Yazar "Wu, Wanqing" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    ASHEED: Attention-shifting mechanism for depolarization of cluster head energy consumption in the smart sensing system
    (Pergamon-Elsevier Science Ltd, 2022) Lu, Xu; Chen, Kezhou; Liu, Jun; Chen, Rongjun; Wu, Wanqing; Polat, Kemal
    The sensing node clustering algorithm is a network topology control method that can effectively extend the lifetime of smart sensing systems (SSSMs). However, the traditional topology algorithms suffer from the excessively early death of cluster heads. Hence, the attention-shifting mechanism for energy consumption based on hybrid energy-efficient distributed clustering (HEED) is proposed in this paper, called attention-shifting hybrid energy-efficient distributed clustering (ASHEED). The energy consumption of the cluster heads are reduced by shifting data reception and fusion energy consumption of the cluster heads to other cluster member nodes (Agents) within its competitive radius. Agent selection is performed by communication energy consumption comparison to ensure the rationality of cluster heads and agent positions with the aim of reducing the communication energy consumption for re-clustering. Experiment results demonstrated that the proposed approach could maximize the balance of energy consumption of cluster heads and common nodes, maintain the integrity of the network, and extend the optimal operation time of SSSMs.
  • Küçük Resim
    Öğe
    Detection of atrial fibrillation from variable-duration ECG signal based on time-adaptive densely network and feature enhancement strategy
    (IEEE-Institute Electrical Electronics Engineers Inc, 2023) Zhang, Xianbin; Jiang, Mingzhe; Polat, Kemal; Alhudhaif, Adi; Hemanth, Jude; Wu, Wanqing
    Atrial fibrillation (AF) is one of the clinic's most common arrhythmias with high morbidity and mortality. Developing an intelligent auxiliary diagnostic model of AF based on a body surface electrocardiogram (ECG) is necessary. Convolutional neural network (CNN) is one of the most commonly used models for AF recognition. However, typical CNN is not compatible with variable-duration ECG, so it is hard to demonstrate its universality and generalization in practical applications. Hence, this paper proposes a novel Time-adaptive densely network named MP-DLNet-F. The MP-DLNet module solves the problem of incompatibility between variable-duration ECG and 1D-CNN. In addition, the feature enhancement module and data imbalance processing module are respectively used to enhance the perception of temporal-quality information and decrease the sensitivity to data imbalance. The experimental results indicate that the proposed MP-DLNet-F achieved 87.98% classification accuracy, and F1-score of 0.847 on the CinC2017 database for 10-second cropped/padded single-lead ECG fragments. Furthermore, we deploy transfer learning techniques to test heterogeneous datasets, and in the CPSC2018 12-lead dataset, the method improved the average accuracy and F1-score by 21.81% and 16.14%, respectively. Experimental results indicate that our method can update the constructed model's parameters and precisely forecast AF with different duration distributions and lead distributions. Combining these advantages, MP-DLNet-F can exemplify all kinds of varied-duration or imbalance medical signal processing problems such as Electroencephalogram (EEG) and Photoplethysmography (PPG).