AU2020103374A4 - Mobile traffic noise measurement and prediction method using machine learning algorithms - Google Patents

Mobile traffic noise measurement and prediction method using machine learning algorithms Download PDF

Info

Publication number
AU2020103374A4
AU2020103374A4 AU2020103374A AU2020103374A AU2020103374A4 AU 2020103374 A4 AU2020103374 A4 AU 2020103374A4 AU 2020103374 A AU2020103374 A AU 2020103374A AU 2020103374 A AU2020103374 A AU 2020103374A AU 2020103374 A4 AU2020103374 A4 AU 2020103374A4
Authority
AU
Australia
Prior art keywords
noise
machine learning
traffic noise
data
mobile
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
AU2020103374A
Inventor
Saurabh Gupta
Garima JAIN
Shafali Jain
P. Karthigeyan
Abhishek Kumar
Vishwas Mishra
K. Muthumayil
Jyothi N. M.
L. Chandra Sekhar Reddy
Mohan Dattu Sangale
Shobhit Tyagi
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NM Jyothi
Original Assignee
NM Jyothi
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NM Jyothi filed Critical NM Jyothi
Priority to AU2020103374A priority Critical patent/AU2020103374A4/en
Application granted granted Critical
Publication of AU2020103374A4 publication Critical patent/AU2020103374A4/en
Ceased legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

MOBILE TRAFFIC NOISE MEASUREMENT AND PREDICTION METHOD USING MACHINE LEARNING ALGORITHMS ABSTRACT The traffic noise increases with the increase in the population using the vehicles. The traffic noise not only creates the exasperation and stress to human, but also creates health defects. So there is a need to detect the moving traffic noise. The datas related to traffic noise are gathered by coupling the sound meter microphone with the mobile noise monitoring, strava smart device. The sound meter microphone captures noise from the traffic route in road map or in any other vehicle routes. The mobile noise monitoring gathers GPS location while running and cycling. The spatial scale monitoring of the data is performed by dark sky application programming interface. The data processed by map matching algorithm is then stored in cloud through the gateway interface. The machine learning algorithm, regression approach with exhaustive search deployed used in the measurement of the mobile traffic noise and makes predictions. The prediction results are visualized in smart device display so that necessary precautions can be taken to reduce noise. 1 P a g e MOBILE TRAFFIC NOISE MEASUREMENT AND PREDICTION METHOD USING MACHINE LEARNING ALGORITHMS Drawings SOUNDMOBILE NOISE METERMONITORING SPATIAL SCALE MONITORING DATA DARK SKY A PT DATA PROCESSING MAP MATCHING ALGORITHM GATEWAY CLOUD MACHINE LEARNING ALGORITHM REGRESSION APPROACH WITH EXHAUSTIVE SEARCH SMART DISPLAY Fig. 1. BLOCK DIAGRAM 1 P a g e

