The Smart Automobile (SAM): An Application Based on Drowsiness Detection, Alcohol Detection, Vital Sign Monitoring and Lane based Auto Drive to avoid Accidents

Hyder, Ghulam; Chowdhry, Bhawani Shankar; Memon, Khuhed; Ahmed, Aisha

doi:10.1109/gcwot49901.2020.9391617

Cited by 9 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…heart rate and electrocardiograph, which can automatically alert and notify emergency contacts and upload the information to the car network when there is a problem with the passenger's vital signs. If there are any emergencies, the fastest path to the hospital can be planned automatically in the system for resuscitation [9].…”

Section: Advantages Of Auto-driving Carsmentioning

confidence: 99%

Research on the application of artificial intelligence to auto-driving cars

Lin

2023

ACE

View full text Add to dashboard Cite

Since the concept of artificial intelligence was introduced in the 1950s, artificial intelligence technologies have emerged more and more frequently. Besides, the application of artificial intelligence technologies in driverless cars has increased, especially in the field of image recognition. Many deep learning methods of image recognition have emerged in the field of autonomous driving. The primary purpose of this paper is to highlight the importance and functionality of using neural networks and image recognition in artificial intelligence for driverless functions. This paper also provides a comprehensive review of the core aspects of driverless technology, the role of image recognition and person recognition in environment perception, the impact of deep learning on driverless behavior decisions, and driverless vehicle kinetic energy control systems. Although the driverless car technology is now being updated, all three modes have great accuracy and results. However, each subsystem still faces many problems and challenges, which may be solved in future research. The driverless car technology would be promoted on a large scale after its safety and suitability are ensured.

show abstract

Section: Advantages Of Auto-driving Carsmentioning

confidence: 99%

Research on the application of artificial intelligence to auto-driving cars

Lin

2023

ACE

View full text Add to dashboard Cite

show abstract

“…On the other hand, Harkous et al [17], presented a two stage machine learning method for drunk driving detection, the proposed methodology uses a series of sensors placed in the vehicle to feed a hidden Markov model that select the best subset of sensors to be used by a recurrent neural network, the system was based on the detection of the vehicle movement rather than the alcohol presence, the system achieved a 75-98% of accuracy depending of the number of sensors used by the model. Recently, Hyder et al [18], developed a system based on an SoC (System on Chip), to detect drowsiness, the system uses a IoT sensor to detect the presence of alcohol, for this the system placed the alcohol detection sensor near the steering wheel to be close of the driver, then using a threshold, the presence of alcohol was detected, the system also detected the drowsiness by using cameras to detect the eye aspect ratio, the authors reported up to 92% of accuracy for the detection of the drowsiness when using the cameras, for the alcohol detection, only the threshold was reported. Vijayan et al [19] also proposed a system to detect driver drowsiness based on the use of image processing, here the authors proposed a system that recorded the drivers's face then was feed to deep neural networks to infer the state of the driver, the system used ResNet50, VGG16, and InceptionV3 to classify the driver's state, the authors reported an accuracy of 76.16%, 71.22%, and 78.43%, respectively.…”

Section: Introductionmentioning

confidence: 99%

In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection

Celaya-Padilla

Romero-González

Galván-Tejada

et al. 2021

Sensors

View full text Add to dashboard Cite

Worldwide, motor vehicle accidents are one of the leading causes of death, with alcohol-related accidents playing a significant role, particularly in child death. Aiming to aid in the prevention of this type of accidents, a novel non-invasive method capable of detecting the presence of alcohol inside a motor vehicle is presented. The proposed methodology uses a series of low-cost alcohol MQ3 sensors located inside the vehicle, whose signals are stored, standardized, time-adjusted, and transformed into 5 s window samples. Statistical features are extracted from each sample and a feature selection strategy is carried out using a genetic algorithm, and a forward selection and backwards elimination methodology. The four features derived from this process were used to construct an SVM classification model that detects presence of alcohol. The experiments yielded 7200 samples, 80% of which were used to train the model. The rest were used to evaluate the performance of the model, which obtained an area under the ROC curve of 0.98 and a sensitivity of 0.979. These results suggest that the proposed methodology can be used to detect the presence of alcohol and enforce prevention actions.

show abstract