genetic programming
در نشریات گروه پزشکی-
Background
The forecasting of daily outpatient visits has significant practical implications in outpatient clinic operation management, not only contributing to guiding long-term resource planning and scheduling but also making tactical resolutions for short-term adjustments on special days such as holidays. We here in propose an effective genetic programming (GP)-based forecasting model to predict daily outpatient visits (OV) in a primary hospital.
MethodsIn the GP-based model, the holiday-based distance outlier mining algorithm was used to determine the holiday effect. In addition, solar terms were applied as the smallest unit to more accurately determine the impact of a change in the climate on the outpatient volume. A segmental learning strategy also was used to predict the daily outpatient volume for the time series data.
ResultsThe GP-based prediction could more effectively extract depth information from a finite training sample size and achieve a better performance for predicting daily outpatient visits, with lower root mean square error (RMSE) and higher coefficient of determination (R2) values, than the seasonal autoregressive integrated moving average (SARIMA) model in the time range of holidays and the holiday effect.
ConclusionGP-based model can achieve better prediction performance by overcoming the shortcomings of the SARIMA model. The results can be applied to support decision-making and planning of outpatient clinic resources, to help managers implement periodic scheduling of available resources on the basis of periodic features, and to perform proactive scheduling of additional resources.
Keywords: Daily outpatient visits, Forecasting, Time series data, Genetic programming, Outlier analysi -
سابقه و هدف
این مطالعه برای اولین بار با هدف تولید کربن فعال (AC) از دور ریز چوب گون جهت دستیابی به جذب سطحی حداکثری جاذب انجام گرفت. بنابراین هدف از این مطالعه حذف رنگزای اسید اورانژ7 (AO7) با استفاده از AC سنتز شده طی فعال سازی فیزیکی بود.
مواد و روش هافعال سازی AC در روش فیزیکی با گاز نیتروژن در دمای 700 درجه سانتی گراد انجام شد. مشخصات ساختاری جاذب، با استفاده از میکروسکوپ الکترونی روبشی و تکنیک ایزوترم تعیین شد. اثر پارامترهای راهبری، سپس ایزوترم ها و سینتیک های واکنش، مطالعه شد.
یافته هاAC سنتز شده دارای سطح ویژه m2/g 774 و حجم کلی حفرات m3/g181/49 است. حداکثر جذب رنگ mg/g57/127 (کارایی 91/4 درصد) در شرایط بهینه آزمایشگاهی شامل 3=pH، 0/04 گرم جاذب در ml 50 محلول، mg/L 50 رنگ در زمان 75 دقیقه به دست آمد. نتایج نشان داد که داده های جذب از مدل ایزوترم جذب لانگمویر و سینتیک شبه درجه دوم پیروی می کنند. قابلیت استفاده مجدد از جاذب با روش حرارت دهی نشان داد که این جاذب می تواند برای 3 مرتبه متوالی با کارایی مناسب استفاده شود. ضرایب همبستگی (R2) برنامه ژنتیک و شبکه عصبی به ترتیب برابر با 0/98 و0/99 بود که بیانگر تطابق داده های آزمایشگاهی با مدل هاست.
استنتاجکربن فعال تهیه شده از دور ریز چوب گون به روش فعال سازی فیزیکی پتانسیل بالایی در جذب AO7 از محلول های آبی دارد.
کلید واژگان: شبکه عصبی، فعال سازی فیزیکی، رنگ، کربن فعال، جذب سطحی، برنامه نویسی ژنتیکBackground and purposeThis study was conducted for the first time to produce activated carbon (AC) from Milkvetch wood by physical activation in order to achieve the maximum adsorbent capacity in adsorption of dye. The aim of this study was to remove acid orange 7 (AO7) dye using AC produced by physical activation with nitrogen gas.
Materials and methodsAC activation was performed by physical method using nitrogen gas at 700°C. Scanning electron microscopy and isotherm technique were used to determine the structural characteristics of the adsorbent. The effect of operating parameters was investigated. The isotherms and kinetics of the dye adsorption were also studied.
ResultsThe synthesized AC-700°C sample had a specific surface area and a total pore volume of 774 m2/g and 181.49 m3/g, respectively. The maximum adsorption of dye was 57.125 mg/g (removal efficiency 91.4%) that occurred at pH= 3, 0.04 g absorbent in 50 ml of solution, and 50 mg/l of dye in 75 min. The adsorption data followed the Langmuir adsorption isotherm model and the pseudo-second order model kinetics. Also, the ability to reuse the adsorbent using the heating method showed that the synthesized adsorbent can be used for three consecutive times with good performance. Correlation coefficients (R2) for genetic program and neural network were 0.98 and 0.99, respectively, indicating the agreement of laboratory data with the models.
ConclusionThe as-prepared AC by physical activation has a high potential for adsorption of AO7 dye from aqueous solutions.
Keywords: neural network, physical activation, dye, activated carbon, adsorption, genetic programming -
Background
Diabetes is a global health challenge that cusses high incidence of major social and economic consequences. As such, early prevention or identification of those people at risk is crucial for reducing the problems caused by it. The aim of study was to extract the rules for diabetes diagnosing using genetic programming.
MethodsThis study utilized the PIMA dataset of the university of California, Irvine. This dataset consists of the information of 768 Pima heritage women, including 500 healthy persons and 268 persons with diabetes. Regarding the missing values and outliers in this dataset, the K-nearest neighbor and k-means methods are applied respectively. Moreover, a genetic programming model (GP) was conducted to diagnose diabetes as well as to determine the most important factors affecting it. Accuracy, sensitivity and specificity of the proposed model on the PIMA dataset were obtained as 79.32, 58.96 and 90.74%, respectively.
ResultsThe experimental results of our model on PIMA revealed that age, PG concentration, BMI, Tri Fold thick and Serum Ins were effective in diabetes mellitus and increased risk of diabetes. In addition, the good performance of the model coupled with the simplicity and comprehensiveness of the extracted rules is also shown by the experimental results.
ConclusionsGPs can effectively implement the rules for diagnosing diabetes. Both BMI and PG concentration are also the most important factors to increase the risk of suffering from diabetes.
Keywords: Diabetes, PIMA, Genetic programming, KNNi, K-means, Missing value, Outlier detection, Rule extraction
- نتایج بر اساس تاریخ انتشار مرتب شدهاند.
- کلیدواژه مورد نظر شما تنها در فیلد کلیدواژگان مقالات جستجو شدهاست. به منظور حذف نتایج غیر مرتبط، جستجو تنها در مقالات مجلاتی انجام شده که با مجله ماخذ هم موضوع هستند.
- در صورتی که میخواهید جستجو را در همه موضوعات و با شرایط دیگر تکرار کنید به صفحه جستجوی پیشرفته مجلات مراجعه کنید.