Analysis of Variational Autoencoders for Imputing Missing Values from Sensor Data of Marine Systems

Objective: Data being missed is an unavoidable problem in cohort studies. This paper compares the imputation effect of eight common missing data imputation methods involved in cutting longitudinal data through simulation study to provide a valuable reference for the treatment of missing data in longitudinal studies. Methods: The simulation study is based on R language software and generates missing longitudinal data by the Monte Carlo method. By comparing the average absolute deviation, average relative deviation, and TypeⅠerror from the regression analysis of different imputation methods, the imputation effect of varying imputation methods on missing longitudinal data and the influence on subsequent multivariate analysis are evaluated. Results: The mean imputation, k nearest neighbor (KNN), regression imputation, and random forest all have a similar imputation effect, which is also steady. However, the hot deck is inferior to the above imputation methods. K-means clustering and expectation maximization (EM) algorithm are among the worst and unstable. Mean imputation, EM algorithm, random forest, KNN, and regression imputation can control TypeⅠerror. Still, multiple imputations, hot deck, and K-means clustering cannot effectively manage the TypeⅠerror. Conclusions: For missing data in longitudinal studies, mean imputation, KNN, regression imputation, and random forest can be used as better imputation methods under the mechanism of missing at random. When the missing ratio is not too large, multiple imputations and hot deck can also perform well, but K-means clustering and EM algorithm are not recommended.

Enhanced Fault Diagnosis in IoT: Uniting Data Fusion with Deep Multi-Scale Fusion Neural Network

BackgroundMissing data are a common problem in prospective studies with a long follow-up, and the volume, pattern and reasons for missing data may be relevant when estimating the cost of illness. We aimed to evaluate the effects of different methods for dealing with missing longitudinal cost data and for costing caregiver time on total societal costs in Alzheimer’s disease (AD).MethodsGERAS is an 18-month observational study of costs associated with AD. Total societal costs included patient health and social care costs, and caregiver health and informal care costs. Missing data were classified as missing completely at random (MCAR), missing at random (MAR) or missing not at random (MNAR). Simulation datasets were generated from baseline data with 10–40 % missing total cost data for each missing data mechanism. Datasets were also simulated to reflect the missing cost data pattern at 18 months using MAR and MNAR assumptions. Naïve and multiple imputation (MI) methods were applied to each dataset and results compared with complete GERAS 18-month cost data. Opportunity and replacement cost approaches were used for caregiver time, which was costed with and without supervision included and with time for working caregivers only being costed.ResultsTotal costs were available for 99.4 % of 1497 patients at baseline. For MCAR datasets, naïve methods performed as well as MI methods. For MAR, MI methods performed better than naïve methods. All imputation approaches were poor for MNAR data. For all approaches, percentage bias increased with missing data volume. For datasets reflecting 18-month patterns, a combination of imputation methods provided more accurate cost estimates (e.g. bias: −1 % vs −6 % for single MI method), although different approaches to costing caregiver time had a greater impact on estimated costs (29–43 % increase over base case estimate).ConclusionsMethods used to impute missing cost data in AD will impact on accuracy of cost estimates although varying approaches to costing informal caregiver time has the greatest impact on total costs. Tailoring imputation methods to the reason for missing data will further our understanding of the best analytical approach for studies involving cost outcomes.Electronic supplementary materialThe online version of this article (doi:10.1186/s12874-016-0188-1) contains supplementary material, which is available to authorized users.

This study uses a wind turbine case study as a subdomain of Industrial Internet of Things (IIoT) to showcase an architecture for implementing a distributed digital twin in which all important aspects of a predictive maintenance solution in a DT use a fog computing paradigm, and the typical predictive maintenance DT is improved to offer better asset utilization and management through real-time condition monitoring, predictive analytics, and health management of selected components of wind turbines in a wind farm. Digital twin (DT) is a technology that sits at the intersection of Internet of Things, Cloud Computing, and Software Engineering to provide a suitable tool for replicating physical objects in the digital space. This can facilitate the implementation of asset management in manufacturing systems through predictive maintenance solutions leveraged by machine learning (ML). With DTs, a solution architecture can easily use data and software to implement asset management solutions such as condition monitoring and predictive maintenance using acquired sensor data from physical objects and computing capabilities in the digital space. While DT offers a good solution, it is an emerging technology that could be improved with better standards, architectural framework, and implementation methodologies. Researchers in both academia and industry have showcased DT implementations with different levels of success. However, DTs remain limited in standards and architectures that offer efficient predictive maintenance solutions with real-time sensor data and intelligent DT capabilities. An appropriate feedback mechanism is also needed to improve asset management operations.

