The automatic detection of atrial fibrillation (AF) is crucial for its association with the risk of embolic stroke. Most of the existing AF detection methods usually convert 1D time-series electrocardiogram (ECG) signal into 2D spectrogram to train a complex AF detection system, which results in heavy training computation and high implementation cost. This paper proposes an AF detection method based on an end-to-end 1D convolutional neural network (CNN) architecture to raise the detection accuracy and reduce network complexity. By investigating the impact of major components of a convolutional block on detection accuracy and using grid search to obtain optimal hyperparameters of the CNN, we develop a simple, yet effective 1D CNN. Since the dataset provided by PhysioNet Challenge 2017 contains ECG recordings with different lengths, we also propose a length normalization algorithm to generate equal-length records to meet the requirement of CNN. Experimental results and analysis indicate that our method of 1D CNN achieves an average F1 score of 78.2%, which has better detection accuracy with lower network complexity, as compared with the existing deep learning-based methods.

SUMMARYThe seamless internetworking among heterogeneous networks is in great demand to provide 'always-on' connectivity services with quality of service (QoS) provision, anywhere at anytime. The integration of wireless-fidelity (Wi-Fi) and wireless metropolitan area networks (WiMAX) networks can combine their best features to provide ubiquitous access, while mediating the weakness of both networks. While it is challenging to obtain optimized handover decision-based dynamic QoS information, users can improve their perceived QoS by using the terminal-controlled handover decision in a single device equipped with multiple radio interfaces. The IEEE 802.21 aims at providing a framework that defines media-independent handover (MIH) mechanism that supports seamless handover across heterogeneous networks. In this paper, an multiple attributes decision making-based terminal-controlled vertical handover decision scheme using MIH services is proposed in the integrated Wi-Fi and WiMAX networks to provide 'always-on' connectivity QoS services. The simulation results show that the proposed scheme provides smaller handover times and lower dropping rate than the RSS-based and cost function-based vertical handover schemes.

No abstract

No abstract

This paper proposes an adaptive downlink bandwidth allocation method (DBAM) for six traffic types—UGS, RT-VR, ERT-VR, NRT-VR, BE, and multicast—to maximize the throughput of broadband WiMAX networks for generic broadband services. Based on traffic throughput and the amount of traffic in different scalable video coding (SVC) layers, two adaptive resource adjustment schemes with SVC technology in the DBAM are proposed and compared. Moreover, a hierarchical priority queuing for different traffic profiles with weighted round robin (HPWRR) scheduling algorithm is proposed to achieve higher resource utilization and to meet the required quality of service (QoS) for each traffic type. Simulation results show that the proposed DBAM with HPWRR can achieve efficient throughput and bandwidth utilization and improve the delay time for RT-VR and multicast traffic.