The automated classification of heart sounds plays a significant role in the diagnosis of cardiovascular diseases (CVDs). With the recent introduction of medical big data and artificial intelligence technology, there has been an increased focus on the development of deep learning approaches for heart sound classification. However, despite significant achievements in this field, there are still limitations due to insufficient data, inefficient training, and the unavailability of effective models. With the aim of improving the accuracy of heart sounds classification, an in-depth systematic review and an analysis of existing deep learning methods were performed in the present study, with an emphasis on the convolutional neural network (CNN) and recurrent neural network (RNN) methods developed over the last five years. This paper also discusses the challenges and expected future trends in the application of deep learning to heart sounds classification with the objective of providing an essential reference for further study.

The intelligent classification of heart-sound signals can assist clinicians in the rapid diagnosis of cardiovascular diseases. Mel-frequency cepstral coefficients (MelSpectrums) and log Mel-frequency cepstral coefficients (Log-MelSpectrums) based on a short-time Fourier transform (STFT) can represent the temporal and spectral structures of original heart-sound signals. Recently, various systems based on convolutional neural networks (CNNs) trained on the MelSpectrum and Log-MelSpectrum of segmental heart-sound frames that outperform systems using handcrafted features have been presented and classified heart-sound signals accurately. However, there is no a priori evidence of the best input representation for classifying heart sounds when using CNN models. Therefore, in this study, the MelSpectrum and Log-MelSpectrum features of heart-sound signals combined with a mathematical model of cardiac-sound acquisition were analysed theoretically. Both the experimental results and theoretical analysis demonstrated that the Log-MelSpectrum features can reduce the classification difference between domains and improve the performance of CNNs for heart-sound classification.

Due to the battery resource constraints, saving energy is a critical issue in wireless sensor networks, particularly in large sensor networks. One possible solution is to deploy multiple sink nodes simultaneously. Another possible solution is to employ an adaptive clustering hierarchy routing scheme. In this paper, we propose a multiple sink cluster wireless sensor networks scheme which combines the two solutions, and propose an efficient transmission power control scheme for a sink-centric cluster routing protocol in multiple sink wireless sensor networks, denoted as MSCWSNs-PC. It is a distributed, scalable, self-organizing, adaptive system, and the sensor nodes do not require knowledge of the global network and their location. All sinks effectively work out a representative view of a monitored region, after which power control is employed to optimize network topology. The simulations demonstrate the advantages of our new protocol.

This paper studies a power minimization problem of an orthogonal frequency-division multiplexing modulated two-way amplify-and-forward relay wireless sensor network (WSN). The objective is to develop effective strategies for controlling the transmit power levels of WSN nodes and assigning the bit rates among different subcarriers to minimize the overall transmit power of the network, while ensuring the end-to-end target rates of the two WSN sources. By using channel knowledge at transmitters, a two-step method is proposed to solve the power minimization problem, resulting in a joint power control and bit rate assignment (JPCBRA) algorithm. At the first step, a per-subcarrier optimization problem concerning the power minimization issue is solved, giving closed-form solutions for individual transmit powers at the WSN sources and the relay. At the second step, the end-to-end target rates of the two WSN sources are allocated to different subcarriers so that the total transmit power can be reduced further while satisfying the initial data-rate requirement of the two WSN sources. Computer simulation results confirmed the effectiveness of the proposed JPCBRA algorithm. It is shown that with the JPCBRA algorithm, the total transmit power of the network can be significantly reduced in any traffic and/or channel cases in contrast to the compared schemes.

We focus on the power consumption problem for a downlink multiuser small-cell network (SCN) considering both the quality of service (QoS) and power constraints. First based on a practical power consumption model taking into account both the dynamic transmit power and static circuit power, we formulate and then transform the power consumption optimization problem into a convex problem by using semidefinite relaxation (SDR) technique and obtain the optimal solution by the CVX tool. We further note that the SDR-based solution becomes infeasible for realistic implementation due to its heavy backhaul burden and computational complexity. To this end, we propose an alternative suboptimal algorithm which has low implementation overhead and complexity, based on minimum mean square error (MMSE) precoding. Furthermore, we propose a distributed correlation-based antenna selection (DCAS) algorithm combining with our optimization algorithms to reduce the static circuit power consumption for the SCN. Finally, simulation results demonstrate that our proposed suboptimal algorithm is very effective on power consumption minimization, with significantly reduced backhaul burden and computational complexity. Moreover, we show that our optimization algorithms with DCAS have less power consumption than the other benchmark algorithms.