scholarly journals Online Semisupervised Learning Approach for Quality Monitoring of Complex Manufacturing Process

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Weng Weiwei ◽  
Mahardhika Pratama ◽  
Andri Ashfahani ◽  
Edward Yapp Kien Yee
Keyword(s):  
Time Series Data ◽  
Random Access ◽  
Ground Truth ◽  
Semisupervised Learning ◽  
Streaming Data ◽  
Quality Monitoring ◽  
Data Driven ◽  
Series Data ◽  
Learning Approach ◽  
Molding Machine

Data-driven quality monitoring is highly demanded in practice since it enables relieving manual quality inspection of the product quality. Conventional data-driven quality monitoring is constrained by its offline characteristic thus being unable to handle streaming nature of sensory data and nonstationary environments of machine operations. Recently, there have been pioneering works of online quality monitoring taking advantage of online learning concepts in the literature, but it is still far from realization of minimum operator intervention in the quality monitoring because it calls for full supervision in labelling data samples. This paper proposes Parsimonious Network++ (ParsNet++) as an online semisupervised learning approach being able to handle extreme label scarcity in the quality monitoring task. That is, it is capable of coping with varieties of semisupervised learning conditions including random access of ground truth and infinitely delayed access of ground truth. ParsNet++ features the one-pass learning approach to deal with streaming data while characterizing elastic structure to overcome rapidly changing data distributions. That is, it is capable of initiating its learning structure from scratch with the absence of a predefined network structure where its hidden nodes can be added and discarded on the fly in respect to drifting data distributions. Furthermore, it is equipped by a feature extraction layer in terms of 1D convolutional layer extracting natural features of multivariate time-series data samples of sensors and coping well with the many-to-one label relationship, a common problem of practical quality monitoring. Rigorous numerical evaluation has been carried out using the injection molding machine and the industrial transfer molding machine from our own projects. ParsNet++ delivers highly competitive performance even compared to fully supervised competitors.

scholarly journals Towards Providing Effective Data-Driven Responses to Predict the Covid-19 in São Paulo and Brazil

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 540
Author(s):  
Fabio Amaral ◽  
Wallace Casaca ◽  
Cassio M. Oishi ◽  
José A. Cuminato
Keyword(s):  
Learning Strategies ◽  
Time Series Data ◽  
Sao Paulo ◽  
The State ◽  
Data Driven ◽  
Series Data ◽  
São Paulo ◽  
Time Data ◽  
Unified Framework ◽  
Infected People

São Paulo is the most populous state in Brazil, home to around 22% of the country’s population. The total number of Covid-19-infected people in São Paulo has reached more than 1 million, while its total death toll stands at 25% of all the country’s fatalities. Joining the Brazilian academia efforts in the fight against Covid-19, in this paper we describe a unified framework for monitoring and forecasting the Covid-19 progress in the state of São Paulo. More specifically, a freely available, online platform to collect and exploit Covid-19 time-series data is presented, supporting decision-makers while still allowing the general public to interact with data from different regions of the state. Moreover, a novel forecasting data-driven method has also been proposed, by combining the so-called Susceptible-Infectious-Recovered-Deceased model with machine learning strategies to better fit the mathematical model’s coefficients for predicting Infections, Recoveries, Deaths, and Viral Reproduction Numbers. We show that the obtained predictor is capable of dealing with badly conditioned data samples while still delivering accurate 10-day predictions. Our integrated computational system can be used for guiding government actions mainly in two basic aspects: real-time data assessment and dynamic predictions of Covid-19 curves for different regions of the state. We extend our analysis and investigation to inspect the virus spreading in Brazil in its regions. Finally, experiments involving the Covid-19 advance in other countries are also given.

scholarly journals Estimating infection-related human mobility networks based on time series data of COVID-19 infection in Japan

2021 ◽  
Author(s):  
Tetsuya Yamada ◽  
Shoi Shi
Keyword(s):  
Time Series ◽  
Infectious Diseases ◽  
Time Series Data ◽  
Human Mobility ◽  
Emerging Infectious Diseases ◽  
Human Movement ◽  
Data Driven ◽  
Disease Spread ◽  
Series Data ◽  
Data Infrastructure

