Добірка наукової літератури з теми "Partial Dependence Plot"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел 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.
Статті в журналах з теми "Partial Dependence Plot":
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.
Дисертації з теми "Partial Dependence Plot":
1
Danesh, Alaghehband Tina Sadat. "Vers une conception robuste en ingénierie des procédés. Utilisation de modèles agnostiques de l'interprétabilité en apprentissage automatique." Electronic Thesis or Diss., Toulouse, INPT, 2023. http://www.theses.fr/2023INPT0138.
Анотація:
La conception de processus robustes revêt une importance capitale dans divers secteurs, tels que le génie chimique et le génie des procédés. La nature de la robustesse consiste à s'assurer qu'un processus peut constamment produire les résultats souhaités pour les décideurs, même lorsqu'ils sont confrontés à une variabilité et à une incertitude intrinsèques. Un processus conçu de manière robuste améliore non seulement la qualité et la fiabilité des produits, mais réduit également de manière significative le risque de défaillances coûteuses, de temps d'arrêt et de rappels de produits. Il améliore l'efficacité et la durabilité en minimisant les déviations et les défaillances du processus. Il existe différentes méthodes pour améliorer la robustesse du système, telles que la conception d'expériences, l'optimisation robuste et la méthodologie de la surface de réponse. Parmi les méthodes de conception robuste, l'analyse de sensibilité pourrait être appliquée comme technique de soutien pour mieux comprendre comment les modifications des paramètres d'entrée affectent les performances et la robustesse. En raison du développement rapide en science de l’ingénieure, les modèles mécanistiques ne captant pas certaines parties des systèmes complexe, peuvent ne pas être l'option la plus appropriée pour d'analyse de sensibilité. Ceci nous amène à envisager l'application de modèles d'apprentissage automatique et la combiner avec l’analyse de sensibilité. Par ailleurs, la question de l'interprétabilité des modèles d'apprentissage automatique a gagné en importance, il est de plus en plus nécessaire de comprendre comment ces modèles parviennent à leurs prédictions ou à leurs décisions et comment les différents paramètres sont liés. Étant donné que leurs performances dépassent constamment celles des modèles mécanistiques, fournir des explications, des justifications et des informations sur les prédictions des modèles de ML permettent non seulement de renforcer leur fiabilité et leur équité, mais aussi de donner aux ingénieurs les moyens de prendre des décisions en connaissance de cause, d'identifier les biais, de détecter les erreurs et d'améliorer les performances globales et la fiabilité des systèmes. Diverses méthodes sont disponibles pour traiter les différents aspects de l'interprétabilité, ces dernières reposent sur des approches spécifiques à un modèle et sur des méthodes agnostiques aux modèles.Dans cette thèse, notre objectif est d'améliorer l'interprétabilité de diverses méthodes de ML tout en maintenant un équilibre entre la précision dans la prédiction et l'interprétabilité afin de garantir aux décideurs que les modèles peuvent être considérés comme robustes. Simultanément, nous voulons démontrer que les décideurs peuvent faire confiance aux prédictions fournies par les modèles ML. Les outils d’interprétabilité ont été testés pour différents scénarios d'application, y compris les modèles basés sur des équations, les modèles hybrides et les modèles basés sur des données. Pour atteindre cet objectif, nous avons appliqué à diverses applications plusieurs méthodes agnostiques aux modèles, telles que partial dependence plots, individual conditional expectations, accumulated local effects, etcRobust process design holds paramount importance in various industries, such as process and chemical engineering. The nature of robustness lies in ensuring that a process can consistently deliver desired outcomes for decision-makers and/or stakeholders, even when faced with intrinsic variability and uncertainty. A robustly designed process not only enhances product quality and reliability but also significantly reduces the risk of costly failures, downtime, and product recalls. It enhances efficiency and sustainability by minimizing process deviations and failures. There are different methods to approach the robustness of a complex system, such as the design of experiments, robust optimization, and response surface methodology. Among the robust design methods, sensitivity analysis could be applied as a supportive technique to gain insights into how changes in input parameters affect performance and robustness. Due to the rapid development and advancement of engineering science, the use of physical models for sensitivity analysis presents several challenges, such as unsatisfied assumptions and computation time. These problems lead us to consider applying machine learning (ML) models to complex processes. Although, the issue of interpretability in ML has gained increasing importance, there