다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Feature selection, as a data preprocessing strategy, has been proven to be effective and efficient in preparing data (especially high-dimensional data) for various data-mining and machine-learning problems. The objectives of feature selection include building simpler and more comprehensible models, improving data-mining performance, and preparing clean, understandable data. The recent proliferation of big data has presented some substantial challenges and opportunities to feature selection. In this survey, we provide a comprehensive and structured overview of recent advances in feature selection research. Motivated by current challenges and opportunities in the era of big data, we revisit feature selection research from a data perspective and review representative feature selection algorithms for conventional data, structured data, heterogeneous data and streaming data. Methodologically, to emphasize the differences and similarities of most existing feature selection algorithms for conventional data, we categorize them into four main groups: similarity-based, information-theoretical-based, sparse-learning-based, and statistical-based methods. To facilitate and promote the research in this community, we also present an open source feature selection repository that consists of most of the popular feature selection algorithms (http://featureselection.asu.edu/). Also, we use it as an example to show how to evaluate feature selection algorithms. At the end of the survey, we present a discussion about some open problems and challenges that require more attention in future research.

https://dl.acm.org/doi/pdf/10.1145/3136625

Feature Selection: A Data Perspective

3D action recognition – analysis of human actions based on 3D skeleton data – becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recent attempts on this problem suggested to develop RNN-based learning methods to model the contextual dependency in the temporal domain. In this paper, we extend this idea to spatio-temporal domains to analyze the hidden sources of action-related information within the input data over both domains concurrently. Inspired by the graphical structure of the human skeleton, we further propose a more powerful tree-structure based traversal method. To handle the noise and occlusion in 3D skeleton data, we introduce new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell. Our method achieves state-of-the-art performance on 4 challenging benchmark datasets for 3D human action analysis.

/pdf/spatio-temporal-lstm-with-trust-gates-for-3d-human-action-489wyqy43d.pdf

Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition

The large pose discrepancy between two face images is one of the key challenges in face recognition. Conventional approaches for pose-invariant face recognition either perform face frontalization on, or learn a pose-invariant representation from, a non-frontal face image. We argue that it is more desirable to perform both tasks jointly to allow them to leverage each other. To this end, this paper proposes Disentangled Representation learning-Generative Adversarial Network (DR-GAN) with three distinct novelties. First, the encoder-decoder structure of the generator allows DR-GAN to learn a generative and discriminative representation, in addition to image synthesis. Second, this representation is explicitly disentangled from other face variations such as pose, through the pose code provided to the decoder and pose estimation in the discriminator. Third, DR-GAN can take one or multiple images as the input, and generate one unified representation along with an arbitrary number of synthetic images. Quantitative and qualitative evaluation on both controlled and in-the-wild databases demonstrate the superiority of DR-GAN over the state of the art.

/pdf/disentangled-representation-learning-gan-for-pose-invariant-40nfrq6ttb.pdf

Disentangled Representation Learning GAN for Pose-Invariant Face Recognition

In the era of the Internet of Things (IoT), an enormous amount of sensing devices collect and/or generate various sensory data over time for a wide range of fields and applications. Based on the nature of the application, these devices will result in big or fast/real-time data streams. Applying analytics over such data streams to discover new information, predict future insights, and make control decisions is a crucial process that makes IoT a worthy paradigm for businesses and a quality-of-life improving technology. In this paper, we provide a thorough overview on using a class of advanced machine learning techniques, namely deep learning (DL), to facilitate the analytics and learning in the IoT domain. We start by articulating IoT data characteristics and identifying two major treatments for IoT data from a machine learning perspective, namely IoT big data analytics and IoT streaming data analytics. We also discuss why DL is a promising approach to achieve the desired analytics in these types of data and applications. The potential of using emerging DL techniques for IoT data analytics are then discussed, and its promises and challenges are introduced. We present a comprehensive background on different DL architectures and algorithms. We also analyze and summarize major reported research attempts that leveraged DL in the IoT domain. The smart IoT devices that have incorporated DL in their intelligence background are also discussed. DL implementation approaches on the fog and cloud centers in support of IoT applications are also surveyed. Finally, we shed light on some challenges and potential directions for future research. At the end of each section, we highlight the lessons learned based on our experiments and review of the recent literature.

Deep Learning for IoT Big Data and Streaming Analytics: A Survey

According to Barrow and Tenenbaum's theory, an image can be decomposed into two images: a reflectance image and an illumination image. This midlevel description of images attracts more and more attentions recently owing to its application in computer vision, i.e. facial image processing and face recognition. However, due to its ill-posed characteristics, this decomposition remains difficult. In this paper, we concentrate on a slightly easier problem: given a simple frontal facial image and a learned near infrared image, could we recover its reflectance image? Experiments show that it is feasible and promising. Based on extensive study on hyperspectral images, skin color model and Quotient Image, we proposed a method to derive reflectance images through division operations. That is to divide visual frontal face images by learned near infrared images which are generated by super-resolution in tensor space. With the operation on grey distribution of frontal facial images, the results after division can represent the reflectance of skin, rarely bearing any illumination information. Experimental results show that our method is reasonable and promising in image synthesis, processing and face recognition.

Recovering facial intrinsic images from a single input

Removal notice to "VitSeg: Weakly supervised vitiligo segmentation in skin image" [Comput. Med. Imag. Graph. 85 (2020) 101779].

RGB-D action streams have aroused impressive attentions for recognition task, for its geometric characteristic and less influence of illumination. However, there exists large divergences of intra-class actions performed between sub-action, multi-subject and multi-modality, which may affect the result of action recognition. In order to solve these three problems, we propose a Sparse alignment guided Non-negative Tensor Factorization (SaNTF) framework with non-negative tensor factorization (NTF) for subspace learning. SaNTF selects the key frames from two intra-class action sequences by sparse regression, and aligns them to mitigate the diversity in the new tensor subspace. In this paper, the high-dimensional RGB-D action sequence is represented as a third-order tensor to preserve the original spatiotemporal structure, and we employ NTF to find a common tensor subspace for realistic action recognition. The experiments on MSRDailyActivity3D action and MSRPair3D action datasets show the higher accuracy compared with the state-of-the-art temporal alignment methods.

Sparse alignment for video analysis in discriminant Tensor space

Sparse Canonical Temporal Alignment with NTF for RGB-D Action Recognition

Many applications require the collection of data on different variables or measurements over many system performance metrics. We term those broadly as measures or variables. Often data collection along each measure incurs a cost, thus it is desirable to consider the cost of measures in modeling. This is a fairly new class of problems in the area of cost-sensitive learning. A few attempts have been made to incorporate costs in combining and selecting measures. However, existing studies either do not strictly enforce a budget constraint, or are not the `most' cost effective. With a focus on classification problem, we propose a computationally efficient approach that could find a near optimal model under a given budget by exploring the most `promising' part of the solution space. Instead of outputting a single model, we produce a model schedule -- a list of models, sorted by model costs and expected predictive accuracy. This could be used to choose the model with the best predictive accuracy under a given budget, or to trade off between the budget and the predictive accuracy. Experiments on some benchmark datasets show that our approach compares favorably to competing methods.

Ming Shao

Papers

Recovering facial intrinsic images from a single input

Removal notice to "VitSeg: Weakly supervised vitiligo segmentation in skin image" [Comput. Med. Imag. Graph. 85 (2020) 101779].

Sparse alignment for video analysis in discriminant Tensor space

Sparse Canonical Temporal Alignment with NTF for RGB-D Action Recognition

Cost-sensitive Selection of Variables by Ensemble of Model Sequences.