Blockchain is a decentralized ledger with a secure and immutable chain structure. The advanced attributes of blockchain, including decentralization, anonymity, transparency, and zero trust support, have positioned it as a transformative technology across different areas of expertise, like medicine, finance, and the Internet of Things (IoT). Nonetheless, blockchain's progress has been constrained in various aspects, revealing inefficiency, privacy, high transaction fees, and challenges with on-chain storage. To address these limitations, off-chain technology has emerged as a solution by moving computation and storage overhead away from the blockchain. However, a comprehensive survey on off-chain schemes is lacking in the current literature. In this article, we conduct a thorough survey on off-chain technologies. We first introduce the fundamental concepts and characteristics of both blockchain and off-chain technologies. Furthermore, we establish a thorough taxonomy of off-chain technologies based on distinct application scenarios. We put forth a series of evaluation criteria, based on which we seriously review and analyze the existing off-chain schemes to assess their strengths and limitations. Conclusively, we outline a list of open issues and propose promising future research directions based on our thorough review and analysis on off-chain technologies.
Many real-world optimization problems exhibit dynamic characteristics, posing significant challenges for traditional optimization methods. Evolutionary Dynamic Optimization Algorithms (EDOAs) have been developed to address these challenges by adapting to changing environments over time. However, the reproducibility and consistency of experimental results in the literature remain limited due to the lack of publicly available source codes and the complexity of accurately re-implementing algorithms and performance evaluation protocols. To support the community, we introduce Evolutionary Dynamic Optimization LABoratory (EDOLAB), an open source MATLAB platform designed for both research and educational purposes. EDOLAB includes 27 EDOAs, four highly configurable benchmark generators, and a growing suite of performance indicators. The platform supports full parameter tuning, batch experiment management, parallel execution, and automated statistical comparisons-including rankings, significance testing, box plots, and performance trend visualizations over time. An educational application allows users to observe: (a) dynamic changes in a 2D problem landscape, (b) the movement of individuals in response to these changes, and (c) the ability of an algorithm to track moving optima. By providing an integrated environment for experimentation, benchmarking, and instructional use, EDOLAB promotes reproducibility, comparative analysis, and a deeper understanding of EDOAs in dynamic environments.
Unmanned Aerial Vehicle (UAV) swarms offer versatile applications in logistics, agriculture, and surveillance, yet controlling them requires expert knowledge for safety and feasibility. Traditional static methods limit adaptability, while Large Language Models (LLMs) enable natural language control but generate unsafe trajectories due to lacking physical grounding. This paper introduces SkySim, a ROS2-based simulation framework in Gazebo that decouples LLM high-level planning from low-level safety enforcement. Using Gemini 3.5 Pro, SkySim translates user commands (e.g., "Form a circle") into spatial waypoints, informed by real-time drone states. An Artificial Potential Field (APF) safety filter applies minimal adjustments for collision avoidance, kinematic limits, and geo-fencing, ensuring feasible execution at 20 Hz. Experiments with swarms of 3, 10, and 30 Crazyflie drones validate spatial reasoning accuracy (100% across tested geometric primitives), real-time collision prevention, and scalability. SkySim empowers non-experts to iteratively refine behaviors, bridging AI cognition with robotic safety for dynamic environments. Future work targets hardware integration.
5605 Background: Epithelial ovarian cancer is the leading cause of gynecologic cancer mortality, with treatment and prognosis strongly dependent on accurate histopathologic subtype classification. The five major epithelial subtypes—high-grade serous, low-grade serous, endometrioid, mucinous, and clear cell carcinoma—exhibit distinct clinical behaviors, yet conventional interpretation is limited by subjectivity and interobserver variability. Although deep learning has advanced digital pathology, most high-performing models require substantial computational resources, limiting clinical scalability. We evaluated whether a lightweight multilayer perceptron (MLP) combined with structured dimensionality reduction could enable accurate and globally deployable ovarian cancer subtyping. Methods: We analyzed 9,521 anonymized histopathology image patches representing five epithelial ovarian cancer subtypes from publicly available datasets with expert pathologist consensus ground truth. Images underwent Gaussian random projection followed by principal component analysis to preserve discriminative morphologic features. A feedforward MLP (2,048→1,024→512→5 neurons) with batch normalization and dropout (p=0.3) was trained using AdamW optimization with cosine annealing over 50 epochs on 80% of the data. External validation was performed on independent datasets. Performance metrics included accuracy, sensitivity, specificity, F1 score, and AUROC. The model was deployed on a cross-platform digital pathology system and evaluated by pathologists across six continents. Results: The MLP achieved 97.4% test accuracy with balanced subtype performance. Sensitivity ranged from 94.2% to 99.3%, with a macro-averaged F1 score of 0.993 and AUROC >0.99 for all classes. External validation accuracy ranged from 91% to 93% across heterogeneous staining protocols. Sensitivity for low-grade serous carcinoma (92.1%) exceeded reported interobserver agreement (52–73%). Inference time averaged 0.33 seconds per image on standard CPU hardware. Pathologists rated the system clinically useful in >90% of evaluations. The model contained 2.8 million parameters, representing an 89% reduction compared with conventional convolutional architectures. Conclusions: A computationally efficient MLP enables accurate and reproducible epithelial ovarian cancer subtype classification while substantially reducing computational complexity. This approach mitigates interobserver variability and supports scalable AI-assisted pathology deployment. Prospective multicenter studies are warranted to assess integration into routine diagnostic workflows and impact on treatment stratification.
Wireless sensor networks (WSNs) are important in real-time applications such as environmental monitoring, health, and automation in industries. Nevertheless, maintaining stable communication and energy efficiency during topology changes and node failures also comes as one of the major challenges. The majority of the currently existing frameworks, such as GSO, OEPO-FPA, and fuzzy-based clustering, specialize in either optimization of energy consumption or fault tolerance, yet many of them do not combine those two concepts effectively. Also, such approaches usually do not have adaptive intelligence to adapt to the evolving network conditions. In order to overcome these shortcomings, the present study is proposing a hybrid neuro-fuzzy optimization (NFO) framework, that is a synergistic combination of fuzzy inference to handle the uncertainty and multilayer perceptron (MLP) to learn fault patterns dynamically, and use particle swarm optimization (PSO) to optimize routing and duty cycles on a global scale. The implementation of the model took place with MATLAB R2023b and NS-3 and was tested on the WSN-DS dataset that includes the main network parameters of residual energy, PDR, and link quality. The proposed approach achieved 92.4% fault detection accuracy, 85% packet delivery ratio, 80% residual energy retention, and extended network lifetime up to 970 rounds, resulting in an improvement of over 15%-25% compared with existing methods. The inclusion of a dynamic feedback loop ensures continuous rule refinement and performance adaptation. This unified and lightweight solution offers a scalable, resilient, and intelligent architecture for self-healing WSNs, presenting a promising direction for future deployments in resource-constrained, mission-critical environments.
