Статті в журналах з теми "Partial Dependence Plot"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Partial Dependence Plot.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Partial Dependence Plot".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Yan, Miaomiao, and Yindong Shen. "Traffic Accident Severity Prediction Based on Random Forest." Sustainability 14, no. 3 (February 2, 2022): 1729. http://dx.doi.org/10.3390/su14031729.
Анотація:
The prediction of traffic accident severity is essential for traffic safety management and control. To achieve high prediction accuracy and model interpretability, we propose a hybrid model that integrates random forest (RF) and Bayesian optimization (BO). In the proposed model, BO-RF, RF is adopted as a basic predictive model and BO is used to tune the parameters of RF. Experimental results show that BO-RF achieves higher accuracy than conventional algorithms. Moreover, BO-RF provides interpretable results by relative importance and a partial dependence plot. We can identify important influential factors for traffic accident severity by relative importance. Further, we can investigate how the influential factors affect traffic accident severity by the partial dependence plot. These results provide insights to mitigate the severity of traffic accident consequences and contribute to the sustainable development of transportation.
2
Dewan, Isha, and Subhash Kochar. "SOME NEW APPLICATIONS OF P–P PLOTS." Probability in the Engineering and Informational Sciences 27, no. 3 (March 28, 2013): 353–66. http://dx.doi.org/10.1017/s0269964813000077.
Анотація:
The P–P plot is a powerful graphical tool to compare stochastically the magnitudes of two random variables. In this note, we introduce a new partial order, called P–P order based on P–P plots. For a pair of random variables (X1, Y1) and (X2, Y2) one can see the relative precedence of Y2 over X2 versus that of Y1 over X1 using P–P order. We show that several seemingly very technical and difficult concepts like convex transform order and super-additive ordering can be easily explained with the help of this new partial order. Several concepts of positive dependence can also be expressed in terms of P–P orders of the conditional distributions.
3
Lee, Changro. "Training and Interpreting Machine Learning Models: Application in Property Tax Assessment." Real Estate Management and Valuation 30, no. 1 (March 1, 2022): 13–22. http://dx.doi.org/10.2478/remav-2022-0002.
Анотація:
Abstract In contrast to the outstanding performance of the machine learning approach, its adoption in industry appears to be relatively slow compared to the speed of its proliferation in a variety of business sectors. The low interpretability of a black-box-type model, such as a machine learning-based valuation model, is one reason for this. In this study, house prices in Seoul and Jeollanam Province, South Korea, were estimated using a neural network, a representative model to implement machine learning, and we attempted to interpret the resultant price estimations using an interpretability tool called a partial dependence plot. Partial dependence analysis indicated that locally optimized valuation models should be designed to enhance valuation accuracy: a land-oriented model for Seoul and a building-focused model for the Jeollanam Province. The interpretable machine learning approach is expected to catalyze the adoption of machine learning in the industry, including property valuation.
4
Fu, Xiao. "The D e (T, t) plot: A straightforward self-diagnose tool for post-IR IRSL dating procedures." Geochronometria 41, no. 4 (December 1, 2014): 315–26. http://dx.doi.org/10.2478/s13386-013-0167-9.
Анотація:
Abstract This study presents a new self-diagnose method for the recently developed post-IR infrared stimulated luminescence (pIRIR) dating protocols. This criterion studies the dependence of equivalent dose (D e) on measurement-temperature (T) and time (t), by applying the D e (t) analysis to the IRLS and pIRIR signals measured under different temperatures, and combines these D e (t) plots into one, so-called the D e (T, t) plot. The pattern of the D e (T, t) plot is shown to be affected by anomalous fading, partial bleaching and non-bleachable signal. A D e plateau can be achieved in the D e (T, t) plot only when the effects of these factors are insignificant. Therefore, this plot can be used as a self-diagnose tool for the validity of pIRIR results. The D e (T, t) analysis has been applied to four recently developed pIRIR protocols, using aeolian samples with different ages. The results show that this self-diagnose tool can be applied to different pIRIR protocols for validating the pIRIR dating results and evaluating the pIRIR measurement conditions.
5
Tran, Van Quan. "Predicting and Investigating the Permeability Coefficient of Soil with Aided Single Machine Learning Algorithm." Complexity 2022 (September 25, 2022): 1–18. http://dx.doi.org/10.1155/2022/8089428.
Анотація:
The permeability coefficient of soils is an essential measure for designing geotechnical construction. The aim of this paper was to select a highest performance and reliable machine learning (ML) model to predict the permeability coefficient of soil and quantify the feature importance on the predicted value of the soil permeability coefficient with aided machine learning-based SHapley Additive exPlanations (SHAP) and Partial Dependence Plot 1D (PDP 1D). To acquire this purpose, five single ML algorithms including K-nearest neighbors (KNN), support vector machine (SVM), light gradient boosting machine (LightGBM), random forest (RF), and gradient boosting (GB) are used to build ML models for predicting the permeability coefficient of soils. Performance criteria for ML models include the coefficient of correlation R2, root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The best performance and reliable single ML model for predicting the permeability coefficient of soil for the testing dataset is the gradient boosting (GB) model, which has R2 = 0.971, RMSE = 0.199 × 10−11 m/s, MAE = 0.161 × 10−11 m/s, and MAPE = 0.185%. To identify and quantify the feature importance on the permeability coefficient of soil, sensitivity studies using permutation importance, SHapley Additive exPlanations (SHAP), and Partial Dependence Plot 1D (PDP 1D) are performed with the aided best performance and reliable ML model GB. Plasticity index, density > water content, liquid limit, and plastic limit > clay content > void ratio are the order effects on the predicted value of the permeability coefficient. The plasticity index and density of soil are the first priority soil properties to measure when assessing the permeability coefficient of soil.
6
Wu, Zihao, Yiyun Chen, Yuanli Zhu, Xiangyang Feng, Jianxiong Ou, Guie Li, Zhaomin Tong, and Qingwu Yan. "Mapping Soil Organic Carbon in Floodplain Farmland: Implications of Effective Range of Environmental Variables." Land 12, no. 6 (June 8, 2023): 1198. http://dx.doi.org/10.3390/land12061198.
Анотація:
Accurately mapping soil organic carbon (SOC) is conducive to evaluating carbon storage and soil quality. However, the high spatial heterogeneity of SOC caused by river-related factors and agricultural management brings challenges to digital soil mapping in floodplain farmland. Moreover, current studies focus on the non-linear relationship between SOC and covariates, but ignore the effective range of environmental variables on SOC, which prevents the revelation of the SOC differentiation mechanism. Using the 375 samples collected from the Jiangchang Town near Han River, we aim to determine the main controlling factors of SOC, reveal the effective range of environmental variables, and obtain the spatial map of SOC by using the gradient boosting decision tree (GBDT) model and partial dependence plots. Linear regression was used as a reference. Results showed that GBDT outperformed linear regression. GBDT results show that the distance from the river was the most important SOC factor, confirming the importance of the Han River to the SOC pattern. The partial dependence plots indicate that all environmental variables have their effective ranges, and when their values are extremely high or low, they do not respond to changes in SOC. Specifically, the influential ranges of rivers, irrigation canals, and rural settlements on SOC were within 4000, 200, and 50 m, respectively. The peak SOC was obtained with high clay (≥31%), total nitrogen (≥1.18 g/kg), and total potassium contents (≥11.1 g/kg), but it remained steady when these covariates further increased. These results highlight the importance of revealing the effective range of environmental variables, which provides data support for understanding the spatial pattern of SOC in floodplain farmland, achieving carbon sequestration in farmland and precision agriculture. The GBDT with the partial dependence plot was effective in SOC fitting and mapping.
7
Patterson, L. D., and G. Blouin-Demers. "Partial support for food availability and thermal quality as drivers of density and area used in Yarrow’s Spiny Lizards (Sceloporus jarrovii)." Canadian Journal of Zoology 98, no. 2 (February 2020): 105–16. http://dx.doi.org/10.1139/cjz-2019-0166.
Анотація:
Contrary to traditional models, habitat selection in ectotherms may be chiefly based on a habitat’s thermal properties rather than its food availability, due to their physiological dependence on environmental temperature. We tested two hypotheses: that microhabitat use in ectotherms is driven by food availability and that it is driven by thermoregulatory requirements. We predicted that the density of lizards would increase and the mean area used would decrease with the natural arthropod (food) availability (or thermal quality) of a plot, as well as after experimentally increasing plot arthropod availability (or thermal quality). We established two plots in each of four treatments (food-supplemented, shaded, food-supplemented and shaded, and control) on a talus slope in Arizona, USA. We measured the density and area used in Yarrow’s Spiny Lizards (Sceloporus jarrovii Cope in Yarrow, 1875) before and after manipulations, and determined whether lizard density and area used were related to natural arthropod availability or thermal quality at the surface and in retreat sites. Density and area used were unaffected by the manipulations, but both increased with natural arthropod availability and decreased with higher thermal quality in retreat sites. These results provide partial support for both food availability and thermal quality as drivers of density and microhabitat use in S. jarrovii.
8
Khoerunnisa, Fitri, Aaron Morelos-Gomez, Hideki Tanaka, Toshihiko Fujimori, Daiki Minami, Radovan Kukobat, Takuya Hayashi, et al. "Metal–semiconductor transition like behavior of naphthalene-doped single wall carbon nanotube bundles." Faraday Discuss. 173 (2014): 145–56. http://dx.doi.org/10.1039/c4fd00119b.