is a growing need to understand how these models arrive at their predictions or decisions and how different parameters are related. As their performance consistently surpasses that of other models, such as knowledge-based models, the provision of explanations, justifications, and insights into the workings of ML models not only enhances their trustworthiness and fairness but also empowers stakeholders to make informed decisions, identify biases, detect errors, and improve the overall performance and reliability of the process. Various methods are available to address interpretability, including model-specific and model-agnostic methods. In this thesis, our objective is to enhance the interpretability of various ML methods while maintaining a balance between accuracy and interpretability to ensure decision-makers or stakeholders that our model or process could be considered robust. Simultaneously, we aim to demonstrate that users can trust ML model predictions guaranteed by model-agnostic techniques, which work across various scenarios, including equation-based, hybrid, and data-driven models. To achieve this goal, we applied several model-agnostic methods, such as partial dependence plots, individual conditional expectations, accumulated local effects, etc., to diverse applications
2
Gomes, Rahul. "Incorporating Sliding Window-Based Aggregation for Evaluating Topographic Variables in Geographic Information Systems." Diss., North Dakota State University, 2019. https://hdl.handle.net/10365/29913.
Анотація:
The resolution of spatial data has increased over the past decade making them more accurate in depicting landform features. From using a 60m resolution Landsat imagery to resolution close to a meter provided by data from Unmanned Aerial Systems, the number of pixels per area has increased drastically. Topographic features derived from high resolution remote sensing is relevant to measuring agricultural yield. However, conventional algorithms in Geographic Information Systems (GIS) used for processing digital elevation models (DEM) have severe limitations. Typically, 3-by-3 window sizes are used for evaluating the slope, aspect and curvature. Since this window size is very small compared to the resolution of the DEM, they are mostly resampled to a lower resolution to match the size of typical topographic features and decrease processing overheads. This results in low accuracy and limits the predictive ability of any model using such DEM data. In this dissertation, the landform attributes were derived over multiple scales using the concept of sliding window-based aggregation. Using aggregates from previous iteration increases the efficiency from linear to logarithmic thereby addressing scalability issues. The usefulness of DEM-derived topographic features within Random Forest models that predict agricultural yield was examined. The model utilized these derived topographic features and achieved the highest accuracy of 95.31% in predicting Normalized Difference Vegetation Index (NDVI) compared to a 51.89% for window size 3-by-3 in the conventional method. The efficacy of partial dependence plots (PDP) in terms of interpretability was also assessed. This aggregation methodology could serve as a suitable replacement for conventional landform evaluation techniques which mostly rely on reducing the DEM data to a lower resolution prior to data processing.National Science Foundation (Award OIA-1355466)
Частини книг з теми "Partial Dependence Plot":
1
Guseo, R. "Partial Mixed Effects Split-Plot Design under Unknown Spatial Dependence." In AMST ’99, 859–66. Vienna: Springer Vienna, 1999. http://dx.doi.org/10.1007/978-3-7091-2508-3_98.
2
Molnar, Christoph, Timo Freiesleben, Gunnar König, Julia Herbinger, Tim Reisinger, Giuseppe Casalicchio, Marvin N. Wright, and Bernd Bischl. "Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process." In Communications in Computer and Information Science, 456–79. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-44064-9_24.
Анотація:
AbstractScientists and practitioners increasingly rely on machine learning to model data and draw conclusions. Compared to statistical modeling approaches, machine learning makes fewer explicit assumptions about data structures, such as linearity. Consequently, the parameters of machine learning models usually cannot be easily related to the data generating process. To learn about the modeled relationships, partial dependence (PD) plots and permutation feature importance (PFI) are often used as interpretation methods. However, PD and PFI lack a theory that relates them to the data generating process. We formalize PD and PFI as statistical estimators of ground truth estimands rooted in the data generating process. We show that PD and PFI estimates deviate from this ground truth not only due to statistical biases, but also due to learner variance and Monte Carlo approximation errors. To account for these uncertainties in PD and PFI estimation, we propose the learner-PD and the learner-PFI based on model refits and propose corrected variance and confidence interval estimators.
