Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.

Stress assessment has been considered essentials in the early stages because stress-related abnormalities tend to increase the risk of strokes, heart attacks, depression, and hypertension. This may also induce suicidal thought within the victims of this neurological state. The CAD (Computer Aided Diagnosis) have been a way forward for both medical experts and people with complications. The recent development of Machine learning revolution has proved to be substantial for medical diagnosis and prediction. This approach can further be used with neurological tools. The initial status of the brain activities would act as a window into the brain; which can be used as an insight. With the influence of machine learning more generalized way of discriminating stress activities with other normal activities can be possible.

The EEG-neurofeedback modality has direct implication on alpha asymmetry. The efficacy of EEG-neurofeedback may be affected by the stimulus contents. This research investigated the effectiveness of 2D and 3D game stimulus content (GSC) on stress mitigation during neurofeedback training (NFT). The effectiveness is compared between stimulus contents by measuring the mean prefrontal alpha asymmetry using quantitative Electroencephalogram (qEEG) analysis. For this, ten healthy participants among university students were recruited and performed twenty-minutes neurofeedback training (NFT) on Fp1-Fp2 within a period of sixty days to record forty sessions of data. The statistical analysis of the data after the neurofeedback training showed an effect of game contents on alpha asymmetry. The graphical analysis of alpha power showed that the 3D game content was more effective than the 2D game content. The outcome of 3D game stimulus content showed effect on the prefrontal alpha asymmetry and improve the treatment efficacy of neurofeedback for stress mitigation.

The proliferation of giant hypermarkets propelled the demand of indoor positioning and navigation system for better customers' shopping experience. A customer that moves around a massive shopping area, for example 500,000-square-foot needs route guidance to search for the desired items and its location. The retailer on other hand wants to send real-time messages based on the customer's current location in the market. This paper addresses aforementioned problem and presents an intelligent solution for route problem for customer. Raw floor map of supermarket under consideration has been manually transformed into graph for combinatorial optimization. To meet the desired objective, Hungarian's and A* Search algorithms have been used in a cascaded manner to facilitate customer in two ways: (1) Chronological sequencing of items list will be suggested to customer based on the distance between current customer location and the location of item of his interest (2) Customer can also view the suggested single shortest path connecting every location of item of his shopping list based on A* findings. Once the proposed intelligent system navigation service is deployed on customer's smartphone, he or she can send or share item list with system to receive traces of desired location within premises. Results show that Hungarian Algorithm will assign optimal ordering for items to be purchased. Similarly A* search results in minimal iterations showing less time consumption and less number of nodes showing least memory requirement compared to Breadth first whilst searching for shortest route.

Huge Gap has been observed on study of projectile simulation models relating it to speed of camera or frame per seconds. The objective of this paper is to explore and investigate time driven simulation models to mimic projectile trajectory; with an intent to highlight importance of game programming on native platforms. The proposed projectile recurrence relation and extensive mathematical modeling based on Triangular Series is an innovative outcome of project and game based learning used in BSCS-514 Computer Graphics Course at Department of Computer Science (DCS) University of Karachi (UOK). Box2D Replica of Popular 2D Mobile Game Angry Bird has been created on desktop to have an in depth mathematical and programming insight of commercial physics engine and discrete event simulation. Analysis has also been performed to answer certain key questions for progressive projectile trajectory for e.g. (1) With What angle, projectile should be launched? (2) What is the maximum height it will reach? (3) How long it will take for landing? (4) What will be its velocity to reach a desired height? (4) Where it will hit? (5) How it will bounce? The above stated questions are important to answer so that projectile motion within engineering, Gaming and other CAD Applications can be taught and programmed correctly specially on native platforms like OpenGL. Besides reporting Numerical results, a successful projectile based game making has been compiled and reported to validate the significance of project based learning in classrooms and labs.