Deepani Babarenda Guruge

Standard objective metrics often fail to correlate accurately with human perception in the evaluation of stereoscopic 3-D (S3D) video watermarking. This study proposes a hybrid Multi-Criteria Decision-Making (MCDM) Watermarking Framework (MCDM-WF) to systematically evaluate and rank the performance of watermarking algorithms based on their robustness and perceptual transparency. Drawing on an analogy to human-centric decision-making modeling, the framework mimics how the brain evaluates and prioritizes conflicting criteria such as imperceptibility and durability, when making judgments under uncertainty. The methodology integrates the Analytic Hierarchy Process (AHP) to derive subjective preference derivation, entropy-based weighting for data-driven objectivity, and the VIekriteri-Jumsko KOmpromisno Rangiranje (VIKOR) for compromise ranking. Experimental validation was conducted according to ITU-R standards using advanced stereoscopic display platforms. The results demonstrate that the proposed framework provides a technically rigorous ranking of watermarking configurations. Specifically, the proposed evaluation algorithm applied within the framework, referred to as the Stereoscopic 3-D watermarking method (S3D-WM), consistently achieved the optimal compromise (Rank 1) by balancing the False Negative Ratio (FNR) against the structural and peak signal fidelity. The hybrid approach advances multimedia security evaluation by unifying algorithmic benchmarking with human-centric decision modeling. This study advances engineering applications through a hybrid framework for rigorous multimedia security evaluation, while contributing to artificial intelligence by formulating a decision-analytic evaluation layer that integrates data-driven metrics with human-centric preference modeling.

Convolutional Neural Networks (CNNs) constitute the foundation of modern computer vision systems, yet their empirical performance is frequently governed as much by training configuration choices as by architectural design. Despite this, critical hyperparameters—including optimizer selection, batch size, learning rate, training duration, dropout regularization, and batch normalization—are often selected heuristically or reported incompletely. Based on two benchmark datasets (CIFAR-10 and MNIST) and two classical CNNs (CifarNet-11 and LeNet-5), this paper presents a systematic, configuration-aware empirical study that quantifies how these variables influence predictive accuracy, convergence stability, generalization behavior, and computational efficiency of CNN models. Using a controlled experimental methodology in which individual configuration variables are isolated and evaluated under identical conditions, we demonstrate that configuration choices can induce performance variations comparable to those achieved through substantial architectural modifications. The results reveal explicit accuracy–efficiency trade-offs, identify regime-dependent optimal configurations, and highlight the central role of early stopping and normalization in stabilizing learning dynamics. These findings elevate configuration-aware optimization to a first-order design principle for reproducible research and reliable deployment of CNN-based artificial intelligence systems.

Academic integrity is a cornerstone of education systems, yet the rise of contract cheating poses significant challenges for higher education institutions. Current approaches to managing contract cheating often lack the comprehensive structure needed to address the complexities of modern cheating methods. The primary objective of this study is to investigate the effectiveness of the proposed Three-Tier Framework (TTF), designed in our previous study to combat contract cheating. The proposed framework comprises three tiers: awareness, monitoring, and evaluation. It engages stakeholders within the system and encourages a proactive and collaborative stance against contract cheating while reinforcing a culture of academic honesty. The evaluation focuses on three key aspects: the clarity of the framework’s functions and objectives, the potential challenges in implementing the proposed monitoring process, and the perceived limitations in detecting and mitigating contract cheating through this framework. Supervised and unsupervised assignments are considered, excluding the option of e-proctoring, as some students encountered difficulties setting up necessary tools and software for online exams. Survey results reveal a broad consensus among respondents, who expressed strong confidence in the clarity and effectiveness of the framework and its monitoring procedures. These positive perceptions were consistent across respondents, regardless of their prior experience or familiarity with contract cheating. Although the overall feedback was positive, concerns were raised regarding implementing the framework in current educational settings. Specific challenges cited include tight timelines and the increased workload associated with the new procedures, emphasising a need for additional guidance, training, and institutional support to ensure effective adoption. The proposed framework incorporates an instructor dashboard designed to streamline academic workflow and simplify the monitoring process introduced in this framework. The survey results confirm that the framework can be adopted to address the unique needs of academics and diverse educational environments; however further research is needed to explore its applicability across the broader higher education community.