3
Baniecki, Hubert, Wojciech Kretowicz, and Przemyslaw Biecek. "Fooling Partial Dependence via Data Poisoning." In Machine Learning and Knowledge Discovery in Databases, 121–36. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-26409-2_8.
Анотація:
AbstractMany methods have been developed to understand complex predictive models and high expectations are placed on post-hoc model explainability. It turns out that such explanations are not robust nor trustworthy, and they can be fooled. This paper presents techniques for attacking Partial Dependence (plots, profiles, PDP), which are among the most popular methods of explaining any predictive model trained on tabular data. We showcase that PD can be manipulated in an adversarial manner, which is alarming, especially in financial or medical applications where auditability became a must-have trait supporting black-box machine learning. The fooling is performed via poisoning the data to bend and shift explanations in the desired direction using genetic and gradient algorithms. We believe this to be the first work using a genetic algorithm for manipulating explanations, which is transferable as it generalizes both ways: in a model-agnostic and an explanation-agnostic manner.
4
Muschalik, Maximilian, Fabian Fumagalli, Rohit Jagtani, Barbara Hammer, and Eyke Hüllermeier. "iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios." In Communications in Computer and Information Science, 177–94. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-44064-9_11.
5
Molnar, Christoph, Gunnar König, Julia Herbinger, Timo Freiesleben, Susanne Dandl, Christian A. Scholbeck, Giuseppe Casalicchio, Moritz Grosse-Wentrup, and Bernd Bischl. "General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models." In xxAI - Beyond Explainable AI, 39–68. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-04083-2_4.
Анотація:
AbstractAn increasing number of model-agnostic interpretation techniques for machine learning (ML) models such as partial dependence plots (PDP), permutation feature importance (PFI) and Shapley values provide insightful model interpretations, but can lead to wrong conclusions if applied incorrectly. We highlight many general pitfalls of ML model interpretation, such as using interpretation techniques in the wrong context, interpreting models that do not generalize well, ignoring feature dependencies, interactions, uncertainty estimates and issues in high-dimensional settings, or making unjustified causal interpretations, and illustrate them with examples. We focus on pitfalls for global methods that describe the average model behavior, but many pitfalls also apply to local methods that explain individual predictions. Our paper addresses ML practitioners by raising awareness of pitfalls and identifying solutions for correct model interpretation, but also addresses ML researchers by discussing open issues for further research.
6
Bloom, Barthe. "Chapter 2. Life at the intersection." In Constructional Approaches to Nordic Languages, 24–54. Amsterdam: John Benjamins Publishing Company, 2023. http://dx.doi.org/10.1075/cal.37.02blo.
Анотація:
In colloquial Norwegian, han ‘he’ and hun ‘she’ can occur as a determiner with common nouns with human reference (e.g., han mannen, lit. ‘he man-the’). This study investigates the lateral relations of this construction (henceforth: han mannen) and two other definite-referring constructions with human reference: noun phrases that contain the adnominal determiner den (i.e., den mannen) and those that realize definiteness by a suffixed article (i.e., mannen). The study argues that han mannen lives at the intersection of these two constructions, i.e., that it is motivated by two constructions to which it is laterally related. The lateral relations between the constructions are evaluated by random forests, variable importance measures, and partial dependence plots.
7
Ray, Robert B. "Yells." In The ABCs of Classic Hollywood, 224–25. Oxford University PressNew York, NY, 2008. http://dx.doi.org/10.1093/oso/9780195322910.003.0077.
Анотація:
Abstract The Maltese Falcon’s abstract, hermetic quality derives partially from its minimal evocation of off screen space, as if its plot were a chemistry experiment dependent on the reduction of variables. The avoidance of location shooting, the suppression of sounds coming from the edges of the story space (like the street and office noises in Godard’s Masculine-Feminine), the strict adherence of the camera to the main characters—these choices produce a self-contained world that rarely refers beyond itself.
