Machine learning based real-time vehicle data analysis for safe driving modeling

This paper provides a complete over view of the current research state of Smart vehicle tracking System with GPS and cellular network. This paper consists of several review aiming to reveal the relevance and methodologies of this research area and create a foundation for future work. In this paper an advanced vehicle observation and IOT based tracking system and autopilot navigation system based on Machine Learning and neural Networking is proposed with all possible scientific validations of the model. The primary purpose of monitoring the vehicles which are moving from one place to the other in order to provide better A.I based autopilot navigation system, safety and security. The proposed method Combined the idea of Java programming, Neural networking concept with machine learning capability processing data with MediaTek mobile processor and its sophisticated features of storing data into several databases. Google Map Engine API v3 was used to display and sense the graphical images of the map and a Vision recognition server system is used to compare and represent the map API in a more realistic look. The proposed project includes the implementation of Global Positioning System (GPS), GPRS and GSM technology for vehicle tracking and monitoring on real time basic purpose using SIM module.[3] The GPS receiver installed o tracking device provides real-time Geolocation Co-ordinate of site of the vehicle; 3 adjacent GSM cellphone tower stations will continuously broadcast co-ordinate of locations and the GPRS technology with TCP based protocol sends the tracking information to the central Monitoring and Imaging server which consist of 3 child servers i)data processing sever, ii) Image and vision based server and iii)A.I. based machine learning server calculate data and minimize the information and maps with the help of Google map API and thus an decision message for next Move/driving path is generated and transmitted to Smart Controlling Device to execute the instructions and to display it in the Monitor of car display and Integrated logged-IN andriod based Google Map API version 3 app on real time basic. Hence, this system will monitor all the driving steps of the driver and provide the real time driving suggestions and feedback to the driver to ensure smooth and safe driving experience. The sensors like temperature sensor ,altitude sensor and smoke sensor send data to the neural processing Server which diagnoses the health and safety measures of the vehicles and generates a report on Car display and andriod App interface if any risk issue is found by sensors.

Download Full-text

A Real-Time Data Analysis Platform for Short-Term Water Consumption Forecasting with Machine Learning

Forecasting ◽

10.3390/forecast3040042 ◽

2021 ◽

Vol 3 (4) ◽

pp. 682-694

Author(s):

Aida Boudhaouia ◽

Patrice Wira

Keyword(s):

Machine Learning ◽

Data Analysis ◽

Real Time ◽

Water Consumption ◽

Short Term Memory ◽

Back Propagation ◽

Time Data ◽

Short Term ◽

Real Time Data ◽

Analysis Platform

This article presents a real-time data analysis platform to forecast water consumption with Machine-Learning (ML) techniques. The strategy fully relies on a web-oriented architecture to ensure better management and optimized monitoring of water consumption. This monitoring is carried out through a communicating system for collecting data in the form of unevenly spaced time series. The platform is completed by learning capabilities to analyze and forecast water consumption. The analysis consists of checking the data integrity and inconsistency, in looking for missing data, and in detecting abnormal consumption. Forecasting is based on the Long Short-Term Memory (LSTM) and the Back-Propagation Neural Network (BPNN). After evaluation, results show that the ML approaches can predict water consumption without having prior knowledge about the data and the users. The LSTM approach, by being able to grab the long-term dependencies between time steps of water consumption, allows the prediction of the amount of consumed water in the next hour with an error of some liters and the instants of the 5 next consumed liters in some milliseconds.

Download Full-text

Machine Learning based Improved Gaussian Mixture Model for IoT Real-Time Data Analysis

Ingeniería solidaria ◽

10.16925/2357-6014.2020.01.02 ◽

2020 ◽

Vol 16 (1) ◽

Author(s):

Sivadi Sivadi ◽

Moorthy Moorthy ◽

Vijender Solanki

Keyword(s):

Machine Learning ◽

Data Analysis ◽

Real Time ◽

Gaussian Mixture Model ◽

Gaussian Mixture ◽

Sensor Data ◽

Cloud Platform ◽

Time Data ◽

Huge Amount ◽

Real Time Data

Introduction: The article is the product of the research “Due to the increase in popularity of Internet of Things (IoT), a huge amount of sensor data is being generated from various smart city applications”, developed at Pondicherry University in the year 2019. Problem:To acquire and analyze the huge amount of sensor-generated data effectively is a significant problem when processing the data. Objective: To propose a novel framework for IoT sensor data analysis using machine learning based improved Gaussian Mixture Model (GMM) by acquired real-time data. Methodology:In this paper, the clustering based GMM models are used to find the density patterns on a daily or weekly basis for user requirements. The ThingSpeak cloud platform used for performing analysis and visualizations. Results:An analysis has been performed on the proposed mechanism implemented on real-time traffic data with Accuracy, Precision, Recall, and F-Score as measures. Conclusions:The results indicate that the proposed mechanism is efficient when compared with the state-of-the-art schemes. Originality:Applying GMM and ThingSpeak Cloud platform to perform analysis on IoT real-time data is the first approach to find traffic density patterns on busy roads. Restrictions:There is a need to develop the application for mobile users to find the optimal traffic routes based on density patterns. The authors could not concentrate on the security aspect for finding density patterns.

