scholarly journals Complete characteristic curve processing method based on improved backpropagation neural network and Logarithmic curve projection

2021 ◽  
Vol 2108 (1) ◽  
pp. 012021
Author(s):  
Baonan Liu ◽  
Jianzhong Zhou
Keyword(s):  
Neural Network ◽  
Transient Process ◽  
Extreme Values ◽  
Characteristic Curve ◽  
Transformation Method ◽  
Backpropagation Neural Network ◽  
Characteristic Curves ◽  
Smooth Flow ◽  
Logarithmic Curve ◽  
Pumped Storage

Abstract The calculation of transient process is the basis of the design and construction of pumped storage power plant, which directly affects operation stability of pumped storage units. However, for satisfying the design of uniform and smooth flow in both directions, the complete characteristic curves of pumped turbine show a significant S feature, which brings difficulties to the interpolation calculation in the transient process as there are crossover and overlap phenomenon in pump and turbine working conditions. In this paper, a transformation method for complete characteristic curves based on logarithmic curve projection and improved backpropagation neural network is presented to solve the above problem. Furthermore, the feasibility and accuracy of the method are verified through the comparison of load rejection condition with on-site measurement, the results show that the proposed method overcomes the multi-value problem that exists in the original curve, in especial makes the small opening region well expressed. The simulation based on the transformed curve reaches a high similarity of transient process with the field test, both in the trend and extreme values, which provides great convenience for the calculation of transient process.

Domain Partitioned Transformation of Pump-Turbine Characteristic Curves in 3-D Space

2014 ◽  
Author(s):  
Wei Zeng ◽  
Jiandong Yang ◽  
Yongguang Cheng
Keyword(s):  
Guide Vane ◽  
Theoretical Method ◽  
Transformation Method ◽  
Measured Data ◽  
Pump Turbine ◽  
Characteristic Curves ◽  
Hydraulic Transient ◽  
Transient Simulations ◽  
Pumped Storage ◽  
Conventional Representation

Pump-turbine characteristic curves are the most important boundary condition in the hydraulic transient simulation of a pumped-storage hydropower station. Conventional representation of them, however, has serious defects, For instance, the “S” and “hump” shapes, composed of multiple values and steep twists, lead to the difficulty in interpolation between known guide-vane opening curves, which is necessary in hydraulic transient simulations. Here, a new transformation method was figured out to settle this problem thoroughly and to improve the accuracy of interpolation between the constant opening curves. Prior to the transformation, the characteristic curves are partitioned into eight domains. Curves of each domain were transformed through different formulae that fit the curves well. Eight characteristic surfaces in the 3-D space can be obtained by adding the guide vane opening as the coordinate axis. The theoretical method has been validated by the excellent agreements achieved by comparing the curves interpolated on the characteristic surfaces with the measured data.

Construction of Pump-Turbine Characteristics at Any Specific Speed by Domain-Partitioned Transformation

2014 ◽  
Vol 137 (3) ◽  
Author(s):  
Wei Zeng ◽  
Jiandong Yang ◽  
Yongguang Cheng
Keyword(s):  
Transformation Method ◽  
Design Stage ◽  
Characteristic Surface ◽  
Pump Turbine ◽  
Characteristic Curves ◽  
Preliminary Design Stage ◽  
Measured Characteristic ◽  
Specific Speed ◽  
Surface Meshes ◽  
Pumped Storage

Pump-turbine characteristics are important for designing pumped-storage plants and indispensable for simulating hydraulic transients, but are often not available in the preliminary design stage. Therefore, constructing a set of pump-turbine characteristics is necessary, when no suitable characteristics at the same specific speed can be used for substitution. In this paper, we propose a new method for pump-turbine characterization at any specific speed using a database of 25 available sets of pump-turbine characteristics. The intersecting curves, defined by the intersections of the characteristic curves with a coordinate axis, are formularized to prepare for the characterization primarily. Next is an introduction of a transformation method for characteristic curves base on domain partition, through which the curves are transformed into eight characteristic surface meshes in eight separate domains. Then, we present the construction procedures in each domain, which include merging the transformed surface meshes for all the sets of collected characteristic curves into a cube mesh, constructing a super surface by interpolation to construct the regular characteristic surface meshes for an arbitrary specific speed, and transforming the constructed meshes reversely to get the conventional characteristic curves. This method is verified by comparing them to measured characteristic curves with reasonable accuracies.

scholarly journals Predicting the 14-Day Hospital Readmission of Patients with Pneumonia Using Artificial Neural Networks (ANN)

