Jia Wei

Bio: Jia Wei is an academic researcher from South China University of Technology. The author has contributed to research in topics: Dimensionality reduction & Graph (abstract data type). The author has an hindex of 18, co-authored 129 publications receiving 1082 citations. Previous affiliations of Jia Wei include Beijing University of Technology & Beijing Institute of Technology.

End-to-End Incomplete Time-Series Modeling From Linear Memory of Latent Variables

Abstract: Time series with missing values (incomplete time series) are ubiquitous in real life on account of noise or malfunctioning sensors. Time-series imputation (replacing missing data) remains a challenge due to the potential for nonlinear dependence on concurrent and previous values of the time series. In this paper, we propose a novel framework for modeling incomplete time series, called a linear memory vector recurrent neural network (LIME-RNN), a recurrent neural network (RNN) with a learned linear combination of previous history states. The technique bears some similarity to residual networks and graph-based temporal dependency imputation. In particular, we introduce a linear memory vector [called the residual sum vector (RSV)] that integrates over previous hidden states of the RNN, and is used to fill in missing values. A new loss function is developed to train our model with time series in the presence of missing values in an end-to-end way. Our framework can handle imputation of both missing-at-random and consecutive missing inputs. Moreover, when conducting time-series prediction with missing values, LIME-RNN allows imputation and prediction simultaneously. We demonstrate the efficacy of the model via extensive experimental evaluation on univariate and multivariate time series, achieving state-of-the-art performance on synthetic and real-world data. The statistical results show that our model is significantly better than most existing time-series univariate or multivariate imputation methods.

Deep learning for time series classification: a review

Abstract: Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.

Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment

Abstract: We present a new algorithm for manifold learning and nonlinear dimensionality reduction. Based on a set of unorganized da-ta points sampled with noise from a parameterized manifold, the local geometry of the manifold is learned by constructing an approxi-mation for the tangent space at each point, and those tangent spaces are then aligned to give the global coordinates of the data pointswith respect to the underlying manifold. We also present an error analysis of our algorithm showing that reconstruction errors can bequite small in some cases. We illustrate our algorithm using curves and surfaces both in 2D/3D Euclidean spaces and higher dimension-al Euclidean spaces. We also address several theoretical and algorithmic issues for further research and improvements.

Functional metal–organic frameworks as effective sensors of gases and volatile compounds

Abstract: Developing efficient sensor materials with superior performance for selective, fast and sensitive detection of gases and volatile organic compounds (VOCs) is essential for human health and environmental protection, through monitoring indoor and outdoor air pollutions, managing industrial processes, controlling food quality and assisting early diagnosis of diseases. Metal–organic frameworks (MOFs) are a unique type of crystalline and porous solid material constructed from metal nodes (metal ions or clusters) and functional organic ligands. They have been investigated extensively for possible use as high performance sensors for the detection of many different gases and VOCs in recent years, due to their large surface area, tunable pore size, functionalizable sites and intriguing properties, such as electrical conductivity, magnetism, ferroelectricity, luminescence and chromism. The high porosity of MOFs allows them to interact strongly with various analytes, including gases and VOCs, thus resulting in easily measurable responses to different physicochemical parameters. Although much of the recent work on MOF-based luminescent sensors have been summarized in several excellent reviews (up to 2018), a comprehensive overview of these materials for sensing gases and VOCs based on chemiresistive, magnetic, ferroelectric, and colorimertic mechanisms is missing. In this review, we highlight the most recent progress in developing MOF sensing and switching materials with an emphasis on sensing mechanisms based on electricity, magnetism, ferroelectricity and chromism. We provide a comprehensive analysis on the MOF–analyte interactions in these processes, which play a key role in the sensing performance of the MOF-based sensors and switches. We discuss in detail possible applications of MOF-based sensing and switching materials in detecting oxygen, water vapor, toxic industrial gases (such as hydrogen sulfide, ammonia, sulfur dioxide, nitrous oxide, carbon oxides and carbon disulfide) and VOCs (such as aromatic and aliphatic hydrocarbons, ketones, alcohols, aldehydes, chlorinated hydrocarbons and N,N′-dimethylformamide). Overall, this review serves as a timely source of information and provides insight for the future development of advanced MOF materials as next-generation gas and VOC sensors.