scholarly journals Human-in-the-Loop Predictive Analytics Using Statistical Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Anusha Ganesan ◽  
Anand Paul ◽  
Ganesan Nagabushnam ◽  
Malik Junaid Jami Gul
Keyword(s):  
Statistical Learning ◽  
Physical System ◽  
Mean Squared Error ◽  
Predictive Analytics ◽  
Learning Algorithm ◽  
Linear Trend ◽  
Cyber Physical System ◽  
Medical Field ◽  
Human In The Loop ◽  
Squared Error

The human-in-the-loop cyber-physical system provides numerous solutions for the challenges faced by the doctors or medical practitioners. There is a linear trend of advancement and automation in the medical field for the early diagnosis of several diseases. One of the critical and challenging diseases in the medical field is coma. In the medical research field, currently, the prediction of these diseases is performed only using the data gathered from the devices only; however, the human’s input is much essential to accurately understand their health condition to take appropriate decision on time. Therefore, we have proposed a healthcare framework involving the concept of artificial intelligence in the human-in- the-loop cyber-physical system. This model works via a response loop in which the human’s intention is concluded by gathering biological signals and context data, and then, the decision is interpreted to a system action that is recognizable to the human in the physical environment, thereby completing the loop. In this paper, we have designed a model for early prognosis of coma using the electroencephalogram dataset. In the proposed approach, we have achieved the best results using a statistical learning algorithm called autoregressive integrated moving average in comparison to artificial neural networks and long short-term memory models. In order to measure the efficiency of our model, we have used the root mean squared error (RMSE), mean absolute error (MAE), and mean squared error (MSE) value to evaluate the linear models as it gives the difference between the measured value and true or correct value. We have achieved the least possible error value for our dataset. To conduct this experiment, we used the dataset available in the phsyionet opensource community.

scholarly journals Map-Reduce based Distance Weighted k-Nearest Neighbor Machine Learning Algorithm for Big Data Applications

2021 ◽  
Author(s):  
Gothai E ◽  
Usha Moorthy ◽  
Sathishkumar V E ◽  
Abeer Ali Alnuaim ◽  
Wesam Atef Hatamleh ◽  
...  
Keyword(s):  
Big Data ◽  
Nearest Neighbor ◽  
Mean Squared Error ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
K Nearest Neighbor ◽  
Squared Error ◽  
Big Data Applications ◽  
Distance Weighted ◽  
Classification Tasks

Abstract With the evolution of Internet standards and advancements in various Internet and mobile technologies, especially since web 4.0, more and more web and mobile applications emerge such as e-commerce, social networks, online gaming applications and Internet of Things based applications. Due to the deployment and concurrent access of these applications on the Internet and mobile devices, the amount of data and the kind of data generated increases exponentially and the new era of Big Data has come into existence. Presently available data structures and data analyzing algorithms are not capable to handle such Big Data. Hence, there is a need for scalable, flexible, parallel and intelligent data analyzing algorithms to handle and analyze the complex massive data. In this article, we have proposed a novel distributed supervised machine learning algorithm based on the MapReduce programming model and Distance Weighted k-Nearest Neighbor algorithm called MR-DWkNN to process and analyze the Big Data in the Hadoop cluster environment. The proposed distributed algorithm is based on supervised learning performs both regression tasks as well as classification tasks on large-volume of Big Data applications. Three performance metrics, such as Root Mean Squared Error (RMSE), Determination coefficient (R2) for regression task, and Accuracy for classification tasks are utilized for the performance measure of the proposed MR-DWkNN algorithm. The extensive experimental results shows that there is an average increase of 3–4.5% prediction and classification performances as compared to standard distributed k-NN algorithm and a considerable decrease of Root Mean Squared Error (RMSE) with good parallelism characteristics of scalability and speedup thus, proves its effectiveness in Big Data predictive and classification applications.

Architecture of a Cyber-Physical System for the Mining Enterprise Ventilation Control Based on the Internet of Things Platform

2021 ◽  
Vol 22 (3) ◽  
pp. 115-123
Author(s):  
A. V. Kychkin ◽  
A. V. Nikolaev
Keyword(s):  
Internet Of Things ◽  
Physical System ◽  
Predictive Analytics ◽  
Underground Mining ◽  
Ventilation System ◽  
The Internet ◽  
Cyber Physical System ◽  
Ventilation Control ◽  
Digital Twin ◽  
The Internet Of Things

