The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Recently, Φ-OTDR based on optical I/Q demodulation has been proposed as a promising solution for distributed acoustic sensing. This paper characterizes the imbalance of coherent-receiver optical front-end, and analyses its impact on phase demodulation in Φ-OTDR with coherent detection.
Zero-shot learning for visual recognition has received much interest in the most recent years. However, the semantic gap across visual features and their underlying semantics is still the biggest obstacle in zero-shot learning. To fight off this hurdle, we propose an effective Low-rank Embedded Semantic Dictionary learning (LESD) through ensemble strategy. Specifically, we formulate a novel framework...
This paper proposes efficient and powerful deep networks for action prediction from partially observed videos containing temporally incomplete action executions. Different from after-the-fact action recognition, action prediction task requires action labels to be predicted from these partially observed videos. Our approach exploits abundant sequential context information to enrich the feature representations...
This study was applied the decision tree to establish the reference rules to predict the characteristics of different characteristics of labor, extract a series of rules with causal relationship, can determine the high risk of occupational hazards. Data were collected by telephone survey of investigation on employment care disability by Taiwan Ministry of Labor in 2015. Employing a cross-sectional...
Facial makeup style plays a key role in the facial appearance making it more beautiful and attractive. Choosing the best makeup style for a certain face to fit a certain occasion is a full art. Also, foretelling how the face will look like after applying the proposed makeup style requires a high imagination. To solve this problem computationally, an automatic and smart facial makeup recommendation...
With our Families In the Wild (FIW) dataset, which consists of labels 1, 000 families in over 12, 000 family photos, we benchmarked the largest kinship verification experiment to date. FIW, with its quality data and labels for full family trees found worldwide, more accurately is the true, global distribution of blood relatives with a total 378, 300 face pairs of 9 different relationship types. This...
Distributed fiber-optic sensing (DFOS) has drawn great attention in both academic research and industrial applications due to its unique advantages. Recent progress at University of Electronic Science and Technology of China (UESTC) in DFOS, mainly on ultra-long-distance Brillouin optical time-domain analysis (BOTDA) and phase-sensitive optical timedomain reflectometry (Φ-OTDR), is discussed in this...
Domain adaptation has achieved promising results in many areas, such as image classification and object recognition. Although a lot of algorithms have been proposed to solve the task with different domain distributions, it remains a challenge for multi-source unsupervised domain adaptation. In addition, most of the existing algorithms learn a classifier on the source domain and predict the labels...
High-throughput technologies have enabled us to rapidly accumulate a wealth of diverse data types. These multi-view data contain much more information to uncover the cluster structure than single-view data, which draws raising attention in data mining and machine learning areas. On one hand, many features are extracted to provide enough information for better representations, on the other hand, such...
Outlier detection is a key technique in data ming and machine learning fields. The deviating characters of outliers make huge detrimental effects on the learning tasks. A lot of algorithms are therefore proposed to handle outliers from different perspectives, such as distance, density, angle and so on. Among these approaches, the density-based methods achieve better performance, but also suffer from...
As innovation becomes important and complex, researchers started to explore innovation process under the background of Big Data. Technology Delivery System (TDS), a systematic method dynamically showing innovation process, has caused the extensive concern worldwide. As an essential step to construct TDS better, this study aims to identify main delivery actors in TDS based on multi-data sources, then...
This paper presents the results of a detailed experimental investigation of the abnormal vibration of the electric locomotive. A locomotive suffered from serious vibration problem was chosen for the test and its normal operations kept unchanged during the test. The wheel out-of-roundness (OOR) and vibrations of key components including the axle box, the bogie frame and the car body were measured before...
The reliability of electronic devices depends not only on the quality of components but also on the environmental condition, such as the humidity and the density of contaminants. For example, electrostatically enhanced dust deposition typically produces a dendritic deposit which induces a short circuit in adjacent conductors. In order to investigate contaminant deposition mechanisms on a printed circuit...
We present a proposal for distributed measurement of Müller matrix with single-polarized probing light in the optical fiber. The physical principle and corresponding mathematical treatment on the propagation of Rayleigh backscattering light is investigated. Through numerical analysis, it can be demonstrated that the distribution of Müller matrix in the fiber can be acquired with the proposed method...
Block truncation coding (BTC) has been considered as a highly efficient compression technique for decades, but the blocking artifact is its main issue. The halftoning-based BTC has significantly eased this issue, yet an apparent impulse noise artifact is accompanied. In this study, an improved BTC, termed adaptive dot-diffused BTC (ADBTC), is proposed to further improve the visual quality. Also, this...
In this article, a control scheme is designed for the vibration attenuation of an axially moving accelerated/decelerated system. Applying S-curve acceleration/deceleration method and backstepping technique, a boundary control is constructed to stabilize the system and sign function is employed to handle unknown boundary disturbance. The bounded stability of the controlled system is achieved through...
Unsupervised transfer learning has attracted a lot of attention in the big data era, due to its capability of extracting knowledge from large-scale unlabeled samples in multiple data domains. Existing unsupervised transfer learning methods mainly focus on learning a common latent space for source and target domains, while the data representation and subspace structure in target domain are usually...
We present a novel online metric learning model, called scalable large margin online metric learning (SLMOML). SLMOML belongs to the passive-aggressive family of learning models. In the formulation of SLMOML, we use the LogDet divergence to measure the closeness between two continuously learned matrices, which naturally ensures the positive semi-definiteness of the learned matrix at each iteration,...
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...
Transfer learning plays a powerful role in mitigating the discrepancy between test data (target) and auxiliary data (source). There is often the case that multiple sources are available in transfer learning. However, naively combining multiple sources does not lead to valid results, since they will introduce negative transfer as well. Furthermore, each single source from multiple sources may not cover...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.