Stay Awake Using Brainwaves Technology
Joyce Chettiar1, Chintan Davda2, Neha Borulkar3, and Pravin Pandey4
Department of Information Technology, St. Francis Institute of Technology, Mumbai, India
[email protected], [email protected], [email protected], [email protected]
AbstractDrowsiness is on of the major cause of incomplete and inefficient work. This paper presents an mobile based application along with brain computer interface (BCI) to analyze and store the brainwaves of the user. BCI is mounted on the head of the user to monitor the users brain frequencies and detect whether the user is in a drowsy state or not.
If the user is in drowsy state the mobile application will generate an alarm to wake the user up. The users sleeping pattern along with his work history is recorded and stored on the cloud. The stored data is further analyzed using support vector machine (SVM) algorithm to predict users health. The project focuses on helping user get their work done alongside to maintaining a healthy sleeping pattern.
Keywords Brain computer interface (BCI); Support vector machine (SVM); EEG; Android application; drowsiness detection.
A study suggested that, an adult brain consists more than an hundred billion neurons interconnected to each other.Electric charges are generated by the neurons while the brain is working. These minimalist electrical charges, provides a very small electric field with varying electrical potential differences around the scalp in microVolts range, which can be measured with the help of sensors. Electrodes or sensors are placed on the scalp at different locations.These electrical potential difference is known as Electroencephalography (EEG). The EEG frequencies or EEG signals are also known as Brainwaves..
Electroencephalographic, EEG is a device that capture the activity of brain. The electrical activity of brain is recorded from the scalp surface at a particular location, thus EEG can be applied repeatedly without any risk to anyone. The captured Brainwaves pattern by EEG normally range from 0.5 to 100?V, and generates a sinusoidal shapes and are measured from peak to peak .
TABLE 1. EEG Brain Waves Signal 
Delta 0.5 – 4 Hz
Theta 4 – 7 Hz
Alpha 7 – 13 Hz
Beta Above 13 Hz
Drowsiness is one of the major cause of incomplete work. Humans have a lot of work to complete and this takes up a lot of time and energy.
The incomplete work results in an inadequate professional life, and to make it sufficient, humans tend to exhaust themselves.By doing so, they are fail to maintain a healthy sleeping pattern, deteriorating their health.
Brainwaves is used to detect the drowsy state and notify the user by generating an alarm to keep him or awake.
The sleeping pattern of every individual is distinct. The sleep data will be stored on the cloud database. The data can be used to analyse the frequency on the basis of age group. The graphs of sleeping data can be generated. These data and graphs are proven to be very essential in determining a persons health condition and whether he/she is living a healthy life.
An Android Application is used to monitor the users sleep pattern. The user sets a timer, and in that time frame the system will analyze the frequency and keep the user awake. The users sleeping data is stored on cloud and is be used for future analyses .
Android Mobile Phone
Arduino IDE 1.8.5
Fig. 1. Schematic placement of 10-20 electrode system
To procure an accurate EEG signal from the human scalp, 3 regions are used, Frontal lobe(F), Parietal lobe(P), and the Temporal lobe(T). The Frontal lobe is the region where all the conscious thoughts and decisions making are done. Parietal lobe function is to integrate all the information stemming signals from internal sensor feedback from limbs, head, skeletal muscles, otoliths, and etc and from the external sources. The Temporal region does all the work associated with processing sensory input like emotional association and visual memories.
A headset module is designed, shown in Fig.4, using the circuit diagrams from. The headset consists of three electrodes. The placement of two electrodes, one at temporal region positioned at T3 and other at the frontal region positioned at F8. The last electrode is used as the reference electrode positioning at Pz .
Fig. 2: Frequency Graphs of EEG Signal
EEG signals can be segregated into different components based on the frequency band. The characteristic of deep sleep are Delta waves and those are high amplitude waves having a frequency ranging from 0 ?f ?4 Hz. Theta waves frequency band is for meditation, idling or drowsiness occur within the 4-8 Hz frequency band. Alpha waves has a frequency range of 8-14 Hz and take place while relaxing or reflecting. Another approach to boost alpha waves is to close the eyes. Beta waves falls in 13-30 Hz frequency band and are feature of the user being alert or active, they become present while the user is concentrating. Gamma waves in the 30-100 Hz range occur during sensory processing of sound and sight. Lastly, mu waves occur in the 8-13 Hz frequency range while motor neurons are at rest. 
