Wireless Sensor Network (WSN) as one of the representatives of the Internet of Things technology has also received much attention. To accurately diagnose fault sensor nodes, a fault diagnosis method based on fireworks algorithm optimization convolutional neural network algorithm is proposed. The weights and biases of the convolutional neural networks are optimized by using the self-regulating mechanism of global and local searching ability of fireworks algorithm. So the problem of convolution neural network in extreme judgment and limited convergence speed is solved, to effectively realize the fault diagnosis of the WSN. Simulation experiments show that this algorithm has higher fault diagnosis accuracy than other classic WSN fault diagnosis algorithms. INDEX TERMS convolution neural network, fault diagnosis, fireworks algorithm, MM* model, wireless sensor network.

We processed MODIS data received from ground receiving stations into the spatial range of the Qinghai-Tibetan Plateau (China) and the eastern margin of the plateau, and then 283 K was set as the threshold value to remove the area covered by clouds. The monthly background field was calculated based on 17 years’ data, then we obtained the spatial Brightness Temperature anomaly of the current month by deducting the background field. Furthermore, the Brightness Temperature anomaly curves for secondary tectonic blocks in the plateau were calculated. The data indicated that since June 2020, the Brightness Temperature radiation within the Qinghai-Tibetan Plateau began to increase abnormally, starting from the western part of the study area and expanding eastward to cover the entire plateau. In January 2021, such an anomaly was seen again, extending to the Sichuan-Yunnan Block in the easternmost part of the study area in april. With the ongoing anomaly, a series of moderate and strong earthquakes occurred in the Qinghai-Tibetan Plateau, and finally, on 22 May 2021, the M7.4 earthquake struck the Madoi County. Moreover, according to the internal Brightness Temperature time series curves of the different secondary tectonic blocks, the Brightness Temperature has increased simultaneously since the beginning of 2020. A twofold standard deviation was found in the middle-east segment of the Bayanhar Block and the Qiangtang Block in October 2020, and an almost twofold standard deviation was found in March, while a twofold standard deviation was found in the Sichuan-Yunnan Block in april 2021. The occurrence of earthquakes in the plateau before the Madoi earthquake coincided with an upward trend of the time series curve. The spatial anomaly of Brightness Temperature over the Qinghai-Tibetan Plateau disappeared and the Brightness Temperature time series curve dropped drastically after the Madoi earthquake. The development of spatial anomaly of Brightness Temperature and the time series curve both coincide with the occurrence of earthquakes and are consistent with the generation of tectonic stress in the Qinghai-Tibetan Plateau. Our study showed that thermal infrared Brightness Temperature radiation reasonably reflects regional stress development and enables the detection of anomalies prior to moderate and strong earthquakes.

No abstract

Gastrointestinal (GI) auscultation (listening to sounds from stomach and bowel) has been applied for abdominal physical assessment for many years. This article evaluates the technique involved in listening to both bowel and stomach sounds and the significance of both normal and abnormal GI auscultation findings. Moreover, intraluminal ultrasonic techniques have been widely used for gastrointestinal disease diagnosis by providing intraluminal images since 1980s, this article also reviews the existing intraluminal ultrasonic technology for diagnosing of GI disorders

An adaptive Hammerstein model with an orthogonal escalator structure as well as a lattice structure for joint processes is developed for short-term load forecasting from one hour to several hours in the future. The method uses a Hammerstein nonlinear time-varying functional relationship between load and temperature. Parameters in both linear and nonlinear parts of the predictor are updated systematically using a scalar orthogonalization procedure. Matrix operations are avoided, thereby allowing better model tracking ability, numerical properties, and performance. Prediction results using actual load-temperature data demonstrate that this algorithm performs better than the commonly used matrix-oriented recursive leastsquare algorithm (RLS) for one-hour-ahead forecasts. IntroductionOn-line short-term load forecasting is an integral part of electric power system control centers. Load forecasts with leadtimes from a few minutes to a day are used for real-time generation control, security analysis, spinning reserve allocation, and intercompany energy interchange planning. Existing load forecasting techniques include state estimation [ 1-21, Box-Jenkins time series [3], exponential smoothing [4], generalized leastsquares [5], expert based system [6], regression [7], and spectral expansion [8] algorithms. In this paper, two innovative techniques are proposed for improving short-term load forecasting. The first addresses modeling the nonlinear time-varying relationship between load and temperature. The second addresses the improvement of model tracking speed and numerical properties for the adaptive model updating procedure. The reasons for using these techniques are described briefly here and are developed in the following sections. Modeling the load-temperature relationshipTemperature information is important for load forecasts with lead-times of one hour or more. One common procedure to model the load-temperature relationship is to transform temperatures to weather variables by a fixed nonlinear function and then relate the residuals of both loads and transformed weather variables through a linear transfer function [3] [5]. Results in [31 demonstrate that using a nonlinear temperature transformation improves forecast performance.