Filters








39,114 Hits in 4.6 sec

The foundations of cost-sensitive causal classification [article]

Wouter Verbeke, Diego Olaya, Jeroen Berrevoets, Sam Verboven, Sebastián Maldonado
2021 arXiv   pre-print
Cost-sensitive and causal classification methods have independently been proposed to improve the performance of classification models.  ...  The framework encompasses a range of existing and novel performance measures for evaluating both causal and conventional classification models in a cost-sensitive as well as a cost-insensitive manner.  ...  To this end, we formalize the foundations of cost-sensitive evaluation of conventional classification models by introducing the effect matrix as the difference between the confusion matrix of a classification  ... 
arXiv:2007.12582v5 fatcat:vqr7c2libfgplov7gn2gkr6v4m

To do or not to do: cost-sensitive causal decision-making [article]

Diego Olaya, Wouter Verbeke, Jente Van Belle, Marie-Anne Guerry
2021 arXiv   pre-print
In this article, we therefore extend upon the expected value framework and formally introduce a cost-sensitive decision boundary for double binary causal classification, which is a linear function of the  ...  The boundary allows causally classifying instances in the positive and negative treatment class to maximize the expected causal profit, which is introduced as the objective at hand in cost-sensitive causal  ...  Acknowledgment: The authors acknowledge the support of Innoviris, the Brussels Region Research funding agency.  ... 
arXiv:2101.01407v1 fatcat:jwommu5rqnfbbb5hqqcs3x6kkm

Causal Associative Classification

Kui Yu, Xindong Wu, Wei Ding, Hao Wang, Hongliang Yao
2011 2011 IEEE 11th International Conference on Data Mining  
rules; and (2) how to deal with the highly sensitive choice of the minimal support threshold.  ...  In order to address these two challenges, we introduce causality into associative classification, and propose a new framework of causal associative classification.  ...  ACKNOWLEDGMENTS This work is supported by the National Natural Science Foundation of China (60975034, 61070131, 61175051 and 61005007), the US National Science Foundation (CCF-0905337), and the US NASA  ... 
doi:10.1109/icdm.2011.30 dblp:conf/icdm/YuWDWY11 fatcat:tsmuoe4nkvfpxgt4x7oebelqr4

Knowledge discovery: Detecting elderly patients with impaired mobility

Der-Fa Lu, William Nick Street, Connie Delaney
2006 Studies in Health Technology and Informatics  
The research method applied an exploratory design and a data mining classification method (cost sensitive Decision Tree J48 from WEKA) to classify patients.  ...  The study can be applied to classify different health problems in different populations and serves as a foundation for the development of healthcare decision support systems.  ...  A cost sensitive classifier was used to increase the weight of Class 1 cases.  ... 
pmid:17102231 fatcat:i42abtvjvrg3neo4w6yss4ebwm

Classification systems in psychiatry

Dan J. Stein, Crick Lund, Randolph M. Nesse
2013 Current Opinion in Psychiatry  
Purpose of review-The development of the fifth edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) and of the eleventh edition of the International Classification of Disease (ICD  ...  Advances in our understanding of the individual-level and society-level causal mechanisms that contribute to vulnerability to mental disorder may ultimately lead to improved classification systems, and  ...  Acknowledgments Conflicts of Interest: Prof Stein has Dr.  ... 
doi:10.1097/yco.0b013e3283642dfd pmid:23867662 pmcid:PMC4270276 fatcat:upb2hbb5ijahfmer3rapj6xjwy

Evolutionary biology: an essential basic science for the training of the next generation of psychiatrists

Riadh Abed, Agnes Ayton, Paul St John-Smith, Annie Swanepoel, Derek K. Tracy
2019 British Journal of Psychiatry  
The authors accordingly make the case for the inclusion of evolutionary biology in the postgraduate education of psychiatric trainees. Declaration of interest None.  ...  Evolutionary science can serve as the high-level organising principle for understanding psychiatry.  ...  Nesse's 'smoke detector principle' 2,3 utilises specific evolutionary observations that, when the cost of activation of defences is trivial, (even when the risk is absent) but there is a massive cost of  ... 
doi:10.1192/bjp.2019.123 pmid:31162000 fatcat:qujtnourrfe7hdrvmq6myakhvi

Abstracting Fairness: Oracles, Metrics, and Interpretability

Cynthia Dwork, Christina Ilvento, Guy N. Rothblum, Pragya Sur, Aaron Roth
2020 Symposium on Foundations of Responsible Computing  
Our results have implications for interpretablity - a highly desired but poorly defined property of classification systems that endeavors to permit a human arbiter to reject classifiers deemed to be "unfair  ...  Our principal conceptual result is an extraction procedure that learns the underlying truth; moreover, the procedure can learn an approximation to this truth given access to a weak form of the oracle.  ...  In this definition, the causal model replaces the metric as the specification of fairness.  ... 
doi:10.4230/lipics.forc.2020.8 dblp:conf/forc/DworkIRS20 fatcat:dc2ahgm5wbhu7j3nmynnx2vq3y

At the borders of medical reasoning: aetiological and ontological challenges of medically unexplained symptoms

