The vibration signal is easily interfered by noise due to the influence of environment and other factors, which can lead to the poor adaptability, low accuracy of remaining useful life (RUL) prediction, and other problems. To solve this problem, this paper proposes a novel RUL prediction method, which is based on multiscale stacking deep residual shrinkage network (MSDRSN). MSDRSN combines the ability of stacking in improving prediction accuracy and the advantages of deep residual shrinkage network (DRSN) in denoising. First, cumulative sum (CUSUM) from statistics is used to divide the full life cycle of the rolling bearings and discover the points of failure. Second, stacking is used for feature learning on the raw data, multiple convolutional kernels of different scales are selected as base‐learners, and fully connected neural networks are selected as meta‐learners for feature fusion and learning. Then, DRSN is used to do prediction, and the acquired results are fitted with Savitzky–Golay (SG) smoothing. Finally, the effectiveness of the proposed method is proved by the IEEE PHM 2012 data challenge dataset. Compared with the multiscale convolutional neural network with fully connected layer (MSCNN‐FC) and the bidirectional long short‐term memory (BiLSTM) for RUL prediction under the noise. Using the proposed method, the mean absolute error (MSE) of the best result is 0.002 and the mean square error (MSE) is 0.014; meanwhile, the coefficient of determination (R2) of the best prediction result can reach 97.6%. It is also compared with other machine learning methods, and all the results prove the accuracy and effectiveness of the proposed method for RUL prediction applications.

To improve the accuracy of cross-domain object detection, the existing unsupervised domain adaptation (UDA) object detection methods mostly use Feature Pyramid Network (FPN), multiple Region Proposal Network (RPN), and multiple domain classifier, but these methods lead to complex network structures, slow model convergence, and low detection efficiency. To solve the above problems, this paper proposes an Efficient and Accurate Cross-domain Object Detection Method Using One-level Feature and Domain Adaptation (OFDA). This method realizes one-level feature object detection through feature fusion and divide-and-conquer technology; realizes overfitting feature suppression and unsupervised domain adaptation through domain-specific suppression and domain feature alignment technology; realizes background feature suppression through the Objectness branch, which replaces the time-consuming Region Proposal Network (RPN) structure and improves the efficiency of unsupervised adaptive detection. The paper verifies the feasibility and superiority of the proposed method by the comparative experiments and ablation experiments of multiple datasets. The proposed OFDA method not only improves the efficiency of object detection, but also ensures the accuracy of cross-domain detection.

With the rapid development of smart cities, smart buildings are generating a massive amount of building sensing data by the equipped sensors. Indeed, building sensing data provides a promising way to enrich a series of data-demanding and cost-expensive urban mobile applications. In this paper, as a preliminary exploration, we study how to reuse building sensing data to predict traffic volume on nearby roads. Compared with existing studies, reusing building sensing data has considerable merits of cost-efficiency and high-reliability. Nevertheless, it is non-trivial to achieve accurate prediction on such cross-domain data with two major challenges. First, relationships between building sensing data and traffic data are not unknown as prior, and the spatio-temporal complexities impose more difficulties to uncover the underlying reasons behind the above relationships. Second, it is even more daunting to accurately predict traffic volume with dynamic building-traffic correlations, which are cross-domain, non-linear, and time-varying. To address the above challenges, we design and implement BuildSenSys, a first-of-its-kind system for nearby traffic volume prediction by reusing building sensing data. Our work consists of two parts, i.e., Correlation Analysis and Cross-domain Learning. First, we conduct a comprehensive building-traffic analysis based on multi-source datasets, disclosing how and why building sensing data is correlated with nearby traffic volume. Second, we propose a novel recurrent neural network for traffic volume prediction based on cross-domain learning with two attention mechanisms. Specifically, a cross-domain attention mechanism captures the building-traffic correlations and adaptively extracts the most relevant building sensing data at each predicting step. Then, a temporal attention mechanism is employed to model the temporal dependencies of data across historical time intervals. The extensive experimental studies demonstrate that BuildSenSys outperforms all baseline methods with up to 65.3 percent accuracy improvement (e.g., 2.2 percent MAPE) in predicting nearby traffic volume. We believe that this work can open a new gate of reusing building sensing data for urban traffic sensing, thus establishing connections between smart buildings and intelligent transportation.

