Journal of Web Engineering

Editorial

In-Young Ko — 2026-04-19

In the era of artificial intelligence (AI), smart devices such as autonomous vehicles, drones, and service robots are increasingly collaborating to perform complex tasks for humans. However, the centralized control and optimiza- tion of these widely distributed devices suffer from significant scalability limitations. At the same time, traditional cloud infrastructures are struggling to meet the demands of collecting and processing massive volumes of data from countless devices, often leading to increased latency and reduced service responsiveness.

To address these challenges, edge-cloud computing has emerged as a promising infrastructure that enhances efficiency, scalability, and data privacy for delivering data-centric, AI-enabled services. In an edge-cloud ecosystem, multiple computing tiers – including edge devices, fog nodes, and centralized clouds – collaborate to support data collection, processing, and decision- making closer to data sources. These tiers must coordinate dynamically, considering available computing resources while ensuring service quality, safety, and accuracy.

Data-driven Adaptive ML-enabled Edge-cloud System Framework for Safe and Efficient Autonomous Systems

Eunho Cho — 2026-04-19

Machine learning (ML)-enabled systems like autonomous driving systems (ADSs) face challenges meeting safety and performance requirements in diverse environments, especially in resource-constrained, latency-sensitive edge-cloud settings. These challenges often arise from the ML models’ limitations, including poor generalization to unseen conditions. Static ML models often struggle to generalize to unseen scenarios, particularly under the latency and resource constraints of edge-cloud infrastructure. Adaptive algorithms using ML system switching have been proposed, but existing approaches frequently lack generalizability, support for common black-box systems, and effective use of distributed edge-cloud resources. This paper presents a novel adaptive ML-enabled edge-cloud system framework to address these shortcomings. Our framework combines cloud-based pre-runtime analysis, which leverages simulation for behavioral understanding and scenario-to-system mapping, with collaborative edge-cloud runtime adaptation featuring dynamic ML model switching. It supports black-box systems and aims to balance safety and efficiency by utilizing appropriate edge and cloud resources situationally. Preliminary CARLA-based evaluation of the edge runtime component suggests our framework can potentially improve the safety-efficiency trade-off compared to single-model ADSs in some scenarios. Moreover, extensive experiments using the MetaDrive simulator with 100,000 randomized driving scenarios demonstrate that the adaptive system improves safety by 2.6% while doubling computational efficiency compared to a single-model baseline. These results validate the framework’s scalability and the feasibility of data-driven scenario–system mapping for adaptive ML-enabled autonomous systems operating across edge and cloud environments.

Towards Real-time Underwater Object Detection and Identification: Integrating Acoustic Sensing with Edge Computing

Shekhar Tyagi — 2026-04-19

In this work, we present a method to streamline underwater object detection, environmental monitoring, and surveillance. The proposed system employs an underwater acoustic sensor (UAS) network to detect and analyses objects within a three-dimensional underwater space, considering constraints imposed by acoustic path loss. The approach combines three key techniques–Delaunay’s convex hull-based reconstruction, the laws of magnetic equilibrium, and the Doppler effect–to improve the identification of object type, shape, location, and motion. Sensors are arranged in an optimized grid, with each grid containing eight sensors and a central insulated magnetometer to measure net magnetic field intensity. Data collected by the sensors is transmitted to a surface anchor or sink node for further processing and analysis. A prototypical deployment in an artificial pond further validates our approach, using a waterproof ultrasonic sensor, an electromagnetic coil, and a magnetometer synchronized via Arduino Uno. Real-time measurements confirm accurate detection and tracking of objects, demonstrating the effectiveness and feasibility of the proposed edge-enabled underwater monitoring framework.

