Early Detection System for Gas Leakage and Fire in Smart Home Using Machine Learning

Author(s):  
Lamine Salhi ◽  
Thomas Silverston ◽  
Taku Yamazaki ◽  
Takumi Miyoshi
2020 ◽  
Vol 10 (8) ◽  
pp. 2890
Author(s):  
Jongseong Gwak ◽  
Akinari Hirao ◽  
Motoki Shino

Drowsy driving is one of the main causes of traffic accidents. To reduce such accidents, early detection of drowsy driving is needed. In previous studies, it was shown that driver drowsiness affected driving performance, behavioral indices, and physiological indices. The purpose of this study is to investigate the feasibility of classification of the alert states of drivers, particularly the slightly drowsy state, based on hybrid sensing of vehicle-based, behavioral, and physiological indicators with consideration for the implementation of these identifications into a detection system. First, we measured the drowsiness level, driving performance, physiological signals (from electroencephalogram and electrocardiogram results), and behavioral indices of a driver using a driving simulator and driver monitoring system. Next, driver alert and drowsy states were identified by machine learning algorithms, and a dataset was constructed from the extracted indices over a period of 10 s. Finally, ensemble algorithms were used for classification. The results showed that the ensemble algorithm can obtain 82.4% classification accuracy using hybrid methods to identify the alert and slightly drowsy states, and 95.4% accuracy classifying the alert and moderately drowsy states. Additionally, the results show that the random forest algorithm can obtain 78.7% accuracy when classifying the alert vs. slightly drowsy states if physiological indicators are excluded and can obtain 89.8% accuracy when classifying the alert vs. moderately drowsy states. These results represent the feasibility of highly accurate early detection of driver drowsiness and the feasibility of implementing a driver drowsiness detection system based on hybrid sensing using non-contact sensors.


2019 ◽  
Vol 3 (3) ◽  
pp. 451-457
Author(s):  
Andi Setiawan ◽  
Ade Irma Purnamasari

The objective developed from this research is to utilize Smart Home with an integrated ESP32 microcontroller with a camera and MC-38 door magnetic switch sensor based on the Internet of Things (IoT) as a research base to detect the security of arumsari earth housing in Cirebon District when left by its inhabitants. ESP32 microcontroller which can be programmed via arduino IDE, then functioned to respond to the integrated camera so that it can transmit images when the MC-38 sensor door magnetic switch sensor is active. Technically the combination of the ESP32 microcontroller and MC-38 door magnetic switch sensor, which was developed as a prototype in this study is called the arumsari housing early detection system. The mechanism of the arumsari housing early detection system is when a house door or window is successfully forcibly broken without going through the system mechanism, then automatically an image or can also be developed into a video from a camera mounted on an ESP32 microcontroller will send the image through a web framework or smartphone as a form early warning of security to housing owners. The results obtained from this study are at the angle of normally open MC-38 door magnetic switch sensor of 60 - 1800, will work sending an image signal which means there is an indication of a burglar or unknown person entering the house. Whereas at the normally closed angle MC-38 door magnetic switch sensor is 00-50, it will not work sending an image signal which means the house is safe.


2020 ◽  
Vol 9 (1) ◽  
pp. 1
Author(s):  
Agung Wahyudi Biantoro

                             Agung Wahyudi Biantoro                       Mechanical Engineering Department,  Universitas Mercu Buana, Jakarta.                               Jl. Meruya Selatan No. 1, Jakarta Barat.  Email : [email protected] the need for efficient transportation is very important for modern human life. Various types of studies continue to be carried out to support the implementation of the use of Gas Fuel (CNG), to reduce dependence on fossil fuels. The use of BBG is considered more efficient and environmentally friendly than using fuel oil (BBM). However, thus, the use of CNG can hurt a negative impact on human safety and even cause considerable losses if it is not used carefully, especially if there is no known leakage from the tube and cause a fire to the vehicle. CNG gas that has a leak does smell so normal leakage is easily detected. However, if the leaky gas seeps into the engine, and the bottom of the bus or under the carpet, it will be difficult to detect. CNG gas is famous for its flammability so that the leakage of CNG equipment is at high risk of fire. Based on this description, the need for an early gas leak detection device using a microcontroller can monitor the presence of gas leaks in vehicles that can be observed directly through the LED screen in the form of a warning that can be placed on the cabin dashboard. From the above problems, the authors are interested in making a study by creating an innovation tool called GLEDS (Gas Leakage Early Detection System) in Microcontroller-Based Motorized Vehicles. The purpose of this study was to determine the condition of the design of the gas cylinder position in motorized vehicles and design the manufacture and GLEDS tool to detect gas leaks in motorized vehicles. Based on the whole system starting from the design and manufacture of GLEDS tools The conclusion is that the GLEDS gas leak detector can work well, this is indicated by the functioning of the tool when given butane gas. The buzzer sounds, the green LED lights up and displays graphical data on Android. Next, the sensor will detect a leak in the gas cylinder, if near the gas cylinder regulator there is really a butane gas content at a concentration of 280 ppm which then increases to 400 ppm. At a concentration of 300 ppm, the tool works well, with active buzzer alarms and LED lights. This GLEDS tool can be placed in the trunk of a car, close to gas cylinders of LNG four-wheeled motorized vehicles. Keywords: Gas Leak Detection, GLEDS, Arduino Uno, Microcontroller


Author(s):  
S. W. Kwon ◽  
I. S. Song ◽  
S. W. Lee ◽  
J. S. Lee ◽  
J. H. Kim ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document