Can We Improve Rater Performance?

2019 ◽  
pp. 255-290
Author(s):  
David W. Bracken ◽  
Christopher T. Rotolo
Keyword(s):  
Model Performance ◽  
Performance Model ◽  
Feedback Process ◽  
Feedback Systems ◽  
Systems Model ◽  
360 Feedback ◽  
The Alamo ◽  
Major Factors ◽  
Rater Performance

When raters in a 360 Feedback process do not perform as desired, the result can be highly skewed distributions: The data lose their utility, especially when they are to be used for decision-making. We use the ALAMO performance model [Performance = Alignment × (Ability × Motivation × Opportunity)] to dissect the causes and possible solutions for suboptimal rater performance. Using a systems model of 360 Feedback, we analyze three major factors that can determine the quality of 360 data (i.e., Instrument/Content, Process Features, and Rater Characteristics). No two 360 Feedback systems are the same. It follows that no two diagnoses or prescriptions will be the same across the dozens of decisions that must be made in the design and implementation of a given process. Some of those decisions can be guided by science, some by the unique organization and its leaders, and most by a combination of both. We strongly recommend that both groups of stakeholders (scientist practitioners and process owners) study this chapter prior to making those decisions.

One-Dimensional, Stage-by-Stage, Axial Compressor Performance Model

1991 ◽  
Author(s):  
Mark S. Johnson
Keyword(s):  
Power Systems ◽  
Gas Turbine ◽  
Model Performance ◽  
Axial Compressor ◽  
Performance Model ◽  
Performance Information ◽  
One Dimensional ◽  
Design Performance ◽  
Systems Model ◽  
Compressor Performance

This paper presents a description of a one-dimensional, constant-radius, stage-by-stage (blade-element) axial compressor model used for compressor map generation and gas turbine off-design performance prediction. This model is designed for investigators who are without access to the proprietary compressor performance information of the gas turbine manufacturers but who are nevertheless interested in predicting the off-design performance of large utility gas turbine power systems. Model performance results (compressor maps) are reported for simulation of a nineteen-stage axial compressor designed by Allison Gas Turbine for the Electric Power Research Institute. The model is further demonstrated by simulating the NACA Eight Stage compressor. The resulting compressor maps are in good qualitative agreement with published maps and are useful for gas turbine power system performance simulation studies. This general-purpose modeling procedure can be applied to any axial compressor for which sufficient airfoil geometry and design-point performance information is known.

scholarly journals Nodule Detection with Convolutional Neural Network Using Apache Spark and GPU Frameworks

2021 ◽  
Vol 11 (6) ◽  
pp. 2838
Author(s):  
Nikitha Johnsirani Venkatesan ◽  
Dong Ryeol Shin ◽  
Choon Sung Nam
Keyword(s):  
Neural Network ◽  
Radiation Dose ◽  
Convolutional Neural Network ◽  
Model Performance ◽  
Performance Comparison ◽  
Apache Spark ◽  
Training Time ◽  
Learning Framework ◽  
Proposed Model

In the pharmaceutical field, early detection of lung nodules is indispensable for increasing patient survival. We can enhance the quality of the medical images by intensifying the radiation dose. High radiation dose provokes cancer, which forces experts to use limited radiation. Using abrupt radiation generates noise in CT scans. We propose an optimal Convolutional Neural Network model in which Gaussian noise is removed for better classification and increased training accuracy. Experimental demonstration on the LUNA16 dataset of size 160 GB shows that our proposed method exhibit superior results. Classification accuracy, specificity, sensitivity, Precision, Recall, F1 measurement, and area under the ROC curve (AUC) of the model performance are taken as evaluation metrics. We conducted a performance comparison of our proposed model on numerous platforms, like Apache Spark, GPU, and CPU, to depreciate the training time without compromising the accuracy percentage. Our results show that Apache Spark, integrated with a deep learning framework, is suitable for parallel training computation with high accuracy.

scholarly journals Modelling Exposure by Spraying Activities—Status and Future Needs

