Estimation of Road Surface Condition during Summer Season Using Machine Learning

Automotive intelligence has become a revolutionary trend in automotive technology. Complex road driving conditions directly affect driving safety and comfort. Therefore, by improving the recognition accuracy of road type or road adhesion coefficient, the ability of vehicles to perceive the surrounding environment will be enhanced. This will further contribute to vehicle intelligence. In this paper, considering that the process of manually extracting image features is complicated and that the extraction method is random for everyone, road surface condition identification method based on an improved ALexNet model, namely, the road surface recognition model (RSRM), is proposed. First, the ALexNet network model is pretrained on the ImageNet dataset offline. Second, the weights of the shallow network structure after training, including the convolutional layer, are saved and migrated to the proposed model. In addition, the fully connected layer fixed to the shallow network is replaced by 2 to 3, which improves the training accuracy and shortens the training time. Finally, the traditional machine learning and improved ALexNet model are compared, focusing on adaptability, prediction output, and error performance, among others. The results show that the accuracy of the proposed model is better than that of the traditional machine learning method by 10% and the ALexNet model by 3%, and it is 0.3 h faster than ALexNet in training speed. It is verified that RSRM effectively improves the network training speed and accuracy of road image recognition.

Download Full-text

Road surface condition detection utilizing impedance spectroscopy and machine-learning algorithm

Life-Cycle Civil Engineering: Innovation, Theory and Practice ◽

10.1201/9780429343292-192 ◽

2021 ◽

pp. 1447-1451

Author(s):

Kang Gui ◽

Genfeng Ge ◽

Xin Cheng ◽

LinYe ◽

Lizhen Huang

Keyword(s):

Machine Learning ◽

Impedance Spectroscopy ◽

Learning Algorithm ◽

Surface Condition ◽

Road Surface ◽

Machine Learning Algorithm

Download Full-text

Smartphone Sensing of Road Surface Condition and Defect Detection

Sensors ◽

10.3390/s21165433 ◽

2021 ◽

Vol 21 (16) ◽

pp. 5433

Author(s):

Dapeng Dong ◽

Zili Li

Keyword(s):

Machine Learning ◽

Defect Detection ◽

Large Scale ◽

Learning Algorithm ◽

Surface Condition ◽

Large Population ◽

Road Surface ◽

Maintenance Cost ◽

Accelerometer Data ◽

Road Maintenance

Road surface condition is vitally important for road safety and transportation efficiency. Conventionally, road surface monitoring relies on specialised vehicles equipped with professional devices, but such dedicated large-scale road surveying is usually costly, time-consuming, and prohibitively difficult for frequent pavement condition monitoring—for example, on an hourly or daily basis. Current advances in technologies such as smartphones, machine learning, big data, and cloud analytics have enabled the collection and analysis of a great amount of field data from numerous users (e.g., drivers) whilst driving on roads. In this regard, we envisage that a smartphone equipped with an accelerometer and GPS sensors could be used to collect road surface condition information much more frequently than specialised equipment. In this study, accelerometer data were collected at low rate from a smartphone via an Android-based application over multiple test-runs on a local road in Ireland. These data were successfully processed using power spectral density analysis, and defects were later identified using a k-means unsupervised machine learning algorithm, resulting in an average accuracy of 84%. Results demonstrated the potential of collecting crowdsourced data from a large population of road users for road surface defect detection on a quasi-real-time basis. This frequent reporting on a daily/hourly basis can be used to inform the relevant stakeholders for timely road maintenance, aiming to ensure the road’s serviceability at a lower inspection and maintenance cost.

Download Full-text

Estimating Spatiotemporal Information from Behavioral Sensing Data of Wheelchair Users by Machine Learning Technologies

Information ◽

10.3390/info10030114 ◽

2019 ◽

Vol 10 (3) ◽

pp. 114 ◽

Cited By ~ 1

Author(s):

Ikuko Yairi ◽

Hiroki Takahashi ◽

Takumi Watanabe ◽

Kouya Nagamine ◽

Yusuke Fukushima ◽

...

