Garuda - Garba Rujukan Digital

Cost-Optimised IoT Architecture for Real-Time E-Waste Monitoring with Operational Validation Belinda Ndlovu; Zvinodashe Revesai; Kudakwashe Maguraushe
Journal of Information System and Informatics Vol 8 No 2 (2026): April
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i2.1553

Electronic waste (e-waste) is the fastest-growing solid waste stream worldwide, yet formal collection systems remain limited. Many existing Internet of Things (IoT) solutions emphasize advanced functionality at the expense of cost efficiency and practical deployability. This paper presents a cost-optimized IoT architecture for real-time monitoring of e-waste bins. The proposed system adopts a four-layer architecture integrating ESP32 microcontrollers, ultrasonic sensors for fill-level detection, and infrared sensors for monitoring, supported by a Node.js backend that provides real-time data updates. System validation was conducted through sensor calibration (n = 30), functional testing, stress testing, and cost-performance benchmarking against RFID-, GSM-, and LoRa-based alternatives. Experimental results demonstrate a fill-level accuracy of ±3.2%, temperature precision of ±1.8°C, system reliability of 97.3%, uptime of 98.7%, and an average latency of 2.1 s. The deployment cost was USD 78 per bin, which is approximately 40% lower than comparable RFID-based systems. In addition, the system reduced unnecessary collection trips by 35% and yielded an estimated return on investment (ROI) of 8.5 months. These results show that a low-complexity, cost-efficient IoT design can provide a scalable and practical solution for e-waste bin monitoring.

Twitter (X) Sentiment Analysis on Monkeypox: A Systematic Literature Review Hazel Chamboko; Kudakwashe Maguraushe; Belinda Ndlovu
IJID (International Journal on Informatics for Development) Vol. 14 No. 2 (2025): IJID December
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2025.5196

Monkeypox has a risk of growing into a global threat. Understanding public sentiments is crucial for effective emergency responses, as it helps counter misinformation, enhance communication, and improve the retention and application of public health information. This systematic review of literature aims to provide foundations for identifying existing algorithms, commonly used data collection methods, and pre-processing techniques applied to Twitter discussions on Mpox. The review followed the PRISMA guidelines. Relevant literature was retrieved from ScienceDirect, IEEE, PubMed, and Springer databases, resulting in 15 studies that met the inclusion criteria. Most preprocessing methods include stop word removal, lemmatisation, and tokenisation; commonly used data collection methods include Twitter API, Academic API V2, Snscrape, Twint, and Tweepy. Classification of sentiment tended to be hybrid models like CNN-LSTM or transformer-based models such as BERT, which also perform well in dealing with complex linguistic patterns. These recent models, additionally, addressed other very important issues like misinformation detection, irony, and bot-generated content, which earlier models would often fail to tackle. Despite these advancements, much work still needs to be done in improving the accuracy, generalizability, and interpretability of sentiment analysis models in live monitoring of public health.

Early Detection of Diabetic Retinopathy Through Explainable AI Models: A Systematic Review Tinashe Ngwazi; Belinda Ndlovu; Kudakwashe Maguraushe
IJID (International Journal on Informatics for Development) Vol. 14 No. 2 (2025): IJID December
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2025.5200

Diabetes, if not detected early, can lead to serious complications such as vision loss, known as diabetic retinopathy. Explainable Artificial Intelligence (XAI) can enhance traditional Machine Learning methods, which are not understandable and transparent in diagnostic tasks. This Systematic Literature Review explores data inputs that influence the performance of XAI models in detecting diabetic retinopathy, how XAI techniques can enhance early detection outcomes in diabetic retinopathy, the challenges in implementing these techniques and the ethical implications of using these models in clinical practice. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses approach guided the search in 4 databases, Springer, Science Direct, PubMed and IEEE Xplore. The findings reveal that XAI techniques like Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP) and Gradient-weighted Class Activation Mapping (GRAD-CAM) offer opportunities like early detection outcomes, integration with existing clinical processes, enhancing trust in AI systems, improving accuracy and personalised treatment. XAI can also facilitate collaboration among clinicians, maintaining fairness in AI systems and supporting adherence to ethical standards. However, research on clinical validation of these models, as well as standardised performance evaluation metrics, is lacking.

Enhancing Education through Leveraging Spatial Computing: A Conceptual Framework Kudakwashe Maguraushe; Pride Dube; Belinda Ndlovu
IJIE (Indonesian Journal of Informatics Education) Vol 9, No 2 (2025): (IJIE) Indonesian Journal of Informatics Education - December
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/ijie.v9i2.103669

Traditional teaching practices are often characterized by passive learning, limited interactivity, and a lack of real-time contextual feedback, which struggle to meet the evolving expectations of 21st-century learners. These limitations hinder learner engagement, knowledge retention, and the development of critical thinking skills. In response to these shortcomings, educators have increasingly explored innovative technologies. Among them, Spatial Computing stands out for its ability to merge physical and digital environments, enabling immersive, hands-on learning that traditional tools like video lectures or slide-based content cannot provide. This systematic literature review analyses 16 peer-reviewed studies published between 2020 and 2025, selected from Google Scholar, IEEE Xplore, ScienceDirect, and Springer. It investigates Spatial Computing's educational applications, benefits, challenges, and the technologies supporting its use. The findings reveal that Spatial Computing bridges virtual and reality, thus making learning content multidimensional. This leads to higher retention, active learning, and critical thinking. The findings report on both the great challenge and opportunity of making Spatial Computing available for learning environments. On one hand, it enables interactive simulation learning environments, real-time visualizations of information, and in-the-sim empirical manipulation of objects. On the other hand, it is limited by challenges associated with prohibitively expensive development costs, technical sophistication, and calls for comprehensive evaluation methodologies, inhibiting wide uptake.Additionally, this research highlights the necessity of close interdisciplinarity and the application of sound design methodologies to effectively leverage Spatial Computing. Overall, the review substantiates that Spatial Computing has the promise of radically overhauling conventional education through interactive, immersive, and personalized learning experiences. Future research needs should focus on simplifying the complexities of technology implementation, optimizing the system's design, and developing benchmarked standards for evaluating the learning effects of Spatial Computing.