Download Full-text

A Survey on Distributed Fibre Optic Sensor Data Modelling Techniques and Machine Learning Algorithms for Multiphase Fluid Flow Estimation

Sensors ◽

10.3390/s21082801 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2801

Author(s):

Hasan Asy’ari Arief ◽

Tomasz Wiktorski ◽

Peter James Thomas

Keyword(s):

Machine Learning ◽

Fluid Flow ◽

Data Analysis ◽

Real Time ◽

Machine Learning Algorithms ◽

Sensor Data ◽

Support Vector ◽

Measurement Technology ◽

Fibre Optic ◽

Multiphase Fluid

Real-time monitoring of multiphase fluid flows with distributed fibre optic sensing has the potential to play a major role in industrial flow measurement applications. One such application is the optimization of hydrocarbon production to maximize short-term income, and prolong the operational lifetime of production wells and the reservoir. While the measurement technology itself is well understood and developed, a key remaining challenge is the establishment of robust data analysis tools that are capable of providing real-time conversion of enormous data quantities into actionable process indicators. This paper provides a comprehensive technical review of the data analysis techniques for distributed fibre optic technologies, with a particular focus on characterizing fluid flow in pipes. The review encompasses classical methods, such as the speed of sound estimation and Joule-Thomson coefficient, as well as their data-driven machine learning counterparts, such as Convolutional Neural Network (CNN), Support Vector Machine (SVM), and Ensemble Kalman Filter (EnKF) algorithms. The study aims to help end-users establish reliable, robust, and accurate solutions that can be deployed in a timely and effective way, and pave the wave for future developments in the field.

Download Full-text

A Novel Algorithm to Reduce Machine Learning Efforts in Real-Time Sensor Data Analysis

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering - Wireless Mobile Communication and Healthcare ◽

10.1007/978-3-319-98551-0_10 ◽

2018 ◽

pp. 83-90

Author(s):

Majid Janidarmian ◽

Atena Roshan Fekr ◽

Katarzyna Radecka ◽

Zeljko Zilic

Keyword(s):

Machine Learning ◽

Data Analysis ◽

Real Time ◽

Sensor Data ◽

Novel Algorithm

Download Full-text

A Machine Learning Based Strategy for Predicting the Sagittal Angles in real-time for Actuating an Active Knee-Ankle Prosthesis

10.1055/s-0040-1717439 ◽

2020 ◽

Author(s):

S Dey ◽

T Yoshida ◽

AF Schilling

Keyword(s):

Machine Learning ◽

Real Time ◽

Ankle Prosthesis

Download Full-text

Creating adaptive predictions for packaging-critical quality parameters using advanced analytics and machine learning

TAPPI Journal ◽

10.32964/tj18.11.679 ◽

2019 ◽

Vol 18 (11) ◽

pp. 679-689

Author(s):

CYDNEY RECHTIN ◽

CHITTA RANJAN ◽

ANTHONY LEWIS ◽

BETH ANN ZARKO

Keyword(s):

Machine Learning ◽

Real Time ◽

Predictive Analytics ◽

Paper Industry ◽

Quality Parameters ◽

Fast Change ◽

The Face ◽

Model Tuning ◽

Reducing Costs ◽

Time Critical

Packaging manufacturers are challenged to achieve consistent strength targets and maximize production while reducing costs through smarter fiber utilization, chemical optimization, energy reduction, and more. With innovative instrumentation readily accessible, mills are collecting vast amounts of data that provide them with ever increasing visibility into their processes. Turning this visibility into actionable insight is key to successfully exceeding customer expectations and reducing costs. Predictive analytics supported by machine learning can provide real-time quality measures that remain robust and accurate in the face of changing machine conditions. These adaptive quality “soft sensors” allow for more informed, on-the-fly process changes; fast change detection; and process control optimization without requiring periodic model tuning. The use of predictive modeling in the paper industry has increased in recent years; however, little attention has been given to packaging finished quality. The use of machine learning to maintain prediction relevancy under everchanging machine conditions is novel. In this paper, we demonstrate the process of establishing real-time, adaptive quality predictions in an industry focused on reel-to-reel quality control, and we discuss the value created through the availability and use of real-time critical quality.

Download Full-text