Using a Selective Ensemble Support Vector Machine to Fuse Multimodal Features for Human Action Recognition

The traditional human action recognition (HAR) method is based on RGB video. Recently, with the introduction of Microsoft Kinect and other consumer class depth cameras, HAR based on RGB-D (RGB-Depth) has drawn increasing attention from scholars and industry. Compared with the traditional method, the HAR based on RGB-D has high accuracy and strong robustness. In this paper, using a selective ensemble support vector machine to fuse multimodal features for human action recognition is proposed. The algorithm combines the improved HOG feature-based RGB modal data, the depth motion map-based local binary pattern features (DMM-LBP), and the hybrid joint features (HJF)-based joints modal data. Concomitantly, a frame-based selective ensemble support vector machine classification model (SESVM) is proposed, which effectively integrates the selective ensemble strategy with the selection of SVM base classifiers, thus increasing the differences between the base classifiers. The experimental results have demonstrated that the proposed method is simple, fast, and efficient on public datasets in comparison with other action recognition algorithms.

What Kind of Travellers Are Using Carsharing in Beijing? A Study Based on Selective Ensemble Learning

As a new urban travel mode, carsharing is significantly different from private cars, buses and other travel modes. Therefore, clarifying the typical characteristics of carsharing, such as individual users’ attributes, travel environment and travel behaviour, is conducive to accurately grasping the development of carsharing. In this study, a selective ensemble learning model is established to analyse typical travel characteristics of carsharing. Firstly, personal characteristics, environmental characteristics and behavioural characteristics were obtained through integrating order data, global positioning system data and station information. Then, based on a consolidated view of carsharing, different types of carsharing travel characteristics were distinguished using selective ensemble learning. Lastly, all kinds of carsharing travel are described in detail. It was identified through this research that carsharing travel can be divided into four kinds: long distance for leisure and entertainment, medium and short distances for business and commuting, a mixed category of medium and short distances for business and residence, and a mixed category of long distance for business and residence. This study can provide a theoretical reference and practical basis for precise planning and design and the scientific operation of carsharing.

Learning to Predict Page View on College Official Accounts With Quality-Aware Features

At present, most of departments in colleges have their own official accounts, which have become the primary channel for announcements and news. In the official accounts, the popularity of articles is influenced by many different factors, such as the content of articles, the aesthetics of the layout, and so on. This paper mainly studies how to learn a computational model for predicting page view on college official accounts with quality-aware features extracted from pictures. First, we built a new picture database by collecting 1,000 pictures from the official accounts of nine well-known universities in the city of Beijing. Then, we proposed a new model for predicting page view by using a selective ensemble technology to fuse three sets of quality-aware features that could represent how a picture looks. Experimental results show that the proposed model has achieved competitive performance against state-of-the-art relevant models on the task for inferring page view from pictures on college official accounts.

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography

Invasive coronary angiography is a primary imaging modality that visualizes the lumen area of coronary arteries for the diagnosis of coronary artery diseases and guidance for interventional devices. In the current practice of quantitative coronary analysis (QCA), semi-automatic segmentation tools require labor-intensive and time-consuming manual correction; this limits their application in the catheterization room. For a more automated QCA, it is necessary to minimize operator intervention through robust segmentation methods with improved predictability. In this study, we introduced two selective ensemble methods that integrated the weighted ensemble approach with per-image quality estimation. In our selective ensemble methods, the segmentation outcomes from five base models with different loss functions were ranked by mask morphology or estimated dice similarity coefficient (DSC). The final output was determined by imposing different weights according to the ranking. The ranking criteria based on mask morphology were determined empirically to avoid frequent types of segmentation errors, whereas the estimation of DSCs was performed by comparing the pseudo-ground truth generated from a meta-learner. In the assessment with 7,426 frames from 2,924 patients, the selective ensemble methods improved segmentation performance with DSCs of up to 93.11\% and provided a better delineation of lumen boundaries near the coronary lesion with local DSCs of up to 94.04\%, outperforming all individual models and hard voting ensembles. The probability of mask disconnection at the most narrowed region could be minimized to <1\%. The robustness of the proposed methods was evident in the external validation. Inference time for major vessel segmentation was approximately one-third, indicating that our selective ensemble methods may allow the real-time application of QCA-based diagnostic methods in routine clinical settings.