Short-term Wind Speed Forecasting Using Multi-Source Multivariate RNN-LSTMs

Current and accurate site-specific employment data is a critical but vexing element in research on travel behavior patterns and trends in regional economic development. Typically, no single source of data provides comprehensive and reliable coverage for a regional metropolitan area. Developing multiple employment data sources is cumbersome and time-consuming, but a procedural approach can streamline data preparation and management. This study proposes a method to assess and integrate multiple sources of employment data using Google Places API and a business existence verification model. Other techniques, including data deduplication and prioritization, address standardization, and missing employer discovery, are addressed as means to improve data accuracy and coverage.

BackgroundHigh-throughput sequencing data are widely collected and analyzed in the study of complex diseases in quest of improving human health. Well-studied algorithms mostly deal with single data source, and cannot fully utilize the potential of these multi-omics data sources. In order to provide a holistic understanding of human health and diseases, it is necessary to integrate multiple data sources. Several algorithms have been proposed so far, however, a comprehensive comparison of data integration algorithms for classification of binary traits is currently lacking.ResultsIn this paper, we focus on two common classes of integration algorithms, graph-based that depict relationships with subjects denoted by nodes and relationships denoted by edges, and kernel-based that can generate a classifier in feature space. Our paper provides a comprehensive comparison of their performance in terms of various measurements of classification accuracy and computation time. Seven different integration algorithms, including graph-based semi-supervised learning, graph sharpening integration, composite association network, Bayesian network, semi-definite programming-support vector machine (SDP-SVM), relevance vector machine (RVM) and Ada-boost relevance vector machine are compared and evaluated with hypertension and two cancer data sets in our study.In general, kernel-based algorithms create more complex models and require longer computation time, but they tend to perform better than graph-based algorithms. The performance of graph-based algorithms has the advantage of being faster computationally.ConclusionsThe empirical results demonstrate that composite association network, relevance vector machine, and Ada-boost RVM are the better performers. We provide recommendations on how to choose an appropriate algorithm for integrating data from multiple sources.

Selection of genes that are differentially expressed and critical to a particular biological process has been a major challenge in post-array analysis. Recent development in bioinformatics has made various data sources available such as mRNA and miRNA expression profiles, biological pathway and gene annotation, etc. Efficient and effective integration of multiple data sources helps enrich our knowledge about the involved samples and genes for selecting genes bearing significant biological relevance. In this work, we studied a novel problem of multi-source gene selection: given multiple heterogeneous data sources (or data sets), select genes from expression profiles by integrating information from various data sources. We investigated how to effectively employ information contained in multiple data sources to extract an intrinsic global geometric pattern and use it in covariance analysis for gene selection. We designed and conducted experiments to systematically compare the proposed approach with representative methods in terms of statistical and biological significance, and showed the efficacy and potential of the proposed approach with promising findings.

Satellite aerosol products provide valuable large-scale atmospheric information for environment and climate research. Nevertheless, limitations due to cloud contamination and retrieval assumptions often result in significant gaps in Aerosol Optical Depth (AOD) observations, diminishing their representativeness and utility. Therefore, we propose an adaptive spatiotemporal reconstruction method (Spatio-Temporal Reconstruction with Ecw and Auds Method, STREAM) based solely on a single data source, which integrates Empirical Correlation Weighting (ECW) for interpolation with Adaptive Up/Down Scaling (AUDS) for seamless reconstruction. This method was applied to Moderate Resolution Imaging Spectroradiometer (MODIS) Deep Blue (DB) AOD over the North China Plain (NCP) from 2002 to 2023 at a 0.05° resolution. Case comparisons demonstrate that STREAM efficiently fills data gaps, and the STREAM AOD presents strong concordance with both the DB AOD and reference datasets. Cross-validation indicates that as the missing rate rises, the correlation (R) between the STREAM AOD and the DB AOD decreases, while Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) increase. Validation against AERONET data shows that STREAM AOD achieves an R value of 0.88, RMSE of 0.29, and MAE of 0.18 for STREAM AOD, with 52.39% of the data falling within the expected error range. Compared to Long-term Gap-free High-resolution Air Pollutants (LGHAP) AOD, our approach reveals minor discrepancies in values and spatial distribution despite relying on a single data source. The robust performance of STREAM AOD in the NCP highlights potential applicability to utilize in broader regions as well as other atmospheric remote sensing products.