Transformer-Based Abstractive Text Summarisation for Real-Time Web Applications: A Browser-Integrated System with REST API Architecture Zvinodashe Revesai; Belinda Ndlovu; Kudakwashe Maguraushe
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12559

The exponential growth of digital textual content has intensified the need for efficient, accessible summarisation tools that support information processing across academic, professional, and research domains. While Transformer-based abstractive summarisation models have demonstrated strong performance in benchmark settings, their real-world deployment remains limited due to computational complexity and lack of user accessibility. This study presents a lightweight Transformer-based abstractive text summarisation system, operationalised as a Google Chrome extension and supported by a REST API, enabling seamless integration into everyday user workflows. The proposed system employs an encoder–decoder framework leveraging a pre-trained Transformer-based encoder and a sequence-to-sequence decoder with attention, fine-tuned on the CNN/Daily Mail dataset. Quantitative evaluation on the benchmark dataset achieved ROUGE-1, ROUGE-2, and ROUGE-L scores of 38.21, 16.54, and 35.12, respectively, demonstrating competitive performance relative to established neural baselines. To address the limitations of lexical evaluation metrics, a complementary human evaluation was conducted using a Likert-scale assessment across coherence, informativeness, and fluency, yielding mean scores above 4.0, thereby confirming the qualitative effectiveness of the generated summaries. In addition to model performance, system-level evaluation assessed functional correctness, latency, scalability, and usability within a real-world deployment context. The system demonstrated stable performance under concurrent usage, with an average response time of 4.2 seconds per request and positive user feedback, validating its practical applicability. The findings demonstrate that high-quality abstractive summarisation can be effectively operationalised within a lightweight, browser-integrated architecture, thereby bridging the gap between research-stage neural models and accessible end-user applications. This work contributes to deployment-oriented natural language processing by emphasising usability, modularity, and real-world integration as critical dimensions of system design.

Deep Learning and XGBoost for Pancreatic Cancer Survival Prediction: A Real-World Evaluation in a Resource-Constrained African Healthcare Setting Zvinodashe Revesai; Kudakwashe Maguraushe; Belinda Ndlovu
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12570

Pancreatic cancer remains one of the most lethal malignancies worldwide, with persistently low survival rates and a pressing need for reliable prognostic tools to support treatment planning in resource-constrained healthcare environments. This study presents a structured comparative evaluation of Artificial Neural Network (ANN) and XGBoost classifiers for predicting 12-month survival using real-world clinical data from 569 pancreatic cancer patients treated at a public hospital in Zimbabwe between 2018 and 2023. The Cross-Industry Standard Process for Data Mining (CRISP-DM) framework guided data understanding, preprocessing, model development, and evaluation. A comprehensive preprocessing pipeline incorporating missing value imputation, outlier management, encoding, feature selection, and normalisation was applied, with all transformations derived exclusively from the training set to prevent data leakage. Models were trained using an 80/20 stratified split with cross-validated hyperparameter optimisation and evaluated on a strictly held-out test set using accuracy, precision, recall, F1-score, ROC analysis, and McNemar’s test. On the test dataset, the ANN model achieved 99% overall accuracy and 99% F1-score, outperforming XGBoost, which attained 90% accuracy and 90% F1-score. The performance difference was statistically significant (p < 0.05). Computational analysis demonstrated inference times below 3 milliseconds per sample, supporting feasibility for clinical deployment. While results indicate strong discriminative capacity within this single-centre dataset, external validation across multi-institutional cohorts is necessary to confirm generalisability. These findings suggest that supervised machine learning can provide clinically meaningful support for survival prediction in African tertiary healthcare settings. This study uniquely contributes a deployment-oriented, real-world evaluation of machine learning models within a resource-constrained African healthcare context, addressing a critical gap in the current oncology informatics literature.

Explainable Deep Learning for Diabetic Retinopathy Detection: A Quantitatively Validated Framework Tinashe Ngwazi; Belinda Ndlovu; Kudakwashe Maguraushe
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12687

Diabetic retinopathy (DR) is a leading cause of preventable blindness, where early and accurate detection is critical for effective intervention. While deep learning models have demonstrated strong performance in DR classification, their limited interpretability and inconsistent evaluation practices hinder clinical trust and deployment. This study proposes an explainable deep learning framework for DR detection based on MobileNetV2, complemented by Integrated Gradients for feature attribution. A curated dataset of 4,464 retinal images was constructed from publicly available sources through systematic preprocessing, including quality filtering, deduplication, and class balancing across five DR stages. To ensure robust evaluation, a multi-level validation strategy was employed, incorporating stratified train–validation–test splits and k-fold cross-validation. The proposed framework achieved 87.0% accuracy and an F1-score of 0.868, outperforming baseline models including EfficientNet-B0, DenseNet121, and VGG16. Beyond predictive performance, explainability was quantitatively evaluated using deletion and insertion metrics, demonstrating that Integrated Gradients provides more faithful feature attribution compared to Grad-CAM and LIME. Error analysis further reveals that misclassifications are concentrated between adjacent DR stages, reflecting the inherent difficulty of fine-grained disease progression modelling. The findings highlight that combining rigorous validation with quantitative explainability evaluation can improve the reliability and transparency of deep learning models for medical imaging. While results are promising, the framework is validated on publicly available datasets and requires further external clinical validation before real-world deployment.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search