Search

Nowadays, visualization is becoming an essential part of data analysis. Business Intelligence Visualization (BIV) is a powerful tool that helps modern business flows faster and smoother than ever before. However, research on BIV evaluation is severely lacking; most evaluation studies for BIV focus on usability, which have limited aspects covered for customers’ needs. The purpose of this research is to develop a UX framework that evaluates BIV (UXBIV), including decision-making experience and interactivity. First, we did a literature survey for good understanding of research progress in related fields, and established a conceptual framework. Second, we performed a case study that implemented this framework to demonstrate how our framework can be used in real business. Our analysis shows that this UXBIV framework is quite reasonable, and it can capture the differences among various BIV designs from the users’ standpoints. This UXBIV framework can help design BIV and promote better decision-making on business affairs.

In recent years, MOOC has become one of the most popular trends in global education. However, the completion of courses is still a great challenge for MOOCs. Thus, the evaluation of MOOCs is of great importance to online education. The goal of this research is to evaluate the interfaces of localized MOOC on PC platforms, specifically, to explore the role of culture on the interface design and its user experience (UX). Three studies were conducted in our research. In study 1, through an interview, we selected two localized MOOCs (Chinese University MOOC and Coursera), typical user tasks, and main factors of UX. In study 2, a content analysis was conducted to compare the interface design of the MOOCs selected in study 1. The results showed significant cultural differences in the interface design between the two localized MOOCs. In study 3, the UX was evaluated on Chinese University MOOC (CUM) and Coursera. It is found that the task-based UX of CUM is better than Coursera on four typical tasks. And the overall UX (usability, aesthetics, and pleasure) is much higher on CUM. The findings reveal the cultural influence on the interface design of localized CUM and Course. Accordingly, the Chinese user experience is better on CUM than Course. This research indicates a better UX of localized MOOCs also depends on culture-preferred interface design. Meanwhile, from the perspective of UX, we also provide some theoretical and practical implications for the enhancement of interface designs of localized MOOCs. Hopefully, this research can contribute to the design of localized MOOCs in China.

With the development of visual sensor equipment (e.g., personal smart phones, vehicle cameras, surveillance videos and camcorders), scene recognition technology has attracted much attention due to its latent applications in visual surveillance, intelligent traffic and aerial remote sensing. Although some progress has been made in the field of scene recognition in recent years, the complexity of scene images and the inadequate numbers of labeled data pose challenges in this area. Hence, to effectively fuse the multiple features of each image and employ the information of both labeled and unlabeled images for scene recognition, we proposed a semi-supervised multi-feature regression (SSMFR) model in this paper. The SSMFR model possesses three advantages. First, the model propagates the labels of labeled data to unlabeled data by utilizing graph-based semi-supervised learning techniques so that both the information regarding unlabeled data and labeled data can be exploited to gain better performance. Second, SSMFR employs multiple graphs to characterize the structures of multiple feature spaces and adaptively assigns the weight to different graphs. Therefore, SSMFR can efficiently preserve the manifold structure of samples in each feature space and adequately exploit the complementary information of multiple features. Moreover, SSMFR adopts a $l_{2,1}$ -norm constraint to learn a sparse and robust classifier for scene recognition. To solve the SSMFR model, we proposed a simple and efficient iterative update optimization scheme. Finally, we also proved the convergence of SSMFR by theoretical analysis and experiments. Experiments were conducted on several benchmark scene datasets, and the experimental results demonstrated that the proposed SSMFR model can obtain better performance for scene recognition than some other state-of-the-art algorithms.

Scene recognition is a significant and challenging problem in the field of computer vision. One of the principal bottlenecks in applying machine learning techniques to scene recognition tasks is the requirement of a large number of labeled training data. However, labeling massive training data manually (especially labeling images and videos) is very expensive in terms of human time and effort. In this paper, we present a novel multicriteria-based active discriminative dictionary learning (M-ADDL) algorithm to reduce the human annotation effort and create a robust scene recognition model. The M-ADDL algorithm possesses three advantages. First, M-ADDL introduces an active learning strategy into the discriminative dictionary learning model so that the performance of discriminative dictionary learning can be improved when the number of labeled samples is small. Second, different from most existing active learning methods that measure either the informativeness or representativeness of unlabeled samples to select useful samples for expanding the training dataset, M-ADDL employs both informativeness and representativeness to query useful unlabeled samples and utilizes the manifold-preserving ability of unlabeled samples as an additional sample selection criterion. Finally, a more effective representativeness criterion is presented based on the reconstruction coefficients of the samples. The experimental results of four standard scene recognition databases demonstrate the feasibility and validity of the proposed M-ADDL algorithm.

Face recognition has a great potential to play an important role in computer vision field. However, the majority of face recognition methods are based on the low-level features, which may not yield good results. Inspired by a simple deep learning model principal component analysis network (PCANet), we propose a novel deep learning network called circular symmetrical Gabor filter (2D)2PCA neural networks [CSGF(2D)2PCANet]. Previous models used in face recognition have three major issues of data redundancy, computation time, and no rotation invariance. We introduce the CSGF to address these issues. Two-directional 2-D PCA [(2D)2PCA] is used in feature extraction stage. Binary hashing, blockwise histograms, and linear SVM are used for the output stage. The proposed CSGF (2D)2PCANet learns highlevel features and provides more recognition information during the training phase, which may result in a higher recognition rate when testing the sample. We tested the proposed method on XM2VTS, ORL, AR, Extend Yale B, and LFW databases. Test results show that the CSGF (2D)2PCANet is more robust to the variation of occlusion, illumination, pose, noise, and expression, which is a promising method in face recognition.

In recent years, graph-based dimensionality reduction methods became increasingly more significant since they have been successfully applied in various computer vision and machine learning problems. The key point in graph-based dimensionality reduction methods is how to construct an appropriate graph to reflect the underlying distribution of data. However, most existing methods usually consider graph construction and dimensionality reduction as two separate processes. To overcome this limitation, a multiple locality-constrained graph optimization for dimensionality reduction (MLGODR) algorithm is proposed in this paper. The proposed MLGODR possesses two characteristics. First, MLGODR integrates graph optimization and dimensionality reduction into a unified framework. Thus, a graph that characterizes the distribution of input data and a matrix that projects the input data into a low-dimensional subspace can be learned simultaneously. Second, to better exploit the local structure of input data, a locality constraint that adaptively combines multiple distance measurements is introduced into our objective function. Moreover, an effective updating algorithm is also designed to solve the proposed MLGODR. Extensive experiments are performed on four image databases and four UCI data sets. The experimental results demonstrate that our method outperforms the compared approaches in both classification and cluster tasks.