Description

MOBILE TRAFFIC NOISE MEASUREMENT AND PREDICTION METHOD USING MACHINE LEARNING ALGORITHMS
Drawings
SOUNDMOBILE NOISE METERMONITORING SPATIAL SCALE MONITORING DATA DARK SKY A PT DATA PROCESSING MAP MATCHING ALGORITHM GATEWAY CLOUD MACHINE LEARNING ALGORITHM REGRESSION APPROACH WITH EXHAUSTIVE SEARCH SMART DISPLAY
Fig. 1. BLOCK DIAGRAM
1 Pag e
MOBILE TRAFFIC NOISE MEASUREMENT AND PREDICTION METHOD USING MACHINE LEARNING ALGORITHMS
Description
Field of the Invention. The Field of invention is related to machine learning algorithms for mobile traffic noise measurement and prediction. Background of the invention. Though the present world has experienced a numerous technologies, on the other hand, it faces lot of defects. One of the most alarming defects the world is currently facing is the noise. The main source of noise are from vehicles that move around. Even the global meteorology and the region land use have a great impact in noise in traffic. Currently, medical field is facing a lot of health related scenarios related to sleep, heart problem, stress and exasperation. This is because of the increased noise level in the outdoor including residential acoustics. To overcome and reduce the health defects, it is necessary to measure and predict the mobile traffic noise. Initially, analytical methods were deployed to study the traffic noise and perform measurement. But it was a complex analysis. Later as the technology is developed, with the help of map data from geographic information system, traffic data is processed and noise level is measured. But it is not flexible. Therefore, the data or the information that needs to be collected uses sound meter microphone coupled with strava. This internet service used with smart device suitable for GPS data while running and cycling. When data is collected, there is a need to have minimum reflection of obstacles and there should not be any talking. The region land use includes minor area, major areas, interconnection of different routes in the road maps and other vehicular routes. The data to be monitored should be in spatial scale observation of including weather parameter and can be done with dark sky API smart device. The weather parameters that need to be considered are speed of the wind, humidity, temperature, rain and storm based on the regions of the location and the land use. Because of the effect of the climatic conditions on the land use, it brings about increase in traffic that create more noise and which in turn have its effect on the human health.
1 Pa g e
The data collected has to be processed using map matching algorithm to categorize the various model and then it has to be sent to the cloud platform through the gateway interface to be computed by machine learning algorithm. The cloud is deployed as it has to store a huge volume of data regarding the map routes along with the longitude, latitude meteorology data of the climatic conditions like rain, storm, wind, etc. It also needs to update the new data that are to be collected with the previous recorded data to maintain a database of the traffic noise. Machine learning algorithms are deployed to make the measurement and prediction for the moving traffic easier. The statistical method of spatial autoregression was earlier adopted for the measurement and prediction model, but capturing non linear parameter relationship is limited. Even Neural networks were also deployed for the prediction but the observation of the data is also limited. The random forest approach deployed for this traffic noise prediction has an overfitting drawback. To adapt to the multicollinearity and capture nonlinear metrics, regression using exhaustive search is deployed. It has scalable factor that model the weak parameters and improves it, thus reflect a better traffic noise capture.
The machine learning algorithm with regression approach with exhaustive search computes and model the training set with the test set of the measurement and can make predictions to be visualized to the end user to adopt some necessary precautions to reduce or control the noise.
Objects of the Invention
The first objective is to collect the traffic noise data source from microphone and smart devices. The second objective is to process the data that has been collected with map matching algorithm.
2 Pag e
The third objective is to deploy machine learning algorithm regression approach with exhaustive search for mobile traffic noise measurement and prediction.
The traffic noise land use data, meteorological data and vehicles datas are gathered by coupling the sound meter microphone with the mobile noise monitoring, strava smart device. The sound meter microphone captures noise from the traffic route may be a major or minor or intersection of the routes in road map or any other vehicle routes. The mobile noise monitoring gathers GPS location while running and cycling. The spatial scale monitoring of the data is performed by a computer interface, application programming interface dark sky. The data is then processed by map matching algorithm. A cloud is deployed to store a high volume of data through the gateway. The machine learning algorithms is used to measure the mobile traffic noise and makes predictions. The most suitable approach for deploying the machine learning algorithm is the regression approach with exhaustive search. The prediction results are displayed in smart display so that necessary precautions can be taken to reduce noise.