Enabled by the increasing availability of sensor data monitored from production machinery, condition monitoring and predictive maintenance methods are key pillars for an efficient and robust manufacturing production cycle in the Industrial Internet of Things. The employment of machine learning models to detect and predict deteriorating behavior by analyzing a variety of data collected across several industrial environments shows promising results in recent works, yet also often requires transferring the sensor data to centralized servers located in the cloud. Moreover, although collaborating and sharing knowledge between industry sites yields large benefits, especially in the area of condition monitoring, it is often prohibited due to data privacy issues. To tackle this situation, we propose an Autoencoder-based Federated Learning method utilizing vibration sensor data from rotating machines, that allows for a distributed training on edge devices, located on-premise and close to the monitored machines. Preserving data privacy and at the same time exonerating possibly unreliable network connections of remote sites, our approach enables knowledge transfer across organizational boundaries, without sharing the monitored data. We conducted an evaluation utilizing two real-world datasets as well as multiple testbeds and the results indicate that our method enables a competitive performance compared to previous results, while significantly reducing the resource and network utilization.

FFQs are a popular method of capturing dietary information in epidemiological studies and may be used to derive dietary exposures such as nutrient intake or overall dietary patterns and diet quality. As FFQs can involve large numbers of questions, participants may fail to respond to all questions, leaving researchers to decide how to deal with missing data when deriving intake measures. The aim of the present commentary is to discuss the current practice for dealing with item non-response in FFQs and to propose a research agenda for reporting and handling missing data in FFQs. Single imputation techniques, such as zero imputation (assuming no consumption of the item) or mean imputation, are commonly used to deal with item non-response in FFQs. However, single imputation methods make strong assumptions about the missing data mechanism and do not reflect the uncertainty created by the missing data. This can lead to incorrect inference about associations between diet and health outcomes. Although the use of multiple imputation methods in epidemiology has increased, these have seldom been used in the field of nutritional epidemiology to address missing data in FFQs. We discuss methods for dealing with item non-response in FFQs, highlighting the assumptions made under each approach. Researchers analysing FFQs should ensure that missing data are handled appropriately and clearly report how missing data were treated in analyses. Simulation studies are required to enable systematic evaluation of the utility of various methods for handling item non-response in FFQs under different assumptions about the missing data mechanism.

Recent heightened enthusiasm towards Industrial Artificial Intelligence (IAI) and Industrial Internet of Things (IIoT) coupled with developments in smart sensor technologies have resulted in simultaneous incorporation of several advanced Condition Monitoring (CM) technologies within manufacturing and industrial sectors. Efficient utilization of CM data leads to enhanced safety, reliability and availability of manufacturing systems. In this regard, the paper proposes an efficient and novel hybrid Maintenance Decision Support System (MDSS) for fault diagnostic and prognostic considering CM data along with event- triggered data. The proposed MDSS model is a hybrid Machine Learning (ML)-based solution coupled with statistical techniques. In order to find an optimal maintenance policy, we concentrate the attention on a time-dependent Proportional Hazards Model (PHM) augmented with a semi-supervised ML approach. The developed hybrid model is capable of inferring and fusing High-Dimensional and Multi-modal Streaming (HDMS) data sources in an adaptive and autonomous fashion to recommend optimal maintenance decisions without human intervention. To illustrate the complete structure of the proposed MDSS, experimental evaluations are designed based on a dataset provided by NASA containing run-to-failure and CM data associated with aircraft engines. The effectiveness of the proposed model is demonstrated through a comprehensive set of comparisons with different ML algorithms.

This article presents an idea of achieving reliability through Industrial Internet of Things (IIoT) for industrial power systems. It proposes hybrid approach for predictive and corrective maintenance. It discusses the self-corrective maintenance (SCM) paradigm as hybrid approach for industrial power systems along with condition-based maintenance approach utilizing IIoT to achieve it. As it is well known that industries pay huge penalty for the down time, and suffer to meet reliability demands for years. Study witnesses its cost in millions of dollars yearly for production disruptions. It can be prevented by proactively following the aggressive maintenance schedule. However, it often becomes expensive as part or service may not be utilized for its full life and failure may occur even in middle of maintenance cycle. On the other hand, condition-based maintenance (CBM) helps utilize the full life and prevents the downtime by predicting the failures ahead. This article reviews current maintenance practices followed by industry leaders and a proposal on self-corrective maintenance based on condition of restorable resources. It is about learning the condition of subsystems by itself and taking corrective action when subsystem is not active. This concept helps reduce manual intervention to correct the problem as well as the maintenance cost. This research also covers the self-uncorrectable issues to be handled by proactively following CBM process through IIoT. This hybrid proposal could be a significant gear shift in maintenance direction for general industry as well as power systems. It can be termed as industry's 5 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> revolution or Industry 5.0.

