Identifying Stress Level Among Gamers Using Electroencephalogram Signals

This research is conducted to identify stress level among gamer using Electroencephalogram Machine (EEG). Electroencephalogram machine or better known as EEG machine is a machine used by neuroscientists to read brain signals activity through various number of channels. The brain signals collected from subjects using 19 channels EEG machine which is DABO Machine. The problem in this research study is to find out if game can induce stress. The expected outcome of this research is that brain signal collected from subjects could give enough evidence about the relationship between playing game and stress level in their daily activities. Objective of the research is to design experimental procedure suitable for understanding the bio-signal of subjects inducing stress and to understand the relationship between four basic emotion (Happy, Calm, Fear, Sad) and the emotion while playing the games. In our research methodology, we focus on five difference stages to complete the research. The stages start with the data collection, pre-processing, features extraction classification and lastly analysis. Later, we able to come out with the result of our research about the stress level for the subject. The experiment was conducted by following a standard protocol experiment for EEG machine. This data will be analysed using Mel Frequency Cepstral Coefficients (MFCC) as feature extraction, and multilayer perceptron (MLP) as classifier. The result show that the subject has positive emotion which is calm and happy at the beginning and ending of playing the game. At the beginning, subject only start with demo, so the subject did not feel pressured and at the end we assumed that the subject feel relieved because of ending the game. After certain time playing the game, the subject starting to have negative emotion until the end of the game. This happen because of subject started to feel stress after plays the higher level of the game. Based on the result, we can conclude that game can induce stress among gamers

Mathefunic: A Mobile Based Game for Engaging Children with ADHD

Attention Deficit Hyperactivity Disorder (ADHD) is a common neurobehavioral disorder that is prevalent in children and adolescents. ADHD affects student’s learning due to its symptoms which are inability to stay focused, hyperactivity, and challenges in self-control. In this paper, we explore the use of mobile games to engage children diagnosed with ADHD. Mobile games are now widely used in learning, which is part of mobile learning. Previous studies have shown a positive relationship between digital games and learning for children with ADHD. Therefore, we designed and developed a mobile game based on existing literature on techniques used to retain the attention and engage children with ADHD. The study was evaluated based on the duration of time the children spent playing the game and their activities and interactions while playing the game. Our findings showed that mobile-based games can be used to engage children with ADHD.

P300 ERP Component on Eating Habits Profiling Using Dynamic Evolving Spiking Neural Network (deSNN)

— Unhealthy eating habits have become a big issue that often causes many chronic diseases in various countries in recent years. The current assessment to identify the status of eating habits is to use self-assessment. However, self-assessment is known to have an error or uncertainty value due to cognitive factors from respondents that affect the results of the assessment. A person's profile is potentially measured by reviewing Event-related potential (ERP) which is an ideal technique for understanding perception and attention. This study uses images of healthy and unhealthy foods as a stimulus when recording EEG data. The method used for classification is dynamic evolving spiking neural network (deSSN) based on the Neucube architecture. The results showed that the mean amplitude of the P300 component discovered in the Parietal and Occipital lobes was higher for healthy food in the healthy eating habits group. Whereas the unhealthy eating habits group was higher for unhealthy foods. The deSNN classification is proven to operate in learning ERP data but the accuracy rate is not too high due to inadequate sample training

Proposed De-noising Algorithm

minimizing noises from images to restore it and increase its quality is a crucial step. For this, an efficient algorithms were proposed to remove noises such as (salt pepper, Gaussian, and speckle) noises from grayscale images. The algorithm did that by selecting a window measuring 3x3 as the center of processing pixels, other algorithms did that by using median filter (MF), adopted median filter (AMF), adopted weighted filter (AWF), and the adopted weighted median filter (AWMF). The results showed that the proposed algorithm compares to previous algorithms by having a better signal-to-noise ratio (PSNR).

Factors Influencing the adoption of e-commerce by Small and Medium-Sized Enterprises (SMEs) in Algeria: a qualitative study

Small and Medium-sized Enterprises (SMEs) are regarded as the engine of the growth of the world economy. They had recently experienced rapid growth and improved their business activities in terms of customers’ number and revenue expansion when they began to embrace e-commerce and started using it in their business. However, although there is a growing interest in e-commerce, its use is still insufficient in Algeria. Therefore, this study aimed to identify the factors that influence the adoption of e-commerce by SMEs in Algeria. This study adopts a qualitative methodology which involves in-depth, structured interviews to identify the factors that affect SMEs for the adoption of e-commerce in Algeria. The result of research found the main factors hindering the adoption of e-commerce by SMEs in Algeria are the e-payment methods, non-readiness of banks, lack of legal protection and lack in awareness of the benefits of e-commerce, as well as fear of risks. However, some other elements are less significant to influence the adoption of e-commerce. These research findings will give an addition in terms of bringing and giving a chance to the SMEs' leaders and the Algerian economic officials and a clear view of e-commerce practices. This can help them to design a strategy to remove barriers tactfully to its advantage.