NodeMCU MicroController is used for computing the processed signals. The FFT function on nodeMCU will then convert the time domain signal into frequency domain signal. These signals will be sent to the cloud using the integrated Wi-FI module on NodeMCU. Simultaneously, a signal will be sent on the users phone if he is in a drowsy state to wake him up. The utmost important task is of the acquisition of signals precisely and adequately.
Fig. 3: NodeMCU module.
A signal without any distortion is required, as the frequency of the brainwaves are extremely low. Low frequencies can cause unpredictable results as a minute interferences from the external environment leads to alteration of the frequency.Once the processed signals are fed into to the microcontroller then it starts computing the signals with the threshold frequency. After the threshold is achieved, the microcontroller is obligated to send the notification onto the mobile application. NodeMCU is then responsible for sending the signal onto the mobile application to notify the user as well as onto the cloud service storing the users sleep data.
Fig. 4: Circuit of EEG Module
The android app will consist of overall four main activities. The Register/Login, The Home, The Work Duration and User Activity. The Register/Login activity will ask the user to log-in, if the user is a new user then the activity will redirect him/her onto the registration page
Fig. 5: Login activity of Mobile Application
Fig. 6: Registration activity of Mobile Application
The home activity will display a list view which contains the number of hours or minutes the user has worked, also it shows whether the user completed his/her work in that time.
Fig. 7: Home activity of Mobile Application
The Work Duration activity contains dropdown ( hours and minute), by clicking on the start button the clock will start working. The Timer activity will appear which will show progress bar with how much time is completed. The user can click on stop button and the timer will be paused. The user can choose to either continue working by clicking Startor choose to stop the activity by clicking Done. Whenever the user is in a drowsy state the alarm will start and stop button will appear to stop the alarm.
Fig. 8: Timer activity of Mobile Application
The user activity will contain the users data. Data like name, age, and gender.
Fig. 9.: User activity of Mobile Application
Brainwaves or EEG Technology has a wide range of applications. It can be easily applied in various medical field to know about a patients mental health or applied into day-to-day activities like driving a car. The physical devices included in the system are EEG module, a cloud database and
a cellular device. A new features can be added into the mobile application is, if the user is using the device and a deep sleep frequency value is achieved so instead of waking the user it should let the user sleep. Another feature is, if the alarm is raised for five times, and the system continuous to receives a drowsy state frequency then the alarm will no longer be generated thus letting the user sleep. As continuously waking a sleepy person repeatedly will affect the health of the user.
A Drowsiness Detection model was designed for people who have plenty of work to complete and are required to stay awake for the same. Staying up after an exhausting day is arduous. This system will detect the user state of the brain with the help of brainwaves. The system monitors an individual and decides whether he or she is drowsy. If an individual is drowsy the system will send an alarm on the users mobile device to wake him or her up.
The individual’s sleep data is stored on the cloud. This data is used to analyze the sleeping pattern of the individual.
Y. S. Soni, S. B. Somani and V. V. Shete, “Biometric user authentication using brain waves,” 2016 International Conference on Inventive Computation Technologies (ICICT), Coimbatore, 2016, pp. 1-6.
B. S. Zainuddin, Z. Hussain and I. S. Isa, “Alpha and beta EEG brainwave signal classification technique: A conceptual study,” 2014
IEEE 10th International Colloquium on Signal Processing and its Applications, Kuala Lumpur, 2014, pp. 233-237.
Anupama Kaushik IOT-An Overview, International Journal of Advanced Research in Computer and Communication Engineering, Vol. 5, Issue 3, March 2016.
Riadh, May. (2016). Notification System to Students using an Android Application. International Journal of Computer Applications. 140.22-27.10.5120 /ijca2016909189
Brain-Computer Interface, Charles Moyes-Mengxiang Jiang:
DIY EEG (and ECG) Circuit Instructables –