This study presents a computational modeling framework for efficient and secure computation offloading in Internet of Things (IoT)-enabled smart contract systems. The integration of IoT, edge computing, and blockchain introduces significant challenges, including limited device capacity, high verification cost, and scalability constraints. Existing blockchain verification approaches depend on computationally intensive cryptographic operations that are inefficient for resource-constrained IoT devices, resulting in increased latency, energy consumption, and transaction costs. To address these issues, this study proposes the Zero-Knowledge Fuzzy Logic Offloading and Rollup (Z-FLOR) framework, an adaptive and energy-efficient model designed to enable secure and verifiable computation in IoT-based smart contract systems. The proposed framework integrates three key components. First, a zero-knowledge proof-based verification model using the Groth16 zkSNARK module generates compact and privacy-preserving proofs that enable fast and reliable verification. Second, a Fuzzy Logic–Driven Energy-Aware Offloading module dynamically allocates computational tasks between IoT devices, edge servers, and cloud platforms based on energy availability, network delay, and device reliability. Third, an Optimistic Rollup Verification module aggregates proofs off-chain and submits them in batches to reduce gas costs and enhance scalability. Extensive simulation and experimental evaluation across diverse IoT scenarios demonstrate the effectiveness of the proposed computational framework. Results indicate that Z-FLOR achieves 99.7% verification accuracy and 98.9% proof compression efficiency, while gas cost analysis indicates gas cost reductions in the range of 80%–98%. Z-FLOR additionally achieves a 44.0% reduction in latency, 51.0% savings in gas costs, and 38.0% energy consumption compared to baseline approaches. These findings highlight the capability of the proposed approach to serve as a scalable and energy-efficient modeling solution for secure IoT smart contract execution in decentralized environments.

Fundoscopic diagnosis involves assessing the proper functioning of the eye’s nerves, blood vessels, retinal health, and the impact of diabetes on the optic nerves. Fundus disorders are a major global health concern, affecting millions of people worldwide due to their widespread occurrence. Fundus photography generates machine-based eye images that assist in diagnosing and treating ocular diseases such as diabetic retinopathy. As a result, accurate fundus detection is essential for early diagnosis and effective treatment, helping to prevent severe complications and improve patient outcomes. To address this need, this article introduces a Derivative Model for Fundus Detection using Deep Neural Networks (DMFD-DNN) to enhance diagnostic precision. This method selects key features for fundus detection using the least derivative, which identifies features correlating with stored fundus images. Feature filtering relies on the minimum derivative, determined by extracting both similar and varying textures. In this research, the DNN model was integrated with the derivative model. Fundus images were segmented, features were extracted, and the DNN was iteratively trained to identify fundus regions reliably. The goal was to improve the precision of fundoscopic diagnosis by training the DNN incrementally, taking into account the least possible derivative across iterations, and using outputs from previous cycles. The hidden layer of the neural network operates on the most significant derivative, which may reduce precision across iterations. These derivatives are treated as inaccurate, and the model is subsequently trained using selective features and their corresponding extractions. The proposed model outperforms previous techniques in detecting fundus regions, achieving 94.98% accuracy and 91.57% sensitivity, with a minimal error rate of 5.43%. It significantly reduces feature extraction time to 1.462 s and minimizes computational overhead, thereby improving operational efficiency and scalability. Ultimately, the proposed model enhances diagnostic precision and reduces errors, leading to more effective fundus dysfunction diagnosis and treatment.