2021 ◽  
Vol 18 (10) ◽  
pp. 5110
Author(s):  
Shu-Farn Tey ◽  
Chung-Feng Liu ◽  
Tsair-Wei Chien ◽  
Chin-Wei Hsu ◽  
Kun-Chen Chan ◽  
...  
Keyword(s):  
Neural Network ◽  
Early Stage ◽  
Characteristic Curve ◽  
Patient Discharge ◽  
Ann Model ◽  
Healthcare Settings ◽  
High Area ◽  
Icd 10 ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Unplanned patient readmission (UPRA) is frequent and costly in healthcare settings. No indicators during hospitalization have been suggested to clinicians as useful for identifying patients at high risk of UPRA. This study aimed to create a prediction model for the early detection of 14-day UPRA of patients with pneumonia. We downloaded the data of patients with pneumonia as the primary disease (e.g., ICD-10:J12*-J18*) at three hospitals in Taiwan from 2016 to 2018. A total of 21,892 cases (1208 (6%) for UPRA) were collected. Two models, namely, artificial neural network (ANN) and convolutional neural network (CNN), were compared using the training (n = 15,324; ≅70%) and test (n = 6568; ≅30%) sets to verify the model accuracy. An app was developed for the prediction and classification of UPRA. We observed that (i) the 17 feature variables extracted in this study yielded a high area under the receiver operating characteristic curve of 0.75 using the ANN model and that (ii) the ANN exhibited better AUC (0.73) than the CNN (0.50), and (iii) a ready and available app for predicting UHA was developed. The app could help clinicians predict UPRA of patients with pneumonia at an early stage and enable them to formulate preparedness plans near or after patient discharge from hospitalization.

scholarly journals Recurrent neural network-based acute concussion classifier using raw resting state EEG data

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Karun Thanjavur ◽  
Arif Babul ◽  
Brandon Foran ◽  
Maya Bielecki ◽  
Adam Gilchrist ◽  
...  
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Resting State ◽  
Short Term Memory ◽  
Characteristic Curve ◽  
Health Concern ◽  
Adolescent Athletes ◽  
Individual Level ◽  
Diffuse Brain Injury ◽  
Eeg Data

AbstractConcussion is a global health concern. Despite its high prevalence, a sound understanding of the mechanisms underlying this type of diffuse brain injury remains elusive. It is, however, well established that concussions cause significant functional deficits; that children and youths are disproportionately affected and have longer recovery time than adults; and that individuals suffering from a concussion are more prone to experience additional concussions, with each successive injury increasing the risk of long term neurological and mental health complications. Currently, the most significant challenge in concussion management is the lack of objective, clinically- accepted, brain-based approaches for determining whether an athlete has suffered a concussion. Here, we report on our efforts to address this challenge. Specifically, we introduce a deep learning long short-term memory (LSTM)-based recurrent neural network that is able to distinguish between non-concussed and acute post-concussed adolescent athletes using only short (i.e. 90 s long) samples of resting state EEG data as input. The athletes were neither required to perform a specific task nor expected to respond to a stimulus during data collection. The acquired EEG data were neither filtered, cleaned of artefacts, nor subjected to explicit feature extraction. The LSTM network was trained and validated using data from 27 male, adolescent athletes with sports related concussion, benchmarked against 35 non-concussed adolescent athletes. During rigorous testing, the classifier consistently identified concussions with an accuracy of > 90% and achieved an ensemble median Area Under the Receiver Operating Characteristic Curve (ROC/AUC) equal to 0.971. This is the first instance of a high-performing classifier that relies only on easy-to-acquire resting state, raw EEG data. Our concussion classifier represents a promising first step towards the development of an easy-to-use, objective, brain-based, automatic classification of concussion at an individual level.

scholarly journals Optimization of Optical Machine Structure by Backpropagation Neural Network Based on Particle Swarm Optimization and Bayesian Regularization Algorithms

Materials ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 2998
Author(s):  
Xinyong Zhang ◽  
Liwei Sun
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Prediction Model ◽  
Bayesian Regularization ◽  
Backpropagation Neural Network ◽  
Swarm Optimization ◽  
Modal Frequency ◽  
Supporting Structure ◽  
First Order ◽  
Machine Structure

