model performance
Recently Published Documents





2022 ◽  
Vol 12 ◽  
Shaowu Lin ◽  
Yafei Wu ◽  
Ya Fang

BackgroundDepression is highly prevalent and considered as the most common psychiatric disorder in home-based elderly, while study on forecasting depression risk in the elderly is still limited. In an endeavor to improve accuracy of depression forecasting, machine learning (ML) approaches have been recommended, in addition to the application of more traditional regression approaches.MethodsA prospective study was employed in home-based elderly Chinese, using baseline (2011) and follow-up (2013) data of the China Health and Retirement Longitudinal Study (CHARLS), a nationally representative cohort study. We compared four algorithms, including the regression-based models (logistic regression, lasso, ridge) and ML method (random forest). Model performance was assessed using repeated nested 10-fold cross-validation. As the main measure of predictive performance, we used the area under the receiver operating characteristic curve (AUC).ResultsThe mean AUCs of the four predictive models, logistic regression, lasso, ridge, and random forest, were 0.795, 0.794, 0.794, and 0.769, respectively. The main determinants were life satisfaction, self-reported memory, cognitive ability, ADL (activities of daily living) impairment, CESD-10 score. Life satisfaction increased the odds ratio of a future depression by 128.6% (logistic), 13.8% (lasso), and 13.2% (ridge), and cognitive ability was the most important predictor in random forest.ConclusionsThe three regression-based models and one ML algorithm performed equally well in differentiating between a future depression case and a non-depression case in home-based elderly. When choosing a model, different considerations, however, such as easy operating, might in some instances lead to one model being prioritized over another.

2022 ◽  
Zhongrun Xiang ◽  
Ibrahim Demir

Recent studies using latest deep learning algorithms such as LSTM (Long Short-Term Memory) have shown great promise in time-series modeling. There are many studies focusing on the watershed-scale rainfall-runoff modeling or streamflow forecasting, often considering a single watershed with limited generalization capabilities. To improve the model performance, several studies explored an integrated approach by decomposing a large watershed into multiple sub-watersheds with semi-distributed structure. In this study, we propose an innovative physics-informed fully-distributed rainfall-runoff model, NRM-Graph (Neural Runoff Model-Graph), using Graph Neural Networks (GNN) to make full use of spatial information including the flow direction and geographic data. Specifically, we applied a time-series model on each grid cell for its runoff production. The output of each grid cell is then aggregated by a GNN as the final runoff at the watershed outlet. The case study shows that our GNN based model successfully represents the spatial information in predictions. NRM-Graph network has shown less over-fitting and a significant improvement on the model performance compared to the baselines with spatial information. Our research further confirms the importance of spatially distributed hydrological information in rainfall-runoff modeling using deep learning, and we encourage researchers to incorporate more domain knowledge in modeling.

2022 ◽  
Vol 10 ◽  
pp. 1-8
Saad Al-Ahmadi

Phishing websites have grown more recently than ever, and they become more intelligent, even against well-designed phishing detection techniques. Formerly, we have proposed in the literature a state-of-the-art URL-exclusive phishing detection solution based on Convolutional Neural Network (CNN) model, which we referred as PUCNN model. Phishing detection is adversarial as the phisher may attempt to avoid the detection. This adversarial nature makes standard evaluations less useful in predicting model performance in such adversarial situations. We aim to improve PUCNN by addressing the adversarial nature of phishing detection with a restricted adversarial scenario, as PUCNN has shown that an unrestricted attacker dominates. To evaluate this adversarial scenario, we present a parameterized text-based mutation strategy used for generating adversarial samples. These parameters tune the attacker’s restrictions. We have focused on text-based mutation due to our focus on URL-exclusive models. The PUCNN model generally showed robustness and performed well when the parameters were low, which indicates a more restricted attacker.

2022 ◽  
Vol 10 (4) ◽  
pp. 605-616
Jody Hendrian ◽  
Suparti Suparti ◽  
Alan Prahutama

Investing in gold is a flexible choice because it can be sold at any time and used as an emergency fund. Investors should have the knowledge to predict data from time to time to achieve investment goals. One of the statistical methods for time series data modeling is ARIMA. The ARIMA model is strict with the assumptions that the data must be stationary, the residuals must be normally distributed, independent, and with constant variance, so an alternative model is proposed, namely nonparametric regression model, which has no modeling assumptions requirement. In this study, the daily world gold price data will be modeled using a local polynomial nonparametric model as an alternative because the assumptions in the ARIMA are not fulfilled. The data is divided into 2 parts, namely in sample data from January 2, 2020 to November 30, 2020 to form a model and out sample data from December 1, 2020 to December 31, 2020 used for evauation of model performance based on MAPE values. The chosen best model is the local polynomial model with Gaussian kernel function of degree 5, bandwidth of 373, and local point of 1744 with an MSE value of 482.6420. The local polynomial model out sample data MAPE value is 0.61%, indicating that the model has excellent forecasting capability. In this study, Graphical User Interface (GUI) using R software with the help of shiny package is also built, making data analyzing easier and generating more interactive display output. 

