Learn More
This paper presents a sensor fault detection and diagnosis approach for industrial combustion processes. Clustering algorithms are applied to the measurements of controllable process variables involved in single-input-single-output feedback control loops. Current data points from the process are compared with the clusters to identify sensor faults. Once the(More)
The paper presents an intelligent wind turbine control system based on models integrating the following three approaches: data mining, model predictive control, and evolutionary computation. To enhance the control strategy of the intelligent system, a multi-objective model is proposed. The model involves five different objectives with different weights(More)
Different models for monitoring wind farm power output are considered. Data mining and evolutionary computation are integrated for building the models for prediction and monitoring. Different models using wind speed as input to predict the total power output of a wind farm are compared and analyzed. The k-nearest neighbor model, combined with the principal(More)
OBJECTIVE To evaluate the risk factors and treatment status of Chinese stroke patients aged 35-45 years old. METHODS We collected data from 1988 in-hospital stroke patients aged 35-45 years old from 36 hospitals in mainland China and compared it to 12,260 health controls with the same age. Information about stroke risk factors was obtained through a(More)
A data-driven approach to the performance analysis of wind turbines is presented. Turbine performance is captured with a power curve. The power curves are constructed using historical wind turbine data. Three power curve models are developed, one by the least squares method and the other by the maximum likelihood estimation method. The models are solved by(More)
The motivation for this work is the necessity to be able to select an appropriate Cloud service provider offering for the migration of existing applications, based on cost minimization. While service providers offer pricing information publicly, and online tools allow for the calculation of cost for various Cloud offerings, the selection of which offering(More)
BACKGROUND AND PURPOSE MicroRNA-128 (miR-128) has been identified as a negative regulator of malignant phenotypes of prostate cancer (PCa) cells. The aim of this study was to evaluate the prognostic implications of both tissue and serum levels of miR-128 expression in PCa patients undergoing radical prostatectomy. METHODS A series of 128 cases with PCa(More)
Depression is a common occurrence in patients with Parkinson's disease (PD). Brain deficits may be the underlying cause of depression in PD. In the present study, we investigated whether morphometric alterations contribute to depression in PD. Seventeen depressed PD patients, 17 non-depressed PD patients and 45 normal controls were enrolled in the study.(More)
OBJECTIVE Research the effect of anti-inflammatory and anti-oxidation drugs on acute stroke patients. METHODS 128 patients with acute ischemic stroke are divided into two groups-combined treatment group (71) and control (57). Test serum biomarkers and evaluate neurological function and living ability before and after therapy, compare between groups and(More)