8
Klinger, William, and Denis Kuljiš. "Oberkrainer Communism." In Tito's Secret Empire, 51–56. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780197572429.003.0008.
Анотація:
This chapter discusses the Sixth Congress, Comintern, which was run by Soviet bigwigs and a few representative party leaders from the West that sat as its steering Political Secretariat. It highlights the Balkan Bureau that was headed by Bohumír Šmeral, one of the founders of the Communist Party of Czechoslovakia. It also mentions British science-fiction writer H. G. Wells, a socialist and communist sympathizer, who visited Moscow in the early 1920s as a guest of Vladimir Lenin and realized that even the highest-ranking officials' clothes were falling apart. The chapter recounts how tried to loosen up the revolutionary course by introducing the NEP, which was supposed to stimulate small farms on private plots to produce basic market supply. It demonstrates how the advance of fascism pushed more parties underground, leading them to become utterly dependent on organizational and material assistance from abroad.
9
"Neighbourhood Influences on Vehicle-Pedestrian Crash Severity." In Big Data Analytics in Traffic and Transportation Engineering, 102–21. IGI Global, 2019. http://dx.doi.org/10.4018/978-1-5225-7943-4.ch005.
Анотація:
Socioeconomic factors are known to be contributing factors to vehicle-pedestrian crashes. Although several studies have examined the socioeconomic factors related to the locations of crashes, few studies have considered the socioeconomic factors of the neighbourhoods where road users live in vehicle-pedestrian crash modelling. In vehicle-pedestrian crashes in the Melbourne metropolitan area, 20% of pedestrians, 11% of drivers, and only 6% of both drivers and pedestrians had the same postcode for the crash and residency locations. Therefore, an examination of the influence of socioeconomic factors of their neighbourhoods, and their relative importance will contribute to advancing knowledge in the field, as very limited research has been conducted on the influence of socioeconomic factors of both the neighbourhoods where crashes occur and where pedestrians live. In this chapter, neighbourhood factors associated with road users' residents and location of crash are investigated using BDT model. Furthermore, partial dependence plots are applied to illustrate the interactions between these factors. The authors found that socioeconomic factors account for 60% of the 20 top contributing factors to vehicle-pedestrian crashes. This research reveals that socioeconomic factors of the neighbourhoods where road users live and where crashes occur are important in determining the severity of crashes, with the former having a greater influence. Hence, road safety counter-measures, especially those focussing on road users, should be targeted at these high-risk neighbourhoods.
Тези доповідей конференцій з теми "Partial Dependence Plot":
1
Rivas, Pablo, Pamela Harper, John Cary, and William Brown. "ML-Based Feature Importance Estimation for Predicting Unethical Behaviour under Pressure." In LatinX in AI at International Conference on Machine Learning 2019. Journal of LatinX in AI Research, 2019. http://dx.doi.org/10.52591/lxai201906155.
Анотація:
We studied the utility of using machine learning algorithms in the estimation of feature importance and to visualize their dependence on Ethicality. Through our analysis and partial dependence plot we found linear relationships among variables and gained insight into features that might cause certain types of ethical behaviour.
2
TEIXEIRA POLEZ, RODRIGO, Luiz Henrique Antunes Rodrigues, and FELIPE FERREIRA BOCCA. "Partial dependence plots for inspecting machine learning models of sugarcane yield." In XXIV Congresso de Iniciação Científica da UNICAMP - 2016. Campinas - SP, Brazil: Galoa, 2016. http://dx.doi.org/10.19146/pibic-2016-50805.
3
Miyaji, Renato Okabayashi, Felipe Valencia Almeida, and Pedro Luiz Pizzigatti Corrêa. "Evaluating the Explainability of Machine Learning Classifiers: A case study of Species Distribution Modeling in the Amazon." In Symposium on Knowledge Discovery, Mining and Learning. Sociedade Brasileira de Computação - SBC, 2023. http://dx.doi.org/10.5753/kdmile.2023.232929.