Thor Eriksen, Roger Kerry, Stephen Mumford, Svein Anders Lie, Rani Anjum
2013 Philosophy, Ethics, and Humanities in Medicine  
centre of any causal set-up, and not only for MUS.  ...  Finally, the outlines of an alternative ontology of causation are offered which place characteristic features of MUS, such as genuine complexity, context-sensitivity, holism and medical uniqueness at the  ...  The work was carried out with support from the Causation in Science (CauSci) Project funded by the Research Council of Norway.  ... 
doi:10.1186/1747-5341-8-11 pmid:24006875 pmcid:PMC3846629 fatcat:pqwhobhp25h77dkgfuwvwrtkfu

Semantic Features Prediction for Pulmonary Nodule Diagnosis based on Online Streaming Feature Selection

Jing Yang, Na Li, Shuai Fang, Kui Yu, Yu Chen
2019 IEEE Access  
The critical challenges in this integration include: 1) the dynamic selection of computational features and 2) how to evaluate the feature subsets and implement causal structure learning.  ...  This study attempts to construct a predictive network between the computational features and semantic features of pulmonary nodules using online feature selection and causal structure learning.  ...  PERFORMANCE MEASURES We use classification accuracy, sensitivity and specificity to measure the performance of the algorithms in the binary classification data set.  ... 
doi:10.1109/access.2019.2903682 fatcat:nj74etenv5hrzjmtvou25n6yrq

Stochastic microstructure characterization and reconstruction via supervised learning

Ramin Bostanabad, Anh Tuan Bui, Wei Xie, Daniel W. Apley, Wei Chen
2016 Acta Materialia  
By treating the digitized microstructure image as a set of training data, we generically learn the stochastic nature of the microstructure via fitting a supervised learning model to it (we focus on classification  ...  The fitted supervised learning model provides an implicit characterization of the joint distribution of the collection of pixel phases in the image.  ...  The characterization (Char.) cost includes the total cost of fitting the tree. The reconstruction (Rec.) cost is associated with reconstructing the patterned blue region in Fig. 7.  ... 
doi:10.1016/j.actamat.2015.09.044 fatcat:6iiie33i7jglhjl5arwbai7ghm

Fall Detection with CNN-Casual LSTM Network

Jiang Wu, Jiale Wang, Ao Zhan, Chengyu Wu
2021 Information  
The decoding layer maps spatio-temporal information to a hidden variable output that is more conducive relative to the work of the classification network, which is classified by ResNet18.  ...  Moreover, we used the public data set SisFall to evaluate the performance of the algorithm. The results of the experiments show that the algorithm has high accuracy up to 99.79%.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/info12100403 fatcat:df5mnijalba47mpfmogz77dsta

Analysis of Travel Mode Choice Behavior Considering the Indifference Threshold

Zhang, Guan, Zhu, Zhu
2019 Sustainability  
This study defines the "indifference threshold" as the traveler's sensitivity to changes in travel utilities.  ...  Therefore, the "indifference threshold" is one of the most important factors influencing a traveler's choice of behavior.  ...  We sincerely thank the reviewers for their professional suggestions and the editors for their patient and meticulous work. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/su11195495 fatcat:ojpdruy6qnhullpjvkypjw6h6e

Abstracting Fairness: Oracles, Metrics, and Interpretability [article]

Cynthia Dwork, Christina Ilvento, Guy N. Rothblum, Pragya Sur
2020 arXiv   pre-print
Our results have implications for interpretablity -- a highly desired but poorly defined property of classification systems that endeavors to permit a human arbiter to reject classifiers deemed to be "  ...  Our principal conceptual result is an extraction procedure that learns the underlying truth; moreover, the procedure can learn an approximation to this truth given access to a weak form of the oracle.  ...  To make such an assertion, the definition relies on a causal model that captures the ways in which these attributes influence other attributes relevant to classification.  ... 
arXiv:2004.01840v1 fatcat:6rcrsu7favcq7mlsuhull3base

Is doing good good for you? how corporate charitable contributions enhance revenue growth

Baruch Lev, Christine Petrovits, Suresh Radhakrishnan
2009 Strategic Management Journal  
This study examines the impact of corporate philanthropy growth on sales growth using a large sample of charitable contributions made by U.S. public companies from 1989 through 2000.  ...  Our results are particularly pronounced for firms that are highly sensitive to consumer perception, where individual consumers are the predominant customers.  ...  of Management Conference for helpful feedback, and John Graham for providing the marginal tax rate data.  ... 
doi:10.1002/smj.810 fatcat:gg5pm4zdwnd2vcpndzfkxhuuey

Stacked Generalizations in Imbalanced Fraud Data Sets using Resampling Methods [article]

Kathleen Kerwin, Nathaniel D. Bastian
2020 arXiv   pre-print
Although the process uses great computational resources, the resulting performance metrics on resampled fraud data show that increased system cost can be justified.  ...  the error rate of each individual algorithm to reduce its bias in the learning set) and then in step two inputting the results into the meta learner with its stacked blended output (demonstrating improved  ...  (Wong, Seng and Wong, 2020 ) used a cost-sensitive neural network ensemble method of Stacked Denoising Autoencoders on six data sets, as well as Cost-Sensitive Deep Neural Network (CSDNN) and Cost-Sensitive  ... 
arXiv:2004.01764v1 fatcat:mcy2rnk2dffn3awn3kfc67pdvm
« Previous Showing results 1 — 15 out of 39,114 results