There has been a growing number of contract cheating incidents recorded in Australia’s higher education system. Such activities create a significant threat to the validity and integrity of qualifications obtained by students. This paper introduces a conceptual framework to combat contract cheating by compiling the findings on domain analysis, institute-wide policy analysis, and by applying self-efficacy theories. The literature review on domain analysis lays out two state-of-the-art strategies to combat contract cheating: detect and mitigate the opportunities. Policy document analysis sheds some light on existing operating mechanisms for handling contract cheating cases and the gaps need to be addressed. The proposed framework has three tiers: Awareness, Monitoring and Evaluation. At the awareness level, students’ awareness concerning contract cheating is enhanced by several activities, and staff skills are strengthened by professional activities. At the monitoring level, student activities associated with assessments are recorded using a Pre-Designed Template (PDT) and are monitored by analysing the data in three databases; Monitoring database, Academic Integrity breach database, software analysis data. At the evaluation level, the institutional policies, procedures and services related to contract cheating are evaluated and revised on a regular basis, using feedback mechanisms. This holistic approach may discourage contract cheating by increasing the awareness among students, developing professional skills of staff and organising continuous course-wide student monitoring using various databases. Finally, the proposed approach fills the gaps in the existing system by utilising a systematic process to evaluate an institute’s policies, procedures and services.

Location prediction in an indoor environment is a challenge, and this has been a research trend for recent years, with many potential applications. In this paper, machine-learning-based regression algorithms and Received Signal Strength Indicator (RSSI) fingerprint data from Wireless Access Points (WAPs) with dual Service set IDentifiers (SSIDs) are used, and positioning prediction and location accuracy are compared with single SSIDs. It is found that using Wi-Fi RSSI data from dual-frequency SSIDs improves the location prediction accuracy by up to 19%. It is also found that Support Vector Regression (SVR) gives the best prediction among classical machine-learning algorithms, followed by K-Nearest Neighbour (KNN) and Linear Regression (LR). Moreover, we analyse the effect of fingerprint grid size, coverage of the Reference Points (RPs) and location of the Test Points (TPs) on the positioning prediction and location accuracy using these three best algorithms. It is found that the prediction accuracy depends upon the fingerprint grid size and the boundary of the RPs. Experimental results demonstrates that reducing fingerprint grid size improves the positioning prediction and location accuracy. Further, the result also shows that when all the TPs are inside the boundary of RPs, the prediction accuracy increases.

In recent years, education institutions have offered a wide range of course selections with overlaps. This presents significant challenges to students in selecting successful courses that match their current knowledge and personal goals. Although many studies have been conducted on Recommender Systems (RS), a review of methodologies used in course RS is still insufficiently explored. To fill this literature gap, this paper presents the state of the art of methodologies used in course RS along with the summary of the types of data sources used to evaluate these techniques. This review aims to recognize emerging trends in course RS techniques in recent research literature to deliver insights for researchers for further investigation. We provide a systematic review process followed by research findings on the current methodologies implemented in different course RS in selected research journals such as: collaborative, content-based, knowledge-based, Data Mining (DM), hybrid, statistical and Conversational RS (CRS). This study analyzed publications between 2016 and June 2020, in three repositories; IEEE Xplore, ACM, and Google Scholar. These papers were explored and classified based on the methodology used in recommending courses. This review has revealed that there is a growing popularity in hybrid course RS and followed by DM techniques in recent publications. However, few CRS-based course RS were present in the selected publications. Finally, we discussed future avenues based on the research outcome, which might lead to next-generation course RS.

As mobile devices have become a part of our everyday life, there is a lot of research going on how to make this technology more productive for the students. Most of the research studies have indicated that, mobile devices are very useful for students while a few research studies negates its effectiveness. In this paper, we have presented the literature survey conducted on the use of mobile technologies in the field of Teaching and Learning (T&L). These studies are broadly classified into three areas: Impact and learning environment; specific applications; and mobile learning framework. We will be exploring all these areas in this paper. Our review in impact and environment of mobile learning indicates that the use of mobile technology is nourishing the knowledge and learning of students in most cases. Our review on specific applications of mobile learning reveals positive impacts on learning in various fields but the key concern raised was difficulties in implementing them and not having proper control guideline. Moreover, our review on frameworks for mobile learning indicates that there are different frameworks developed for different applications. Most of the applications are limited to non-technical areas. However, we can observed that there is a lack of connectivity between course development and framework for mobile learning. Therefore, the future course developers need to address the gap by taking into account of learners’ behavior in using mobile devices and their cultures to enrich student engagement and learning.

Error Correction Schemes (ECSs) significantly contribute to enhancing reliability and energy efficiency of Wireless Sensor Networks (WSNs). This review paper offers an overview of the different types of ECS used in communication systems and a synopsis of the standards for WSN. We also discuss channels and network models for WSN as they are crucial for efficient ECS design and implementation. The literature review conducted on the proposed energy consumption and efficiency models for WSN indicates that existing research work has not considered Single Hop Asymmetric Structure (SHAS) with high performing Error Correcting Codes (ECCs). We present a review on proposed ECS for WSN based on three criteria: Forward Error Correction (FEC), adaptive error correction techniques, and other techniques. Based on our review work, we found that there are limited works on ECS design on a realistic network model i.e., a modified multi-hop WSN model. Finally, we offer future research challenges and opportunities on ECS design and implementation for WSN.