Full Research Paper – Page 15 – NPS Australia Submission System

Creating Competitive Game Situation Using Cognitive Load

This study identifies effective interventions that can create competitive situations in a memory-based card game. The competitive condition entertains people of all ages in the game. A competitive game situation would create a flow state in players. This study focuses on Pelmanism as a memory-based game. The study identifies gimmicks to interfere with a player superior to the others with the player unnoticed to create a competitive situation in a memory game. Experimental results show that interference with higher cognitive load has a greater effect on the outcome of the game. In the experiment, the interference requiring high cognitive load degrades the correct answer rate from 33.2% to 24.0%. The results of the random forest analysis indicate the importance of influencing the working memory in the memory game. It means the cognitive load on the working memory can lead to game situations that all people enjoy.

Semantic segmentation of block-divided images – Consideration on evaluation method –

Drones having high resolution cameras and sensors have become more available and cheaper. We use drone-captured images taken directly above the plantation to research how well the types and areas of fruit trees, as well as other features, can be recognized. Wide-area images are synthesized from numerous locally captured images taken by the drone and are then divided into blocks (image blocks) with a certain amount of overlap to increase the number of blocks available for training. In this paper, semantic segmentation is applied to these blocks, and their classification performance is evaluated. In these evaluations, it is clarified that the overlaps in the blocks make it difficult to properly separate the training data for training the semantic segmentation network from the test data for performance evaluation. To address these issues, data augmentation is applied to the test data, and the evaluation results are presented.

Unveiling the Dynamics of Customer Shopping Trends Using Machine Learning Algorithm: A Comprehensive Analysis of Demographics, Purchase Behavior, and Payment Preferences

The present paper deeply investigates consumer shopping behaviour guided by the methods of machine learning. Having used the assessment of demographic parameters, purchase behaviour, and payment tendencies, this research comes up with deep-rooted consumer behaviour trends diversified across the various categories of consumer segments. The research includes an extensive database where advanced Artificial Intelligence technologies like clustering, classification, and forecasting are used to extract invaluable intelligence. The results underline certain differences in consumption patterns of clients belonging to the same demographic group which include people of different ages, genders, income levels, and geographical regions. The inclusion of machine learning technologies allows for gaining a supply of information about consumer behaviour that helps to make decisions wisely having sustainable development in the complex and competitive retail environment.

The AI Pentad, the CHARME2D Model, and an Assessment of Current-State AI Regulation

The contributions of this article are threefold: 1) we first introduce the AI Pentad to better understand and identify regulatory intervention points within AI’s core components, 2) we present the CHARME$^{2}$D model, a universal framework that can help frame, construct, and evaluate legislative efforts, 3) we conduct a broad assessment of the AI regulatory progress of selected countries and regions against the CHARME$^{2}$D model to highlight strengths, weaknesses, and gaps. This comparative evaluation offers insights for future legislative work in the AI domain.

Estimation of Likelihood for Prosocial Behavior from Physiological Responses during Listening to Music

The study proposes a method to measure the likelihood for target people to take prosocial behavior using their objective physiological data as well as Prosocial behavior means attempts to help others without expecting any external reward. Conventional methods use questionnaires to identify people with a strong likelihood to engage in prosocial behavior. The conventional methods impose an undesirable burden on them because the questionnaires on prosocial behavior are unusual to them. To avoid the unusuality, the proposed method makes people listen to heart-breaking music, recording a time series of their electrodermal activities (EDA), which are physiological responses expressing their emotional changes. An experiment turns out people likely to take prosocial people would show emotional responses to both acoustics and lyrics. An experiment turns out people likely to take prosocial people would show emotional responses to both acoustics and lyrics.

Three-Way Task Scheduling Algorithm for Cloud Computing

Cloud task scheduling is a crucial aspect of a cloud computing system, and its scheduling technique directly influences cloud platform resource usage and user service quality. This study presents a cloud task scheduling optimization algorithm, known as CTSA-3WD, which aims to address the issues of load imbalance, low resource utilization, and lengthy job completion time. In the suggested approach, the execution duration of cloud jobs and the actual computing resources situation restrict the task set’s light-load and heavy-load functions. The algorithm is based on the fundamental idea of three-way decision-making, and separates the work set into three pieces according to the percentage of the two jobs inside it. The system focuses on three distinct task sets and determines an optimal scheduling strategy by employing the Max-Min algorithm for the task set containing a significant proportion of light-load jobs, the Min-Min algorithm for the task set with a substantial percentage of heavy-load studies, and a combination of the Min-Min and Max-Min algorithms for the task set that includes both light and heavy load tasks. Essential resources within the designated nodes are rearranged, and the task that is most suitable for the underutilized resources is assigned to them in order to achieve the objective of reducing the overall time required for completion. The experimental results conducted on the CloudSim simulation platform demonstrate that the CTSA-3WD algorithm, when compared to Min-Min, Max-Min, and selective scheduling algorithms, effectively enhances overall resource utilization, user service quality, and resource efficiency. Additionally, it enables improved load balancing across the entire system.

Designing and Evaluating an Innovative Text Analytics Solution for Online Retailers’ Operational Decision Support

This research contributes to the field of text analytics by providing a structured methodology for developing and evaluating solutions that can transform customer feedback into actionable insights. The findings highlight the potential of such solutions to significantly improve decision-making processes and strategic planning in online retail, ultimately leading to enhanced customer satisfaction and business performance.

Feature enhancement and matching algorithms for material ablation measurement in high temperature wind tunnels

Aimed at the special requirements for dynamic measurement of material ablation inside high-temperature wind tunnels, a binocular stereo vision system based on straight slider rail laser projection and high-speed camera capture is designed. A feature enhancement method for ablation measurement objects in high-temperature and high-enthalpy environments is proposed, and a mathematical expression formula based on multi-line laser feature enhancement description and extraction of the light strip centerline is derived for adaptive rapid feature matching. This formula takes into account the grayscale centroid, camera frame rate, and the correlation between line laser scanning ranges, effectively reducing search complexity and dependence on high-frame-rate cameras. Experimental results show that the system can complete a 200mm scan within 1 second at a distance of 1350mm. Experiments on planar objects and spherical convex surface platform under various conditions demonstrate that the system can control the total error within 0.5mm at the normal distribution confidence levels of 1σ, 2σ, and 3σ which proving the efficiency, accuracy, and high dynamic characteristics of this method for non-contact measurement of material erosion in high-temperature wind tunnel environments.

Predicting Electricity Market Price Using Machine Learning and Quantifying Dependency Beyond Renewable Energy

We offer (i) a detailed analysis on the impact of variables beyond renewable energy sources on electricity price, and (ii) a unified machine learning-based platform that integrates other diverse factors beyond renewable energy to improve electricity price forecasting.
Our machine learning models predict electricity price by quantifying the dependency on renewable energy and other important diverse factors under unified settings.

Numerical Methods for the Minimum Energy Among Three Dynamic Systems Governed by a Class of Weakly Singular Integro-Differential Equations

In this study, we presented numerical methods for determining the minimum energy state among three dynamic systems governed by a class of integro-differential equation with weakly singular kernels (Abel-type). These equations were developed from a class of integro-differential equations originating from an aeroelasticity problem. By weighting energy criteria for the three systems, we intend to numerically reveal the most stable energy state for the systems with various initial conditions and tracking targets. A part of the numerical scheme is constructed by interchanging the differentiation and integration operations in the integro-differential equation. Promising numerical results are provided.

Paper Type: Full Research Paper