The objective of multi-dimensional classification is to learn a function that accurately maps each data instance to a vector of class labels. Multi-dimensional classification appears in a wide range of applications including text categorization, gene functionality classification, semantic image labeling, etc. Usually, in such problems, the class variables are not independent, but rather exhibit conditional dependence relations among them. Hence, the key to the success of multi-dimensional classification is to effectively model such dependencies and use them to facilitate the learning. In this paper, we propose a new probabilistic approach that represents class conditional dependencies in an effective yet computationally efficient way. Our approach uses a special treestructured Bayesian network model to represent the conditional joint distribution of the class variables given the feature variables. We develop and present efficient algorithms for learning the model from data and for performing exact probabilistic inferences on the model. Extensive experiments on multiple datasets demonstrate that our approach achieves highly competitive results when it is compared to existing state-of-the-art methods.

Medical errors remain a significant problem in healthcare. This paper investigates a data-driven outlier-based monitoring and alerting framework that uses data in the Electronic Medical Records (EMRs) repositories of past patient cases to identify any unusual clinical actions in the EMR of a current patient. Our conjecture is that these unusual clinical actions correspond to medical errors often enough to justify their detection and alerting. Our approach works by using EMR repositories to learn statistical models that relate patient states to patient-management actions. We evaluated this approach on the EMR data for 24,658 intensive care unit (ICU) patient cases. A total of 16,500 cases were used to train statistical models for ordering medications and laboratory tests given the patient state summarizing the patient’s clinical history. The models were applied to a separate test set of 8,158 ICU patient cases and used to generate alerts. A subset of 240 alerts generated by the models were evaluated and assessed by eighteen ICU clinicians. The overall true positive rates for the alerts (TPARs) ranged from 0.44 to 0.71. The TPAR for medication order alerts specifically ranged from 0.31 to 0.61 and for laboratory order alerts from 0.44 to 0.75. These results support outlier-based alerting as a promising new approach to data-driven clinical alerting that is generated automatically based on past EMR data.

No abstract

This paper compares artificial intelligence (AI) methods to predict mechanical properties of sheet metal in stamping processes. The deviation of the mechanical properties of each blank leads to unpredicted failures in stamping processes, such as fracture and spring back. The research team of this paper has been building a real time control system for stamping process in a smart factory. In order to facilitate that, it is necessary to predict the mechanical properties of each blank with non-destructive testing. The regression models based on the linear algebraic scheme have traditionally brought reliable results in terms of matching the measured non-destructive testing values to the mechanical properties. With a parallel to algebraic regression models, in recent studies on various domains, AI models have been adopted to improve the accuracy of the end-results and effectiveness of the models. This paper discusses the applicability of AI models for predicting the mechanical properties based on the eddy-current non-destructive testing method. For the study, 6 input features are collected through the eddy-current non-destructive testing to map eddy-current input data to mechanical properties of the blank. Yield stress and uniform elongation were predicted by using five AI methods, i.e., regularized linear regression, support vector regularized linear regression, support vector regression, multi-layer neural network, random forest regression, and gradient boosting regression were compared. The model performance, validated with 20% of test data that are intact during the training phase, is the main discussion point of this paper. Future works to improve the predictive accuracy of AI models is also discussed.

This paper overviews the background, goals, past achievements and future directions of our research that aims to build a multivariate conditional anomaly detection framework for the clinical application.