Datasets on South Korean manufacturing factories’ electricity consumption and demand response participation

Lee, Eunjung; Baek, Keon; Kim, Jinho

doi:10.1038/s41597-022-01357-8

Cited by 9 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used publicly available data from VitalDB (30) (Vital Signs DataBase), published by Seoul National University Hospital and collected via the Vital Recorder (39), a software for the automated recording of time-synchronised data. VitalDB includes high-resolution multi-parameter data of 6388 non-cardiac surgeries taking place between June 2016 and August 2017.…”

Section: Methodsmentioning

confidence: 99%

“…Here, we propose a Long Short-Term Memory (LSTM, (29)) model to accurately predict the occurrence of imminent IOH events 5 minutes ahead and provide a time-resolved early warning risk score. To achieve this, the analysis uses EHR and physiological time-series data collected from 604 patients undergoing colorectal surgery under general anesthesia from the Vital Signs DataBase (VitalDB), published by Seoul National University Hospital (30). We additionally investigate whether the predictive performance of the baseline model (the model trained on all data) can be improved by training the model on different clusters of patients that have been partitioned according to their clinical characteristics and intra-operative vitals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards personalised early prediction of Intra-Operative Hypotension following anesthesia using Deep Learning and phenotypic heterogeneity

Garmendia¹,

Gkouzionis

Triantafyllidis

et al. 2023

Preprint

View full text Add to dashboard Cite

Intra-Operative Hypotension (IOH) is a haemodynamic abnormality that is commonly observed in operating theatres following general anesthesia with associated life-threatening post-operative complications. Here, we apply Deep Learning (DL) and more specifically Long Short Term Memory (LSTM) models across different patient groups for the classification of IOH events five minutes before onset, using Electronic Health Records (EHR) and time-series intra-operative data of 604 patients that had undergone colorectal surgery. K-means clustering was used to group patients based on pre-clinical data. As part of a sensitivity analysis, the model was also trained on patients clustered according to Mean arterial Blood Pressure (MBP) time-series trends at the start of the operation using K-means with Dynamic Time Warping. The baseline LSTM model trained on all patients yielded an Area Under the Curve (AUC) value of 0.83. In contrast, training the model on smaller sized clusters (grouped by EHR) improved the AUC value (0.85). Similarly, the AUC was increased by 4.8% (0.87) when training the model on clusters grouped by MBP. The encouraging results of the baseline model demonstrate the applicability of the approach in a clinical setting. Furthermore, the increased predictive performance of the model after being trained using a clustering approach first, paves the way for a more personalised patient stratification approach to IOH prediction using clinical data.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Towards personalised early prediction of Intra-Operative Hypotension following anesthesia using Deep Learning and phenotypic heterogeneity

Garmendia¹,

Gkouzionis

Triantafyllidis

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…These characteristics pose challenges for NILM methods in industrial environments, such as high signal processing difficulty, low classification accuracy, and wide application scenarios [6], [7]. In addition, due to the high confidentiality requirement of industrial users for their own production information, public data sets available for NILM training and analysis are very scarce [8]. To reduce the uncertainty caused by the dataset and the underlying algorithm on the experimental results, this paper uses a temporal convolutional network-conditional random field (TCN-CRF) model that can comprehensively consider long-term operation and load state modeling as the baseline model for performance evaluation [9], and conducts experiments using its open-source highfrequency public industrial dataset [10].…”

Section: Training Stagementioning

confidence: 99%

Achieving Sustained Improvement in Identification Accuracy with a Semi-Supervised Learning Approach for NILM Systems

Zhang¹,

Li²,

Guo³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Non-Intrusive Load Monitoring (NILM) systems are widely used for energy management, but their accuracy can be limited by the removal of monitoring equipment after the initial training phase. This removal results in a lack of ongoing training data and impairs the ability to improve recognition accuracy. To address this challenge, this research proposes a novel semi-supervised learning approach for NILM systems. The approach is based on a previously proposed temporal convolutional network-conditional random field (TCN-CRF) model. It uses optimal interval filtering and unanimous voting to control the quality of pseudo-labels. The approach identifies high-precision segments in the sequence-to-sequence algorithm as semi-supervised learning targets and generates pseudo-labels, allowing for continuous self-supervised learning and sustained improvement in recognition accuracy. The results show that the proposed method can effectively combine unlabeled data to improve model accuracy, and achieve up to 14% highest improvement in algorithm accuracy over fully self-supervised methods in small sample training.</p>

show abstract

“…ISO provides utility-scale load data for a total of 46 months from March 1, 2003, to December 31, 2006 in New Zealand 13 . In particular, since core information such as sales and operating conditions of a company can be analyzed from its load data, such kind of data is regarded as a commercial secret and is rarely disclosed 14 . To the best of the authors’ knowledge, public industrial load datasets are limited.…”

Section: Background and Summarymentioning

confidence: 99%

“…A one-year dataset of electricity load curves with a temporal resolution of 15 minutes for 50 small and mid-size enterprises in Germany is released 15 . The electricity data of 10 manufacturing companies is collected at one-minute intervals for seven months from 1 March to 30 September 2019 14 . The electricity consumption data of food and paper industries is presented 16 and machine-level load data of a paper manufacturing factory in Brazil is investigated 17 .…”

Section: Background and Summarymentioning

confidence: 99%

EWELD: A Large-Scale Industrial and Commercial Load Dataset in Extreme Weather Events

Liu,

Bai

et al. 2023

Sci Data

View full text Add to dashboard Cite

Load forecasting is crucial for the economic and secure operation of power systems. Extreme weather events, such as extreme heat and typhoons, can lead to more significant fluctuations in power consumption, making load forecasting more difficult. At present, due to the lack of relevant public data, the research on load forecasting under extreme weather events is still blank, so it is necessary to release a large-scale load dataset containing extreme weather events. The dataset includes electricity consumption data of industrial and commercial users under extreme weather events such as typhoons and extreme heat, which are collected at 15-minute intervals. The data is collected over six years from smart meters installed at the power entry points of users in southern China. The dataset consists of electricity consumption data from 386 industrial and commercial users in 17 industries, with more than 50 million records. During the recording period, extreme weather events such as typhoons and extreme heat are marked to form a total of 5,741 event records.

show abstract

Datasets on South Korean manufacturing factories’ electricity consumption and demand response participation

Cited by 9 publications

References 27 publications

Towards personalised early prediction of Intra-Operative Hypotension following anesthesia using Deep Learning and phenotypic heterogeneity

Towards personalised early prediction of Intra-Operative Hypotension following anesthesia using Deep Learning and phenotypic heterogeneity

Achieving Sustained Improvement in Identification Accuracy with a Semi-Supervised Learning Approach for NILM Systems

EWELD: A Large-Scale Industrial and Commercial Load Dataset in Extreme Weather Events

Contact Info

Product

Resources

About