2021 ◽  
Vol 18 (15) ◽  
pp. 7737
Author(s):  
Stefan Hahn ◽  
Jessica Meyer ◽  
Michael Roitzsch ◽  
Christiaan Delmaar ◽  
Wolfgang Koch ◽  
...  
Keyword(s):  
Current Knowledge ◽  
Model Performance ◽  
Relevant Information ◽  
Systematic Evaluation ◽  
Model Accuracy ◽  
Efficient Manner ◽  
User Perspective ◽  
Model Predictions ◽  
Spray Applications

Spray applications enable a uniform distribution of substances on surfaces in a highly efficient manner, and thus can be found at workplaces as well as in consumer environments. A systematic literature review on modelling exposure by spraying activities has been conducted and status and further needs have been discussed with experts at a symposium. This review summarizes the current knowledge about models and their level of conservatism and accuracy. We found that extraction of relevant information on model performance for spraying from published studies and interpretation of model accuracy proved to be challenging, as the studies often accounted for only a small part of potential spray applications. To achieve a better quality of exposure estimates in the future, more systematic evaluation of models is beneficial, taking into account a representative variety of spray equipment and application patterns. Model predictions could be improved by more accurate consideration of variation in spray equipment. Inter-model harmonization with regard to spray input parameters and appropriate grouping of spray exposure situations is recommended. From a user perspective, a platform or database with information on different spraying equipment and techniques and agreed standard parameters for specific spraying scenarios from different regulations may be useful.

scholarly journals Development of prognostic models for Health-Related Quality of Life following traumatic brain injury

2021 ◽  
Author(s):  
Isabel R. A. Retel Helmrich ◽  
David van Klaveren ◽  
Simone A. Dijkland ◽  
Hester F. Lingsma ◽  
Suzanne Polinder ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Model Performance ◽  
Prognostic Models ◽  
Health Related Quality ◽  
Mild Tbi ◽  
Related Quality ◽  
Health Related

Abstract Background Traumatic brain injury (TBI) is a leading cause of impairments affecting Health-Related Quality of Life (HRQoL). We aimed to identify predictors of and develop prognostic models for HRQoL following TBI. Methods We used data from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) Core study, including patients with a clinical diagnosis of TBI and an indication for computed tomography presenting within 24 h of injury. The primary outcome measures were the SF-36v2 physical (PCS) and mental (MCS) health component summary scores and the Quality of Life after Traumatic Brain Injury (QOLIBRI) total score 6 months post injury. We considered 16 patient and injury characteristics in linear regression analyses. Model performance was expressed as proportion of variance explained (R2) and corrected for optimism with bootstrap procedures. Results 2666 Adult patients completed the HRQoL questionnaires. Most were mild TBI patients (74%). The strongest predictors for PCS were Glasgow Coma Scale, major extracranial injury, and pre-injury health status, while MCS and QOLIBRI were mainly related to pre-injury mental health problems, level of education, and type of employment. R2 of the full models was 19% for PCS, 9% for MCS, and 13% for the QOLIBRI. In a subset of patients following predominantly mild TBI (N = 436), including 2 week HRQoL assessment improved model performance substantially (R2 PCS 15% to 37%, MCS 12% to 36%, and QOLIBRI 10% to 48%). Conclusion Medical and injury-related characteristics are of greatest importance for the prediction of PCS, whereas patient-related characteristics are more important for the prediction of MCS and the QOLIBRI following TBI.