2022 ◽  
James Devasia ◽  
Hridyanand Goswami ◽  
Subitha Lakshminarayanan ◽  
Manju Rajaram ◽  
Subathra Adithan ◽  

Abstract Chest X-ray based diagnosis of active Tuberculosis (TB) is one of the oldest ubiquitous tests in medical practice. Artificial Intelligence (AI) based automated detection of abnormality in chest radiography is crucial in radiology workflow. Most deep convolutional neural networks (DCNN) for diagnosing TB by transfer learning from natural images and using the same dataset to evaluate the model performance and diagnostic accuracy. However, dataset shift is a known issue in predictive models in AI, which is unexplored. In this work, we fine-tuned, validated, and tested two benchmark architectures and utilized the transfer learning methodology to measure the diagnostic accuracy on cross-population datasets. We achieved remarkable calcification accuracy of 100% and area under the receiver operating characteristic (AUC) 1.000 [1.000 – 1.000] (with a sensitivity 0.985 [0.971 – 1.000] and a specificity of 0.986 [0.971 – 1.000]) on intramural test set, but significant drop in extramural test set. Accuracy on various extramural test sets varies 50% - 70%, AUC ranges 0.527 – 0.865 (sensitivity and specificity fluctuate 0.394 – 0.995 and 0.443 – 0.864 respectively). Diagnostic performance on the intramural test set observed in this study shows that DCNN can accurately classify active TB and normal chest radiographs, however the external test set shows DCNN is less likely to generalize well on models trained on specific population dataset.

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 632
Jie Li ◽  
Zhixing Wang ◽  
Bo Qi ◽  
Jianlin Zhang ◽  
Hu Yang

In this paper, a mutually enhanced modeling method (MEMe) is presented for human pose estimation, which focuses on enhancing lightweight model performance, but with low complexity. To obtain higher accuracy, a traditional model scale is largely expanded with heavy deployment difficulties. However, for a more lightweight model, there is a large performance gap compared to the former; thus, an urgent need for a way to fill it. Therefore, we propose a MEMe to reconstruct a lightweight baseline model, EffBase transferred intuitively from EfficientDet, into the efficient and effective pose (EEffPose) net, which contains three mutually enhanced modules: the Enhanced EffNet (EEffNet) backbone, the total fusion neck (TFNeck), and the final attention head (FAHead). Extensive experiments on COCO and MPII benchmarks show that our MEMe-based models reach state-of-the-art performances, with limited parameters. Specifically, in the same conditions, our EEffPose-P0 with 256 × 192 can use only 8.98 M parameters to achieve 75.4 AP on the COCO val set, which outperforms HRNet-W48, but with only 14% of its parameters.

Hallie C Prescott ◽  
Rajendra P Kadel ◽  
Julie R Eyman ◽  
Ron Freyberg ◽  
Matthew Quarrick ◽  

Abstract Background The US Veterans Affairs (VA) healthcare system began reporting risk-adjusted mortality for intensive care (ICU) admissions in 2005. However, while the VA’s mortality model has been updated and adapted for risk-adjustment of all inpatient hospitalizations, recent model performance has not been published. We sought to assess the current performance of VA’s 4 standardized mortality models: acute care 30-day mortality (acute care SMR-30); ICU 30-day mortality (ICU SMR-30); acute care in-hospital mortality (acute care SMR); and ICU in-hospital mortality (ICU SMR). Methods Retrospective cohort study with split derivation and validation samples. Standardized mortality models were fit using derivation data, with coefficients applied to the validation sample. Nationwide VA hospitalizations that met model inclusion criteria during fiscal years 2017–2018(derivation) and 2019 (validation) were included. Model performance was evaluated using c-statistics to assess discrimination and comparison of observed versus predicted deaths to assess calibration. Results Among 1,143,351 hospitalizations eligible for the acute care SMR-30 during 2017–2019, in-hospital mortality was 1.8%, and 30-day mortality was 4.3%. C-statistics for the SMR models in validation data were 0.870 (acute care SMR-30); 0.864 (ICU SMR-30); 0.914 (acute care SMR); and 0.887 (ICU SMR). There were 16,036 deaths (4.29% mortality) in the SMR-30 validation cohort versus 17,458 predicted deaths (4.67%), reflecting 0.38% over-prediction. Across deciles of predicted risk, the absolute difference in observed versus predicted percent mortality was a mean of 0.38%, with a maximum error of 1.81% seen in the highest-risk decile. Conclusions and Relevance The VA’s SMR models, which incorporate patient physiology on presentation, are highly predictive and demonstrate good calibration both overall and across risk deciles. The current SMR models perform similarly to the initial ICU SMR model, indicating appropriate adaption and re-calibration.