With the unprecedented demand of location-based services in indoor scenarios, wireless indoor localization is emerging as an essential application for mobile users. While the line-of-sight GPS signal is not available at indoor spaces, WiFi fingerprinting using received signal strength (RSS) has become popular with its ubiquitous accessibility. Although the fingerprinting data can be easily collected by portable mobile devices, to achieve robust and efficient indoor localization remains challenging with two constraints. First, the localization accuracy will be degraded by the random fluctuation of signals that caused by multipath effects from RSS signals. Second, indoor localization algorithms are time-consuming due to the handcrafting features and complex filtering on raw dataset. To achieve high localization accuracy with WiFi fingerprinting, in this paper, we propose CapsLoc, a robust indoor localization system by using capsule networks. Specifically, the capsule network model can efficiently extract hierarchical structures from WiFi fingerprint with three main components, including a convolutional layer, a primary capsule layer and a feature capsule layer. We conduct a real-world experimental field test with over 33600 data points. The experimental results show that CapsLoc can achieve accurate indoor localization with an averaged error of 0.68 m, which outperforms conventional machine learning methods (KNN and SVM) and existing deep learning methods (CNN and SAE-CNN).

Crew scheduling of the passenger dedicated line is the daily work plan of train attendants, and crew scheduling problem is one of the key problems of the train crew management. Considering the actual condition of China's railway and crew rules, a crew scheduling model is established in this paper to minimize rest time between two consecutive shifts in all roundtrips. In order to solve the scheduling model, in this paper a serial-parallel ant colony optimization algorithm (SP-ACO) is provided. The SP-ACO proposed two improvements: (1) a serial-parallel ant grouping strategy, it means that we let every group of ants find the solution one group by one group for reflecting the positive feedback in a generation; (2) the transition method based on the roulette wheel selection, it means that we randomly select between the certain search and the roulette wheel to make the diversity of solutions for avoiding all ants toward the same part of the search space. Finally, two application cases of the scheduling model are represented. The two cases results show that the methods can not only automatically set roundtrips, but also decrease the number of roundtrips, and the results also show that the feasibility of model and the validity of improved ant colony algorithm for crew scheduling.

Extraction-Transformation-Loading (ETL) tools are pieces of software responsible for the extraction of data from several sources, their cleaning, customization and insertion into Data Warehouses (DWs). Complexity, usability and maintainability are the primary problems concerning ETL processes. To deal with these problems, in this paper we provide a dynamic approach for designing, modeling and realizing ETL processes. We propose a new architecture based on Unified Views Model (UVM) for ETL processes, in which Unified view layer is added between source data level and DWs level. The unified views model serves as the means to conform the structure and semantics of the source data to the ones of the data warehouses, and help designers understand and analyze the meaning, relationships and lineage of information. In order to guarantee the transparency access and the usability, two mapping methods are adopted between Unified view level and source data level as well as between DWs level and Unified view level. Based on this architecture, the method of constructing UVM and ETL operations among three levels is given. Then, we describe how to build the conceptual modeling for ETL processes based on UVM by using an extension of the Unified Modeling Language (UML). Finally, we present an ETL tool based on UVM (UVETL) with the goal of facilitating the design, modeling and realization of ETL processes, and give a case study to exemplify the benefits of our proposal.

A novel fast binary pyramid motion estimation (FBPME) algorithm is presented in this paper. The proposed FBPME scheme is based on binary multiresolution layers, exclusive-or (XOR) Boolean block matching, and a N-scale tiling search scheme. Each video frame is converted into a pyramid structure of K-1 binary layers with resolution decimation, plus one integer layer at the lowest resolution. At the lowest resolution layer, the N-scale tiling search is performed to select initial motion vector candidates. Motion vector fields are gradually refined with the XOR Boolean block-matching criterion and the N-scale tiling search schemes in higher binary layers. FBPME performs several thousands times faster than the conventional full-search block-matching scheme at the same PSNR performance and visual quality. It also dramatically reduces the bus bandwidth and on-chip memory requirement. Moreover, hardware complexity is low due to its binary nature. Fully functional software MPEG-2 MP@ML encoders and Advanced Television Standard Committee high definition television encoders based on the FBPME algorithm have been implemented. FBPME hardware architecture has been developed and is being incorporated into single-chip MPEG encoders. A wide range of video sequences at various resolutions has been tested. The proposed algorithm is also applicable to other digital video compression standards such as H.261, H.263, and MPEG4.

A new image sequence coding technique based on robust median-based predictors is presented for the transmission of image sequences over noisy channels. We analyze the robustness of median-based predictors against channel errors. A heuristic algorithm for the design of a robust predictor from a given median-based predictor is presented. It is shown that with small modifications in terms of a necessary requirement for a median-based predictor to be robust against channel errors, the robustness of a given median-based predictor can be considerably improved. Simulations on a real image sequence show significant improvement over the conventional differential pulse code modulation (DPCM) at high bit error rate (BER) using this new technique. The technique does not increase the transmission rate. It is shown that the quality of reconstructed images obtained by robust median-based predictors can be further improved by postprocessing the image using a nonlinear detail-preserving noise-smoothing filter.