Prediction of quality of life in people with ALS

2021 ◽  
Vol 21 (2) ◽  
pp. 5-17
Author(s):  
Anna Markella Antoniadi ◽  
Miriam Galvin ◽  
Mark Heverin ◽  
Orla Hardiman ◽  
Catherine Mooney
Keyword(s):  
Quality Of Life ◽  
Disease Onset ◽  
Model Performance ◽  
Sampling Technique ◽  
Clinical Decision ◽  
Gradient Boosting ◽  
Rapid Decline ◽  
Extreme Gradient Boosting ◽  
Lateral Sclerosis

Amyotrophic Lateral Sclerosis (ALS) is a rare neurodegenerative disease that causes a rapid decline in motor functions and has a fatal trajectory. ALS is currently incurable, so the aim of the treatment is mostly to alleviate symptoms and improve quality of life (QoL) for the patients. The goal of this study is to develop a Clinical Decision Support System (CDSS) to alert clinicians when a patient is at risk of experiencing low QoL. The source of data was the Irish ALS Registry and interviews with the 90 patients and their primary informal caregiver at three time-points. In this dataset, there were two different scores to measure a person's overall QoL, based on the McGill QoL (MQoL) Questionnaire and we worked towards the prediction of both. We used Extreme Gradient Boosting (XGBoost) for the development of the predictive models, which was compared to a logistic regression baseline model. Additionally, we used Synthetic Minority Over-sampling Technique (SMOTE) to examine if that would increase model performance and SHAP (SHapley Additive explanations) as a technique to provide local and global explanations to the outputs as well as to select the most important features. The total calculated MQoL score was predicted accurately using three features - age at disease onset, ALSFRS-R score for orthopnoea and the caregiver's status pre-caregiving - with a F1-score on the test set equal to 0.81, recall of 0.78, and precision of 0.84. The addition of two extra features (caregiver's age and the ALSFRS-R score for speech) produced similar outcomes (F1-score 0.79, recall 0.70 and precision 0.90).

Decision-Feedback Stages Revealed by Hidden Markov Modeling of EEG

2021 ◽  
pp. 2150031
Author(s):  
Qin Tao ◽  
Yajing Si ◽  
Fali Li ◽  
Peiyang Li ◽  
Yuqin Li ◽  
...  
Keyword(s):  
Frontal Lobe ◽  
Visual Information ◽  
Hidden Markov ◽  
Decision Feedback ◽  
Markov Modeling ◽  
Feedback Process ◽  
Feedback Systems ◽  
Left Frontal Lobe ◽  
Hidden Markov Modeling ◽  
Independent Decision

Decision response and feedback in gambling are interrelated. Different decisions lead to different ranges of feedback, which in turn influences subsequent decisions. However, the mechanism underlying the continuous decision-feedback process is still left unveiled. To fulfill this gap, we applied the hidden Markov model (HMM) to the gambling electroencephalogram (EEG) data to characterize the dynamics of this process. Furthermore, we explored the differences between distinct decision responses (i.e. choose large or small bets) or distinct feedback (i.e. win or loss outcomes) in corresponding phases. We demonstrated that the processing stages in decision-feedback process including strategy adjustment and visual information processing can be characterized by distinct brain networks. Moreover, time-varying networks showed, after decision response, large bet recruited more resources from right frontal and right center cortices while small bet was more related to the activation of the left frontal lobe. Concerning feedback, networks of win feedback showed a strong right frontal and right center pattern, while an information flow originating from the left frontal lobe to the middle frontal lobe was observed in loss feedback. Taken together, these findings shed light on general principles of natural decision-feedback and may contribute to the design of biologically inspired, participant-independent decision-feedback systems.

EHR-based machine learning modeling for preterm birth prediction: A systematic review (Preprint)

2021 ◽  
Author(s):  
Zahra Sharifiheris ◽  
Juho Laitala ◽  
Antti Airola ◽  
Amir M Rahmani ◽  
Miriam Bender
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Preterm Birth ◽  
Model Performance ◽  
Bibliographic Databases ◽  
Complementary Approach ◽  
Prisma Statement ◽  
Comprehensive Search ◽  
First Time