Adam Schreiner-McGraw ◽  
Hoori Ajami ◽  
Ray Anderson ◽  
Dong Wang

Accurate simulation of plant water use across agricultural ecosystems is essential for various applications, including precision agriculture, quantifying groundwater recharge, and optimizing irrigation rates. Previous approaches to integrating plant water use data into hydrologic models have relied on evapotranspiration (ET) observations. Recently, the flux variance similarity approach has been developed to partition ET to transpiration (T) and evaporation, providing an opportunity to use T data to parameterize models. To explore the value of T/ET data in improving hydrologic model performance, we examined multiple approaches to incorporate these observations for vegetation parameterization. We used ET observations from 5 eddy covariance towers located in the San Joaquin Valley, California, to parameterize orchard crops in an integrated land surface – groundwater model. We find that a simple approach of selecting the best parameter sets based on ET and T performance metrics works best at these study sites. Selecting parameters based on performance relative to observed ET creates an uncertainty of 27% relative to the observed value. When parameters are selected using both T and ET data, this uncertainty drops to 24%. Similarly, the uncertainty in potential groundwater recharge drops from 63% to 58% when parameters are selected with ET or T and ET data, respectively. Additionally, using crop type parameters results in similar levels of simulated ET as using site-specific parameters. Different irrigation schemes create high amounts of uncertainty and highlight the need for accurate estimates of irrigation when performing water budget studies.

Abstract We propose the objective long-range forecasting model based on Gaussian processes (OLRAF-GP), focusing on summertime near-surface air temperatures in June (1-month lead), July (2-month lead), and August (3-month lead). The predictors were objectively selected based on their relationships with the target variables, either from observations (GP-OBS) or from observations and dynamical climate model results from APEC Climate Center multi-model ensemble (APCC MME) for the period with no observed data (GP-MME). The performances of the OLRAF-GP models were compared with the model with pre-determined predictors from observations (GP-PD). Both GP-MME and GP-OBS outperformed GP-PD in June (Heidke skill score; HSS = 0.46, 0.72, and 0.16 for mean temperature) and July (HSS = 0.53, 0.3, and 0.07 for mean temperature). Furthermore, GP-MME mostly outperformed GP-OBS and GP-PD in August (HSS = 0.52, 0.28, and 0.5, respectively, for mean temperature), implying larger contributions of the additional predictors from MME. OLRAF-GP models, especially GP-MME, are expected to better forecast summertime temperatures in regions where existing models have been struggling. We find that the physical processes associated with the notable predictors are aligned with those in previous studies, such as the attribution of the La Niña conditions in the previous winter, the related Indian Ocean capacitor effect, and the impacts of wintertime Polar/Eurasia pattern. These results imply that the mechanisms of the objectively selected predictors can be physically meaningful, and their inclusion can improve model performance and efficiency.

2022 ◽  
Vol 53 (2) ◽  
pp. 119-126
R. K. MALL ◽  

Actual evapotranspiration of wheat crop during different year from 1978-79 to 1992-93 was measured daily in Varanasi, Uttar Pradesh using lysimeter. In this study three evapotranspiration computing models namely Doorenbos and Pruitt, Thornthwaite and Soil Plant Atmosphere Water (SPAW) have been used. Comparisons of these three methods show that the SPAW model is better than the other two methods for evapotraspiration estimation. In the present study the MBE (Mean-Bias-Error), RMSE (Root Mean Square Error) and t-statistic have also been obtained for better evaluations of a model performance.

Sign in / Sign up

Export Citation Format

Share Document