Conventional remote data access middlewares usually provide client applications with either a pre‐staging scheme or an on‐demand access scheme to fetch data. The pre‐staging scheme uses parallel downloads to fetch a completed input file from multiple data sources, even when only a tiny file fragment is required. Such a transfer scheme consumes unnecessary data transmission time and storage space. In contrast, the on‐demand scheme downloads only the required data blocks from a single data source and does not fully utilize the downstream bandwidth of the computing nodes. This paper presents a middleware called ‘Spigot’ that facilitates legacy (grid‐unaware) applications to transparently access remote data by using native I/O function calls. Spigot uses the on‐demand concept to avoid unnecessary data transfer and adopts a co‐allocation download algorithm to improve the data transfer performance. Moreover, it uses the pre‐fetching strategy to reduce the data waiting time by overlapping data acquisition and data processing. It also provides the client application with its own user‐level cache, which is advantageous since a larger cache space is available in comparison with the kernel‐level cache. Further, it is easy to maintain data consistency between Spigot nodes. The experimental results indicate that Spigot achieves superior performance in reducing the data waiting time than the pre‐staging and the on‐demand access schemes. Copyright © 2010 John Wiley & Sons, Ltd.

In recent years, huge different biological databases have been stored in various locations. Using distinct data sets from multiple sources results in more reliable data analysis. However, it is so difficult to combine heterogeneous data in one single server. The most obvious reasons include data privacy, large data sizes, costs, and different geographical locations of data sources. In this paper, we present two new algorithms for clustering data from multiple remote data sources using kernel k-means. The first algorithm is the center-based algorithm built on k-means algorithm. The second algorithm uses distributed kernel k-means over multiple data sources. In the distributed scheme, clustering methods are executed only on their local data sources themselves. Partial clustering results are synched between data sources. To evaluate performance of our proposed algorithms, we merged all data from different sources into one large data set to perform kernel k-means. The results showed that our center-based algorithm greatly reduced transmission data between data sources while still yielding acceptable clustering results. Our distributed kernel k-means algorithm achieved even better performance. The clustering results are very close to those generated by kernel k-means on one merged data set.

In this paper, we focus on the visualization of heterogeneous semantic networks obtained from multiple data sources. A semantic network comprising a set of entities and relationships is often used for representing knowledge derived from textual data or database records. Although the semantic networks created for the same domain at different data sources may cover a similar set of entities, these networks could also be very different because of naming conventions, coverage, view points, and other reasons. Since digital libraries often contain data from multiple sources, we propose a visualization tool to integrate and analyze the differences among multiple social networks. Through a case study on two terrorism-related semantic networks derived from Wikipedia and Terrorism Knowledge Base (TKB) respectively, the effectiveness of our proposed visualization tool is demonstrated.

The role of data source selection in chemical hazard assessment: A case study on organic photovoltaics.

Single source refers to the unified measurement of different aspects of the same individual based on data from multiple sources. In the context of UGC, single source data can be used to study at least two important but as yet insufficiently investigated theoretical issues. First, single source data are ideal sources for studying inter-platform dynamics such as user migration across UGC platforms. Second, single source data can help to link individual self-reported cognitive factors with web crawled individual behavior logs, to achieve better understanding of individual behavior. In this paper, we select a random sample of Sina Blog users and collect their behavior information on both Sina Blog and Sina Weibo platforms; we also conduct an online survey to collect information about their cognitive factors. Merging all data together, we observe and quantify different behavior patterns of the same people across Blog and Weibo; we also identify alternative attractiveness and perceived popularity as significant drivers of one of the most important inter-platform dynamics---switching behavior.