Анотація:
Naphthalene (N) or naphthalene-derivative (ND) adsorption-treatment evidently varies the electrical conductivity of single wall carbon nanotube (SWCNT) bundles over a wide temperature range due to a charge–transfer interaction. The adsorption treatment of SWCNTs with dinitronaphthalene molecules enhances the electrical conductivity of the SWCNT bundles by 50 times. The temperature dependence of the electrical conductivity of N- or ND-adsorbed SWCNT bundles having a superlattice structure suggests metal–semiconductor transition like behavior near 260 K. The ND-adsorbed SWCNT gives a maximum in the logarithm of electrical conductivity vs. T−1 plot, which may occur after the change to a metallic state and be associated with a partial unravelling of the SWCNT bundle due to an evoked librational motion of the moieties of ND with elevation of the temperature.
9
Chang, Shih-Chieh, Chan-Lin Chu, Chih-Kuang Chen, Hsiang-Ning Chang, Alice M. K. Wong, Yueh-Peng Chen, and Yu-Cheng Pei. "The Comparison and Interpretation of Machine-Learning Models in Post-Stroke Functional Outcome Prediction." Diagnostics 11, no. 10 (September 28, 2021): 1784. http://dx.doi.org/10.3390/diagnostics11101784.
Анотація:
Prediction of post-stroke functional outcomes is crucial for allocating medical resources. In this study, a total of 577 patients were enrolled in the Post-Acute Care-Cerebrovascular Disease (PAC-CVD) program, and 77 predictors were collected at admission. The outcome was whether a patient could achieve a Barthel Index (BI) score of >60 upon discharge. Eight machine-learning (ML) methods were applied, and their results were integrated by stacking method. The area under the curve (AUC) of the eight ML models ranged from 0.83 to 0.887, with random forest, stacking, logistic regression, and support vector machine demonstrating superior performance. The feature importance analysis indicated that the initial Berg Balance Test (BBS-I), initial BI (BI-I), and initial Concise Chinese Aphasia Test (CCAT-I) were the top three predictors of BI scores at discharge. The partial dependence plot (PDP) and individual conditional expectation (ICE) plot indicated that the predictors’ ability to predict outcomes was the most pronounced within a specific value range (e.g., BBS-I < 40 and BI-I < 60). BI at discharge could be predicted by information collected at admission with the aid of various ML models, and the PDP and ICE plots indicated that the predictors could predict outcomes at a certain value range.
10
Shiroyama, Risa, Manna Wang, and Chihiro Yoshimura. "Effect of sample size on habitat suitability estimation using random forests: a case of bluegill, Lepomis macrochirus." Annales de Limnologie - International Journal of Limnology 56 (2020): 13. http://dx.doi.org/10.1051/limn/2020010.
Анотація:
Species distribution models (SDMs) have been used to understand the habitat suitability of key species. Habitat suitability plots, one outcome from SDMs, are valuable for understanding the habitat suitability and behavior of organisms. The sample size is often constrained by budget and time, and could largely influence the reliability of habitat suitability plots. To understand the effect of sample size on habitat suitability plots, the present study utilized random forests (RF) combined with partial dependence function. And the bluegill (Lepomis macrochirus), a main exotic fish species in the Japan rivers, was selected as target species in this study. Total of 1010 samples of bluegill observations along with four environmental variables were surveyed by the National Censuses on River Environments. The area under curves was calculated after generating RF models, to assess the predictive model performance, and this process was repeated 1000 times. To draw habitat suitability plots, we applied partial dependence function to the formulated RF models, and 15 different sample sizes were set to examine the effect on habitat suitability plots. We concluded that habitat suitability plots are affected by sample size and prediction performance. Notably, habitat suitability plots drawn from the sample size of 50 greatly varied among the 1000-time iterations, and they are all different from the observations. Furthermore, to deal with the case of limited samples, we proposed a novel approach “averaged habitat suitability plot” for delineating habitat suitability plots. The proposed approach enables us to assess the habitat suitability even with a small sample size.
11
Lin, Ming-Yen, Yuan-Ming Chang, Chi-Chun Li, and Wen-Cheng Chao. "Explainable Machine Learning to Predict Successful Weaning of Mechanical Ventilation in Critically Ill Patients Requiring Hemodialysis." Healthcare 11, no. 6 (March 21, 2023): 910. http://dx.doi.org/10.3390/healthcare11060910.
Анотація:
Lungs and kidneys are two vital and frequently injured organs among critically ill patients. In this study, we attempt to develop a weaning prediction model for patients with both respiratory and renal failure using an explainable machine learning (XML) approach. We used the eICU collaborative research database, which contained data from 335 ICUs across the United States. Four ML models, including XGBoost, GBM, AdaBoost, and RF, were used, with weaning prediction and feature windows, both at 48 h. The model’s explanations were presented at the domain, feature, and individual levels by leveraging various techniques, including cumulative feature importance, the partial dependence plot (PDP), the Shapley additive explanations (SHAP) plot, and local explanation with the local interpretable model-agnostic explanations (LIME). We enrolled 1789 critically ill ventilated patients requiring hemodialysis, and 42.8% (765/1789) of them were weaned successfully from mechanical ventilation. The accuracies in XGBoost and GBM were better than those in the other models. The discriminative characteristics of six key features used to predict weaning were demonstrated through the application of the SHAP and PDP plots. By utilizing LIME, we were able to provide an explanation of the predicted probabilities and the associated reasoning for successful weaning on an individual level. In conclusion, we used an XML approach to establish a weaning prediction model in critically ill ventilated patients requiring hemodialysis.
12
Núñez, Jorge, Catalina B. Cortés, and Marjorie A. Yáñez. "Explainable Artificial Intelligence in Hydrology: Interpreting Black-Box Snowmelt-Driven Streamflow Predictions in an Arid Andean Basin of North-Central Chile." Water 15, no. 19 (September 26, 2023): 3369. http://dx.doi.org/10.3390/w15193369.
Анотація:
In recent years, a new discipline known as Explainable Artificial Intelligence (XAI) has emerged, which has followed the growing trend experienced by Artificial Intelligence over the last decades. There are, however, important gaps in the adoption of XAI in hydrology research, in terms of application studies in the southern hemisphere, or in studies associated with snowmelt-driven streamflow prediction in arid regions, to mention a few. This paper seeks to contribute to filling these knowledge gaps through the application of XAI techniques in snowmelt-driven streamflow prediction in a basin located in the arid region of north-central Chile in South America. For this, two prediction models were built using the Random Forest algorithm, for one and four months in advance. The models show good prediction performance in the training set for one (RMSE:1.33, R2: 0.94, MAE:0.55) and four (RMSE: 5.67, R2:0.94, MAE: 1.51) months in advance. The selected interpretation techniques (importance of the variable, partial dependence plot, accumulated local effects plot, Shapley values and local interpretable model-agnostic explanations) show that hydrometeorological variables in the vicinity of the basin are more important than climate variables and this occurs both for the dataset level and for the months with the lowest streamflow records. The importance of the XAI approach adopted in this study is discussed in terms of its contribution to the understanding of hydrological processes, as well as its role in high-stakes decision-making.
13
Tran, Anh-Tuan, Thanh-Hai Le, and Huu May Nguyen. "Forecast of surface chloride concentration of concrete utilizing ensemble decision tree boosted." Journal of Science and Transport Technology 2, no. 1 (March 25, 2022): 44–56. http://dx.doi.org/10.58845/jstt.utt.2022.en57.
Анотація:
This study proposes the application of Ensemble Decision Tree Boosted (EDT Boosted) model for forecasting the surface chloride concentration of marine concrete A database of 386 experimental results was collected from 17 different sources covering twelve variables was used to build and verify the predictive power of the EDT model. The input factors considered the changes in eleven variables, including the contents of cement, fly ash, blast furnace slag, silica fume, superplasticizer, water, fine aggregate, coarse aggregate, annual mean temperature, chloride concentration in seawater, and exposure time. The results indicate that EDT Boosted is a good predictor of as verified via good performance evaluation criteria, i.e., R2, RMSE, MAE, MAPE values were 0.84, 0.16, 0.17, and 17%, respectively. Partial dependence plot (PDP) was then developed to correlate the eleven input variables with the . PDP implied that the strongest factor affecting Cs was the amount of fine aggregate content, chloride concentration, exposure time, amount of cement, and water, which is useful for material engineers in the design of the grade.
14
Jung, Jinwoo, Jihwan Kim, and Changha Jin. "DOES MACHINE LEARNING PREDICTION DAMPEN THE INFORMATION ASYMMETRY FOR NON-LOCAL INVESTORS?" International Journal of Strategic Property Management 26, no. 5 (November 14, 2022): 345–61. http://dx.doi.org/10.3846/ijspm.2022.17590.
Анотація:
In this study, we examine the prediction accuracy of machine learning methods to estimate commercial real estate transaction prices. Using machine learning methods, including Random Forest (RF), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), and Deep Neural Networks (DNN), we estimate the commercial real estate transaction price by comparing relative prediction accuracy. Data consist of 19,640 transaction-based office properties provided by Costar corresponding to the 2004–2017 period for 10 major U.S. CMSA (Consolidated Metropolitan Statistical Area). We conduct each machine learning method and compare the performance to identify a critical determinant model for each office market. Furthermore, we depict a partial dependence plot (PD) to verify the impact of research variables on predicted commercial office property value. In general, we expect that results from machine learning will provide a set of critical determinants to commercial office price with more predictive power overcoming the limitation of the traditional valuation model. The result for 10 CMSA will provide critical implications for the out-of-state investors to understand regional commercial real estate market.
