Psychophysiological Tracing of Game Addicts and Non-Addicts by Statistical Modelling with EEG Signals

Project Title

Psychophysiological Tracing of Game Addicts and Non-Addicts by Statistical Modelling with EEG Signals

Project Area of Specialization Wearables and ImplantableProject Summary

Harmful consequences of video game addiction include lack of concentration, ignoring intimate relationships, sleep deprivation, fatigue, increasing loneliness, aggressive behavior, maladaptive memory, inattention, suicidal thoughts, and death. There are several methods that have already been used to detect gaming addiction, of which survey assessment is very common. Suravy assessment is not accurate method, as it rely entirely on the reliability of the data and the validity of a person's self-description of feelings and moods. There is a need for an approach that can be more precise to observe gaming activities and can be more authentic.  

The first of aim of this project is to examine the EEG (electroencephalograms) signal frequency attributes of excessive video game players, in order to trace early symtoms of video game addiction. The second aim of this project is to develop video game addiction tracing alert system based on EEG signals. Based on two aims, this project will be made up of two components. The first component would be a psycho-physiological analysis of the player’s state of video game addiction, and the second part would be a model that would practically integrate the findings of the developed system to trace video addicts based on compact handheld tracing device system.

A quantitative scale for evaluating the activities of video gamers will be developed and used to track precise demographic data and pre-categorization of video game addiction. In order to gain quantitative information for the detection of addicted video game players, a transient and frequency domain study would be applied to EEG data. It has been reported in literature that generally  values of  ? and ?  bands is dramatically higher in addicts.

Project Objectives

The main objectives of the project are

(I) To examine the frequency and time domain features of EEG data to ascertain any discrepancies or associations between addiction and normal gaming behavior.

(II) To classify EEG data into different degree of addiction and normal behavior, specifically using regression models, the  EEG data that will be generated from commercially available MUSE headsets.

(III) To spot early unusual gameplay activities and to help alert others to the limitations of playing normal video games.

 (IV) To create a procedure prescribed for the diagnosis of video game addiction, the procedure my potentially be used by doctors

Project Implementation Method

The preliminary step will be a questionnaire-based assessment. We will then use the data obtained from these experiments for the pre-assessment of addicted and non addicted subject.

The experimental work will start by implementing addict and non-addict EEG signal correlation in of participating subjects during video game play. The develop algorithm will execute both the encoding and the tracing examination of the brainwaves. Simple signal-processing,  including  artifact elimination, and bandstop filtering will be carried to obtain noise free signal and information.

In this proposed project, there are two possible diagnostic tracks that include a cross-correlation of the EEG signal or an extraction function of the alpha and theta occipital regions. By having an addicted signal in the application database as a reference signal to be used by other users, cross-correlation is made between the two signals. The effects of the cross-correlation of signals will be transmitted directly to the main judgment block of the device. 

The second step is the use of the alpha and theta wave characteristics of the occipital signal for diagnosis. In order to compare results, thresholds for addicted and non-addicted subjects can be drawn from the database and a decision can be taken through input on the main decision block. In comparison, an addicted and non-addicted model is present in order to compare the various properties of the alpha and theta frequencies. The final results can be shown in terms of the proportion of the level of addiction (i.e., low-, medium- or high-risk states).

Benefits of the Project

The best advantage of this project is that by personalized low cost EEG headsets, we will be able to help the patients (Video Game Addicts) by conveying degree of addiction

1. The proposed project design can be used for personal assistance to the subject or may be used to suggest better recovery from any specialist. The develop algorithm will conduct both the encoding and diagnostic analysis of the EEG signal on a cell device or computer.
2. Not only for video games, but even by researching the frequency components in greater detail, this project may help to detect depression accurately, and other cognitive and behavioral problems may be monitored and used for a number of purposes. In order to mitigate health risks and maximize healthy results, this technology will then be used to integrate these data into smart self-monitoring gadgets.
3. Rehabilitation and recovery will both be strongly supported by this project, as any addiction requires a clear understanding of the changes needed as part of the addiction process. There are currently no formal physiological diagnostic criteria to explain the excessive or addictive play of video games.
4. To date, there are numerous methodological shortcomings of gaming addiction, one of the most important of which is that the majority of the study depends on sample evaluations. Self-reporting approaches and retrospective analyzes rely entirely on the reliability of the data and the validity of a person's self-description of feelings and moods. Our project work can be much more diverse and involve multi-method approaches in which objective gaming behaviour analysis is carried out to associate this behavior with real-time implications and to include psycho-physiological testing for the identification of emotional, neurological and neural changes.

Technical Details of Final Deliverable

1 Identification low cost full setup Based on EEG signals, with a smart phone application to determine the extent of addiction from Bluetooth data obtained. The diagnosis was modelled and a device architecture was proposed to use this data to practically alert the patient of possible addiction.

2. In terms of the percentage of the addiction stage, the final findings will be shown (i.e., low-, medium- or high-risk states).

3. Conference/Journal publication

4. Expertise development in EEG signal analysis

5. A. QUESTIONAIRE BASED PRE EVALUATION Results

6. Algorithm developed CROSS CORRELATION Analysis

7. Algorithm Built for POWER SPECTRAL VALUE ANALYSIS.

8. Algorithm developed LOGISTIC REGRESSION MODELING

Final Deliverable of the Project HW/SW integrated systemCore Industry MedicalOther Industries Health Core Technology NeuroTechOther Technologies Robotics, Wearables and ImplantablesSustainable Development Goals Good Health and Well-Being for People, Industry, Innovation and Infrastructure, Sustainable Cities and CommunitiesRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	67765
Arduino Wi-Fi Shield	Equipment	1	7500	7500
Header Pin to Touch Proof Electrode Adapter	Equipment	1	4125	4125
EMG/ECG Snap Electrode Cables	Equipment	1	3500	3500
EMG/ECG Foam Solid Gel Electrodes	Equipment	30	70	2100
Dry EEG Comb Electrodes	Equipment	30	170	5100
MyoWare Muscle Sensor	Equipment	1	6900	6900
Pulse Sensor (Heart-Rate Monitor)	Miscellaneous	1	420	420
Ten20 Paste Jars 3-Packs	Equipment	3	1540	4620
Muse Headband	Equipment	1	33500	33500