Methods of treatment (case reports)

SNSJam: Road traffic analysis and prediction by fusing data from multiple social networks

Activities related to agricultural cultivation are some of the major human drivers of landscape change on the Earth’s surface. Archaeological remains can provide qualitative evidence for studies of past agricultural development and environmental conditions. The ancient Juyan Oasis, which once flourished along the historic Silk Road, was a typical oasis of downstream inland river basins in the arid zone of northwestern China. Historical records and archaeological discoveries have qualitatively shown that the oasis supported extensive agricultural activities in this historical period from the Han Dynasty to the early Ming Dynasty (B.C. 202-A.D. 1375), which can be traced back to 2,000 years ago. In this study, different types of archaeological remains (including archaeological sites, ground surface artifacts, ancient cultivation ruins, and agricultural irrigation canals) that were obtained and identified from previous archaeological reports, field inspections, and remote sensing imagery were used to determine the spatial extent of the agricultural oasis in the historical period of interest. Our approach used multiple data sources in order to increase the accuracy and reliability of the results compared to previous studies. Our results distinctly suggested that much of the oasis was cultivated during the historical periods considered. Additionally, the arable land area in the historical period considered was roughly estimated to be approximately (3.39–4.75) × 104 ha. These findings regarding the spatial distribution of this ancient agricultural oasis and its arable land were reasonably determined to represent the ancient agricultural development that occurred in the Juyan Oasis better than results obtained from single sources of data.

Humans are complex and their behaviors follow complex multi-modal patterns, however to solve many social computing problems one often looks at complexity in large-scale yet single point data sources or methodologies. While single data/single method techniques, fueled by large scale data, enjoyed some success, it is not without fault. Often with one type of data and method, all the other aspects of human behavior are overlooked, discarded, or, worse, misrepresented. We identify this as two succinct problems. First, social computing problems that cannot be solved using a single data source and need intelligence from multiple modals and, second, social behavior that cannot be fully understood using only one form of methodology. Throughout this talk, we discuss these problems and their implications, illustrate examples, and propose new directives to properly approach in the social computing research in today's age.

Detecting functional modules from protein-protein interaction (PPI) networks is an active research area with many practical applications. However, there is always a critical concern on the false PPI interactions which are derived from the high-throughput experiments and the unsatisfactory results obtained from single PPI network with severe information insufficiency. To address this problem, we propose a Collective Non-negative Matrix Factorization (CoNMF) based soft clustering method which efficiently integrates information of gene ontology (GO), gene expression data and PPI networks. In our method, the three data sources are formed into two graphs with similarity adjacency matrices and these graphs are approximated by a matrix factorization with their common factor which provides the straight-forward interpretation of clustering results. Extensive experiments show that we can improve the module detection performance by integrating multiple biological data sources and that CoNMF yields superior results compared to other multiple data sources fusion methods by identifying a larger number of more precise protein modules with actual biological meaning and certain degree of overlapping.

This paper investigates the application of the Autoregressive Integrated Moving Average (ARIMA) model to predict future trends in Chinese housing prices. The Chinese real estate market, characterized by its volatility, especially during the post-COVID-19 period, presents a complex environment for buyers and investors. The paper investigates how the ARIMA model is employed to make informed predictions in this uncertain market. Although it has some limitations, such as a heavy reliance on historical data and insensitivity to unexpected macroeconomic shifts, the ARIMA model offers a structure for understanding and anticipating housing price trends. The paper integrates various data sources, including long-term housing price statistics, to build a comprehensive ARIMA model tailored to the nuances of China’s housing market. This essay demonstrates the ARIMA model's utility in aiding stakeholders to make more confident and informed decisions in an increasingly complex and unpredictable market. The analysis further suggests refinements to the ARIMA model, considering the multifaceted nature of the housing market, influenced by macroeconomic factors and public perception. The final goal is to enhance the model's accuracy and reliability, making it an indispensable tool in economic and policy decision-making in China's evolving real estate landscape.