Keyword(s):

Machine Learning ◽

Evaluation System ◽

Surface Condition ◽

Learning Technologies ◽

Road Surface ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Prototype System ◽

Wheelchair Users ◽

The Road

Recent expansion of intelligent gadgets, such as smartphones and smart watches, familiarizes humans with sensing their activities. We have been developing a road accessibility evaluation system inspired by human sensing technologies. This paper introduces our methodology to estimate road accessibility from the three-axis acceleration data obtained by a smart phone attached on a wheelchair seat, such as environmental factors, e.g., curbs and gaps, which directly influence wheelchair bodies, and human factors, e.g., wheelchair users’ feelings of tiredness and strain. Our goal is to realize a system that provides the road accessibility visualization services to users by online/offline pattern matching using impersonal models, while gradually learning to improve service accuracy using new data provided by users. As the first step, this paper evaluates features acquired by the DCNN (deep convolutional neural network), which learns the state of the road surface from the data in supervised machine learning techniques. The evaluated results show that the features can capture the difference of the road surface condition in more detail than the label attached by us and are effective as the means for quantitatively expressing the road surface condition. This paper developed and evaluated a prototype system that estimated types of ground surfaces focusing on knowledge extraction and visualization.

Download Full-text

Distinction of Wet Road Surface Condition at Night-time using Texture Features

IEEJ Transactions on Electronics Information and Systems ◽

10.1541/ieejeiss.132.1488 ◽

2012 ◽

Vol 132 (9) ◽

pp. 1488-1493 ◽

Cited By ~ 1

Author(s):

Keiji Shibata ◽

Tatsuya Furukane ◽

Shohei Kawai ◽

Yuukou Horita

Keyword(s):

Surface Condition ◽

Texture Features ◽

Road Surface ◽

Night Time

Download Full-text

EFFICIENCY IMPROVEMENT OF ROAD SURFACE INSPECTION USING MACHINE LEARNING TECHNOLOGY

Journal of Japan Society of Civil Engineers Ser F3 (Civil Engineering Informatics) ◽

10.2208/jscejcei.73.i_409 ◽

2017 ◽

Vol 73 (2) ◽

pp. I_409-I_415

Author(s):

Naoko FUKUSHI ◽

Daishiro KOBAYASHI ◽

Seiji IWAO ◽

Ryosuke KASAHARA ◽

Nobuyoshi YABUKI

Keyword(s):

Machine Learning ◽

Road Surface ◽

Surface Inspection ◽

Learning Technology ◽

Efficiency Improvement

Download Full-text

Exploratory Analysis of Driving Force of Wildfires in Australia: An Application of Machine Learning within Google Earth Engine

Remote Sensing ◽

10.3390/rs13010010 ◽

2020 ◽

Vol 13 (1) ◽

pp. 10

Author(s):

Andrea Sulova ◽

Jamal Jokar Arsanjani

Keyword(s):

Climate Change ◽

Machine Learning ◽

Random Forest ◽

Google Earth ◽

Summer Season ◽

Driving Factors ◽

Machine Learning Algorithms ◽

Classification And Regression Tree ◽

Training Dataset ◽

Google Earth Engine

Recent studies have suggested that due to climate change, the number of wildfires across the globe have been increasing and continue to grow even more. The recent massive wildfires, which hit Australia during the 2019–2020 summer season, raised questions to what extent the risk of wildfires can be linked to various climate, environmental, topographical, and social factors and how to predict fire occurrences to take preventive measures. Hence, the main objective of this study was to develop an automatized and cloud-based workflow for generating a training dataset of fire events at a continental level using freely available remote sensing data with a reasonable computational expense for injecting into machine learning models. As a result, a data-driven model was set up in Google Earth Engine platform, which is publicly accessible and open for further adjustments. The training dataset was applied to different machine learning algorithms, i.e., Random Forest, Naïve Bayes, and Classification and Regression Tree. The findings show that Random Forest outperformed other algorithms and hence it was used further to explore the driving factors using variable importance analysis. The study indicates the probability of fire occurrences across Australia as well as identifies the potential driving factors of Australian wildfires for the 2019–2020 summer season. The methodical approach and achieved results and drawn conclusions can be of great importance to policymakers, environmentalists, and climate change researchers, among others.

Download Full-text