LLM-driven Multi-agent Architecture for QoS-aware Server Recommendation in Mobile-Edge-Cloud Environments

Eunjeong Ju — 2026-04-19

Mobile edge computing (MEC) has become a key paradigm for supporting latency-sensitive and bandwidth-intensive applications. However, existing server recommendation methods rely on static heuristics and lack adaptability to dynamic environments with incomplete quality of service (QoS) data. This study aims to address these limitations by enabling adaptive and context-aware server recommendations that effectively manage user mobility and missing QoS information in real time. We propose an intelligent MEC server recommendation framework built on a multi-agent architecture spanning mobile, edge, and cloud layers. The mobility layer predicts user movement, the edge layer performs LLM-based decision-making, and the cloud layer imputes QoS through multi-source data fusion. Lightweight gRPC and WebSocket protocols ensure scalability across multi-user environments. Experiments demonstrate that the proposed system outperforms the baseline, achieving 85% Top-1 accuracy and confirming its effectiveness and scalability for real-world MEC applications.

Learning by Experiencing: An Immersive Digital Twin Tool for ECG Education

Daniel Flores-Martin — 2026-04-19

Practical training in electrocardiogram (ECG) interpretation remains uneven, particularly in resource-limited settings, despite the central role of ECGs in cardiovascular diagnosis. This work evaluates whether an ECG-focused digital twin that integrates interactive simulation and deep learning guidance can achieve educationally valid realism, improve recognition of patterns and abnormalities through interactivity, and enhance accuracy and learner motivation via predictive feedback. We present ECGTwinMentor, a cross-platform system that synthesizes parameterized ECG waveforms, enables fine-grained control of physiologic variables, and delivers immediate predictive feedback for formative assessment. The diagnostic model supports low-latency inference on modest hardware. Validation with healthcare experts and medical students showed positive evaluations for realism, usability, and integration potential. Experts reported average ratings between 3.5 and 4.5 out of 5, while students rated usability between 4.6 and 4.8 and motivation and realism at 5.0, with most items scoring at least 4. These findings support the conclusion that an interactive, predictive digital twin can narrow the gap between theory and practice in ECG interpretation, offering an accessible, scalable, and reproducible approach to ECG education.

Project Evolution-aware Prompting of LLMs for Just-in-time Defect Prediction in Edge-cloud Systems

Inseok Yeo — 2026-04-19

Edge-cloud systems, which bring computing, storage, and networking resources closer to end-users, offer significant advantages in reducing latency and enabling real-time data processing. These systems are increasingly deployed across diverse domains, such as smart manufacturing, autonomous vehicles, and large-scale IoT networks, to support big data-driven services that require continuous analytics and rapid response. Ensuring software reliability in these environments is critical, which has led to growing attention on just-in-time (JIT) defect prediction as an effective technique for prioritizing testing efforts by identifying code changes likely to introduce defects. However, existing techniques struggle to perform accurately on new or low-data projects due to insufficient training data.

In this paper, we propose PROPER-SDP, a prompt-based approach that leverages large language models. By incorporating project evolution data directly into prompts, our approach enables LLMs to effectively capture the contextual information essential for accurate JIT defect prediction. By doing so, we effectively address the cold-start problem, allowing accurate JIT defect prediction even in the absence of project-specific training data. Evaluation results demonstrate that our method significantly improves prediction performance, surpassing baseline methods by an average of 19.7% in F1-score. Our approach enables reliable JIT defect prediction even in rapidly evolving, resource-constrained edge-cloud systems.

Spatio-temporal Mamba for User Mobility Prediction in Mobile Edge Computing

Jeonghwa Lee — 2026-04-19

In mobile edge computing (MEC), frequent server handovers due to user mobility increase latency and degrade quality of service (QoS). This study enhances MEC service stability by predicting user mobility for efficient server transitions. The proposed spacio-temporal (ST)-Mamba model combines Mamba (state-space encoder) and a gated recurrent unit (GRU) in parallel to capture both long-term and short-term dependencies, while Fourier feature embedding enriches spatial-temporal representation. Experiments show that ST-Mamba achieves about 9–10% lower root mean square error (RMSE) and mean absolute error (MAE) than long short-term memory (LSTM), GRU, and Transformer baselines, with statistically significant improvements confirmed by Welch’s t-test. These results demonstrate that hybrid state space model (SSM)–RNN architectures are promising for mobility-aware QoS optimization in MEC, with future work extending to real-world and multi-user settings.