Summary of the Invention
At present there are many health issues occurring around us. Especially with the increase in traffic noise, the risk factors of health deterioration increase rapidly. And also as the usage of vehicles increases with the increase in the population with respect to the region land use, there is a need to gather all the relevant datas regarding the traffic noise land use data, meteorological data and vehicles datas. They are gathered by coupling the sound meter microphone with the mobile noise monitoring, strava. The sound meter microphone captures noise data as a source from the traffic route. The traffic route map may be a major area or minor area or intersection of the routes in road map or any other vehicle routes. The mobile noise monitoring gathers internet service GPS location while running and cycling using strava, smart device. The spatial scale monitoring done by application programming interface dark sky. The data processing is then done with map matching algorithm. A cloud stores the data through the gateway interface. The machine learning algorithm is used in computation of the mobile traffic noise measurement and makes predictions regarding the
3|Page traffic noise. The regression approach with exhaustive search machine learning algorithm models the training set with the test set to make predictions. The prediction results are displayed in smart display device for visualization and so that necessary steps can be taken to reduce noise.
Detailed Description of the Invention
Fig. 1 illustrates the block diagram of the mobile traffic noise measurement and prediction method using machine learning algorithms. Fig. 2 illustrates the data collection in the mobile traffic noise measurement and prediction.
Detailed Description of the Invention
Fig.1 illustrates the block diagram of deploying the machine learning algorithms for mobile traffic noise measurement and prediction. At present there are many health defects that rise around us. Especially with the increase in vehicle traffic noise, the risk of health deterioration increases rapidly. The usage of vehicles increases with the increase in the population with respect to the region land use, either commercial or residential location. There is a need to gather all the relevant datas regarding the traffic noise land use data, meteorological data, and vehicles datas with respect to GPS. They are gathered by coupling the sound meter microphone with the mobile noise monitoring. The sound meter microphone captures noise information as a source from the vehicle traffic route which may be a major area or minor area or intersection of any vehicle routes. The mobile noise monitoring, Strava gathers GPS location. It captures while running and cycling using the smart device, strava. The spatial scale monitoring performed by API dark sky. The data processing is then carried out with map matching algorithm. A cloud stores a huge volume of processed data through the gateway interface. The machine learning algorithms is deployed performs the computation of the mobile traffic noise measurement and makes predictions regarding the traffic noise. The regression approach with exhaustive search machine learning algorithm models the training set with the test set to make predictions.
4|Page
The prediction results are displayed in smart display device for visualization and so that necessary precautions or steps can be taken to reduce the vehicle traffic noise.
Fig. 2 shows the data to be collected for deploying the machine learning algorithms for mobile traffic noise measurement and prediction. Though the present world faces technology updates every day, it also experiences defects on the other hand. One of the most critical defects the world is currently facing is the noise from vehicles that move around. Even the global meteorology and the region land use have a great impact in noise in traffic. At present, medical field faces a lot of health deterioration scenarios related to sleep, exasperation, heart problem and stress. This is because of the noise level in the outdoor including residential acoustics. To overcome and reduce the health issues, it is a need to measure and predict the mobile traffic noise to take necessary precaution to reduce the health deteriorating noise. The traffic noise in the commercial and the residential area has to be collected as this has increased vehicle usage. The region land use includes minor areas or major areas or interconnection of different routes in the road maps and other vehicular routes along with the longitude, latitude data's have to be collected. The meteorological data which shows the weather parameters that need to be considered are speed of the wind, humidity, temperature, rain, and storm based on the regions of the location and the land use. The data varies for different climatic conditions like rain, storm, wind, etc. and because of the effect of the climatic conditions on the land use, brings about increase in traffic that create more noise and which in turn have its effect on the human health. The global positioning system is used to get the information on route map of the vehicles and the traffic of vehicles that may produce noise because of increased traffic. These information are gathered, processed, and computed so that ML can make predictions.
|Page

