
doi: 10.26456/fssc90
В статье описаны результаты разработки алгоритма обнаружения аномалий временных рядов с учетом особенностей предметной области. Алгоритм предполагает нахождение прогноза временных рядов с использованием LSTM-сетей, обнаружение аномалий по полученному прогнозу, фильтрацию найденных аномалий в соответствии с возможными отклонениями значений временного ряда от тренда, отраженными в онтологии, и логический вывод результатов поиска с использованием набора SWRL-правил. Эффективность предложенного подхода подтверждена рядом экспериментов, проводимом на бенчмарке данных по работе нефтяных вышек. The paper describes the results of the development of an algorithm for detecting anomalies in time series, taking into account the specifics of the subject area. The algorithm involves finding a time series forecast using LSTM networks, detecting anomalies based on the obtained forecast, filtering the found anomalies in accordance with possible deviations of the time series values from the trend reflected in the ontology, and logically deriving search results using a set of SWRL rules. The effectiveness of the proposed approach has been confirmed by a number of experiments conducted on the benchmark of data on the operation of oil rigs.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
