Cloud Computing and Data Science

FLUDITY Unleashed: Dynamic Blockchain-Enabled Federated Learning Architecture for Tactile IoT Applications

Omar Alnajar — 2025-08-08

The Tactile Internet of Things (TIoT) demands ultra-reliable, low-latency communication for real-time haptic applications in domains such as remote surgery and human-robot collaboration. Conventional Federated Learning (FL) architectures-centralized, hierarchical, or purely decentralized-each suffer from bottlenecks in scalability, latency, or trust. We propose Federated Learning Using Distributed Infrastructure for TIoT (FLUDITY), a hybrid FL framework leveraging Blockchain, Multi-Edge Computing (MEC), and a Dynamic Aggregation Decision Algorithm (DADA). Evaluated via the TACTO (a fast and flexible tactile simulator) tactile simulator in a remote grasping task, FLUDITY achieves up to 30% reduction in convergence time (880 s vs. 1,258 s), 15% fewer Floating Point Operations (FLOPs) (74.8 × 10¹² vs. 88 × 10¹²), and 25% lower communication overhead (1,575 MB vs. 2,099.9 MB) compared to static blockchain FL.

Leveraging AI for Continuous Quality Assurance in Agile Software Development Cycles

Sanjay Polampally — 2025-09-03

In the era of Agile software development, where rapid releases and continuous integration are essential, ensuring consistent software quality becomes increasingly complex. This research explores the integration of Artificial Intelligence (AI) into Continuous Quality Assurance (CQA) within Agile Software Development Cycles. Using the PROMISE dataset comprising 10,885 entries of real-world software metrics and defect labels, we implemented and evaluated AI models for real-time defect prediction, complexity analysis, and risk assessment. The Naive Bayes classifier achieved an accuracy of 98.16%, with high precision and recall across both defective and non-defective classes. Linear Regression, applied for defect-proneness estimation, yielded a low RMSE of 0.25, indicating strong predictive performance and effectively predicting defect-prone modules. As a result, our approach led to a 15.48% reduction in post-release bugs and an 80.71% decrease in manual testing time, significantly improving sprint-level feedback and delivery quality. Compared to manual testing, the AI-driven approach significantly improved defect detection rates and reduced testing time, supporting faster and more reliable software delivery. These results validate that AI integration in Agile environments not only automates and accelerates the quality declaration development but also sustains software reliability in all iterative development cycles.

Automating Data Collection to Support Conflict Analysis: Scraping the Internet for Monitoring Hourly Conflict in Sudan

Yahya Masri — 2025-12-15

The ongoing conflicts in Sudan have escalated rapidly, highlighting the critical need for timely and accurate data to inform humanitarian responses, policy decisions, and research needs. While existing datasets such as the Armed Conflict Location & Event Data Project (ACLED) and the Uppsala Conflict Data Program Georeferenced Event Dataset (UCDP GED) provide valuable insights into conflicts, they suffer from update delays and lack source transparency, which hinders timely incident reporting and comprehensive analysis. To address these limitations, we developed a web scraping toolset that collects hourly data from the Internet, deploying the tools to support Sudan conflict analysis. The scraped data was used to build an open-access database that houses 6,946 articles as of October 25, 2024, from national, regional, and international sources, offering a transparent and easily accessible resource for further analysis. A case study is presented to demonstrate the scraper’s practical application in covering the siege of Sinjah, successfully capturing spatial and temporal events within a conflict zone. The scraped data outperformed the UCDP GED in capturing incidents but missed some smaller-scale incidents recorded by ACLED, highlighting areas for improvement through expanding source diversity. Overall, the scraper demonstrates great potential for improving conflict monitoring and could be further enhanced by incorporating additional sources and automation techniques.

Prediction of Mortality in Intubated Patients Following Admission to the Intensive Care Unit After an Emergency Room Visit: A Retrospective Cohort Study of Machine Learning Techniques Using Electronic Medical Records

Junghyun Lee — 2025-12-23

Objectives: The purpose of this study is to develop a mortality prediction model for Intensive Care Unit (ICU) patients following endotracheal intubation using machine learning and identify key predictors of outcomes. Methods: A retrospective cohort study analysis was conducted using electronic medical records of 1,229 adult patients who were admitted to the ICU through the Emergency Department (ED) from January 2018 to December 2022. The collected data included general characteristics, blood test results at the time of ED and ICU admission, vital signs, the Braden scale, the Acute Physiology and Chronic Health Evaluation (APACHE) II score, and the duration of stay in both the ED and ICU. A comparison of five machine learning models (Logistic Regression, Decision Tree, Support Vector Machine, Random Forest, and Xtreme Gradient Boosting (XGBoost)) was performed. Model performance was evaluated using stratified k-fold cross-validation, and key metrics were reported as mean ± standard deviation. The bestperforming model was further analyzed using SHapley Additive exPlanations (SHAP) to ensure interpretability. Results: The Logistic regression analysis revealed that intubation time, time to transfer to the ICU after intubation, duration of stay in the ICU, total length of hospital stay, lactic acid levels in both the ED and ICU, APACHE II scores, and oxygen saturation significantly influenced mortality. Among the five machine learning models compared, the XGBoost model showed the highest predictive performance based on stratified k-fold cross-validation. SHAP analysis of the XGBoost model identified Total Length of Stay (T_LOS), ICU Length of Stay (I_LOS), and the APACHE II score as the most influential variables for predicting outcomes. Conclusions: The XGBoost model demonstrated high accuracy in predicting mortality. The combination of this high-performing model with SHAP analysis provides a powerful tool for clinical decision-making, offering both predictive accuracy and transparent, patient-specific interpretations. Implications for Clinical Practice: In managing patients in the ED and ICU, total length of stay ICU length of stay and APACHE II score can be considered to predict patient prognosis and develop tailored treatment plans.