Claims (9)

MOBILE TRAFFIC NOISE MEASUREMENT AND PREDICTION METHOD USING MACHINE LEARNING ALGORITHMS CLAIMS: I/We Claim:
1. High speed wireless internet connection deployed in the mobile traffic noise measurement and prediction.
2. Highly configured computer deployed perform the computations.
3. Sound meter microphone collects the data traffic noise.
4. Strava, a smart device mobile noise monitoring coupled to sound meter microphone.
5. Dark sky API deployed performs spatial scale monitoring.
6. Map matching algorithm carried out in processing the data.
7. Data stored in cloud computing platform through gateway interface.
8. Machine learning algorithm is deployed with regression approach exhaustive search for modeling the training set with test set.
9. The predicted results are viewed in smart display so that necessary precautions can be taken.
1 Pag e
MOBILE TRAFFIC NOISE MEASUREMENT AND PREDICTION 11 Nov 2020
METHOD USING MACHINE LEARNING ALGORITHMS
Drawings 2020103374
Fig. 1. BLOCK DIAGRAM
1|Page
Fig.2 DATA COLLECTION
2|Page
AU2020103374A 2020-11-11 2020-11-11 Mobile traffic noise measurement and prediction method using machine learning algorithms Ceased AU2020103374A4 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2020103374A AU2020103374A4 (en) 2020-11-11 2020-11-11 Mobile traffic noise measurement and prediction method using machine learning algorithms

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AU2020103374A AU2020103374A4 (en) 2020-11-11 2020-11-11 Mobile traffic noise measurement and prediction method using machine learning algorithms

Publications (1)

Publication Number Publication Date
AU2020103374A4 true AU2020103374A4 (en) 2021-01-28

Family

ID=74192183

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2020103374A Ceased AU2020103374A4 (en) 2020-11-11 2020-11-11 Mobile traffic noise measurement and prediction method using machine learning algorithms

Country Status (1)

Country Link
AU (1) AU2020103374A4 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115235614A (en) * 2022-09-23 2022-10-25 广州声博士声学技术有限公司 Urban environmental noise real-time monitoring method, system, equipment and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115235614A (en) * 2022-09-23 2022-10-25 广州声博士声学技术有限公司 Urban environmental noise real-time monitoring method, system, equipment and storage medium

Similar Documents

Publication Publication Date Title
WO2018214060A1 (en) Small-scale air quality index prediction method and system for city
JP7221423B2 (en) Time-varying loudness prediction system
US9229132B2 (en) Meteorological parameter forecasting
KR20200135125A (en) Method and apparatus for predicting severe convection weather
CN105074493B (en) Drive support technology
Grubeša et al. Mobile crowdsensing accuracy for noise mapping in smart cities
Garcia et al. A real time urban flood monitoring system for metro Manila
CN104850734A (en) Air quality index prediction method based on spatial and temporal distribution characteristics
Jonnalagadda et al. Forecasting atmospheric visibility using auto regressive recurrent neural network
Ganji et al. Design, calibration, and testing of a mobile sensor system for air pollution and built environment data collection: The urban scanner platform
AU2020103374A4 (en) Mobile traffic noise measurement and prediction method using machine learning algorithms
CN113286984A (en) Providing additional instructions for difficult maneuvers during navigation
Ambrosino et al. Rainfall-derived growing season characteristics for agricultural impact assessments in South Africa
Can et al. CENSE Project: general overview
Wang et al. Hybrid model for prediction of carbon monoxide and fine particulate matter concentrations near a road intersection
CN113744888B (en) Regional epidemic trend prediction and early warning method and system
Porto et al. Machine learning approaches to extreme weather events forecast in urban areas: Challenges and initial results
Shen et al. Real-time road traffic fusion and prediction with GPS and fixed-sensor data
Huang et al. Estimating urban noise along road network from street view imagery
CN117177096A (en) High-voltage transmission line monitoring method and system based on narrow-band satellite network
Shen et al. Traffic velocity prediction using GPS data: IEEE ICDM contest task 3 report
US20240346831A1 (en) Investigation area determination device, investigation area determination method, and recording medium
Samal et al. Predicting the least air polluted path using the neural network approach
Habtie et al. Road Traffic state estimation framework based on hybrid assisted global positioning system and uplink time difference of arrival data collection methods
CN109118125B (en) Urban environment and economy comprehensive evaluation system

Legal Events

Date Code Title Description
FGI Letters patent sealed or granted (innovation patent)
MK22 Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry