstracted as runtime knowledge graphs that are automatically connected with the corresponding systems. Last, a method of automatically generating smart home applications is proposed. Our approach can reduce code by about 85 percent at least, and an experiment on a real-world application scenario demonstrates the feasibility, effectiveness, and benefits of the new approach to smart home application development.

In this paper, the Hopf bifurcation in a delayed fractional-order SIR epidemic model is investigated. Firstly, the associated characteristic equation is analyzed by using time delay as a bifurcation parameter. It is shown that time delay can effect the stability of the diseases prevalence. Finally, some numerical simulations are presented to illustrate our theoretical results.

Dissolved gas analysis (DGA) has been proven an effective method to diagnose the internal fault of transformers for decades. This paper proposes an approach of DGA based on Deep Belief Networks (DBN) which belongs to deep-learning theory. With composed of Restricted Boltzmann Machines (RBMs), DBN can built the mapping relationship between the characteristic gas and the fault types automatically to achieve the accurate diagnosis, namely Pattern Recognition (PR). In this paper, DGA data is divided into three categories, called training data, fine-tuning data and test data. Training data is used for unsupervised-learning to initialize parameters of RBMs in DBN, and fine-tuning data is for supervised-learning with fault modes to optimize parameters. Finally, the test data is used to calculate the recognition rate of transformer fault diagnosis. It comes to conclusion that DBN model proposed shows a promising results of transformer fault diagnosis with high accuracy of 84.87% Compared with Back Propagation Neural Network (BPNN) method, DBN model not only achieves a high recognition rata of transformer fault, but also have strong generalization ability under big data, which could provide a powerful tool for the internal fault diagnosis of transformers.

With the wide application of big data and the development of computer computing capability, deep Convolutional Neural Network (CNN) has been widely applied in the field of computer vision. The current architecture of deep neural network is becoming deeper and more complex for achieving a better performance. However, their natural disadvantages such as larger consumption of computation or memory, and longer run-time make CNN models difficult to be applied to the mobile and embedded devices. In this paper, we learn a Smart Convolutional Neural Network (S-CNN) under the guide of neurons' high-level semantic information distilled from a cumbersome neural network. S-CNN can be seen as an improved CNN model, which is with less consumption of computation and memory in the predicted process. We verify the superiority of S-CNN in terms of image classification task on three benchmarking datasets, including CIFAR-10, CIFAR-100 and SVHN. Experimental results clearly demonstrate that the proposed S-CNN can get an exciting performance compared with traditional CNN models.

Nowadays, Wireless Sensor Networks (WSNs) have been widely deployed and applied. Due to energy consumption is one of the critical problems existing in WSNs, many energy-optimization related routing mechanisms are proposed. However, most of existing routing mechanisms rarely focus on both energy consumption and data transmission delay in high-loss WSN environments. Therefore, in this paper, we formulate the routing problem in high-loss WSNs with the considerations of energy efficiency improvement and data transmission delay reduction. Through exploiting the stochastic Lyapunov optimization approaches, the formulated problem is converted to a queue stability problem with virtual queues and is further decomposed into three subproblems, including transmission control, admission control and utility maximization. By solving the three decomposed problems, Stochastic Optimal Routing Algorithm (SORA) is established and proposed. Finally, the performance of SORA is evaluated by comprehensive simulations.

In recent years, the ever-growing number of mobile users and demands for mobile services exert great pressure on wireless content transmission. It is still a challenge to provide high-quality service in mobile scenario. To improve the quality of mobile service, proactive caching is proposed to push popular and requested service content to the nearest base stations or access points from mobile users through mobility prediction and content prefteching and caching. Despite a lot of proactive caching algorithms have been proposed, there is few research has been done to design and establish a network architecture which is capable of providing smart and native support for proactive caching. Therefore, in this paper, a Smart Proactive Caching Network (SPCN) is proposed to fill the gap. The architecture and working procedure of SPCN is presented and network model is established. The performance is also evaluated.

In wireless sensor networks, maximizing the lifetime of a data gathering tree is known to be NP-hard, so various (exponential-time) exact algorithms are designed to find the best data gathering tree. The state-of-the-art exact algorithm recursively performs graph decomposition to reduce search space. However, it essentially enumerates all possibilities in adjacent graph decompositions, and cannot handle moderately large sensor networks. In this paper, we propose an exact algorithm using integer linear programming. The challenge is that some constraints are not linear in the optimization problem. To address this challenge, instead of the optimization problem, we formulate the decision problem, and solve each decision problem by integer linear programming. The optimal value is then found by binary search over all possible lifetimes. To reduce the running time, we preprocess the graph by decomposing it into bi- connected subnetworks, and propose various rules to reduce the number of candidate lifetimes. Numerical results on simulated networks show that, within two hours, our algorithm can solve more problem instances than previous algorithms.

Hot-swappable devices play an important role for achieving high availability and easy maintainability in power grids, especially in substations. However, they also present a potential attack vector for malware to penetrate an otherwise highly closed system. We propose SwapGuard, a software-only solution that effectively guards a power grid system against swapped-in devices infected with malware. Built upon existing software-based attestation techniques, SwapGuard's design can securely handle hot-swapping event and accommodate different types of devices and networks. We evaluate SwapGuard on real-world power grid devices. The experimental results show that SwapGuard incurs low overhead to the operation of the system, in terms of the additional time required before a swapped-in device starts to function, the overhead to bootstrap the whole system, and the overhead to defend against unattested devices.