Stock Price Prediction: A Machine Learning Approach

Moses Ashawa — 2025-12-03

Accurately predicting stock prices remains a complex task due to market volatility influenced by economic indicators and geopolitical events. This study presents a Hybrid Stock Sequence Learner (HSSL) model that integrates Support Vector Machine (SVM), Support Vector Regression (SVR), and Linear Regression (LR) to improve forecasting performance in dynamic financial environments. The model employs an attention-gated mechanism and regularization to capture higher-order feature interactions while preventing overfitting. SVM captures non-linear patterns, LR enhances interpretability by calculating feature impacts, and SVR enables adaptive modelling through high-dimensional feature mapping. The HSSL model was empirically evaluated using historical stock data from five entities, namely Apple, Microsoft, Walt Disney, Alphabet, and the S&P 500 index. This data was sourced from Yahoo Finance. Results show that HSSL achieves a Mean Squared Error (MSE) of 4.414 and a Root Mean Squared Error (RMSE) of 29.843, outperforming baseline models. These results demonstrate that our model effectively reduces prediction errors and captures market trends. Our proposed approach offers a robust and interpretable forecasting framework suitable for short-term stock price prediction and decision-making in highly volatile markets, serving as a vital tool for stock investors to evaluate potential risks and adjust strategies to minimize losses.

Retraction Note to "Usability of University Websites as Information Sources: A Review and Synthesis Based on 2021 Publications Indexed in Scopus Database" [Cloud Computing and Data Science, Volume 4 Issue 1 (2023), 60-76]

Universal Wiser Publisher — 2025-09-16

The Editor-in-Chief and the Editorial Office of Cloud Computing and Data Science (CCDS) have retracted the following article:

Yap C K, Hashim H, Ainuddin M H, et al. Usability of University Websites as Information Sources: A Review and Synthesis Based on 2021 Publications Indexed in Scopus Database. Cloud Computing and Data Science. 2023; 4(2): 60-76.

This article has been retracted at the request of the Editor-in-Chief.

Following a journal-wide investigation, it was identified that this article falls outside the scope of the journal, and does not align with the thematic focus or subject matter requirements as outlined by the journal's editorial policies.

The retraction is in accordance with the Committee on Publication Ethics (COPE) guidelines, ensuring the integrity of the publication record is maintained. As part of journal's ongoing efforts to improve the quality of publications, the editorial office will continue to rigorously conduct preliminary review and peer review to ensure that only manuscripts that align with the journal's scope and meet the highest academic standards are published.

The editorial office sincerely apologize for any confusion or inconvenience this retraction may have caused.

The corresponding author, as the representative of all authors, has been given the opportunity to register their agreement or disagreement to this retraction. We have kept a record of any response received.

Retraction Note to "Design of a Smart Cabin Lighting System Based on Internet of Things" [Cloud Computing and Data Science, Volume 4 Issue 2 (2023), 112-121]

Universal Wiser Publisher — 2025-09-18

The Editor-in-Chief and the Editorial Office of Cloud Computing and Data Science (CCDS) have retracted the
following article:

Huang Y K. Design of a Smart Cabin Lighting System Based on Internet of Things. Cloud Computing and Data
Science. 2023; 4(2): 112-121.

This article has been retracted at the request of the Editor-in-Chief.

Following a journal-wide investigation, it was identified that this article falls outside the scope of the journal, and
does not align with the thematic focus or subject matter requirements as outlined by the journal's editorial policies.

The editorial office sincerely apologize for any confusion or inconvenience this retraction may have caused.

None of the authors have responded to the Editor about this retraction notice.

A Review on Architectures and Applications of Medical Imaging Cloud

Mohammad Reza Ghaderi — 2025-12-29

Cloud-based medical imaging stands as a crucial aspect of cloud computing, significantly impacting the medical field. By integrating cloud computing into medical imaging, we facilitate the sharing of vital information across medical institutions, consulting centers, and educational establishments. This approach allows patients to access essential medical resources with ease, irrespective of spatial limitations. Once medical images are obtained from the diagnostic devices, they can be uploaded to the cloud. This enables the rapid retrieval and sharing of these images, ensuring they are accessible for viewing and utilization by all users. In this article, we explore diverse applied architectures for implementing cloud-based medical imaging systems and discuss their applications. Additionally, we delve into crucial aspects of medical imaging cloud requirements, such as the security and privacy of medical data, service level agreements (SLAs), and quality of service (QoS). Addressing these concerns is paramount in ensuring the seamless and secure integration of cloud-based medical imaging systems in our healthcare landscape.