A.5. I/O and Data Communications
Somayyeh Jafarali Jassbi; Sajjad Daliri
Abstract
The rapid growth of the Internet‑of‑Things (IoT) imposes significant challenges on task offloading in fog environments, including service latency, resource constraints, and trust management. Fog computing mitigates these limitations by moving computation and storage closer to end devices. This paper ...
Read More
The rapid growth of the Internet‑of‑Things (IoT) imposes significant challenges on task offloading in fog environments, including service latency, resource constraints, and trust management. Fog computing mitigates these limitations by moving computation and storage closer to end devices. This paper presents BCOFF (Blockchain‑based Computation Offloading Framework for Fog), a secure and efficient framework that jointly optimizes resource allocation and enables verifiable task offloading. In BCOFF, resource allocation is performed using the Grey Wolf Optimization (GWO) algorithm, while blockchain provides a tamper-resistant execution record. Specifically, the blockchain serves three purposes: (i) recording offloading decisions and cryptographic hashes of task results to support post‑execution auditability, (ii) validating the integrity of returned results by matching them with the on‑chain hash reference, and (iii) coordinating consensus among fog nodes through a lightweight Validator‑Selection Proof‑of‑Stake (VNPoS) mechanism. VNPoS is a simplified adaptation of the Nominated Proof‑of‑Stake (NPoS) model that selects validators using stake‑based nomination with variance‑aware stake normalization. By avoiding computationally intensive cryptographic puzzles, VNPoS significantly reduces consensus overhead and is therefore suitable for resource‑constrained fog environments. Experimental evaluation using the iFogSim simulator with workloads of 800–1500 tasks shows that BCOFF reduces execution time by 15–27%, lowers host‑selection latency by 22–25%, and decreases energy consumption by 5–9% compared with existing approaches. These results demonstrate that integrating GWO‑based scheduling with the VNPoS blockchain mechanism provides a more efficient and verifiable fog-offloading framework.
H.3. Artificial Intelligence
Ali Rebwar Shabrandi; Ali Rajabzadeh Ghatari; Mohammad Dehghan nayeri; Nader Tavakoli; Sahar Mirzaei
Abstract
This study proposes a high-level design and configuration for an intelligent dual (hybrid and private) blockchain-based system. The configuration includes the type of network, level of decentralization, nodes, and roles, block structure information, authority control, and smart contracts and intended ...
Read More
This study proposes a high-level design and configuration for an intelligent dual (hybrid and private) blockchain-based system. The configuration includes the type of network, level of decentralization, nodes, and roles, block structure information, authority control, and smart contracts and intended to address the two main categories of challenges–operation management and data management–through three intelligent modules across the pandemic stages. In the pre-hospital stage, an intelligent infection prediction system is proposed that utilizes in-house data to address the lack of a simple, efficient, agile, and low-cost screening method for identifying potentially infected individuals promptly and preventing the overload of patients entering hospitals. In the in-hospital stage, an intelligent prediction system is proposed to predict infection severity and hospital Length of Stay (LoS) to identify high-risk patients, prioritize them for receiving care services, and facilitate better resource allocation. In the post-hospital stage, an intelligent prediction system is proposed to predict the reinfection and readmission rates, to help reduce the burden on the healthcare system and provide personalized care and follow-up for higher-risk patients. In addition, the distribution of limited Personal protective equipment (PPE) is made fair using private blockchain (BC) and smart contracts. These modules were developed using Python and utilized to evaluate the performance of state-of-the-art machine learning (ML) techniques through 10-fold cross-validation at each stage. The most critical features were plotted and analyzed using SHapely Adaptive exPlanations (SHAP). Finally, we explored the implications of our system for both research and practice and provided recommendations for future enhancements.
