Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone Sensors
In this work, we present a novel method, namely dynamic basic activity sequence matching (DAS), a combination of machine learning methods and flexible threshold based methods for distinguishing normal and abnormal driving patterns. Indeed, DAS relies on the activity detection module (ADM) presented...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/2/217 |
| _version_ | 1798024221151985664 |
|---|---|
| author | Thi-Hau Nguyen Dang-Nhac Lu Duc-Nhan Nguyen Ha-Nam Nguyen |
| author_facet | Thi-Hau Nguyen Dang-Nhac Lu Duc-Nhan Nguyen Ha-Nam Nguyen |
| author_sort | Thi-Hau Nguyen |
| collection | DOAJ |
| description | In this work, we present a novel method, namely dynamic basic activity sequence matching (DAS), a combination of machine learning methods and flexible threshold based methods for distinguishing normal and abnormal driving patterns. Indeed, DAS relies on the activity detection module (ADM) presented in our previous work to analyze each driving pattern as a sequence of basic activities—stopping (S), going straight (G), turning left (L), and turning right (R). In fact, the threshold value and other parameters like the duration of long and short activities are iteratively induced from the collected dataset. Hence, DAS is flexible and independent of driving contexts such as vehicle modes and road conditions. Experimental results, on the dataset collected from numerous motorcyclists, show the outperformance of our proposed method against dynamic time warping and the two popular machine learning methods—random forest and neural network—in distinguishing the normal and abnormal driving patterns. Moreover, we propose an efficient framework composing of two phases: in the first phase, the normal and abnormal driving patterns are distinguished by relying on DAS. In the second phase, the detected abnormal patterns are further classified into various specific abnormal driving patterns—weaving, sudden braking, etc. This fusion framework again achieves the highest overall accuracy of 97.94%. |
| first_indexed | 2024-04-11T17:58:53Z |
| format | Article |
| id | doaj.art-a5247ba4bd754798b27f7ccf2f16714c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-11T17:58:53Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-a5247ba4bd754798b27f7ccf2f16714c2022-12-22T04:10:35ZengMDPI AGElectronics2079-92922020-01-019221710.3390/electronics9020217electronics9020217Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone SensorsThi-Hau Nguyen0Dang-Nhac Lu1Duc-Nhan Nguyen2Ha-Nam Nguyen3Faculty of Information Technology, VNU University of Engineering and Technology, Vietnam National University in Hanoi (VNU-UET), Hanoi 123105, VietnamAcademy of Journalism and Communication (AJC), Hanoi 123105, VietnamFaculty of Telecommunications, Posts and Telecommunications Institute of Technology in Hanoi (PTIT), Hanoi 151100, VietnamVNU Information Technology Institute, Vietnam National University in Hanoi (VNU-ITI), Hanoi 123105, VietnamIn this work, we present a novel method, namely dynamic basic activity sequence matching (DAS), a combination of machine learning methods and flexible threshold based methods for distinguishing normal and abnormal driving patterns. Indeed, DAS relies on the activity detection module (ADM) presented in our previous work to analyze each driving pattern as a sequence of basic activities—stopping (S), going straight (G), turning left (L), and turning right (R). In fact, the threshold value and other parameters like the duration of long and short activities are iteratively induced from the collected dataset. Hence, DAS is flexible and independent of driving contexts such as vehicle modes and road conditions. Experimental results, on the dataset collected from numerous motorcyclists, show the outperformance of our proposed method against dynamic time warping and the two popular machine learning methods—random forest and neural network—in distinguishing the normal and abnormal driving patterns. Moreover, we propose an efficient framework composing of two phases: in the first phase, the normal and abnormal driving patterns are distinguished by relying on DAS. In the second phase, the detected abnormal patterns are further classified into various specific abnormal driving patterns—weaving, sudden braking, etc. This fusion framework again achieves the highest overall accuracy of 97.94%.https://www.mdpi.com/2079-9292/9/2/217abnormal driving patternsbasic driving activitiessmartphone sensor datasequence matchingmulticlass classification |
| spellingShingle | Thi-Hau Nguyen Dang-Nhac Lu Duc-Nhan Nguyen Ha-Nam Nguyen Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone Sensors Electronics abnormal driving patterns basic driving activities smartphone sensor data sequence matching multiclass classification |
| title | Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone Sensors |
| title_full | Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone Sensors |
| title_fullStr | Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone Sensors |
| title_full_unstemmed | Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone Sensors |
| title_short | Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone Sensors |
| title_sort | dynamic basic activity sequence matching method in abnormal driving pattern detection using smartphone sensors |
| topic | abnormal driving patterns basic driving activities smartphone sensor data sequence matching multiclass classification |
| url | https://www.mdpi.com/2079-9292/9/2/217 |
| work_keys_str_mv | AT thihaunguyen dynamicbasicactivitysequencematchingmethodinabnormaldrivingpatterndetectionusingsmartphonesensors AT dangnhaclu dynamicbasicactivitysequencematchingmethodinabnormaldrivingpatterndetectionusingsmartphonesensors AT ducnhannguyen dynamicbasicactivitysequencematchingmethodinabnormaldrivingpatterndetectionusingsmartphonesensors AT hanamnguyen dynamicbasicactivitysequencematchingmethodinabnormaldrivingpatterndetectionusingsmartphonesensors |