15
Tran, Anh-Tuan, Thanh-Hai Le, and Huu May Nguyen. "Forecast of surface chloride concentration of concrete utilizing ensemble decision tree boosted." Journal of Science and Transport Technology 2, no. 1 (March 25, 2022): 44–56. http://dx.doi.org/10.58845/jstt.utt.2022.en.2.44-56.
Анотація:
This study proposes the application of Ensemble Decision Tree Boosted (EDT Boosted) model for forecasting the surface chloride concentration of marine concrete A database of 386 experimental results was collected from 17 different sources covering twelve variables was used to build and verify the predictive power of the EDT model. The input factors considered the changes in eleven variables, including the contents of cement, fly ash, blast furnace slag, silica fume, superplasticizer, water, fine aggregate, coarse aggregate, annual mean temperature, chloride concentration in seawater, and exposure time. The results indicate that EDT Boosted is a good predictor of as verified via good performance evaluation criteria, i.e., R2, RMSE, MAE, MAPE values were 0.84, 0.16, 0.17, and 17%, respectively. Partial dependence plot (PDP) was then developed to correlate the eleven input variables with the . PDP implied that the strongest factor affecting Cs was the amount of fine aggregate content, chloride concentration, exposure time, amount of cement, and water, which is useful for material engineers in the design of the grade.
16
Tran, Anh-Tuan, Thanh-Hai Le, and Huu May Nguyen. "Forecast of surface chloride concentration of concrete utilizing ensemble decision tree boosted." Journal of Science and Transport Technology 2, no. 1 (March 25, 2022): 44–56. http://dx.doi.org/10.58845/jstt.utt.2022.en.2.1.44-56.
Анотація:
This study proposes the application of Ensemble Decision Tree Boosted (EDT Boosted) model for forecasting the surface chloride concentration of marine concrete A database of 386 experimental results was collected from 17 different sources covering twelve variables was used to build and verify the predictive power of the EDT model. The input factors considered the changes in eleven variables, including the contents of cement, fly ash, blast furnace slag, silica fume, superplasticizer, water, fine aggregate, coarse aggregate, annual mean temperature, chloride concentration in seawater, and exposure time. The results indicate that EDT Boosted is a good predictor of as verified via good performance evaluation criteria, i.e., R2, RMSE, MAE, MAPE values were 0.84, 0.16, 0.17, and 17%, respectively. Partial dependence plot (PDP) was then developed to correlate the eleven input variables with the . PDP implied that the strongest factor affecting Cs was the amount of fine aggregate content, chloride concentration, exposure time, amount of cement, and water, which is useful for material engineers in the design of the grade.
17
Zhang, Yupeng, Lin Cheng, Aonan Pan, Chengyang Hu, and Kaiming Wu. "Phase Transformation Temperature Prediction in Steels via Machine Learning." Materials 17, no. 5 (February 29, 2024): 1117. http://dx.doi.org/10.3390/ma17051117.
Анотація:
The phase transformation temperature plays an important role in the design, production and heat treatment process of steels. In the present work, an improved version of the gradient-boosting method LightGBM has been utilized to study the influencing factors of the four phase transformation temperatures, namely Ac1, Ac3, the martensite transformation start (MS) temperature and the bainitic transformation start (BS) temperature. The effects of the alloying element were discussed in detail by comparing their influencing mechanisms on different phase transformation temperatures. The training accuracy was significantly improved by further introducing appropriate features related to atomic parameters. The melting temperature and coefficient of linear thermal expansion of the pure metals corresponding to the alloying elements, atomic Waber–Cromer pseudopotential radii and valence electron number were the top four among the eighteen atomic parameters used to improve the trained model performance. The training and prediction processes were analyzed using a partial dependence plot (PDP) and Shapley additive explanation (SHAP) methods to reveal the relationships between the features and phase transformation temperature.
18
Zhang, Shuai, Emmanuel John M. Carranza, Changliang Fu, Wenzhi Zhang, and Xiang Qin. "Interpretable Machine Learning for Geochemical Anomaly Delineation in the Yuanbo Nang District, Gansu Province, China." Minerals 14, no. 5 (May 10, 2024): 500. http://dx.doi.org/10.3390/min14050500.
Анотація:
Machine learning (ML) has shown its effectiveness in handling multi-geoinformation. Yet, the black-box nature of ML algorithms has restricted their widespread adoption in the domain of mineral prospectivity mapping (MPM). In this paper, methods for interpreting ML model predictions are introduced to aid ML-based MPM, with the goal of extracting richer insights from the ML modeling of an exploration geochemical dataset. The partial dependence plot (PDP) and accumulated local effect (ALE) plot, along with the SHAP value analysis, were utilized to demonstrate the application of random forest (RF) modeling within both regression and classification frameworks. Initially, the random forest regression (RFR) model established the relationship between the concentrations of Au and those of elements such as As, Sb, and Hg in the study area, and from this model, the most important geochemical elements and their quantitative relationships with Au were revealed by their contributions in the modeling through PDP and ALE analyses. Secondly, the RF classification modeling established the relationships of mineralization occurrences (i.e., known mineral deposits) with geochemical elements (i.e., Au, As, Sb, Hg, Cu, Pb, Zn, and Ag), as did RFR modeling. The most important geochemical elements for indicating regional Au mineralization and the trajectories of PDP and ALE reached a consensus that As and Sb contributed the most, both in the regression and classification modeling, with regard to Au mineralization. Finally, the SHAP values illustrated the behavior of the training samples (i.e., known mineral deposits) in RF modeling, and the resulting prospectivity map was evaluated using receiver operating characteristics.
19
Kim, Gil-jae, and Byoung-joo Kim. "Analysis of Factors Influencing Satisfaction on Kindergarten Information Disclosure Using Machine Learning." Korean Society for the Economics and Finance of Education 32, no. 3 (September 30, 2023): 187–214. http://dx.doi.org/10.46967/jefe.2023.32.3.187.
Анотація:
The purpose of this study is to identify the use of kindergarten notifications, which can be the realization of the information disclosure system and to predict overall satisfaction using statistical analysis methods and random forest algorithms. Based on the results of the annual kindergarten notification satisfaction survey conducted by the Korea Educational Information Service, differences in user response were analyzed, and random forest was used to identify factors that affect overall satisfaction prediction among machine learning algorithms. As a result of the t-test and one-way distribution variance analysis, the difference in use status according to gender, age, residential area, and type was statistically significant. As a result of random forest model learning, Accuracy 0.85 and F1 Score 0.84 were shown. Explanable artificial intelligence such as variable importance, SHAP plot, and partial dependence charts of the learned model was used to identify variables that affect the prediction of kindergarten information disclosure. It was confirmed that the usage status variable contributed more to the satisfaction prediction than the user's background variable, and based on the results, the direction of improvement of kindergarten information disclosure and kindergarten notification was derived.
20
Reyes-Urrutia, Andres, Juan Pablo Capossio, Cesar Venier, Erick Torres, Rosa Rodriguez, and Germán Mazza. "Artificial Neural Network Prediction of Minimum Fluidization Velocity for Mixtures of Biomass and Inert Solid Particles." Fluids 8, no. 4 (April 11, 2023): 128. http://dx.doi.org/10.3390/fluids8040128.
Анотація:
The fluidization of certain biomasses used in thermal processes, such as sawdust, is particularly difficult due to their irregular shapes, varied sizes, and low densities, causing high minimum fluidization velocities (Umf). The addition of an inert material causes its Umf to drop significantly. The determination of the Umf of the binary mixture is however hard to obtain. Generally, predictive correlations are based on a small number of specific experiments, and sphericity is seldom included. In the present work, three models, i.e., an empirical correlation and two artificial neural networks (ANN) models were used to predict the Umf of biomass-inert mixtures. An extensive bibliographical survey of more than 200 datasets was conducted with complete data about densities, particle diameters, sphericities, biomass fraction, and Umf. With the combined application of the partial dependence plot (PDP) and the ANN models, the average effect of sphericity on Umf was quantitatively determined (inverse relationship) together with the average impact of the biomass fraction on Umf (direct relationship). In comparison with the empirical correlations, the results showed that both ANN models can accurately predict the Umf of the presented binary mixtures with errors lower than 25%.
21
Lee, Do-Hyun, Sang-Hun Lee, Saem-Ee Woo, Min-Woong Jung, Do-yun Kim, and Tae-Young Heo. "Prediction of Complex Odor from Pig Barn Using Machine Learning and Identifying the Influence of Variables Using Explainable Artificial Intelligence." Applied Sciences 12, no. 24 (December 16, 2022): 12943. http://dx.doi.org/10.3390/app122412943.
Анотація:
Odor is a very serious problem worldwide. Thus, odor prediction research has been conducted consistently to help prevent odor. Odor substances that are complex odors are known, but complex odors and odor substances do not have a linear dependence. In addition, depending on the combination of odor substances, the causal relationships, such as synergy and antagonism, are different for complex odors. Research is needed to know this, but the situation is incomplete. Therefore, in this study, research was conducted through data-based research. The complex odor was predicted using various machine learning methods, and the effect of odor substances on the complex odor was verified using an explainable artificial intelligence method. In this study, according to the Malodor Prevention Act in Korea, complex odors are divided into two categories: acceptable and unacceptable. Analysis of variance and correlation analysis were used to determine the relationships between variables. Six machine learning methods (k-nearest neighbor, support vector classification, random forest, extremely randomized tree, eXtreme gradient boosting, and light gradient boosting machine) were used as predictive classification models, and the best predictive method was chosen using various evaluation metrics. As a result, the support vector machine that performed best in five out of six evaluation metrics was selected as the best model (f1-score = 0.7722, accuracy = 0.8101, sensitivity = 0.7372, specificity = 0.8656, positive predictive value = 0.8196, and negative predictive value = 0.8049). In addition, the partial dependence plot method from explainable artificial intelligence was used to understand the influence and interaction effects of odor substances.
