Data matching is the process of finding, matching, and combining records from many databases or even within one database that belong to the same entities. All parts of the data matching process have been improved during the previous decade as a result of research in various disciplines such as applied statistics, data mining, machine learning, database administration, and digital libraries.Indeed, with the significant advance in artificial intelligence over the past decade, all aspects of the data identification process, especially on how to improve the accuracy of data matching. Firstly, this paper presents the process of comparing data, detailing the steps to perform pre-processing data, comparing the data fields of each record, classification, and quality assessment. Secondly, the paper introduces a method to expand the problem of identifying duplicate objects with big data. Third, the paper also provides specific aspects of unstructured data matching times. Moreover, the methodology of solving big data matching problems by machine learning is proposed. Finally, the proposed method is applied to the problem of database cleanup and identification of identifier abnormalities at the national credit centre CIC with correct results from 96\% to 98\%. The achieved results are not only theoretical but also practical in business operations at CIC.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Accurate electricity load forecasting is essential for operating electrical systems. Most of the studies on electricity load forecasting are based on electricity load data or weather data, which is air temperature, but there are not consider the heat index. This paper proposes a short-term electricity load forecasting model using Long-Short Term Memory (LSTM) based on electricity load history and heat index data. In addition, the proposed model is applied to the data of IEVN NLDC (National Load Dispatching Center) in forecasting electricity load before 48 hours. This model is used to predict the electricity load of the Vietnamese nation and the power corporations of Vietnam. For a fair comparison, the LSTM network has fixed parameters, then compared the results when using temperature and the heat index. According to experimental results based on the Mean absolute percentage errors (MAPE) assessment, the proposed model has better accuracy than the model based on electricity load history and temperature.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.