The lubricant condition monitoring industry is entering a technology-enabled frontier. Sensor data are more accessible via the industrial Internet of things and scrutinized more closely with the help of artificial intelligence. Meanwhile, human-enabled inspections are often overlooked despite the unmatched capabilities of human inspectors. Like other lubricant condition monitoring strategies, human-enabled inspections need guidance. By developing a set of standards, condition monitoring professionals can ensure the right observations are made and followed with the right corrective actions. Otherwise, these efforts can end up counterproductive and waste resources. A major opportunity with sensor-based condition monitoring is the ability to achieve real-time surveillance of the machine. When subtle unfavorable changes in lubricant condition are noticed quickly, proactive corrective actions can be taken before any incipient machine fails, avoiding costly downtime. Human-enabled inspections, although not continuous in nature, are often just as effective at detecting machine failures early, particularly when performed with the correct frequency and abetted by the human factor. Typical maintenance procedures for inspections are unspecific and poorly defined, with one-line instructions that may simply read “inspect this machine.” These create three inaccurate assumptions: (1) that the inspector is knowledgeable in what to examine, (2) that the inspector knows what inspection tools to use, and (3) that the machine is modified appropriately for the necessary inspections. If detailed standards are not in place, not only could potentially inspectable “alert” conditions go unreported, but there is also no accountability from the inspector about what may have gone unnoticed. This paper presents the suggestions for standardized requirements for human-based inspections. The needs are supported by findings from an extensive study of lubricated equipment identifying the lack of well-equipped machines for routine inspections. The suggestions are supported by the validation of effective measures, such as with improved inspection procedures and machines better equipped for inspections.

Efficient heterogeneous signcryption scheme based on Edge Computing for Industrial Internet of Things

Gene expression data often contain missing expression values. Effective missing value estimation methods are needed since many algorithms for gene expression data analysis require a complete matrix of gene array values. In this paper, imputation methods based on the least squares formulation are proposed to estimate missing values in the gene expression data, which exploit local similarity structures in the data as well as least squares optimization process. The proposed local least squares imputation method (LLSimpute) represents a target gene that has missing values as a linear combination of similar genes. The similar genes are chosen by k-nearest neighbors or k coherent genes that have large absolute values of Pearson correlation coefficients. Non-parametric missing values estimation method of LLSimpute are designed by introducing an automatic k-value estimator. In our experiments, the proposed LLSimpute method shows competitive results when compared with other imputation methods for missing value estimation on various datasets and percentages of missing values in the data. The software is available at http://www.cs.umn.edu/~hskim/tools.html hpark@cs.umn.edu

Recent advancements of the Industrial Internet of Things (IIoT) have revolutionized modern urbanization and smart cities. While IIoT data contain rich events and objects of interest, processing a massive amount of IIoT data and making predictions in real-time are challenging. Recent advancements in artificial intelligence (AI) allow processing such a massive amount of IIoT data and generating insights for further decision-making processes. In this article, we propose several key aspects of AI-enabled IIoT data for smart city monitoring. First, we have combined a human-intelligence-enabled crowdsourcing application with that of an AI-enabled IIoT framework to capture events and objects from IIoT data in real time. Second, we have combined multiple AI algorithms that can run on distributed edge and cloud nodes to automatically categorize the captured events and objects and generate analytics, reports, and alerts from the IIoT data in real time. The results can be utilized in two scenarios. In the first scenario, the smart city authority can authenticate the AI-processed events and assign these events to the appropriate authority for managing the events. In the second scenario, the AI algorithms are allowed to interact with humans or IIoT for further processes. Finally, we will present the implementation details of the scenarios mentioned above and the test results. The test results show that the framework has the potential to be deployed within a smart city.

A Comparison of Multiple Imputation and Optimal Estimation for Missing and Uncertain Urban Air Toxics Data

Hybrid platforms are based on the new technologies of the fourth industrial revolution such as IIoT and cloud computing, which allow local and remote operation. A hybrid system presents a low cost of operation and maintenance. This paper describes the development of a hybrid IIoT (Industrial Internet of Things) & Arduino IoT (Internet of Things) Cloud platform for the analysis of continuous industrial process data in real time through the cloud. This procedure offers a more stable and secure control through the new Cloud technology. The IIoT platform consists of industrial equipment and sensors that are controlled through Delta IIoT devices. An Arduino IoT Cloud with ESP32 module has the functionality of a router that allows sending data to the cloud, thereby achieving the control and monitoring of level and temperature variables of a continuous process. With this type of architecture, the industrial sector has great opportunities to improve its competitiveness by being able to analyze large amounts of data collected from sensors. In addition, the hybrid platform guarantees the visibility of the variables in real time from anywhere in the world where connectivity exists. The results are presented in graphs and are promising as there is no data loss in the cloud and data latency is almost negligible.KeywordsIndustrial Internet of Things (IIoT)Internet of Things (IoT)Industry 4.0Hybrid IIoT

In this paper, five imputation methods namely Constant (zero), Mean, Median, Maximum Likelihood, and Multiple Imputation methods have been applied to compensate for missing values in Electric Vehicle (EV) charging data. The outcome of each of these methods have been used as the input to a prediction algorithm to forecast the EV load in the next 24 hours at each individual outlet. The data is real world data at the outlet level from the UCLA campus parking lots. Given the sparsity of the data, both Median and Constant (=zero) imputations improved the prediction results. Since in most missing value cases in our database, all values of that instance are missing, the multivariate imputation methods did not improve the results significantly compared to univariate approaches.