Analysis on Continuous Monitoring Data for ICU Based on On-Line Segmentation Algorithm

2013 ◽  
Vol 427-429 ◽  
pp. 1489-1492
Author(s):  
Fang Wang
Keyword(s):  
Time Series ◽  
Continuous Monitoring ◽  
Evaluation Method ◽  
Time Series Data ◽  
Segmentation Algorithm ◽  
Monitoring Data ◽  
Series Data ◽  
Recursion Method ◽  
On Line ◽  
Line Segmentation

It is all kinds of data monitoring for ICU that are very important, on the one hand, it can provide reliable reference for medical personnel, so that they can care for critical patients in time, on the other hand, it also can avoid bringing trouble which is caused by instrument to severe patients. Through the mining technology of time series data ,this paper uses online segmentation algorithm of time series, establishing continuous monitoring data model for ICU and creating a time series Table, from the data of which, it can quickly extract monitoring data, and do real-time analysis. On this basis, this paper also puts forward an evaluation method for on-line segmentation algorithm performance , and also puts forward a kind of algorithm to speed up the time sequence segmentation recursion method, which can quickly extract the key components in the data, so as to accelerate the analysis on continuous monitoring data . Finally, through the continuous monitoring and analysis on the pressure of the severe patients who are inserted artificial airway balloon, this paper tests the reliability of the algorithm, and through the analysis and comparison with the data, it proves the quickness of algorithm, and provides a theoretical basis for analysis on continuous monitoring data for ICU.

News Article Based Industry Risk Index Prediction for Industry-Specific Evaluation

2021 ◽  
Author(s):  
Kyungwon Kim ◽  
Kyoungro Yoon
Keyword(s):  
Time Series ◽  
Time Delay ◽  
Evaluation Method ◽  
Time Series Data ◽  
Risk Index ◽  
News Article ◽  
Series Data ◽  
Specific Interest ◽  
Analysis Model ◽  
Long Time

The existing industry evaluation method utilizes the method of collecting the structured information such as the financial information of the companies included in the relevant industry and deriving the industrial evaluation index through the statistical analysis model. This method takes a long time to calculate the structured data and cause the time delay problem. In this paper, to solve this time delay problem, we derive monthly industry-specific interest and likability as a time series data type, which is a new industry evaluation indicator based on unstructured data. In addition, we propose a method to predict the industrial risk index, which is used as an important factor in industrial evaluation, based on derived industry-specific interest and likability time series data.

scholarly journals Adaptive Kernel Quantile Regression for Anomaly Detection

2009 ◽  
Vol 13 (3) ◽  
pp. 230-236
Author(s):  
Hiroyuki Moriguchi ◽  
◽  
Ichiro Takeuchi ◽  
Masayuki Karasuyama ◽  
Shin-ichi Horikawa ◽  
...  
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Quantile Regression ◽  
Time Series Data ◽  
Data Distribution ◽  
Optimal Solution ◽  
Series Data ◽  
Future Time ◽  
Adaptive Kernel ◽  
On Line

In this paper, we study a problem of anomaly detection from time series-data. We use kernel quantile regression (KQR) to predict the extreme (such as 0.01 or 0.99) quantiles of the future time-series data distribution. It enables us to tell whether the probability of observing a certain time-series sequence is larger than, say, 1 percent or not. In this paper, we develop an efficient update algorithm of KQR in order to adapt the KQR in on-line manner. We propose a new algorithm that allows us to compute the optimal solution of the KQR when a new training pattern is inserted or deleted. We demonstrate the effectiveness of our methodology through numerical experiment using real-world time-series data.

scholarly journals Loss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis

2019 ◽  
Vol 11 (12) ◽  
pp. 3489
Author(s):  
Hyungjin Ko ◽  
Jaewook Lee ◽  
Junyoung Byun ◽  
Bumho Son ◽  
Saerom Park
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Data ◽  
Learning Algorithm ◽  
Data Distribution ◽  
Series Data ◽  
Learning Models ◽  
Classification Problems ◽  
Ensemble Models ◽  
On Line

Developing a robust and sustainable system is an important problem in which deep learning models are used in real-world applications. Ensemble methods combine diverse models to improve performance and achieve robustness. The analysis of time series data requires dealing with continuously incoming instances; however, most ensemble models suffer when adapting to a change in data distribution. Therefore, we propose an on-line ensemble deep learning algorithm that aggregates deep learning models and adjusts the ensemble weight based on loss value in this study. We theoretically demonstrate that the ensemble weight converges to the limiting distribution, and, thus, minimizes the average total loss from a new regret measure based on adversarial assumption. We also present an overall framework that can be applied to analyze time series. In the experiments, we focused on the on-line phase, in which the ensemble models predict the binary class for the simulated data and the financial and non-financial real data. The proposed method outperformed other ensemble approaches. Moreover, our method was not only robust to the intentional attacks but also sustainable in data distribution changes. In the future, our algorithm can be extended to regression and multiclass classification problems.

scholarly journals Time Series RUL Estimation of Medium Voltage Connectors to Ease Predictive Maintenance Plans

2020 ◽  
Vol 10 (24) ◽  
pp. 9041
Author(s):  
Álvaro Gómez-Pau ◽  
Jordi-Roger Riba ◽  
Manuel Moreno-Eguilaz
Keyword(s):  
Time Series ◽  
Electrical Resistance ◽  
Time Series Data ◽  
Critical Role ◽  
Remaining Useful Life ◽  
Predictive Maintenance ◽  
Series Data ◽  
Economic Losses ◽  
Medium Voltage ◽  
On Line

The ageing process of medium voltage power connectors can lead to important power system faults. An on-line prediction of the remaining useful life (RUL) is a convenient strategy to prevent such failures, thus easing the application of predictive maintenance plans. The electrical resistance of the connector is the most widely used health indicator for condition monitoring and RUL prediction, even though its measurement is a challenging task because of its low value, which typically falls in the range of a few micro-ohms. At the present time, the RUL of power connectors is not estimated, since their electrical parameters are not monitored because medium voltage connectors are considered cheap and secondary devices in power systems, despite they play a critical role, so their failure can lead to important power flow interruptions with the consequent safety risks and economic losses. Therefore, there is an imperious need to develop on-line RUL prediction strategies. This paper develops an on-line method to solve this issue, by predicting the RUL of medium voltage connectors based on the degradation trajectory of the electrical resistance, which is characterized by analyzing the electrical resistance time series data by means of the autoregressive integrated moving average (ARIMA) method. The approach proposed in this paper allows applying predictive maintenance plans, since the RUL enables determining when the power connector must be replaced by a new one. Experimental results obtained from several connectors illustrate the feasibility and accuracy of the proposed approach for an on-line RUL prediction of power connectors.

Graphical Exploratory Data Analysis for Categorical Longitudinal and Time Series Data

2013 ◽  
Author(s):  
Stephen J. Tueller ◽  
Richard A. Van Dorn ◽  
Georgiy Bobashev ◽  
Barry Eggleston
Keyword(s):  
Time Series ◽  
Data Analysis ◽  
Exploratory Data Analysis ◽  
Time Series Data ◽  
Series Data ◽  
Exploratory Data
Sign in / Sign up

Export Citation Format

Share Document