Fit of the highly nonlinear functional relationship between input variables and output response is important and challenging for the optical machine structure optimization design process. The backpropagation neural network method based on particle swarm optimization and Bayesian regularization algorithms (called BMPB) is proposed to solve this problem. A prediction model of the mass and first-order modal frequency of the supporting structure is developed using the supporting structure as an example. The first-order modal frequency is used as the constraint condition to optimize the lightweight design of the supporting structure’s mass. Results show that the prediction model has more than 99% accuracy in predicting the mass and the first-order modal frequency of the supporting structure, and converges quickly in the supporting structure’s mass-optimization process. The supporting structure results demonstrate the advantages of the method proposed in the article in terms of high accuracy and efficiency. The study in this paper provides an effective method for the optimized design of optical machine structures.

scholarly journals Deep Learning Versus Logistic Regression to Predict Opioid Dose Reduction After Spinal Cord Stimulation

Neurosurgery ◽  
2020 ◽  
Vol 67 (Supplement_1) ◽  
Author(s):  
Syed M Adil ◽  
Lefko T Charalambous ◽  
Kelly R Murphy ◽  
Shervin Rahimpour ◽  
Stephen C Harward ◽  
...  
Keyword(s):  
Neural Network ◽  
Spinal Cord ◽  
Deep Learning ◽  
Dose Reduction ◽  
Spinal Cord Stimulation ◽  
Network Architecture ◽  
Characteristic Curve ◽  
Model Performance ◽  
Health Crisis ◽  
Opioid Dose

Abstract INTRODUCTION Opioid misuse persists as a public health crisis affecting approximately one in four Americans.1 Spinal cord stimulation (SCS) is a neuromodulation strategy to treat chronic pain, with one goal being decreased opioid consumption. Accurate prognostication about SCS success is key in optimizing surgical decision making for both physicians and patients. Deep learning, using neural network models such as the multilayer perceptron (MLP), enables accurate prediction of non-linear patterns and has widespread applications in healthcare. METHODS The IBM MarketScan® (IBM) database was queried for all patients ≥ 18 years old undergoing SCS from January 2010 to December 2015. Patients were categorized into opioid dose groups as follows: No Use, ≤ 20 morphine milligram equivalents (MME), 20–50 MME, 50–90 MME, and >90 MME. We defined “opiate weaning” as moving into a lower opioid dose group (or remaining in the No Use group) during the 12 months following permanent SCS implantation. After pre-processing, there were 62 predictors spanning demographics, comorbidities, and pain medication history. We compared an MLP with four hidden layers to the LR model with L1 regularization. Model performance was assessed using area under the receiver operating characteristic curve (AUC) with 5-fold nested cross-validation. RESULTS Ultimately, 6,124 patients were included, of which 77% had used opioids for >90 days within the 1-year pre-SCS and 72% had used >5 types of medications during the 90 days prior to SCS. The mean age was 56 ± 13 years old. Collectively, 2,037 (33%) patients experienced opiate weaning. The AUC was 0.74 for the MLP and 0.73 for the LR model. CONCLUSION To our knowledge, we present the first use of deep learning to predict opioid weaning after SCS. Model performance was slightly better than regularized LR. Future efforts should focus on optimization of neural network architecture and hyperparameters to further improve model performance. Models should also be calibrated and externally validated on an independent dataset. Ultimately, such tools may assist both physicians and patients in predicting opioid dose reduction after SCS.

A conditional approach for the receiver operating characteristic curve construction to evaluate diagnostic test performance in a family-matched case–control design

2021 ◽  
pp. 096228022199595
Author(s):  
Yalda Zarnegarnia ◽  
Shari Messinger
Keyword(s):  
Receiver Operating Characteristic Curve ◽  
Receiver Operating Characteristic ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Case Control ◽  
Paired Data ◽  
Characteristic Curves ◽  
Receiver Operating Characteristic Curves ◽  
Operating Characteristic Curve ◽  
Receiver Operating

Receiver operating characteristic curves are widely used in medical research to illustrate biomarker performance in binary classification, particularly with respect to disease or health status. Study designs that include related subjects, such as siblings, usually have common environmental or genetic factors giving rise to correlated biomarker data. The design could be used to improve detection of biomarkers informative of increased risk, allowing initiation of treatment to stop or slow disease progression. Available methods for receiver operating characteristic construction do not take advantage of correlation inherent in this design to improve biomarker performance. This paper will briefly review some developed methods for receiver operating characteristic curve estimation in settings with correlated data from case–control designs and will discuss the limitations of current methods for analyzing correlated familial paired data. An alternative approach using conditional receiver operating characteristic curves will be demonstrated. The proposed approach will use information about correlation among biomarker values, producing conditional receiver operating characteristic curves that evaluate the ability of a biomarker to discriminate between affected and unaffected subjects in a familial paired design.

Sign in / Sign up

Export Citation Format

Share Document