Road Accident Analysis using Raspberry Pi -Data mining has been proven as a reliable technique to analyze road accidents and provide productive results. Most road accident data analysis uses data mining techniques, focusing on identifying factors that affect the severity of an accident. However, any damage resulting from road accidents is always unacceptable in terms of health, property damage, and other economic factors. Sometimes, it is found that road accident occurrences are more frequent at certain specific locations. KNN is one of the popular data mining techniques that identify the correlation in various attributes of road accidents with the use of predefined data sets. also, this system can detect any accident using an accelerometer sensor. If an accident is detected then an alert can be sent to the rescue or emergency team.
Road accidents severity is increasing at an alarming rate. Regulating traffic accidents on roads is a vital task. Roads (ODRs) form the pecuniary cornerstone of the state. The importance of the study is to analyze the traffic accident data factors of State Highways (SHs) and Ordinary District Roads (ODRs). Perceiving the solemnity of the issue, restorative measures are taken to curb the menace caused by road accidents. The rationale behind the investigation is to analyze the accidental data using data mining techniques on various categories of roads such as plan roads, link roads, and central government-funded roads (PMGSY Roads). Data mining is an approach for locating interesting trends as well as illustrative, comprehensible models from huge datasets. The knowledge-driven version deals with harvesting and analysis of data, demand-driven collection of sources of information, security and privacy contemplation, and modeling according to user interests.
- In the existing system, there is no possibility of the earlier prediction.
- Sensors are only used to detect roadside problems and accident causes.
- The data mining concepts were not used.
- Hard to setup
- Needs more components
- The accuracy of output is less
- Not a user-friendly system
- In our system, here we used the data mining process to predict the accidental causes.
- The location-based predictions with using of GPS
- The efficient KNN algorithm will be used to predict the data mining process.
- Accuracy of output is increased
- Easy to setup compared to old methods
- User-friendly system
- It is a cost-effective system
BLOCK DIAGRAM EXPLANATION
- Raspberry pi acts as the heart of this system
- GPS is interfaced with raspberry pi for finding the location of the desired vehicle
- The alarming device is interfaced with raspberry pi for alerting the driver
- The ultrasonic sensor is interfaced with raspberry pi for detecting nearby vehicles
- Alcohol sensor is interfaced with ADC then to raspberry pi for detecting the driver is drunk or not
- Mems accelerometer is interfaced with ADC then to raspberry pi for detecting accidents
- The input data are given by sensors and the data are processed
- Then the processed data delivers the output
- Raspberry Pi
- Alarming device (Buzzer)
- Mems accelerometer
- Ultrasonic sensor
- MQ-3 Alcohol sensor
- Operating system: Raspbian Jessie
- Programming language: Python
- Programming platform: Python IDE
- Data mining algorithm: K-Means Nearest neighbor
 Maizatul Akmar Ismail, Tutut Herawan, Ashish Dutt, “A Systematic Review on Educational Data Mining,” IEEE, 2017.
 Uwe Becker, Geltmar von Buxhoeveden, “Comparison of Traffic Incident Data in Individual and Public Transport,” in International Conference on Systems and Informatics, 2016, pp. 1067-1071.
 Williamjeet Singh, Dheeraj Khera, “Prediction and Analysis of injury Severity in traffic system using data mining technique,” National Journal of Computer Applications, 2015.
 Sarbajit Bhattacharyya, Mrinal Roy, Pinak Paul, Rupanjan Chakraborty, “Accident Analysis and the Suggestion of an Accident Prediction Model for Guwahati city,” International Journal of Innovative Research in Science, Engineering and Technology, 2015.
 R.P. Kulkarni, S.U. Bobade, M.S. Patil, A.M. Talathi, I.Y.Sayyad, S.V.Apte, R.R.Sorate, “Identification of Accident Black Spots on National Highway 4,”, 2015.