22
Qiu, Haijun, Yao Xu, Bingzhe Tang, Lingling Su, Yijun Li, Dongdong Yang, and Mohib Ullah. "Interpretable Landslide Susceptibility Evaluation Based on Model Optimization." Land 13, no. 5 (May 8, 2024): 639. http://dx.doi.org/10.3390/land13050639.
Анотація:
Machine learning (ML) is increasingly utilized in Landslide Susceptibility Mapping (LSM), though challenges remain in interpreting the predictions of ML models. To reveal the response relationship between landslide susceptibility and evaluation factors, an interpretability model was constructed to analyze how the results of the ML model are realized. This study focuses on Zhenba County in Shaanxi Province, China, employing both Random Forest (RF) and Support Vector Machine (SVM) to develop LSM models optimized through Random Search (RS). To enhance interpretability, the study incorporates techniques such as Partial Dependence Plot (PDP), Local Interpretable Model-Agnostic Explanations (LIMEs), and Shapley Additive Explanations (SHAP). The RS-optimized RF model demonstrated superior performance, achieving an Area Under the Curve (AUC) of 0.965. The interpretability model identified the NDVI and distance from road as important factors influencing landslides occurrence. NDVI plays a positive role in the occurrence of landslides in this region, and the landslide-prone areas are within 500 m from the road. These analyses indicate the importance of improved hyperparameter selection in enhancing model accuracy and performance. The interpretability model provides valuable insights into LSM, facilitating a deeper understanding of landslide formation mechanisms and guiding the formulation of effective prevention and control strategies.
23
Zeng, Yelong, Li Jia, Min Jiang, Chaolei Zheng, Massimo Menenti, Ali Bennour, and Yunzhe Lv. "Hydrological Factor and Land Use/Land Cover Change Explain the Vegetation Browning in the Dosso Reserve, Niger." Remote Sensing 16, no. 10 (May 13, 2024): 1728. http://dx.doi.org/10.3390/rs16101728.
Анотація:
The West Sahel is facing significant threats to its vegetation and wildlife due to the land degradation and habitat fragmentation. It is crucial to assess the regional vegetation greenness dynamics in order to comprehensively evaluate the effectiveness of protection in the natural reserves. This study analyzes the vegetation greenness trends and the driving factors in the Dosso Partial Faunal Reserve in Niger and nearby unprotected regions—one of the most important habitats for endemic African fauna—using satellite time series data from 2001 to 2020. An overall vegetation browning trend was observed throughout the entire region with significant spatial variability. Vegetation browning dominated in the Dosso Reserve with 17.7% of the area showing a significant trend, while the area with significant greening was 6.8%. In a comparison, the nearby unprotected regions to the north and the east were found to be dominated by vegetation browning and greening, respectively. These results suggest that the vegetation protection practice was not fully effective throughout the Dosso Reserve. The dominant drivers were also diagnosed using the Random Forest model-based method and the Partial Dependence Plot tool, showing that water availability (expressed as soil moisture) and land use/land cover change were the most critical factors affecting vegetation greenness in the study region. Specifically, soil moisture stress and specific land management practices associated with logging, grazing, and land clearing appeared to dominate vegetation browning in the Dosso Reserve. In contrast, the vegetation greening in the central Dosso Reserve and the nearby unprotected region to the east was probably caused by the increase in shrubland/forest, which was related to the effective implementation of protection. These findings improve our understanding of how regional vegetation greenness dynamics respond to environmental changes in the Dosso Reserve and also highlight the need for more effective conservation planning and implementation to ensure sustainable socio-ecological development in the West Sahel.
24
Yu, Chenyan, Yao Li, Minyue Yin, Jingwen Gao, Liting Xi, Jiaxi Lin, Lu Liu, et al. "Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis." Journal of Personalized Medicine 12, no. 11 (November 19, 2022): 1930. http://dx.doi.org/10.3390/jpm12111930.
Анотація:
Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H2O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.
25
Passera, Roberto, Sofia Zompi, Jessica Gill, and Alessandro Busca. "Explainable Machine Learning (XAI) for Survival in Bone Marrow Transplantation Trials: A Technical Report." BioMedInformatics 3, no. 3 (September 1, 2023): 752–68. http://dx.doi.org/10.3390/biomedinformatics3030048.
Анотація:
Artificial intelligence is gaining interest among clinicians, but its results are difficult to be interpreted, especially when dealing with survival outcomes and censored observations. Explainable machine learning (XAI) has been recently extended to this context to improve explainability, interpretability and transparency for modeling results. A cohort of 231 patients undergoing an allogeneic bone marrow transplantation was analyzed by XAI for survival by two different uni- and multi-variate survival models, proportional hazard regression and random survival forest, having as the main outcome the overall survival (OS) and its main determinants, using the survex package for R. Both models’ performances were investigated using the integrated Brier score, the integrated Cumulative/Dynamic AUC and the concordance C-index. Global explanation for the whole cohort was performed using the time-dependent variable importance and the partial dependence survival plot. The local explanation for each single patient was obtained via the SurvSHAP(t) and SurvLIME plots and the ceteris paribus survival profile. The survex package common interface ensured a good feasibility of XAI for survival, and the advanced graphical options allowed us to easily explore, explain and compare OS results coming from the two survival models. Before the modeling results to be suitable for clinical use, understandability, clinical relevance and computational efficiency were the most important criteria ensured by this XAI for survival approach, in adherence to clinical XAI guidelines.
26
Liu, Chengcheng, Xuandong Wang, Weidong Cai, Yazhou He, and Hang Su. "Machine Learning Aided Prediction of Glass-Forming Ability of Metallic Glass." Processes 11, no. 9 (September 21, 2023): 2806. http://dx.doi.org/10.3390/pr11092806.
Анотація:
The prediction of the glass-forming ability (GFA) of metallic glasses (MGs) can accelerate the efficiency of their development. In this paper, a dataset was constructed using experimental data collected from the literature and books, and a machine learning-based predictive model was established to predict the GFA. Firstly, a classification model based on the size of the critical diameter (Dmax) was established to determine whether an alloy system could form a glass state, with an accuracy rating of 0.98. Then, regression models were established to predict the crystallization temperature (Tx), glass transition temperature (Tg), and liquidus temperature (Tl) of MGs. The R2 of the prediction model obtained in the test set was greater than 0.89, which showed that the model had good prediction accuracy. The key features used by the regression models were analyzed using variance, correlation, embedding, recursive, and exhaustive methods to select the most important features. Furthermore, to improve the interpretability of the prediction model, feature importance, partial dependence plot (PDP), and individual conditional expectation (ICE) methods were used for visualization analysis, demonstrating how features affect the target variables. Finally, taking Zr-Cu-Ni-Al system MGs as an example, a prediction model was established using a genetic algorithm to optimize the alloy composition for high GFA in the compositional space, achieving the optimal design of alloy composition.
27
Gaevskii, A., and D. Diomin. "INFLUENCE OF SOLAR PANELS TILT ANGLE AND GROUND COVER RATIO ON PV PLANT PERFORMANCE." Alternative Energy and Ecology (ISJAEE), no. 25-30 (December 7, 2018): 12–24. http://dx.doi.org/10.15518/isjaee.2018.25-30.012-024.
Анотація:
One of the main factors affecting the photovoltaic (PV) plant power is the self-shading from adjacent rows of solar panels. Due to the peculiarities of the electric connections of photovoltaic cells in PV modules and the presence of bypass diodes, the partial shading is capable of significantly decreasing the PV plant power at certain times of the day. The partial shading of solar panels effects in different ways on the energy production in cases of the vertical placement of PV modules in the panel’s frame (portrait mounting) and the horizontal placement of PV modules (landscape mounting). This work presents a novel analytical approach for determining of the inter-row shading effect on the large PV plant efficiency which is applicable for any seasonal period of PV operation. The initial data for calculations are the hourly generation of shaded and fully illuminated solar panels. On the base of these data, we have calculated the power factor that describes the dependence of the module's electrical power on the shading degree. The power factor is used to determine the amount of radiation entering the panel’s tilted surface during each day of the operation period. The long-term meteorological data for the main radiation components and one of the known anisotropic radiation model are necessary for these calculations. The main calculations result is the distribution maps for the average daily energy output which first proposed in our work. These maps have the form of contour graphs which build in the coordinates “the ground cover ratio – the tilt angle” as construction parameters. Using this maps one can find the optimal ratios of these parameters for two types of optimization problems: (1) ensure the maximum possible output under given installed PV power and (2) the determination of the most rational use of a land plot for PV plant, i.e. the obtaining of maximum PV production per unit of land area. The advantage of the analytical approach is that it allows scaling to large PV systems without increasing the computation time. As examples, the paper performs the optimization calculations based on the monitoring output data for the commercial PV plant located in Germany and on the experimental partial shading data in Odessa region.
28
Fohlmeister, Jürgen F. "Voltage gating by molecular subunits of Na+ and K+ ion channels: higher-dimensional cubic kinetics, rate constants, and temperature." Journal of Neurophysiology 113, no. 10 (June 2015): 3759–77. http://dx.doi.org/10.1152/jn.00551.2014.