Advanced Voting System Using Fingerprint

A Fingerprint is an important identifier for the humans. This paper proposes finger print voting system with Arduino. The majority of the worldwide election were using a paper-based voting rather than using biometric system. The current voting process has safety problems such as authenticity of voters. In proposed system, a voter identity can be proved instantly. All voters’ information was stored securely to register in the system. The main objective is to enhance the security in order to prevent duplication and provide a system which reduce the burden for people on conducting a voting. Thus, by implementing this system, user can put their vote with fingerprint instead of paper without doubting about their security. Voting Using Fingerprint reduce the polling time, it provides easy and accurate counting without human labor.

Development of Classification Methods for Wheeze and Crackle Using Mel Frequency Cepstral Coefficient (MFCC): A Deep Learning Approach

The most common method used by physicians and pulmonologists to evaluate the state of the lung is by listening to the acoustics of the patient's breathing by a stethoscope. Misdiagnosis and eventually, mistreatment are rampant if auscultation is not done properly. There have been efforts to address this problem using a myriad of machine learning algorithms, but little has been done using deep learning. A CNN model with MFCC is expected to mitigate these problems. The problem has been in the paucity of large enough datasets. Results show 0.76 and 0.60 for recall for wheeze and crackle respectively, these number are set to increase with optimization.

Emergency Smartwatch for Fisherman

This work is about designing a smartwatch that is used mostly by fishermen. The watch provides the location of the user using the global positioning system (GPS) and a panic button that he can use in case of emergency. It can record the heart rate by using a heart rate sensor. The paper works with a software that is used by the appropriate authorities; they record the information provided by the smartwatch. The third part of the paper is a mobile application used by the rescue team; the application shows the location of the fisherman. This paper aims to help fishermen in case of emergency cases, they can be saved by the rescue team. Based on the heart rate sensor and the panic button provided by the smartwatch, the appropriate authorities can know when a fisherman needs help and send the rescue team.

Prediction of the Level of Air Pollution During Wildfires Using Machine Learning Classification Methods

The recent increase of forest fires due to agricultural field burning in the South East Asian region has led to haze episodes in Malaysia which contributed to the increasing number of hospital visits for treatments related to respiratory diseases. With the increase of air pollution, it becomes a necessity to attempt at investigating and predicting the air pollution levels, which would in turn which would lead to proper strategies so untimely effects to human health can be kept at a minimum. The Air Pollutant Index is used to identify and classify the ambient air quality status, However the lack of ground air quality monitors which compute the API generally leads to unreliable warning information. Recent studies indicate that data retrieved from remote sensing satellites is now an emerging alternative for air quality prediction at the ground level, hence this research aims to use satellite-based data to predict the air quality of East Malaysian cities with the help of different classification algorithms. Aerosol Optical data, Meteorological data and Fire data were collected from different satellite sources, two algorithms were selected and modelled. The two algorithms which were implemented, were Random Forest and Gradient Boosting, when trained and validated they both algorithms performed reasonably well with an accuracy 0.89 and 0.85 respectively, for the city of Kuching.

Waste Management Using Machine Learning and Deep Learning Algorithms

Waste Management is one of the essential issues that the world is currently facing does not matter if the country is developed or under developing. The key issue in this waste segregation is that the trash bin at open spots gets flooded well ahead of time before the beginning of the following cleaning process. The isolation of waste is done by unskilled workers which is less effective, time-consuming, and not plausible because of a lot of waste. So, we are proposing an automated waste classification problem utilizing Machine Learning and Deep Learning algorithms. The goal of this task is to gather a dataset and arrange it into six classes consisting of glass, paper, and metal, plastic, cardboard, and waste. The model that we have used are classification models. For our research we did comparisons between four algorithms, those are CNN, SVM, Random Forest, and Decision Tree. As our concern is a classification problem, we have used several machine learning and deep learning algorithm that best fits for classification solutions. For our model, CNN accomplished high characterization on accuracy around 90%, while SVM additionally indicated an excellent transformation to various kinds of waste which were 85%, and Random Forest and Decision Tree have accomplished 55% and 65% respectively