The article considers the architecture of the ventilation control system for underground mining enterprises, equipped with a digital twin with online functions such as simulation modeling and predictive analytics. The system is focused on the main fan unit (MFU) control taking into account changing parameters of external air supplied to mine shafts. In contrast to the existing ones, the proposed method of control takes into account the influence of these parameters on changes in the total volume of natural draught, on which the total volume of air supplied to the mine (mine) depends. It is known that ventilation systems of such enterprises consume from 30 to 50 % of all electricity consumed for the mining process. In this regard, the proposed control models can be used to optimize energy costs and energy savings in ventilation. The Internet of things (IoT) InfluxData of stack TICK is offered for the realization. The offered architecture of cyber-physical system (CPS) consists of four subsystems: physical object subsystem, network and computing infrastructure IoT, digital twin, user interface. Architecture of CPS provides data processing from energy meters, control controllers and sensors of air environment parameters, implemented in blocks of on-line and off-line calculations. The digital twin of the ventilation system is made with the use of a time series database and a database of attributes that store information on changes in equipment parameters by time, air indicators, performance indicators, statistics on accidents and fan runtime, CPS characteristics, etc. CPS of the given architecture means connection of additional data sources, providing calculations of rational volumes of air delivery taking into account safety norms and requirements of energy efficiency.

scholarly journals Predictive Analysis of Cryptocurrencies for Developing an Interactive Cryptocurrency Chatbot using IBM Watson Assistant

2019 ◽  
Vol 8 (10) ◽  
pp. 436-447
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Mean Squared Error ◽  
Predictive Analytics ◽  
Arima Model ◽  
Additive Model ◽  
Series Data ◽  
Predictive Analysis ◽  
Squared Error ◽  
Ibm Watson

The main objective of this paper is to analyze the characteristics and features that affects the fluctuations of cryptocurrency prices and to develop aninteractive cryptocurrencychatbot for providing the predictive analysis of cryptocurrency prices. The chatbot is developed using IBM Watson assistant service. The predictive analytics is performed by analyzing the datasets of various cryptocurrencies and applying appropriate time series models. Time Series Forecasting is used for predicting the future values of the prices. Predictive models like ARIMA model is used for calculating the mean squared error of the fitted model. Facebook’s package prophet () which implements a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly and weekly seasonality are further used to predict cryptocurrency prices.

scholarly journals Integrating Physics and Data Driven Cyber-Physical System for Condition Monitoring of Critical Transmission Components in Smart Production Line

2021 ◽  
Vol 11 (19) ◽  
pp. 8967
Author(s):  
Lin Song ◽  
Liping Wang ◽  
Jun Wu ◽  
Jianhong Liang ◽  
Zhigui Liu
Keyword(s):  
Signal Processing ◽  
Deep Learning ◽  
Condition Monitoring ◽  
Physical System ◽  
Production Line ◽  
Learning Algorithm ◽  
Data Driven ◽  
Equation Modeling ◽  
Cyber Physical System ◽  
Deep Learning Algorithm

In response to the lack of a unified cyber–physical system framework, which combined the Internet of Things, industrial big data, and deep learning algorithms for the condition monitoring of critical transmission components in a smart production line. In this study, based on the conceptualization of the layers, a novel five-layer cyber–physical systems framework for smart production lines is proposed. This architecture integrates physics and is data-driven. The smart connection layer collects and transmits data, the physical equation modeling layer converts low-value raw data into high-value feature information via signal processing, the machine learning modeling layer realizes condition prediction through a deep learning algorithm, and scientific decision-making and predictive maintenance are completed through a cognition layer and a configuration layer. Case studies on three critical transmission components—spindles, bearings, and gears—are carried out to validate the effectiveness of the proposed framework and hybrid model for condition monitoring. The prediction results of the three datasets show that the system is successful in distinguishing condition, while the short time Fourier transform signal processing and deep residual network deep learning algorithm is superior to that of other models. The proposed framework and approach are scalable and generalizable and lay the foundation for the extension of the model.

Mathematical Model of Human Operator Using Fractional Calculus for Human-in-the-Loop Control

2015 ◽  
Author(s):  
Jiacai Huang ◽  
YangQuan Chen ◽  
Zhuo Li
Keyword(s):  
Mathematical Models ◽  
Mean Squared Error ◽  
Research Area ◽  
Human Operator ◽  
Loop Control ◽  
Human In The Loop ◽  
Squared Error ◽  
Active Research ◽  
Operator Behavior ◽  
Active Research Area

Mathematical models of human operator play a very important role in the Human-in-the-Loop manual control system. For several decades, modeling human operator’s dynamic has been an active research area. The traditional classical human operator models are usually developed using the Quasi-linear transfer function method, the optimal control theory method, and so on. The human operator models established by the above methods have deficiencies such as complicated and over parameterized, even for basic control elements. In this paper, based on the characteristics of human brain and behaviour, two kinds of fractional order mathematical models for describing human operator behavior are proposed. Through validation and comparison by the actual data, the best_fit model with smallest root mean squared error (RMSE) is obtained, which has simple structure with only few parameters, and each parameter has definite physical meaning.

Sign in / Sign up

Export Citation Format

Share Document