11 January 2016 in IEEE/CAA Journal of Automatica Sinica
How to design an energy-efficient algorithm to maximize the network lifetime in complicated scenarios is a critical problem for heterogeneous wireless sensor networks (HWSN). In this paper, a clustering-tree topology control algorithm based on the energy forecast (CTEF) is proposed for saving energy and ensuring network load balancing, while considering the link quality, packet loss rate, etc. In CTEF, the average energy of the network is accurately predicted per round (the lifetime of the network is denoted by rounds) in terms of the difference between the ideal and actual average residual energy using central limit theorem and normal distribution mechanism, simultaneously. On this basis, cluster heads are selected by cost function (including the energy, link quality and packet loss rate) and their distance. The non-cluster heads are determined to join the cluster through the energy, distance and link quality. Furthermore, several non-cluster heads in each cluster are chosen as the relay nodes for transmitting data through multi-hop communication to decrease the load of each cluster-head and prolong the lifetime of the network. The simulation results show the efficiency of CTEF. Compared with low-energy adaptive clustering hierarchy (LEACH), energy dissipation forecast and clustering management (EDFCM) and efficient and dynamic clustering scheme (EDCS) protocols, CTEF has longer network lifetime and receives more data packets at base station.
17 June 2022 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing, and memory. Discovering the specialized CNN that meets a specific constraint requires a substantial effort of human experts. Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual architecture design process and has attracted increasing interest in spoken language processing tasks such as speaker recognition. In this paper, we propose EfficientTDNN, an efficient architecture search framework consisting of a TDNN-based supernet and a TDNN-NAS algorithm. The proposed supernet introduces temporal convolution of different ranges of the receptive field and feature aggregation of various resolutions from different layers to TDNN. On top of it, the TDNN-NAS algorithm quickly searches for the desired TDNN architecture via weight-sharing subnets, which surprisingly reduces computation while handling the vast number of devices with various resources requirements. Experimental results on the VoxCeleb dataset show the proposed EfficientTDNN enables approximate $10^{13}$ architectures concerning depth, kernel, and width. Considering different computation constraints, it achieves a 2.20% equal error rate (EER) with 204 M multiply-accumulate operations (MACs), 1.41% EER with 571 M MACs as well as 0.94% EER with 1.45 G MACs. Comprehensive investigations suggest that the trained supernet generalizes subnets not sampled during training and obtains a favorable trade-off between accuracy and efficiency.
22 October 2018 in IEEE Transactions on Information Forensics and Security
Cyber-physical systems (CPS) have been deployed in many areas and have reached unprecedented levels of performance and efficiency. However, the security and privacy problems in CPS have not been properly addressed, e.g., the monitored source location can be inferred by an attacker, which can substantially undermine the reliability of CPS. Unfortunately, the existing techniques to protect against the leakage of the source location do not achieve an acceptable balance among the source location privacy, transmission delay, and energy consumption to guarantee high reliability. To address this issue, we propose an attacker location evaluation-based fake source scheduling (FSSE) for source location privacy in CPS to enhance the privacy level and maintain the system performance. The proposed FSSE contains two main phases. The first, backbone construction, is dependent on the probability of capture derived from the communication information of self and neighboring nodes. This phase aims to build a backbone to form a baseline with respect to the source location privacy and transmission delay. The second phase is fake message scheduling, which is established to provide a trade-off among privacy, transmission delay, and communication overhead in terms of the hypothesized location of the attacker by using stochastic processes. Through analysis and simulation, we demonstrate that the proposed method has a more stable privacy level and more efficient transmission delay and energy consumption than the three compared algorithms, i.e., phantom routing, tree-based diversionary routing, and dynamic fake source selection.
10 July 2024 in Expert Systems with Applications
8 October 2016 in Peer-to-Peer Networking and Applications