Анотація:
Machine Learning Models are widely used in Computational Ecology. They can be applied for Species Distribution Modeling, which aims to determine the probability of occurrence of a species, given the environmental conditions. However, for ecologists, these models are considered as "black boxes", since basic Machine Learning knowledge is necessary to interpret them. Thus, in this work four Explainable Artificial Intelligence techniques - Local Interpretable Model-Agnostic Explanation (LIME), SHapley Additive exPlanations (SHAP), BreakDown and Partial Dependence Plots - were evaluated to the Random Forests classifier for Coragyps atratus in the Amazon Basin region. It was found that the SHapley Additive exPlanations technique and Partial Dependence Plots are able to improve the explainability of the model.
4
Eswaran, M., та U. K. Saha. "Low Steeping Waves Simulation in a Vertical Excited Container Using σ Transformation". У ASME 2009 28th International Conference on Ocean, Offshore and Arctic Engineering. ASMEDC, 2009. http://dx.doi.org/10.1115/omae2009-80248.
Анотація:
A fluid partially occupying a moving tank undergoes wave motions (sloshing). These motions generate severe hydrodynamic loads that can be dangerous for structural integrity and stability of rockets, satellites, LNG ships, trucks and even stationary petroleum containers. Free surface motions of the liquid in partially filled tanks under gravity are of practical significance particularly in marine and road transportation applications. For this reason, liquid sloshing has always been a research subject attracting great concern during the last several decades. In this paper, a fully non-linear finite difference model has been developed based on the inviscid flow equations, and a simple mapping function was used to remove the time-dependence of the free surface in the fluid domain. The time-varying fluid surface can be mapped onto a rectangular domain by the σ-transformation. This method is a simple way to simulate non-breaking waves quickly and accurately especially that has a low steepness. The fluid motion is solved in a unit square mesh in the transformed flow domain (i.e., computational domain). The fourth order central difference scheme and the Gauss–Seidel point successive over-relaxation iterative procedure are used to capture the free surface wave profiles and the free surface elevation plots of the fluid domain. Difference between the peaks and troughs of waves are discussed for the case of vertical excitation of first three natural frequency of the tank. Phase-plane diagrams are drawn to show the non-linearity of the motion of time dependent free surface. The results agree well with the previously published results.
5
Nyantekyi-Kwakye, B., S. Clark, M. F. Tachie, J. Malenchak, and G. Muluye. "Flow Characteristics and Structure of 3D Turbulent Offset Jets." In ASME 2014 4th Joint US-European Fluids Engineering Division Summer Meeting collocated with the ASME 2014 12th International Conference on Nanochannels, Microchannels, and Minichannels. American Society of Mechanical Engineers, 2014. http://dx.doi.org/10.1115/fedsm2014-21276.
Анотація:
Three-dimensional turbulent offset jets were investigated with a particle image velocimetry (PIV) technique. Detailed velocity measurements for the flow were performed at an exit Reynolds number ranging from 8080–12080 for three offset height ratios of 0, 2 and 4. Profiles of the maximum mean velocity decay and wall-normal spread rates were observed to be sensitive to offset height ratio. Contour plots of mean velocity and turbulence kinetic energy exhibited dependence on offset height ratio. The reattachment lengths of the turbulent three-dimensional offset jets were observed to increase with offset height ratio. The results within the symmetry plane revealed that the production of Reynolds shear stress was not significantly enhanced by offset height ratio further downstream.
6
Anand, Sushant, and R. C. Arora. "Comparative Analysis of Different Thermal Conductivity Models for Nanofluids in a Square Enclosure Under Natural Convection Conditions." In ASME 2005 International Mechanical Engineering Congress and Exposition. ASMEDC, 2005. http://dx.doi.org/10.1115/imece2005-82576.
