Robust deep auto-encoding Gaussian process regression for unsupervised anomaly detection

Anomaly detection in images with shared autoencoders

Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased toward one class (normal) due to the insufficient sample size of the other class (abnormal). We introduce a novel model that utilizes two decoders to share two encoders, respectively, forming two sets of network structures of encoder-decoder-encoder called EDE, which are used to map image distributions to predefined latent distributions and vice versa. In addition, we propose an innovative two-stage training mode. The first stage is roughly the same as the traditional autoencoder (AE) training, using the reconstruction loss of images and latent vectors for training. The second stage uses the idea of generative confrontation to send one of the two groups of reconstructed vectors into another EDE structure to generate fake images and latent vectors. This EDE structure needs to achieve two goals to distinguish the source of the data: the first is to maximize the difference between the fake image and the real image; the second is to maximize the difference between the fake latent vector and the reconstructed vector. Another EDE structure has the opposite goal. This network structure combined with special training methods not only well avoids the shortcomings of generative adversarial networks (GANs) and AEs, but also achieves state-of-the-art performance evaluated on several publicly available image datasets.

The Efficacy of Machine-Learning-Supported Smart System for Heart Disease Prediction

The disease may be an explicit status that negatively affects human health. Cardiopathy is one of the common deadly diseases that is attributed to unhealthy human habits compared to alternative diseases. With the help of machine learning (ML) algorithms, heart disease can be noticed in a short time as well as at a low cost. This study adopted four machine learning models, such as random forest (RF), decision tree (DT), AdaBoost (AB), and K-nearest neighbor (KNN), to detect heart disease. A generalized algorithm was constructed to analyze the strength of the relevant factors that contribute to heart disease prediction. The models were evaluated using the datasets Cleveland, Hungary, Switzerland, and Long Beach (CHSLB), and all were collected from Kaggle. Based on the CHSLB dataset, RF, DT, AB, and KNN models predicted an accuracy of 99.03%, 96.10%, 100%, and 100%, respectively. In the case of a single (Cleveland) dataset, only two models, namely RF and KNN, show good accuracy of 93.437% and 97.83%, respectively. Finally, the study used Streamlit, an internet-based cloud hosting platform, to develop a computer-aided smart system for disease prediction. It is expected that the proposed tool together with the ML algorithm will play a key role in diagnosing heart diseases in a very convenient manner. Above all, the study has made a substantial contribution to the computation of strength scores with significant predictors in the prognosis of heart disease.

An Integrated Data Mining Framework for Organizational Resilience Assessment and Quality Management Optimization in Trauma Centers

Every second counts for patients with life-threatening injuries, and trauma centers deliver timely emergency care to patients with traumatic injuries. Quality assessment and improvement are some of the most fundamental concerns in trauma centers. In this study, a comprehensive organizational resilience approach is proposed to evaluate performance in trauma centers using the European Foundation for Quality Management as a fundamental and strategic approach. We propose a unique intelligent algorithm composed of parametric and non-parametric statistical methods to determine the type and the extent of influence within the organizational resilience and quality management perspectives. We use structural equation modeling to examine the reliability and validity of the input data. The efficiency of each trauma center is then measured using a machine learning method with genetic programming, support vector regression, and Gaussian process regression. The mean absolute percentage error is used to determine the optimal model, and a fuzzy data envelopment analysis model is used to verify and validate the results obtained from the optimal model. The results show that customer results, human capital results, and key performance results have the highest importance weights and positive influence on quality management. Cognitive resources, roles and responsibilities, and self-organization have the highest importance weights and positive influence on organizational resilience.

Machine Learning for Identifying Group Trajectory Outliers

Prior works on the trajectory outlier detection problem solely consider individual outliers. However, in real-world scenarios, trajectory outliers can often appear in groups, e.g., a group of bikes that deviates to the usual trajectory due to the maintenance of streets in the context of intelligent transportation. The current paper considers the Group Trajectory Outlier (GTO) problem and proposes three algorithms. The first and the second algorithms are extensions of the well-known DBSCAN and k NN algorithms, while the third one models the GTO problem as a feature selection problem. Furthermore, two different enhancements for the proposed algorithms are proposed. The first one is based on ensemble learning and computational intelligence, which allows for merging algorithms’ outputs to possibly improve the final result. The second is a general high-performance computing framework that deals with big trajectory databases, which we used for a GPU-based implementation. Experimental results on different real trajectory databases show the scalability of the proposed approaches.