Imbalanced data with a skewed class distribution are common in many real-world applications. Deep Belief Network (DBN) is a machine learning technique that is effective in classification tasks. However, conventional DBN does not work well for imbalanced data classification because it assumes equal costs for each class. To deal with this problem, cost-sensitive approaches assign different misclassification costs for different classes without disrupting the true data sample distributions. However, due to lack of prior knowledge, the misclassification costs are usually unknown and hard to choose in practice. Moreover, it has not been well studied as to how cost-sensitive learning could improve DBN performance on imbalanced data problems. This paper proposes an evolutionary cost-sensitive deep belief network (ECS-DBN) for imbalanced classification. ECS-DBN uses adaptive differential evolution to optimize the misclassification costs based on the training data that presents an effective approach to incorporating the evaluation measure (i.e., G-mean) into the objective function. We first optimize the misclassification costs, and then apply them to DBN. Adaptive differential evolution optimization is implemented as the optimization algorithm that automatically updates its corresponding parameters without the need of prior domain knowledge. The experiments have shown that the proposed approach consistently outperforms the state of the art on both benchmark data sets and real-world data set for fault diagnosis in tool condition monitoring.

A Cost-Sensitive Deep Belief Network for Imbalanced Classification

In the application of face recognition, eyeglasses could significantly degrade the recognition accuracy. A feasible method is to collect large-scale face images with eyeglasses for training deep learning methods. However, it is difficult to collect the images with and without glasses of the same identity, so that it is difficult to optimize the intra-variations caused by eyeglasses. In this paper, we propose to address this problem in a virtual synthesis manner. The high-fidelity face images with eyeglasses are synthesized based on 3D face model and 3D eyeglasses. Models based on deep learning methods are then trained on the synthesized eyeglass face dataset, achieving better performance than previous ones. Experiments on the real face database validate the effectiveness of our synthesized data for improving eyeglass face recognition performance.

/pdf/face-synthesis-for-eyeglass-robust-face-recognition-31b7r3rjtx.pdf

Face Synthesis for Eyeglass-Robust Face Recognition

Visual analytics tools are of paramount importance in handling high-dimensional datasets such as those in our turbine performance assessment. Conventional tools such as RadViz have been used in 2D exploratory data analysis. However, with the increase in dataset size and dimensionality, the clumping of projected data points toward the origin in RadViz causes low space utilization, which largely degenerates the visibility of the feature characteristics. In this study, to better evaluate the hidden patterns in the center region, we propose a new focus + context distortion approach, termed PolarViz, to manipulate the radial distribution of data points. We derive radial equalization to automatically spread out the frequency, and radial specification to shape the distribution based on user’s requirement. Computational experiments have been conducted on two datasets including a benchmark dataset and a turbine performance simulation data. The performance of the proposed algorithm as well as other methods for solving the clumping problem in both data space and image space are illustrated and compared, and the pros and cons are analyzed. Moreover, a user study was conducted to assess the performance of the proposed method.

PolarViz: a discriminating visualization and visual analytics tool for high-dimensional data

Accurate modeling of 3D objects exhibiting transparency, reflections and thin structures is an extremely challenging problem. Inspired by billboards and geometric proxies used in computer graphics, this paper proposes Generative Latent Textured Objects (GeLaTO), a compact representation that combines a set of coarse shape proxies defining low frequency geometry with learned neural textures, to encode both medium and fine scale geometry as well as view-dependent appearance. To generate the proxies’ textures, we learn a joint latent space allowing category-level appearance and geometry interpolation. The proxies are independently rasterized with their corresponding neural texture and composited using a U-Net, which generates an output photorealistic image including an alpha map. We demonstrate the effectiveness of our approach by reconstructing complex objects from a sparse set of views. We show results on a dataset of real images of eyeglasses frames, which are particularly challenging to reconstruct using classical methods. We also demonstrate that these coarse proxies can be handcrafted when the underlying object geometry is easy to model, like eyeglasses, or generated using a neural network for more complex categories, such as cars.

GeLaTO: Generative Latent Textured Objects

Corrective lenses introduce distortion caused by the refraction effect, which changes the wear’s appearance. To give users a more realistic experience, a virtual try-on system for prescription eyeglasses modifies an input video and virtually inserts prescription eyeglasses, producing an output similar to a virtual mirror. The proposed system generates a 3D representation of the corrective lenses mounted into the eyeglasses frame and modifies the video sequence to virtually insert the eyeglasses through image-based rendering. Unlike existing virtual try-on systems, this approach simulates the refraction effects due to the corrective lens and takes into account reflections and shading.

A Virtual Try-On System for Prescription Eyeglasses

In our turbine performance assessment, we need to provide an effective visual analytics tool in handling high-dimensional datasets. We have employed RadViz in 2D exploratory data analysis. However, with the increase of dataset size and dimensionality, the clumping of projected data points towards the origin in RadViz causes low space utilization, which largely degenerates the visibility of the feature characteristics. In this study, to better evaluate the hidden patterns in the center region, we propose histogram-based techniques to manipulate the radial distribution of data points in RadViz. We present RadViz in the polar coordinate system for convenient radial operations. Based on this, we define the radial equalization method to automatically spread out the frequency and the radial specification method to shape the distribution based on the user's requirement. Furthermore, we utilize the information in high-dimensional space as histogram and reference point to design and control the radial distribution of RadViz. Computational experiments have been conducted on turbine performance simulation data. Our proposed techniques are shown advantageous in query result display and outlier detection with a set of high-dimensional datasets.

Histogram equalization and specification for high-dimensional data visualization using RadViz

The heart of every vehicle is its engine. Many factors, either internal or external, contribute to the aircraft engine's durability and lifespan. In this paper, we aim to assist the analyst with a qualitative analysis of the possible external cause of engine failures. We work closely with domain experts to study the domain knowledge, analyze challenging tasks, and abstract user requirements. We present EngineQV, a visualization system that integrates multiple geo-temporal engine-associated records. It provides intuitive exploration and understanding of the data from various aspects. The system features a dynamic query on the datasets and incorporates several customized interactive visualizations. A user may query a certain group of engines or compare multiple engine groups, identify an issue, and find its potential causes. The functionality and usability of EngineQV are evaluated by two case studies, through knowledge discovery from records of a single engine and visual comparison of multiple engines. The validity of the system is confirmed by expert feedback.

EngineQV: Investigating External Cause of Engine Failures Based on Geo-Temporal Association

Identifying the potential factors that contribute to an aircraft engine’s durability is a big challenge. In this paper, we propose an interactive system to link the engine maintenance history data, flight route history data, and volcanic ash eruption data, and then visualize the relations among them. Several kinds of visualization forms are used to present the datasets. We implement the React-Redux framework to manage the visual components in the frontend, along with a backend to handle the database. This highly tailored system shows how datasets of different sources can be linked and visualized with interactivity. Data analysts and developers can benefit from full-stack development process from data to intuition, meeting the requirements of customized visualization.

Qian Zhang

Papers

PolarViz: a discriminating visualization and visual analytics tool for high-dimensional data

A Virtual Try-On System for Prescription Eyeglasses

Histogram equalization and specification for high-dimensional data visualization using RadViz

EngineQV: Investigating External Cause of Engine Failures Based on Geo-Temporal Association

Interactive geo-temporal data visualization for aircraft engine