Анотація:
Previous investigations have revealed that addition of nanoparticles dispersed in conventional fluids such as water or ethylene glycol result in a new class of coolant which has anomalously high thermal conductivity under stagnation conditions. Few theoretical models have been proposed to resolve this abnormal behavior of nanofluids. This study focuses on the comparative study of some of these models namely, Wasp’s model, Choi’s modified Maxwell model, Bruggeman model and Xue’s model for complex nanoparticles. Flow in a cavity has been considered with insulated horizontal walls and vertical walls at different uniform temperatures under Boussinesq’s approximation. Results obtained are presented in form of plots of streamlines, isotherms and Nusselt number. Steady state solutions have been obtained for natural convection in a square cavity partially filled with copper-water. Parameters considered are Grashof number (103 to 105) and particle concentration (φ = 0%–20%). The results validate the stand that nanofluids are better coolants under dynamic conditions than conventional fluids. The flow properties have been found to be dependent upon the choice of thermal conductivity models chosen. The flow patterns predicted by various models have been found to be in close agreement with each other; however substantial variance has been found to exist in Nusselt numbers predicted by these models.
7
Argente del Castillo Martínez, Juan Pablo, and Isabel P. Albaladejo. "Understanding the effects of Covid-19 on P2P hospitality: Comparative classification analysis for Airbnb-Barcelona." In CARMA 2022 - 4th International Conference on Advanced Research Methods and Analytics. valencia: Universitat Politècnica de València, 2022. http://dx.doi.org/10.4995/carma2022.2022.15091.
Анотація:
The Covid-19 pandemic has produced significant changes in tourism markets around the world. The large amount of data available on the Airbnb platform, one of the world's largest hosting services, makes it an ideal prospecting place to try to find out what the aftermath of this event has been. This paper explores the entire Airbnb housing stock in the city of Barcelona with the aim of identifying the key characteristics of the homes that have remained operational during the 2019-2021 period. We carried out this analysis by using two classification methods, the random forest and logistic regression with elastic net. The objective is to classify the houses that have remained on the platform against those that have not. Finally, we analyze the results obtained and compare both the general performance of the models and the individual information of each variable through partial dependence plots (PDP). We found a better performance of Random Forest over logistic regression, but not significant differences in the relevant variables chosen by each method. It is worth noting the importance of the geographical location, the number of amenities in the home or the price in the survival of the homes.
8
Adeeyo, Yisa Ademola, Anuola Ayodeji Osinaike, and Gamaliel Olawale Adun. "Estimation of Fluid Saturation Using Machine Learning Algorithms: A Case Study of Niger Delta Sandstone Reservoirs." In SPE Reservoir Characterisation and Simulation Conference and Exhibition. SPE, 2023. http://dx.doi.org/10.2118/212696-ms.
Анотація:
Abstract Water Saturation (Sw) is a critical input to reserves estimation and reservoir modeling workflows which ultimately informs effective reservoir management and decision-making. Without laboratory analysis on expensive core data, Sw is estimated using traditional correlations—commonly Archie's equation. However, using such a correlation in routine petrophysical analysis for estimating reservoir properties on a case-by-case basis is challenging and time-consuming. This study employs a data-driven approach to model Sw in Niger Delta sandstone reservoirs using readily available geophysical well logs. We evaluate the performance of several generic and ensemble machine learning (ML) algorithms for predicting Archie's computed Sw. ML techniques such as unsupervised anomaly detection and multivariate single imputation were used for preprocessing the data and feature engineering was used to improve the predictive quality of the input well logs. The generalization ability of the ML models was assessed on the individual training wells as well as a held-out test well. Model hyperparameters were tuned using Bayesian Optimization in the cross-validation process to achieve a high rate of success. Several evaluation metrics and graphical methods such as learning curves, convergence plots, and partial dependence plots (PDPs) were then used to assess the predictive performance of the models and explain their behavior. This revealed the Tree Boosting ensembles as the top performers. The superior performance of the Tree Boosting ensembles over the benchmark linear model reveals that the relationship between the transformed logs and Sw is complex and better modeled in the nonlinear domain. Based on the results obtained in this research, we propose the Tree Boosting ensembles as potential models for rapidly estimating Sw for reservoir characterization. A broader field application of the proposed methodologies is expected to provide greater insight into subsurface fluid distribution thereby improving hydrocarbon recovery.