BACKGROUND Preterm birth (PTB) as a common pregnancy complication is responsible for 35% of the 3.1 million pregnancy-related deaths each year and significantly impacts around 15 million children annually across the world. Conventional approaches to predict PTB may neither be applicable for first-time mothers nor possess reliable predictive power. Recently, machine learning (ML) models have shown the potential as an appropriate complementary approach for PTB prediction. OBJECTIVE In this article we systematically reviewed the literature concerned with PTB prediction using ML modeling. METHODS This systematic review was conducted in accordance with the PRISMA statement. A comprehensive search was performed in seven bibliographic databases up until 15 May 2021. The quality of studies was assessed, and the descriptive information including socio-demographic characteristics, ML modeling processes, and model performance were extracted and reported. RESULTS A total of 732 papers were screened through title and abstract. Of these, 23 studies were screened by full text resulting in 13 papers that met the inclusion criteria. CONCLUSIONS We identified various ML models used for different EHR data resulting in a desirable performance for PTB prediction. However, evaluation metrics, software/package used, data size and type, and selected features, and importantly data management method often varied from study to study threatening the reliability and generalizability of the model. CLINICALTRIAL n.a.

scholarly journals A Direct-Steam Linear Fresnel Performance Model for NREL’S System Advisor Model

2012 ◽  
Author(s):  
Michael J. Wagner ◽  
Guangdong Zhu
Keyword(s):  
Heat Loss ◽  
Mathematical Formulation ◽  
Model Performance ◽  
Performance Model ◽  
Electricity Production ◽  
Steam Generation ◽  
Time Step ◽  
Wide Range ◽  
Direct Steam ◽  
Solar Field

This paper presents the technical formulation and demonstrated model performance results of a new direct-steam-generation (DSG) model in NREL’s System Advisor Model (SAM). The model predicts the annual electricity production of a wide range of system configurations within the DSG Linear Fresnel technology by modeling hourly performance of the plant in detail. The quasi-steady-state formulation allows users to investigate energy and mass flows, operating temperatures, and pressure drops for geometries and solar field configurations of interest. The model includes tools for heat loss calculation using either empirical polynomial heat loss curves as a function of steam temperature, ambient temperature, and wind velocity, or a detailed evacuated tube receiver heat loss model. Thermal losses are evaluated using a computationally efficient nodal approach, where the solar field and headers are discretized into multiple nodes where heat losses, thermal inertia, steam conditions (including pressure, temperature, enthalpy, etc.) are individually evaluated during each time step of the simulation. This paper discusses the mathematical formulation for the solar field model and describes how the solar field is integrated with the other subsystem models, including the power cycle and optional auxiliary fossil system. Model results are also presented to demonstrate plant behavior in the various operating modes.

scholarly journals Modelling the hydrology and water quality of 3S river system (Sekong, Sesan and Srepok)

2016 ◽  
Vol 19 (2) ◽  
pp. 107-117
Author(s):  
Trang Thi Thuy Nguyen ◽  
Khoi Nguyen Dao
Keyword(s):  
Water Quality ◽  
Swat Model ◽  
Model Performance ◽  
River System ◽  
Water Quality Assessment ◽  
River Basin Management ◽  
Analysis Tool ◽  
Nitrogen And Phosphorus ◽  
Model Soil

The objective of this study was to simulate the hydrologic characteristic and water quality of 3S rivers system (Sekong, Sesan and Srepok) using SWAT model (Soil and Water Analysis Tool). Agriculture and forest are the main land use types in this basin accounting for more than 80 % of the total area. Therfore, nitrogen and phosphorus were selected to be parameters for water quality assessment. SWAT-CUP model was applied to calibrate the model for stream flow and water quality based on SUFI-2 (Sequential Uncertainty Fitting version 2) method. The model performance has been assessed by three statistical indices, including coefficient corellation (R2), Nash-Sutcliffe efficient coefficience (NSE) and percentage Bias (PBIAS). The results showed that SWAT model was well calibrated for simulating the streamflow and water quality with the values of R2 greater than 0.5 except for the Attapeu and Kontum stations, and of PBIAS less than 10 % and 35 % for streamflow and water quality, respectively. The well-calibrated SWAT model can be applied in predicting the hydrology and water quality for other application. Furthermore, it is a tool supporting the policy makers to offer a suitable decisions regarding the sustainable river basin management.

Sign in / Sign up

Export Citation Format

Share Document