EVALUATING AND CHOOSING A MACHINE LEARNING ALGORITHM FOR CLASSIFYING ROAD SURFACE QUALITY DATA

  • Type: Project
  • Department: Computer Science
  • Project ID: CPU2015
  • Access Fee: ₦5,000 ($14)
  • Pages: 43 Pages
  • Format: Microsoft Word
  • Views: 453
  • Report This work

For more Info, call us on
+234 8130 686 500
or
+234 8093 423 853

ABSTRACT Considering the importance of roads to a community, stakeholders (Governments, Motorists etc) need up-to-date information about the state of roads for decision making . This problem inspired Vorgbe’s (2014) work in implementing a machine learning classifier that could accurately classify roads as “good”, “fair” or “bad”. This information can then be visualised on Google Maps. However, with his algorithm failing to accurately classify some roads, this project seeks to evaluate five classification algorithms to determine which one is best for classifying road surface quality data. To do this, we collected x, y, z acceleration and location data, extracted the desired features from it, performed a 10-fold cross-validation training on the data to choose the best model and then tested on a new set of examples to determine the model that accurately classifies the data. From the data available, the decision tree model produced the best performance with true positives of 97% accuracy for bad roads, 81% accuracy for fair roads and 93% accuracy for good roads. The overall accuracy on the test set is 92% with a precision of 92% and recall of 90%. This means that, this model is more likely to accurately predict a new data point as belonging to its true class. The other algorithms (Logistic Regression, Random Forests, Support Vector Machines and Nearest Neighbour) performed well when classifying the “good” and “bad” road data but instead classified the “fair” road data as “good” road. 

EVALUATING AND CHOOSING A MACHINE LEARNING ALGORITHM FOR CLASSIFYING ROAD SURFACE QUALITY DATA
For more Info, call us on
+234 8130 686 500
or
+234 8093 423 853

Share This
  • Type: Project
  • Department: Computer Science
  • Project ID: CPU2015
  • Access Fee: ₦5,000 ($14)
  • Pages: 43 Pages
  • Format: Microsoft Word
  • Views: 453
Payment Instruction
Bank payment for Nigerians, Make a payment of ₦ 5,000 to

Bank GTBANK
gtbank
Account Name Obiaks Business Venture
Account Number 0211074565

Bitcoin: Make a payment of 0.0005 to

Bitcoin(Btc)

btc wallet
Copy to clipboard Copy text

500
Leave a comment...

    Details

    Type Project
    Department Computer Science
    Project ID CPU2015
    Fee ₦5,000 ($14)
    No of Pages 43 Pages
    Format Microsoft Word

    Related Works

    ABSTRACT In the quest to reduce customer churn rate and retain existing customers, organizations have resorted to investing fortunes in their customer care services, which proves to be a relatively cheaper means of staying in business. In this regard, this project sought to explore a less costly way of providing quality customer care services to... Continue Reading
    Abstract In nations worldwide, roads play a major part in the livelihood of individuals. They aid in the transport of both people and goods from one location to another. In developed countries, most roads are tarred making travel easier and quicker. In developing countries, this is not the case. Quite an amount of road work and development is... Continue Reading
    Net Surface Shortwave Radiation (NSSR) is a key quantity for the estimation of net radiation ( 𝑅𝑛 ) and 𝑅𝑛 is a key component of the Earth energy balance. The most practical and reliable method for estimating solar radiation is based on remote sensing because remote sensing observation values are practical than location based... Continue Reading
    ABSTRACT Images are the most populous cover files for steganography algorithm because of their large amount of redundant bits that are suitable in the transmission of information over the internet. The joint photographic Expert Group (JPEG) is example of images formats that uses the compression techniques. The JPEG is the most populous image file... Continue Reading
    Abstract The microbiological and organic pollutants characteristics of umuosoko stream in ikwuano local government area, Enugu state, Nigeria were carried out. Twenty water samples were collected from four different parts of the river.  The pour plate technique was employed for the isolation of micro-organisms. Colonial morphology, Gram staining... Continue Reading
    (A CASE STUDY OF EKULU RIVER, ENUGU) Abstract The microbiological and organic pollutants characteristics of umuosoko stream in ikwuano local government area, Enugu state, Nigeria were carried out. Twenty water samples were collected from four different... Continue Reading
    ABSTRACT Water quality is very important in the environment, because life depends on this, it's very good to check the quality of water time to time to check the rate at which it is been degraded. The objective of this work is to determine the physiochemical and heavy metal parameter of abattoir effluent to surface water and compare the standard... Continue Reading
    ABSTRACT Pollution of water bodies due to human activities such as industrial waste disposal is a serious challenge facing most developing countries in the world today. Thus the management and supply of freshwater to the public is compromised and the ecological integrity of these rivers is lost due to adverse impacts such as eutrophicaton with... Continue Reading
    ABSTRACT Water quality is very important in the environment, because life depends on this, it's very good to check the quality of water time to time to check the rate at which it is been degraded. The objective of this work is to determine the physiochemical and heavy metal parameter of abattoir effluent to surface water and compare the standard... Continue Reading
    ABSTRACT The Chemical and miCrobial assessment of water quality was investigated with a view to obtain a qualitative and quantitative information on the state of drinking water in Bwari Area Council of Abuja., which. is known for its poor sanitary conditions. Samples of water were collected from boreholes., wells and stream from selected sites and... Continue Reading
    Call Us
    whatsappWhatsApp Us