Анотація:
The structural similarity between the primary molecules of voltage-gated Na and K channels (alpha subunits) and activation gating in the Hodgkin-Huxley model is brought into full agreement by increasing the model's sodium kinetics to fourth order (m3 → m4). Both structures then virtually imply activation gating by four independent subprocesses acting in parallel. The kinetics coalesce in four-dimensional (4D) cubic diagrams (16 states, 32 reversible transitions) that show the structure to be highly failure resistant against significant partial loss of gating function. Rate constants, as fitted in phase plot data of retinal ganglion cell excitation, reflect the molecular nature of the gating transitions. Additional dimensions (6D cubic diagrams) accommodate kinetically coupled sodium inactivation and gating processes associated with beta subunits. The gating transitions of coupled sodium inactivation appear to be thermodynamically irreversible; response to dielectric surface charges (capacitive displacement) provides a potential energy source for those transitions and yields highly energy-efficient excitation. A comparison of temperature responses of the squid giant axon (apparently Arrhenius) and mammalian channel gating yields kinetic Q10 = 2.2 for alpha unit gating, whose transitions are rate-limiting at mammalian temperatures; beta unit kinetic Q10 = 14 reproduces the observed non-Arrhenius deviation of mammalian gating at low temperatures; the Q10 of sodium inactivation gating matches the rate-limiting component of activation gating at all temperatures. The model kinetics reproduce the physiologically large frequency range for repetitive firing in ganglion cells and the physiologically observed strong temperature dependence of recovery from inactivation.
29
Sridhar, Srinivasan, Bradley Whitaker, Amy Mouat-Hunter, and Bernadette McCrory. "Predicting Length of Stay using machine learning for total joint replacements performed at a rural community hospital." PLOS ONE 17, no. 11 (November 10, 2022): e0277479. http://dx.doi.org/10.1371/journal.pone.0277479.
Анотація:
Background Predicting patient’s Length of Stay (LOS) before total joint replacement (TJR) surgery is vital for hospitals to optimally manage costs and resources. Many hospitals including in rural areas use publicly available models such as National Surgical Quality Improvement Program (NSQIP) calculator which, unfortunately, performs suboptimally when predicting LOS for TJR procedures. Objective The objective of this research was to develop a Machine Learning (ML) model to predict LOS for TJR procedures performed at a Perioperative Surgical Home implemented rural community hospital for better accuracy and interpretation than the NSQIP calculator. Methods A total of 158 TJR patients were collected and analyzed from a rural community hospital located in Montana. A random forest (RF) model was used to predict patient’s LOS. For interpretation, permuted feature importance and partial dependence plot methods were used to identify the important variables and their relationship with the LOS. Results The root mean square error for the RF model (0.7) was lower than the NSQIP calculator (1.21). The five most important variables for predicting LOS were BMI, Duke Activity Status-Index, diabetes, patient’s household income, and patient’s age. Conclusion This pilot study is the first of its kind to develop an ML model to predict LOS for TJR procedures that were performed at a small-scale rural community hospital. This pilot study contributes an approach for rural hospitals, making them more independent by developing their own predictions instead of relying on public models.
30
Kim, Hyun Woo, Dakota McCarty, and Minju Jeong. "Examining Commercial Crime Call Determinants in Alley Commercial Districts before and after COVID-19: A Machine Learning-Based SHAP Approach." Applied Sciences 13, no. 21 (October 26, 2023): 11714. http://dx.doi.org/10.3390/app132111714.
Анотація:
Although several previous studies have examined factors influencing crime at a specific point in time, limited research has assessed how factors influencing crime change in response to social disasters such as COVID-19. This study examines factors, along with their relative importance and trends over time, and their influence on 112 commercial crime reports (illegal street vendors, dining and dashing, minor quarrels, theft, drunkenness, assault, vagrancy and disturbing the peace) in Seoul’s alley commercial districts between 2019 and 2021. Variables that may affect the number of commercial crime reports are classified into four characteristics (socioeconomic, neighborhood, park/greenery and commercial district attributes), explored using machine learning regression-based modeling and analyzed through the use of Shapley Additive exPlanations to determine the importance of each factor on crime reports. The Partial Dependence Plot is used to understand linear/non-linear relationships between key independent variables and crime reports. Among several machine learning models, the Extra Trees Regressor, which has the highest performance, is selected for the analysis. The results show a mixture of linear and non-linear relationships with the increasing crime rates, finding that store density, dawn sales ratio, the number of gathering facilities, perceived urban decline score, green view index and land appraisal value may play a crucial role in the number of commercial crimes reported, regardless of social trends. The findings of this study may be used as a basis for building a safe commercial district that can respond resiliently to social disasters.
31
Nagy, Marcell. "Lemorzsolódás előrejelzése személyre szabott értelmezhető gépi tanulási módszerek segítségével." Scientia et Securitas 3, no. 3 (April 6, 2023): 270–81. http://dx.doi.org/10.1556/112.2022.00107.
Анотація:
Összefoglalás. A hallgatói lemorzsolódás az egyik legégetőbb probléma a felsőoktatásban. Ebben a munkában a lemorzsolódás előrejelzésén keresztül bemutatjuk, hogyan tudják segíteni a felsőoktatás résztvevőit a magyarázható mesterséges intelligencia (XAI) eszközök, mint például a permutációs fontosság, a parciális függőségi ábra és a SHAP. Végül pedig kitérünk a kutatás gyakorlati hasznosulásának lehetőségeire, például, hogy az egyéni előrejelzések magyarázata hogyan teszi lehetővé a személyre szabott beavatkozást. Az elemzések során azt találtuk, hogy a középiskolai tanulmányi átlag bír a legnagyobb prediktív erővel a végzés tényére vonatkozóan. Továbbá annak ellenére, hogy egy műszaki egyetem adatait elemeztük, azt találtuk, hogy a humán tárgyaknak is nagy inkrementális prediktív erejük van a végzés tényére vonatkozóan a reál tárgyakhoz képest. Summary. Delayed completion and student drop-out are some of the most critical problems in higher education, especially regarding STEM programs. A high drop-out rate induces both individual and economic loss, hence a detailed investigation of the main reasons for dropping out is warranted. Recently, there has been a lot of interest in the use of machine learning methods for the early detection of students at risk of dropping out. However, there has not been much debate on the use of interpretable machine learning (IML) and explainable artificial intelligence (XAI) technologies for dropout prediction. In this paper, we show how IML and XAI techniques can assist educational stakeholders in dropout prediction using data from the Budapest University of Technology and Economics. We demonstrate that complex black-box machine learning algorithms, for example CatBoost, are able to effectively detect at-risk student using only pre-enrollment achievement measures, but they lack interpretability. We demonstrate how the predictions can be explained both globally and locally using IML methods including permutation importance (PI), partial dependence plot (PDP), LIME, and SHAP values. Using global interpretations, we have found that the factor that has the greatest impact on academic performance is the high school grade point average, which measures general knowledge by taking into account grades in history, mathematics, Hungarian language and literature, a foreign language and a science subject. However, we also found that both mathematics and the subject of choice are among the most important variables, which suggests that program-specific knowledge is not negligible and complements general knowledge. We discovered that students are more likely to drop out if they do not start their university studies immediately after leaving secondary school. Using a partial dependence plot, we showed that humanities also have incremental predictive power, despite the fact that this analysis is based on data from a technical university. Finally, we also discuss the potential practical applications of our work, such as how the explanation of individual predictions allows for personalized interventions, for example by offering appropriate remedial courses and tutoring sessions. Our approach is unique in that we not only estimate the probability of dropping out, but also interpret the model and provide explanations for each prediction. As a result, this framework can be used in several fields. By predicting which majors they could be most successful in based on high school performance indicators, it might, for instance, assist high school students in selecting the appropriate programs at universities and hence this way it could be used for career assistance. Through the explanations of local predictions, the framework provided can also assist students in identifying the skills they need to develop to succeed in their university studies.
32
Wang, Xiaoxiao, Lan Wang, Mingsheng Shang, Lirong Song, and Kun Shan. "Revealing Physiochemical Factors and Zooplankton Influencing Microcystis Bloom Toxicity in a Large-Shallow Lake Using Bayesian Machine Learning." Toxins 14, no. 8 (August 2, 2022): 530. http://dx.doi.org/10.3390/toxins14080530.
Анотація:
Toxic cyanobacterial blooms have become a severe global hazard to human and environmental health. Most studies have focused on the relationships between cyanobacterial composition and cyanotoxins production. Yet, little is known about the environmental conditions influencing the hazard of cyanotoxins. Here, we analysed a unique 22 sites dataset comprising monthly observations of water quality, cyanobacterial genera, zooplankton assemblages, and microcystins (MCs) quota and concentrations in a large-shallow lake. Missing values of MCs were imputed using a non-negative latent factor (NLF) analysis, and the results achieved a promising accuracy. Furthermore, we used the Bayesian additive regression tree (BART) to quantify how Microcystis bloom toxicity responds to relevant physicochemical characteristics and zooplankton assemblages. As expected, the BART model achieved better performance in Microcystis biomass and MCs concentration predictions than some comparative models, including random forest and multiple linear regression. The importance analysis via BART illustrated that the shade index was overall the best predictor of MCs concentrations, implying the predominant effects of light limitations on the MCs content of Microcystis. Variables of greatest significance to the toxicity of Microcystis also included pH and dissolved inorganic nitrogen. However, total phosphorus was found to be a strong predictor of the biomass of total Microcystis and toxic M. aeruginosa. Together with the partial dependence plot, results revealed the positive correlations between protozoa and Microcystis biomass. In contrast, copepods biomass may regulate the MC quota and concentrations. Overall, our observations arouse universal demands for machine-learning strategies to represent nonlinear relationships between harmful algal blooms and environmental covariates.
33
Huang, Di, Zhennan Li, Kuo Wang, Haixin Zhou, Xiaojie Zhao, Xinyu Peng, Rui Zhang, Jipeng Wu, Jiaojiao Liang, and Ling Zhao. "Probing the Effect of Photovoltaic Material on Voc in Ternary Polymer Solar Cells with Non-Fullerene Acceptors by Machine Learning." Polymers 15, no. 13 (July 5, 2023): 2954. http://dx.doi.org/10.3390/polym15132954.
Анотація:
The power conversion efficiency (PCE) of ternary polymer solar cells (PSCs) with non-fullerene has a phenomenal increase in recent years. However, improving the open circuit voltage (Voc) of ternary PSCs with non-fullerene still remains a challenge. Therefore, in this work, machine learning (ML) algorithms are employed, including eXtreme gradient boosting, K-nearest neighbor and random forest, to quantitatively analyze the impact mechanism of Voc in ternary PSCs with the double acceptors from the two aspects of photovoltaic materials. In one aspect of photovoltaic materials, the doping concentration has the greatest impact on Voc in ternary PSCs. Furthermore, the addition of the third component affects the energy offset between the donor and acceptor for increasing Voc in ternary PSCs. More importantly, to obtain the maximum Voc in ternary PSCs with the double acceptors, the HOMO and LUMO energy levels of the third component should be around (−5.7 ± 0.1) eV and (−3.6 ± 0.1) eV, respectively. In the other aspect of molecular descriptors and molecular fingerprints in the third component of ternary PSCs with the double acceptors, the hydrogen bond strength and aromatic ring structure of the third component have high impact on the Voc of ternary PSCs. In partial dependence plot, it is clear that when the number of methyl groups is four and the number of carbonyl groups is two in the third component of acceptor, the Voc of ternary PSCs with the double acceptors can be maximized. All of these findings provide valuable insights into the development of materials with high Voc in ternary PSCs for saving time and cost.
34
Ge, Yuankai, Longlong Zhao, Jinsong Chen, Xiaoli Li, Hongzhong Li, Zhengxin Wang, and Yanni Ren. "Study on Soil Erosion Driving Forces by Using (R)USLE Framework and Machine Learning: A Case Study in Southwest China." Land 12, no. 3 (March 8, 2023): 639. http://dx.doi.org/10.3390/land12030639.
Анотація:
Soil erosion often leads to land degradation, agricultural production reduction, and environmental deterioration, which seriously restricts the sustainable development of regions. Clarifying the driving factors of soil erosion is the premise of preventing soil erosion. Given the lack of current research on the driving factors/force changes of soil erosion in different regions or under different erosion intensity grades, this paper pioneered to use machine learning methods to address this problem. Firstly, the widely used (Revised) Universal Soil Loss Equation ((R)USLE) framework was applied to simulate the spatial distribution of soil erosion. Then, the K-fold algorithm was used to evaluate the accuracy and stability of five machine learning algorithms for fitting soil erosion. The random forest (RF) method performed best, with average accuracy reaching 86.35%. Then, the Permutation Importance (PI) and the Partial Dependence Plot (PDP) methods based on RF were introduced to quantitatively analyze the main driving factors under different geological conditions and the driving force changes of each factor under different erosion intensity grades, respectively. Results showed that the main drivers of soil erosion in Chongqing and Guizhou were cover management factors (PI: 0.4672, 0.4788), while that in Sichuan was slope length and slope factor (PI: 0.6165). Under different erosion intensity grades, the driving force of each factor shows nonlinear and complex inhibitory or promoting effects with factor value changing. These findings can provide scientific guidance for the refined management of soil erosion, which is significant for halting or reversing land degradation and achieving sustainable use of land resources.
35
Fedyk, Tamara. "Memoir structures of the narrative in the play Tetyana Ivashenko «The Mystery of Being»." Vìsnik Marìupolʹsʹkogo deržavnogo unìversitetu. Serìâ: Fìlologìâ 15, no. 26-27 (2022): 194–201. http://dx.doi.org/10.34079/2226-3055-2022-15-26-27-194-201.
Анотація:
The article analyzes the peculiarities of the use of narrative structures of memory in T. Ivashchenko's play «The Secret of Being». The relevance of the study is determined by the popularity of the genre of artistic biography, which is drawn from the desire to deeply rethink the lives of key cultural and historical figures and the availability of a wide range of tools for this literary representation. Also, the play «The Secret of Being» is interesting for researchers of biographical drama due to the peculiar construction of the plot. During the research, first and foremost, the content of the basic terminology was clarified - the concepts of «narrative», «memories-narrative», «dependency», «addictive behavior». Secondly, the chronotopic structures of the narrative were distinguished. Then, the connecting elements of the chronotopic structures – memories-narratives were determined, and the features of memories were analyzed – narratives as which containing markers of addiction. In T. Ivashchenko's play «The Secret of Being» two chronotopic structures are closely intertwined: the first – Olha Franko recalls her youth at the end of her life; the second – the actual memories of the woman from the moment she met Ivan Franko and their married life in general. The difference in time and space, which is quite significant in chronotopic structures, is overcoming not only due to the presence of memories-narratives but also due to the inherent meaning - addiction. Most of the immanent signs of addiction – compulsive behavior, anxiety, and partial creation of an alternative reality – are realized in the text of the play at the lexical and stylistic levels. A specific tool for manifesting the other two – the loss of the sense of reality and the creation of an alternative reality – is the reception of hallucinations and delusions. Thus, interpersonal dependence pervades the memories-narratives and acts as the unifying element, thanks to which the play is perceived as a complete work. Taking into account the results of the research, it is worth extending the proven methodology of analysis to other biographical plays, intending to identify a number of possible meanings that can serve as a connecting element.
36
Xia, Yu, Ta Xu, Ming-Xia Wei, Zhen-Ke Wei, and Lian-Jie Tang. "Predicting Chain’s Manufacturing SME Credit Risk in Supply Chain Finance Based on Machine Learning Methods." Sustainability 15, no. 2 (January 6, 2023): 1087. http://dx.doi.org/10.3390/su15021087.
Анотація:
Supply chain finance is an effective way to solve the financial problems of small and medium-sized manufacturing enterprises, and the assessment of credit risk is one of the key issues in supply chain financing. However, traditional credit risk assessment models cannot truly reflect the credit status of financing companies. In recent years, scholars working in this field have proposed using machine learning methods to predict the credit risk of supply chain enterprises, achieving good results. Nonetheless, there is no consensus on which approach is the most suitable for manufacturing companies. This study took small and medium-sized manufacturing enterprises as the research object, selected risk evaluation indicators according to the characteristics of the small and medium-sized manufacturing enterprises, and built a credit risk evaluation system. On this basis, we selected SMEs on China’s stock market from 2015 to 2020 as the sample data and evaluated corporate credit risk based on four commonly used machine learning algorithms. Then, combined with the evaluation results, a partial dependence plot method was used to visually analyze the important indicators. The results showed that a credit risk evaluation system for supply chain finance for manufacturing SMEs could be composed of the profile of the financing companies, the asset status of the financing companies, the profile of the core companies, and the operation of supply chains. The use of a random forest algorithm made it possible to more accurately assess the credit risk of manufacturing supply chain finance. Since the impacts of different indicators on the evaluation results were quite different, supply chain enterprises and financial service institutions should formulate corresponding strategies according to specific situations.
37
Kim, Ki Hong, Jeong Ho Park, Young Sun Ro, Ki Jeong Hong, Kyoung Jun Song, and Sang Do Shin. "Emergency department routine data and the diagnosis of acute ischemic heart disease in patients with atypical chest pain." PLOS ONE 15, no. 11 (November 5, 2020): e0241920. http://dx.doi.org/10.1371/journal.pone.0241920.
Анотація:
Background Due to an aging population and the increasing proportion of patients with various comorbidities, the number of patients with acute ischemic heart disease (AIHD) who present to the emergency department (ED) with atypical chest pain is increasing. The aim of this study was to develop and validate a prediction model for AIHD in patients with atypical chest pain. Methods and results A chest pain workup registry, ED administrative database, and clinical data warehouse database were analyzed and integrated by using nonidentifiable key factors to create a comprehensive clinical dataset in a single academic ED from 2014 to 2018. Demographic findings, vital signs, and routine laboratory test results were assessed for their ability to predict AIHD. An extreme gradient boosting (XGB) model was developed and evaluated, and its performance was compared to that of a single-variable model and logistic regression model. The area under the receiver operating characteristic curve (AUROC) was calculated to assess discrimination. A calibration plot and partial dependence plots were also used in the analyses. Overall, 4,978 patients were analyzed. Of the 3,833 patients in the training cohort, 453 (11.8%) had AIHD; of the 1,145 patients in the validation cohort, 166 (14.5%) had AIHD. XGB, troponin (single-variable), and logistic regression models showed similar discrimination power (AUROC [95% confidence interval]: XGB model, 0.75 [0.71–0.79]; troponin model, 0.73 [0.69–0.77]; logistic regression model, 0.73 [0.70–0.79]). Most patients were classified as non-AIHD; calibration was good in patients with a low predicted probability of AIHD in all prediction models. Unlike in the logistic regression model, a nonlinear relationship-like threshold and U-shaped relationship between variables and the probability of AIHD were revealed in the XGB model. Conclusion We developed and validated an AIHD prediction model for patients with atypical chest pain by using an XGB model.
38
Shi, Guifang, and Limei Luo. "Prediction and Impact Analysis of Passenger Flow in Urban Rail Transit in the Postpandemic Era." Journal of Advanced Transportation 2023 (August 2, 2023): 1–12. http://dx.doi.org/10.1155/2023/3448864.
Анотація:
In the postpandemic era, exploring the relationship between the daily new COVID-19 cases and passenger flow in urban rail transit can help effectively predict the impact of future pandemic situations on rail transit. In this study, based on a gated recurrent unit (GRU) neural network model, the daily passenger flow in urban rail transit in the postpandemic era was predicted, and the results were compared with those obtained using the long short-term memory (LSTM) neural network and other conventional time series analysis models such as SARIMA (seasonal autoregressive integrated moving average). Based on the trained GRU model, a partial dependence plot (PDP) was adopted to explore the quantitative relationship between the daily passenger flow and the daily new cases or weather attribute. The results showed that (1) the prediction accuracy of the GRU neural network model was 95.25%, which was the highest among the prediction models studied, indicating that the GRU could achieve the best performance. (2) The GRU model did not fluctuate significantly in the initial training stage, and its convergence rate was higher than that of the LSTM. (3) The number of daily new cases was negatively correlated with the daily passenger flow. For every new case on the previous day, the daily passenger flow fell by an average of 54,600 person-times. (4) Compared with no rain condition, the daily passenger flow decreased by 207,600 person-times on an average on rainy days. In summary, the neural network could achieve accurate prediction, while the PDP could compensate for the “black box” disadvantage of nonparametric models, owing to which the quantitative relationship between the number of new cases and daily passenger flow could be successfully explored. Our study can serve as a basis for demand prediction, operational organization, and policy implementation related to urban rail transit.
39
Choi, Jiyoun. "Exploring influential factors on elementary and middle school students’ reading practice using random forests." Korean Association For Learner-Centered Curriculum And Instruction 24, no. 8 (April 30, 2024): 239–50. http://dx.doi.org/10.22251/jlcci.2024.24.8.239.
Анотація:
Objectives The purposes of this study factors affecting elementary and middle school students’ reading practice were explored using the random forest technique. Methods For this purpose, data from the 13th year (sixth grade of elementary school) and the 14th year (first year of middle school) of the Korean Children's Panel were used. Using reading practice as a response variable and 111 explanatory variables from household, parent, child, and school/private education surveys, factors affecting their reading practice were explored based on the importance index, and a partial dependence plot (PDP) was used. We used this to understand the relationship of influence. Results As a result of examining the top 10 Mean Decrease Accuracy (MDA) predicting reading performance, in the case of 6th grade elementary school students, the results were achievement pressure, learning activities, teacher relationship, strict rules and directive atmosphere, overall happiness, academic stress, peer relationships, and school rules. , physical self-image, and self-esteem appeared in that order. In the case of first-year middle school students, the order was learning activities, achievement pressure, school rules, peer relationships, overall happiness, academic stress, strict rules and directive atmosphere, teacher relationship, physical self-image, and teacher support. Conclusions Factors that affect elementary and middle school students' reading practice are generally more influenced by the school environment than their parents, and the fact that parents' achievement pressure, school adaptation, and strict rules and directive atmosphere are predicted to affect reading practice. It can be seen that coercion has an effect to some extent. As for other variables, there was a difference in what was predicted by ‘self-esteem’ in the 6th grade of elementary school and ‘teacher’s support’ in the 1st grade of middle school.
40
Greenwell, Brandon,M. "pdp: An R Package for Constructing Partial Dependence Plots." R Journal 9, no. 1 (2017): 421. http://dx.doi.org/10.32614/rj-2017-016.
41
Johnson, Phillip, Anna Trybala, and Victor Starov. "Kinetics of Spreading over Porous Substrates." Colloids and Interfaces 3, no. 1 (March 15, 2019): 38. http://dx.doi.org/10.3390/colloids3010038.
Анотація:
The spreading of small liquid drops over thin and thick porous layers (dry or saturated with the same liquid) is discussed in the case of both complete wetting (silicone oils of different viscosities over nitrocellulose membranes and blood over a filter paper) and partial wetting (aqueous SDS (Sodium dodecyl sulfate) solutions of different concentrations and blood over partially wetted substrates). Filter paper and nitrocellulose membranes of different porosity and different average pore size were used as a model of thin porous layers, sponges, glass and metal filters were used as a model of thick porous substrates. Spreading of both Newtonian and non-Newtonian liquid are considered below. In the case of complete wetting, two spreading regimes were found (i) the fast spreading regime, when imbibition is not important and (ii) the second slow regime when imbibition dominates. As a result of these two competing processes, the radius of the drop goes through a maximum value over time. A system of two differential equations was derived in the case of complete wetting for both Newtonian and non-Newtonian liquids to describe the evolution with time of radii of both the drop base and the wetted region inside the porous layer. The deduced system of differential equations does not include any fitting parameter. Experiments were carried out by the spreading of silicone oil drops over various dry microfiltration membranes (permeable in both normal and tangential directions) and blood over dry filter paper. The time evolution of the radii of both the drop base and the wetted region inside the porous layer were monitored. All experimental data fell on two universal curves if appropriate scales are used with a plot of the dimensionless radii of the drop base and of the wetted region inside the porous layer on dimensionless time. The predicted theoretical relationships are two universal curves accounting quite satisfactorily for the experimental data. According to the theory prediction, (i) the dynamic contact angle dependence on the same dimensionless time as before should be a universal function and (ii) the dynamic contact angle should change rapidly over an initial short stage of spreading and should remain a constant value over the duration of the rest of the spreading process. The constancy of the contact angle on this stage has nothing to do with hysteresis of the contact angle: there is no hysteresis in the system under investigation in the case of complete wetting. These conclusions again are in good agreement with experimental observations in the case of complete wetting for both Newtonian and non-Newtonian liquids. Addition of surfactant to aqueous solutions, as expected, improve spreading over porous substrates and, in some cases, results in switching from partial to complete wetting. It was shown that for the spreading of surfactant solutions on thick porous substrates there is a minimum contact angle after which the droplet rapidly absorbs into the substrate. Unfortunately, a theory of spreading/imbibition over thick porous substrates is still to be developed. However, it was shown that the dimensionless time dependences of both contact angle and spreading radius of the droplet on thick porous material fall on to a universal curve in the case of complete wetting.
42
Spinolo, Giorgio, Umberto Anselmi-Tamburini, and Paolo Ghigna. "An Exact and Simple Approach to log-log Plots for Defect and Ionic Equilibria." Zeitschrift für Naturforschung A 52, no. 8-9 (September 1, 1997): 629–36. http://dx.doi.org/10.1515/zna-1997-8-914.
Анотація:
Abstract An alternative approach to log-log plots for defect equilibria in the solid state and ionic equilibria in solution is presented. The method is based on the strictly monotone character of the functional dependence of an externally controlled thermodynamic variable (e.g. the oxygen partial pressure P(O2) for the defect equilibria in a simple oxide, or a total concentration for the ionic equilibria in solution) on a chemically relevant compositional variable (such as the electron concentration n for defect equilibria, or [H3O+] or a free ligand concentration for solution equilibria). This functional dependency can be safely inverted. The concentration of all species and the externally controlled thermodynamic variable can be calculated as a function of the chemically relevant compositional variable. The appropriate plots are then obtained using naively a spreadsheet program. This method gives exact results in many more cases than the traditional approach.
43
Zhang, Weichun, Yunyi Zhang, Xin Zhang, Wei Wu, and Hongbin Liu. "The Spatiotemporal Variability of Soil Available Phosphorus and Potassium in Karst Region: The Crucial Role of Socio-Geographical Factors." Land 13, no. 6 (June 18, 2024): 882. http://dx.doi.org/10.3390/land13060882.
Анотація:
The contents of soil available phosphorus (AVP) and potassium (AVK) in karstic mountainous agricultural areas have changed rapidly in recent decades. This temporal variation displays strong spatial heterogeneity due to these areas’ complex topography and anthropogenic activities. Socio-geographical factors can reflect the changes in the natural environment caused by human beings, and our objective is to enhance understanding of their role in explaining the changes of AVP and AVK. In a typical karst region (611.5 km2) with uniform soil parent material and low climatic variability, 255 topsoil samples (138 in 2012 and 117 in 2021) were collected to quantify the temporal AVP and AVK changes. Random forest (RF) and partial dependence plot analyses were conducted to investigate the responses of these changes to socio-geographical factors (distance from the nearest town center [DFT] and village density [VD]), topography, biology, and landscape pattern indexes. The mean values of AVP (48.25 mg kg−1) and AVK (357.67 mg kg−1) in 2021 were significantly (p < 0.01) higher than those in 2012 (28.84 mg kg−1 and 131.67 mg kg−1, respectively). Semi-variance analysis showed strong spatial autocorrelation for AVP and AVK, ranging from 7.29% to 10.95% and 13.31% to 10.33% from 2012 to 2021, respectively. Adding socio-geographical factors can greatly improve the explanatory power of RF modeling for AVP and AVK changes by 19% and 27%, respectively. DFT and VD emerged as the two most important variables affecting these changes, followed by elevation. These three variables all demonstrated clear nonlinear threshold effects on AVP and AVK changes. A strong accumulation of AVP and AVK was observed at DFT < 5 km and VD > 20. The AVP changes increased dramatically when the elevation ranged between 1298 m and 1390 m, while the AVK changes decreased rapidly when the elevation ranged between 1350 m and 1466 m. The interaction effects of DFT and VD with elevation on these changes were also demonstrated. Overall, this study examined the important role of socio-geographical factors and their nonlinear threshold and interaction effects on AVP and AVK changes. The findings help unravel the complex causes of these changes and thus contribute to the design of optimal soil phosphorus and potassium management strategies.