Comprehensive and evidence-based countermeasures against emerging infectious diseases have become increasingly important in recent years. COVID-19 and many other infectious diseases are spread by human movement and contact, but complex transportation networks in 21 century make it difficult to predict disease spread in rapidly changing situations. It is especially challenging to estimate the network of infection transmission in the countries that the traffic and human movement data infrastructure is not yet developed. In this study, we devised a method to estimate the network of transmission of COVID-19 from the time series data of its infection and applied it to determine its spread across areas in Japan. We incorporated the effects of soft lockdowns, such as the declaration of a state of emergency, and changes in the infection network due to government-sponsored travel promotion, and predicted the spread of infection using the Tokyo Olympics as a model. The models used in this study are available online, and our data-driven infection network models are scalable, whether it be at the level of a city, town, country, or continent, and applicable anywhere in the world, as long as the time-series data of infections per region is available. These estimations of effective distance and the depiction of infectious disease networks based on actual infection data are expected to be useful in devising data-driven countermeasures against emerging infectious diseases worldwide.

A data-driven stochastic parametrisation of intermittent turbulence in the stably stratified atmospheric boundary layer

2021 ◽  
Author(s):  
Vyacheslav Boyko ◽  
Sebastian Krumscheid ◽  
Nikki Vercauteren
Keyword(s):  
Boundary Layer ◽  
Time Series Data ◽  
Stable Stratification ◽  
Data Driven ◽  
Series Data ◽  
Similarity Function ◽  
Intermittent Turbulence ◽  
Stochastic Perturbations ◽  
Model Based Clustering ◽  
Flux Gradient

<p>We present results on the modelling of intermittent turbulence in the nocturnal boundary layer using a data-driven approach. In conditions of high stratification and weak wind, the bulk shear can be too weak to sustain continuous turbulence, and the sporadic submeso motions play an important role for the turbulence production. We show a way to stochastically parametrise the effect of the unresolved submeso scales and include it into a 1.5-order turbulence closure scheme. This is achieved by introducing a stochastic equation, which describes the evolution of the non-dimensional flux-gradient stability correction for momentum ($\phi_m$). The unperturbed equilibrium solution of the equation follows the functional form of the universal similarity function. The stochastic perturbations reflect the instantaneous excursions from its equilibrium state, and the distribution of values covers the scatter found in observations at high stability.</p><p>The non-stationary parameters of this equations are estimated from a time-series data of the FLOSS2 experiment using a model-based clustering approach. The clustering analysis of the parameters shows a scaling relationship with the local gradient Ri number, leading to a suggested closed-form model for the stochastic flux-gradient stability correction. The spatial correlation in height of the perturbations is included in the model as well. The resulting equation captures the transition of the stability correction across and beyond the critical Ri up to a value of 10. The out-of-sample prediction shows a valid transient dynamics into and within the regime of strongly-stable stratification.</p>

scholarly journals Partial Correlation-Based Attention for Multivariate Time Series Forecasting

2020 ◽  
Vol 34 (10) ◽  
pp. 13720-13721
Author(s):  
Won Kyung Lee
Keyword(s):  
Time Series ◽  
Partial Correlation ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Time Series Forecasting ◽  
Data Driven ◽  
Series Data ◽  
Time Lags ◽  
Dependency Structure ◽  
Agnostic Learning

A multivariate time-series forecasting has great potentials in various domains. However, it is challenging to find dependency structure among the time-series variables and appropriate time-lags for each variable, which change dynamically over time. In this study, I suggest partial correlation-based attention mechanism which overcomes the shortcomings of existing pair-wise comparisons-based attention mechanisms. Moreover, I propose data-driven series-wise multi-resolution convolutional layers to represent the input time-series data for domain agnostic learning.

scholarly journals A Hybrid Deep Learning Framework for Unsupervised Anomaly Detection in Multivariate Spatio-Temporal Data

2020 ◽  
Vol 10 (15) ◽  
pp. 5191
Author(s):  
Yıldız Karadayı ◽  
Mehmet N. Aydin ◽  
A. Selçuk Öğrenci
Keyword(s):  
Deep Learning ◽  
Anomaly Detection ◽  
Hurricane Katrina ◽  
Time Series Data ◽  
Hybrid Approach ◽  
Ground Truth ◽  
Outbreak Detection ◽  
Series Data ◽  
Detection Techniques ◽  
Spatio Temporal

