Sleep apnea syndrome (SAS) is a very common sleep disorder disease. Reliable detection of apnea is very crucial for subsequent treatment. In this article, a novel method based on artificial neural network is proposed for such purpose. With its time-invariant property the time delay neural network (TDNN) is adopted in this system to employ the temporal trend of apnea event. As airflow and SaO2 take the most important roles in sleep apnea syndrome diagnosis, features extracted from both of them are simultaneously fed into the neural network. The proposed algorithm was tested with 15 overnight polysomnographic (PSG) records, and with a sensitivity rate of 90.7% and 80.8%, a specificity rate of 86.4% and 81.4% for apnea and hypopnea detection, respectively. Furthermore, the proposed algorithm can accommodate in some manner the airflow sensor failure due to technical errors. But, as the SaO2 changes are commonly delayed by 10 or more seconds compared to the airflow signal, integration of SaO2 make this method only suited for offline detection. In conclusion, systems based on this algorithm can be used as a valuable timesaving adjunct for PSG SAS diagnosis.
A hybrid system for automated EEG sleep staging is presented in this article. By combining a self-organizing feature map (SOFM) with a fuzzy reasoning-based classifier (FRBC) and utilizing both temporal and spectrum features of the EEG signal, the system provides a reliable tool for automatic EEG sleep staging. Conceptually, the system is divided into four passes: artifact detection, rough staging, stage refinement and post processing. The artifact detection module is firstly employed to exclude stage movement from other stages. Then, the SOFM with features as its inputs derived from the power spectrum divides sleep into three "extreme" stages: Wake, Light/REM and Deep stage. In stage refinement pass, the FRBC, which takes characteristic waveforms' activities as inputs, subdivides the extreme stages into the exact stages (i.e., stage 1, stage 2) defined by R&K standard. At last, in post processing pass, a stage-smoothing method that mainly utilizes the temporal context information is used to correct unexpected stage transitions, thus to improve the system's performance. The system was tested with eight whole night sleep records with an average man-machine agreement of 85.3%. Compared with the high inter-scorer disagreement, the performance is desirable.
In this paper we present a data-driven joint inversion of seismic and well data. Rather than using a theoretical operator, we learn the forward operator using a BP neural network trained by the data set with well data as input and seismic recordings near the well as desired output. Then, we start the inversion by inputing the initial model of each trace into the trained BP network and propagating the output errors backward through the network iteratively to modify the input stratum model. The inversion is verified and its robustness analyzed using synthetic data. A field case involving a migrated seismic section and two wells was inverted to obtain the desired pseudo-log sonic and density profiles. The research results show that the technique can perform multiparameter inversion constrained with multiple wells, and deal with complex nonlinear problems. Introduction The strategy of seismic inversion is commonly in looking for an optimal geophysical model which minimizes the residuals between the model responses and observed data. The responses of the model are conventionally calculated by a theoretical forward operator, such as a convolution or wave equation operator1,2. Artificial neural networks(ANN) have recently attracted a great deal of attention for their ability to "learn," or "estimate" the mapping operator from training data which describe the mapping relationship. Among neural networks for function approximation, the feed forward network trained by error back propagation (BP)3 algorithm is one of the most effective and popular neural networks. It has been shown that the BP neural network with one hidden layer is a universal function approximator 4. In the learning of the BP (error back-propagation) neural network, the output error is propagated backward through the network to modify the link weights of the network, and the mapping relationship between the input and desired output vectors is encoded in the weights with a distributed form. Linen and Kinderman5 have shown that the same mechanism of the weight learning can also be applied to update the input of the network to iteratively invert the input parameter model of the network. In their approach, the output errors of the network are ascribed to the input errors of the network, rather than the weight errors. The iterative inversion of a BP network is, thus, to search the input signals in the input space to minimize the output errors, while the learning of it is to find a set of weights in the weight space to minimize the output errors Hoskins and Hwang6 apply the iterative inversion technique to their adaptive controllers. They learn the forward model of the plant, and perform the iterative inversion to generate control commands. They conclude that the proposed control approach allows the controllers to respond on line to changes in plant dynamics. Here, we apply the technique to the joint inversion of well-log and seismic data. We first learn the forward operator using a BP network trained by the data set consisting of well data as input and seismic recordings located at or near the well as desired output. Then upon the trained BP network, we iteratively invert seismic recordings into the stratum parameters trace by trace. As the approximation of the forward operator is adaptively driven by well-log and seismic data and there are no assumptions about the operator and the medium, the inversion can be nonlinear with a high degree of complexity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.