9
Pirrone, Marco, Satria Andrianata, Sara Moriggi, Giuseppe Galli, and Simone Riva. "Full Analytical Modeling Of Intrawell Chemical Tracer Concentration For Robust Production Allocation In Challenging Environments." In SPE Annual Technical Conference and Exhibition. SPE, 2021. http://dx.doi.org/10.2118/206245-ms.
Анотація:
Abstract Conventional downhole dynamic characterization is based on data from standard production logging tool (PLT) strings. Such method is not a feasible option in long horizontal drains, deep water scenarios, subsea clusters, pump-assisted wells and in presence of asphaltenes/solids deposition, mainly due to high costs and risk of tools stuck. In this respect, intrawell chemical tracers (ICT) can represent a valid and unobtrusive monitoring alternative. This paper deals with a new production allocation interpretation model of tracer concentration behavior that can overcome the limitation of standard PLT analyses in challenging environments. ICT are installed along the well completion and are characterized by a unique oil and/or water tracer signature at each selected production interval. Tracer concentration is obtained by dedicated analyses performed for each fluid sample taken at surface during transient production. Next, tracer concentration behavior over time is interpreted, for each producing interval, by means of an ad-hoc one-dimensional partial differential equation model with proper initial and boundary conditions, which describes tracer dispersion and advection profiles in such transient conditions. The full time-dependent analytical solutions are then utilized to obtain the final production allocation. The methodology has been developed and validated using data from a dozen of tracer campaigns. The approach is here presented through a selected case study, where a parallel acquisition of standard PLT and ICT data has been carried out in an offshore well. The aim was to understand if ICT could be used in substitution of the more impacting PLT for the future development wells in the field. At target, the well completion consists of a perforated production liner with tubing. The latter, which is slotted in front of the perforations, includes oil and water tracer systems. The straightforward PLT interpretation shows a clear dynamic well behavior with an oil production profile in line with the expectations from petrophysical information. Then, after a short shut-in period, the ICT-based production allocation has been performed in transient conditions with a very good match with the available outcomes from PLT: in fact, the maximum observed difference in the relative production rates is 5%. In addition, the full analytical solution of the ICT model has been fundamental to completely characterize some complex tracer concentration behaviors over time, corresponding to non-simultaneous activation of the different producing intervals. Given the consistency of the independent PLT and ICT interpretations, the monitoring campaign for the following years has been planned based on ICT only, with consequent impact on risk and cost mitigations. Although the added value of ICT is relatively well known, the successful description of the tracer signals through the full mathematical model is a novel topic and it can open the way for even more advanced applications.
10
Butryn, Krzysztof, and Edward Preweda. "Analysis of the Impact of Quantitative and Qualitative Price-setting Attributes on a Market of Real Estate Intended for the Purpose of the Transformer Stations on the Example of Krakow." In Environmental Engineering. VGTU Technika, 2017. http://dx.doi.org/10.3846/enviro.2017.177.
Анотація:
Based on appraisal reports, obtained from the City Office of Krakow, there were formulated base of real estate properties on which is situated the building of transformer station or which are intended for such purpose. The base consists of 90 properties located in the administrative boundaries of the city of Krakow. Most of these properties are the plots of very small areas, mainly in the range from 30 to 70 square meters. Based on the completed database, there were conducted a statistical analysis of the relevant market the property. In order to determine the relationship between the attributes and the price of real estate, there were calculated coefficients of the Pearson complete correlation and coefficients of the Spearman correlation. The analysis showed significant differences between quantitative and qualitative correlation coefficients for some variables. In order to improve the consistency of the database, using statistical methods eliminated property turned out. Finally, the analysis considered two bases, numbering respectively 90 and 77 real estates. In the following values, there were defined standardized regression coefficients (scale 9), the partial correlation coefficients for the dependent variable (price) relative to the rest of variables and coefficients of determination. On the basis of calculations and analysis, there have been drawn conclusions on the impact of each attribute on the market prices of these unusual properties.