Multivariate time-series data with a contextual spatial attribute have extensive use for finding anomalous patterns in a wide variety of application domains such as earth science, hurricane tracking, fraud, and disease outbreak detection. In most settings, spatial context is often expressed in terms of ZIP code or region coordinates such as latitude and longitude. However, traditional anomaly detection techniques cannot handle more than one contextual attribute in a unified way. In this paper, a new hybrid approach based on deep learning is proposed to solve the anomaly detection problem in multivariate spatio-temporal dataset. It works under the assumption that no prior knowledge about the dataset and anomalies are available. The architecture of the proposed hybrid framework is based on an autoencoder scheme, and it is more efficient in extracting features from the spatio-temporal multivariate datasets compared to the traditional spatio-temporal anomaly detection techniques. We conducted extensive experiments using buoy data of 2005 from National Data Buoy Center and Hurricane Katrina as ground truth. Experiments demonstrate that the proposed model achieves more than 10% improvement in accuracy over the methods used in the comparison where our model jointly processes the spatial and temporal dimensions of the contextual data to extract features for anomaly detection.

scholarly journals A deep learning approach for anomaly detection with industrial time series data: a refrigerators manufacturing case study

2019 ◽  
Vol 38 ◽  
pp. 233-240 ◽  
Author(s):  
Mattia Carletti ◽  
Chiara Masiero ◽  
Alessandro Beghi ◽  
Gian Antonio Susto
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Series Data ◽  
Learning Approach

scholarly journals A Hybrid Learning Approach to Prognostics and Health Management Applied to Military Ground Vehicles Using Time-Series and Maintenance Event Data

2020 ◽  
Vol 12 (1) ◽  
pp. 10
Author(s):  
W Glenn Bond ◽  
Haley Dozier ◽  
Thomas L Arnold ◽  
Michael Y Lam ◽  
Quyen T Dong ◽  
...  
Keyword(s):  
Time Series ◽  
Data Analytics ◽  
High Performance ◽  
Time Series Data ◽  
Data Driven ◽  
Series Data ◽  
Event Data ◽  
Ground Vehicles ◽  
Operational Data ◽  
Operational Time

Attempts to leverage operational time-series data in Condition Based Maintenance (CBM) approaches to optimize the life cycle management and Reliability, Availability, and Maintainability (RAM) of military vehicles have encountered several obstacles over decades of data collection. These obstacles have beset similar approaches on civilian ground vehicles, as well as on aircraft and other complex systems. Analysis of operational data is critical because it represents a continuous recording of the state of the system. Applying rudimentary data analytics to operational data can provide insights like fuel usage patterns or observed reliability of one vehicle or even a fleet. Monitoring trends and analyzing patterns in this data over time, however, can provide insight into the health of a vehicle, a complex system, or a fleet, predicting mean time to failure or compiling logistic or life cycle needs. Such High-Performance Data Analytics (HPDA) on operational time-series datasets has been historically difficult due to the large amount of data gathered from vehicle sensors, the lack of association between clusters observed in the data and failures or unscheduled maintenance events, and the deficiency of unsupervised learning techniques for time-series data. We present an HPDA environment and a method of discovering patterns in vehicle operational data that determines models for predicting the likelihood of imminent failure, referred to as Parameter-Based Indicators (PBIs). Our method is a data-driven approach that uses both time-series and relational maintenance data. This hybrid approach combines both supervised and unsupervised machine learning and data analytic techniques to correlate labeled, relational maintenance event data with unlabeled operational time-series data utilizing the DoD High Performance Computing (HPC) capabilities at the U.S. Army Engineer Research and Development Center. In leveraging both time-series and relational data, we demonstrate a means of fast, purely data-driven model creation that is more broadly applicable and requires less a priori information than physics informed, data-driven models. By blending these approaches, this system will be able to relate some lifecycle management goals through the workflow to generate specific PBIs that will predict failures or highlight appropriate areas of concern in individual or collective vehicle histories.