44
Shyr, David C., Bing Melody Zhang, Robertson Parkman, and Simon E. Brewer. "Machine Learning Methods to Better Predict Post-Hematopoietic Stem Cell Transplant (HSCT) Leukemic Relapse in Pediatric Patients with Acute Lymphoblastic Leukemia: Random Forest (RF) Classification Featuring Serial Post-Transplant Lineage-Specific Chimerism." Blood 136, Supplement 1 (November 5, 2020): 6–7. http://dx.doi.org/10.1182/blood-2020-139104.
Анотація:
The ability to accurately predict leukemic relapse post-HSCT would improve outcomes by allowing pre-emptive therapeutic strategies. Recent studies have identified post-transplant T- and CD34 cell chimerism as predictors of relapse in patients, who had undergone HSCT for hematologic malignancies (Preuner et al, 2016; Lee et al, 2015). However, these studies assess relapse risk looking at only a single threshold of chimerism using standard regression analysis, which permits only limited consideration of other patient variables. As the result, the findings of these analysis are frequently not applicable to patients generally. Machine learning methods offer the possibility to capture nonlinear relationships and simultaneous interactions between multiple variables, thus better recapitulate the dynamics and nuances of the relapse process in different patients. We use machine learning methods, specifically random forest classification (RF), to build a predictive model of post-transplant relapse and to analyze the data from a cohort of 46 pediatric patients, who received HSCT for acute lymphoblastic leukemia (ALL) and had serial lineage-specific chimerism testing post-transplant. Our model achieved 58 % sensitivity and 98% specificity at predicting relapses in cross validation compared to a baseline model (24% sensitivity, 76% specificity). Consistent with previous reports, our model implicates both peripheral blood (PB) donor CD34 and CD3 chimerism as important variables for relapse. More importantly, the RF showed how different variables interacted with each other, providing additional insights into how to best interpret post-transplant chimerism results. To our knowledge, this is the first study featuring RF machine learning methods in the clinical setting of relapse after HSCT. We use a dataset of patients with ALL undergoing HSCT at Lucile Packard Children's Hospital from 2012 to 2018. Variables collected are summarized in Table 1. The analytical sensitivity of STR-based chimerism testing is 1%. Chimerism results on the same day of relapse were excluded from the analysis. The RF model is based on a set of 500 individual decision trees, each based on a bootstrapped sample of the patient data. A 5-fold cross-validation was used to test predictive skill, with 20% of patients excluded from each fold. We compared results with a Monte Carlo baseline model in which relapse status was repeatedly assigned randomly to each patient with a probability based on the prevalence of relapse in our cohort. Patients, transplantation, and relapse characteristics are summarized in Table 2. Chimerism data are summarized in Table 3. The cross-validation results show a robust predictive skill of relapse within 2 years post-transplant. Our RF achieved 58% sensitivity and 98% specificity, greatly improving the predictive values from the base model (Table 4). Variable importance, the ability of a variable to decrease the error of the prediction model, was calculated for all variables used in our RF (Figure 1). Our analysis shows that the age at the time of transplant has the highest importance, followed by PB donor CD34 chimerism. Bone marrow chimerism generally has lower importance suggesting PB monitoring only is adequate in the clinical setting. We showcase the relationships of 1) age at transplant, 2) donor PB CD34, and 3) donor PB CD3 chimerism to the odds of relapse using a partial dependence plot. Younger patients relapse less often. Donor PB CD34 chimerism exhibits a threshold effect, in which the odds of relapse dramatically decreases when it is above 95% while donor PB CD3 chimerism has a more gradual linear profile (Figure 2). 2D dependence plot of donor PB CD34 and PB CD3 chimerism shows the interaction of the two variables (Figure 3) as continuous variables; relapse risk remaining low with even if donor PB CD3 chimerism is as low as 50% as long as donor PB CD34 chimerism is > 95%. Our study shows that machine learning methods such as RF can be very useful at making accurate predictive model of post-HSCT complications that incorporates multiple variables, allowing for more granular differentiation between different patients. Such analyses can enable more effective deployment of risk-adapted, personalized treatment. By building hundreds of independent decision trees, the RF is also able provide useful insights to the interaction between different variables in a clinically relevant manner. Disclosures No relevant conflicts of interest to declare.
45
Zhao, Xiaohua, Haiyi Yang, Ying Yao, Hang Qi, Miao Guo, and Yuelong Su. "Factors affecting traffic risks on bridge sections of freeways based on partial dependence plots." Physica A: Statistical Mechanics and its Applications 598 (July 2022): 127343. http://dx.doi.org/10.1016/j.physa.2022.127343.
46
Shi, Haoze, Naisen Yang, Xin Yang, and Hong Tang. "Clarifying Relationship between PM2.5 Concentrations and Spatiotemporal Predictors Using Multi-Way Partial Dependence Plots." Remote Sensing 15, no. 2 (January 6, 2023): 358. http://dx.doi.org/10.3390/rs15020358.
Анотація:
Atmospheric fine particles (PM2.5) have been found to be harmful to the environment and human health. Recently, remote sensing technology and machine learning models have been used to monitor PM2.5 concentrations. Partial dependence plots (PDP) were used to explore the meteorology mechanisms between predictor variables and PM2.5 concentration in the “black box” models. However, there are two key shortcomings in the original PDP. (1) it calculates the marginal effect of feature(s) on the predicted outcome of a machine learning model, therefore some local effects might be hidden. (2) it requires that the feature(s) for which the partial dependence is computed are not correlated with other features, otherwise the estimated feature effect has a great bias. In this study, the original PDP’s shortcomings were analyzed. Results show the contradictory correlation between the temperature and the PM2.5 concentration that can be given by the original PDP. Furthermore, the spatiotemporal heterogeneity of PM2.5-AOD relationship cannot be displayed well by the original PDP. The drawbacks of the original PDP make it unsuitable for exploring large-area feature effects. To resolve the above issue, multi-way PDP is recommended, which can characterize how the PM2.5 concentrations changed with the temporal and spatial variations of major meteorological factors in China.
47
Baidada, Chafik, Hamid Hrimech, Mustapha Aatila, Mohamed Lachgar, and Younes Ommane. "Machine learning for real-time prediction of complications induced by flexible uretero-renoscopy with laser lithotripsy." International Journal of Electrical and Computer Engineering (IJECE) 14, no. 1 (February 1, 2024): 971. http://dx.doi.org/10.11591/ijece.v14i1.pp971-982.
Анотація:
It is not always easy to predict the outcome of a surgery. Peculiarly, when talking about the risks associated to a given intervention or the possible complications that it may bring about. Thus, predicting those potential complications that may arise during or after a surgery will help minimize risks and prevent failures to the greatest extent possible. Therefore, the objectif of this article is to propose an intelligent system based on machine learning, allowing predicting the complications related to a flexible uretero-renoscopy with laser lithotripsy for the treatment of kidney stones. The proposed method achieved accuracy with 100% for training and, 94.33% for testing in hard voting, 100% for testing and 95.38% for training in soft voting, with only ten optimal features. Additionally, we were able to evaluted the machine learning model by examining the most significant features using the shpley additive explanations (SHAP) feature importance plot, dependency plot, summary plot, and partial dependency plots.
48
Szepannaek, Gero, and Karsten Lübke. "How much do we see? On the explainability of partial dependence plots for credit risk scoring." Argumenta Oeconomica 2023, no. 2 (2023): 137–50. http://dx.doi.org/10.15611/aoe.2023.1.07.
Анотація:
Risk prediction models in credit scoring have to fulfil regulatory requirements, one of which consists in the interpretability of the model. Unfortunately, many popular modern machine learning algorithms result in models that do not satisfy this business need, whereas the research activities in the field of explainable machine learning have strongly increased in recent years. Partial dependence plots denote one of the most popular methods for model-agnostic interpretation of a feature’s effect on the model outcome, but in practice they are usually applied without answering the question of how much can actually be seen in such plots. For this purpose, in this paper a methodology is presented in order to analyse to what extent arbitrary machine learning models are explainable by partial dependence plots. The proposed framework provides both a visualisation, as well as a measure to quantify the explainability of a model on an understandable scale. A corrected version of the German credit data, one of the most popular data sets of this application domain, is used to demonstrate the proposed methodology.
49
Johnson, Paul M., William Barbour, Janey V. Camp, and Hiba Baroud. "Using machine learning to examine freight network spatial vulnerabilities to disasters: A new take on partial dependence plots." Transportation Research Interdisciplinary Perspectives 14 (June 2022): 100617. http://dx.doi.org/10.1016/j.trip.2022.100617.
50
Begum, Zareena, P. B. Sandhya Sri, D. B. Karuna Kumar, K. Rayapa Reddy, and C. Rambabu. "Partial molar volumes partial molar adiabatic compressibilities and molar Gibbs energies of anisaldehyde with some alkoxyethanols — Insights through plots showing compositional, volumetric and temperature dependence." Journal of Molecular Liquids 184 (August 2013): 33–42. http://dx.doi.org/10.1016/j.molliq.2013.04.007.