scholarly journals Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System

2021 ◽  
Vol 9 ◽  
Author(s):  
Moritz Stüber ◽  
Felix Scherhag ◽  
Matthieu Deru ◽  
Alassane Ndiaye ◽  
Muhammad Moiz Sakha ◽  
...  
Keyword(s):  
Smart Grids ◽  
Time Series Data ◽  
Short Term Memory ◽  
Data Driven ◽  
Series Data ◽  
Small Scale ◽  
Pv System ◽  
Advantages And Disadvantages ◽  
Forecast Quality

In the context of smart grids, the need for forecasts of the power output of small-scale photovoltaic (PV) arrays increases as control processes such as the management of flexibilities in the distribution grid gain importance. However, there is often only very little knowledge about the PV systems installed: even fundamental system parameters such as panel orientation, the number of panels and their type, or time series data of past PV system performance are usually unknown to the grid operator. In the past, only forecasting models that attempted to account for cause-and-effect chains existed; nowadays, also data-driven methods that attempt to recognize patterns in past behavior are available. Choosing between physics-based or data-driven forecast methods requires knowledge about the typical forecast quality as well as the requirements that each approach entails. In this contribution, the achieved forecast quality for a typical scenario (day-ahead, based on numerical weather predictions [NWP]) is evaluated for one physics-based as well as five different data-driven forecast methods for a year at the same site in south-western Germany. Namely, feed-forward neural networks (FFNN), long short-term memory (LSTM) networks, random forest, bagging and boosting are investigated. Additionally, the forecast quality of the weather forecast is analyzed for key quantities. All evaluated PV forecast methods showed comparable performance; based on concise descriptions of the forecast approaches, advantages and disadvantages of each are discussed. The approaches are viable even though the forecasts regularly differ significantly from the observed behavior; the residual analysis performed offers a qualitative insight into the achievable forecast quality in a typical real-world scenario.

scholarly journals Deep Learning and Autoregressive Approach for Prediction of Time Series Data

2021 ◽  
Vol 3 (2) ◽  
pp. 1
Author(s):  
Akhter Mohiuddin Rather
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Deep Learning ◽  
Statistical Models ◽  
Time Complexity ◽  
Time Series Data ◽  
Series Data ◽  
Learning Approach ◽  
Proposed Model ◽  
Artificial Neural

Fractional This paper proposes a deep learning approach for prediction of nonstationary data. A new regression scheme has been used in the proposed model. Any non-stationary data can be used to test the efficiency of the proposed model, however in this work stock data has been used due to the fact that stock data has a property of being nonlinear or non-stationary in nature. Beside using proposed model, predictions were also obtained using some statistical models and artificial neural networks. Traditional statistical models did not yield any expected results; artificial neural networks resulted into high time complexity. Therefore, deep learning approach seemed to be the best method as of today in dealing with such problems wherein time complexity and excellent predictions are of concern.

scholarly journals Smart Helmet: Thresh-Learner–Online Machine Learning on Data Streams

2019 ◽  
Vol 9 (1S3) ◽  
pp. 466-473
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Real Life ◽  
General Purpose ◽  
Streaming Data ◽  
Series Data ◽  
Dynamic Threshold ◽  
Wide Range ◽  
Set Up

Today, with an enormous generation and availability of time series data and streaming data, there is an increasing need for an automatic analyzing architecture to get fast interpretations and results. One of the significant potentiality of streaming analytics is to train and model each stream with unsupervised Machine Learning (ML) algorithms to detect anomalous behaviors, fuzzy patterns, and accidents in real-time. If executed reliably, each anomaly detection can be highly valuable for the application. In this paper, we propose a dynamic threshold setting system denoted as Thresh-Learner, mainly for the Internet of Things (IoT) applications that require anomaly detection. The proposed model enables a wide range of real-life applications where there is a necessity to set up a dynamic threshold over the streaming data to avoid anomalies, accidents or sending alerts to distant monitoring stations. We took the major problem of anomalies and accidents in coal mines due to coal fires and explosions. This results in loss of life due to the lack of automated alarming systems. We propose Thresh-Learner, a general purpose implementation for setting dynamic thresholds. We illustrate it through the Smart Helmet for coal mine workers which seamlessly integrates monitoring, analyzing and dynamic thresholds using IoT and analysis on the cloud.

Sign in / Sign up

Export Citation Format

Share Document