As the next-generation Internet paradigm, the metaverse can provide users with immersive physical-virtual experiences without spatial limitations. However, there are various concerns to be overcome, such as resource allocation, resource pricing, and transaction security issues. To address the above challenges, we integrate blockchain technology into the metaverse to manage and automate complex interactions effectively and securely utilizing the advantages of blockchain. With the objective of promoting the Quality of Experience (QoE), Metaverse Service Users (MSUs) purchase rendering and bandwidth resources from the Metaverse Service Provider (MSP) to access low-latency and high-quality immersive services. The MSP maximizes the profit by controlling the unit prices of resources. In this paper, we model the interaction between the MSP and MSUs as a Stackelberg game, in which the MSP acts as the leader and MSUs are followers. The existence of Stackelberg equilibrium is analyzed and proved mathematically. Besides, we propose an efficient greedy-and-search-based resource allocation and pricing algorithm (GSRAP) to solve the Stackelberg equilibrium (SE) point. Finally, we conduct extensive simulations to verify the effectiveness and efficiency of our designs. The experiment results show that our algorithm outperforms the baseline scheme in terms of improving the MSP's profit and convergence speed.
Gabriel Chukwunonso Amaizu, Akshita Maradapu Vera Venkata Sai, Sanjay Bhardwaj, Dong‐Seong Kim · 6 authors
The increasing prevalence of cancer necessitates advanced methodologies for early detection and diagnosis. Early intervention is crucial for improving patient outcomes and reducing the overall burden on healthcare systems. Traditional centralized methods of medical image analysis pose significant risks to patient privacy and data security, as they require the aggregation of sensitive information in a single location. Furthermore, these methods often suffer from limitations related to data diversity and scalability, hindering the development of universally robust diagnostic models. Recent advancements in machine learning, particularly deep learning, have shown promise in enhancing medical image analysis. However, the need to access large and diverse datasets for training these models introduces challenges in maintaining patient confidentiality and adhering to strict data protection regulations. This paper introduces FedViTBloc, a secure and privacy-enhanced framework for medical image analysis utilizing Federated Learning (FL) combined with Vision Transformers (ViT) and blockchain technology. The proposed system ensures patient data privacy and security through fully homomorphic encryption and differential privacy techniques. By employing a decentralized FL approach, multiple medical institutions can collaboratively train a robust deep-learning model without sharing raw data. Blockchain integration further enhances the security and trustworthiness of the FL process by managing client registration and ensuring secure onboarding of participants. Experimental results demonstrate the effectiveness of FedViTBloc in medical image analysis while maintaining stringent privacy standards, achieving 67% accuracy and reducing loss below 2 across 10 clients, ensuring scalability and robustness.
Open access
Artificial Intelligence in Healthcare and Education
D. Mythili, M. Ganeshwari, Suleiman Ibrahim Shelash Mohammad, B. Anitha · 6 authors
Crypto-tech is a technology secured by cryptography, which enables the exchange of data and facilitates duplicated and distributed transactions across the entire network of computer systems on the blockchain. This paper aims to study cryptocurrency’s Awareness, perception, and impact among investors with special reference to Coimbatore city. This study will help provide baseline information on the factors influencing investors in cryptocurrency investing. The study found that cryptocurrency is likely to become the next financial platform due to the large amount of cryptocurrency flows in different systems, the huge increase and growth in cryptocurrency consumption and production, and the opportunities that cryptocurrency systems offer. And the level of awareness and preference in the use of cryptocurrency is moderate. However, investors are not yet fully aware of the dangers of using cryptocurrencies. Many cryptocurrency forms do not yet qualify for that level of trust. Investors should take extra precautionary measures when using cryptocurrency until it is well maintained. The future of the cryptocurrency concept is bright as there are many opportunities for positive change and progress in the e-business and e-payment sectors. As technology advances rapidly, cryptocurrency development continues.
This article examines the integration of blockchain technology with enterprise resource planning (ERP) systems to enhance supply chain transparency and data integrity. Blockchain technology creates immutable, decentralized digital ledgers that fundamentally transform how organizations track transactions, verify product authenticity and maintain regulatory compliance. The implementation architecture features multi-layered components, including consensus mechanisms, smart contracts, middleware integration, and application interfaces that connect seamlessly with existing ERP environments. Through end-to-end traceability, cryptographic verification, and fraud prevention mechanisms, blockchain addresses critical vulnerabilities in traditional supply chains across pharmaceuticals, food production, automotive, and luxury goods sectors. Smart contracts further automate complex business processes, particularly in procurement cycles, by converting traditional agreements into self-executing code. Despite significant benefits, organizations face integration complexities, scalability constraints, and change management challenges that must be addressed for successful adoption. Future developments include cross-chain interoperability, zero-knowledge proofs, artificial intelligence integration, and asset tokenization that will further enhance enterprise blockchain capabilities.
In modern distributed systems, achieving consensus and reconciliation among diverse nodes across varying network conditions is a significant challenge. CohortSync, a novel micro-cohort-based protocol, addresses this challenge by leveraging scalable and fault-tolerant mechanisms to ensure data consistency and system reliability. The core innovation of CohortSync lies in its utilization of dynamically formed micro-cohorts, which are small, manageable groups of nodes that collaborate to achieve consensus without the overhead associated with traditional large-scale consensus protocols. CohortSync operates by first classifying nodes based on their network latency, data relevance, and operational load. This classification enables the protocol to intelligently form micro-cohorts that are geographically and contextually optimized, reducing the latency typically experienced in global consensus operations. Each micro-cohort is responsible for a subset of the reconciliation tasks, allowing for parallel processing and significantly reducing the time to reach consensus. The protocol incorporates a hybrid approach to consensus that combines elements of both deterministic and probabilistic consensus mechanisms. This hybrid model allows CohortSync to maintain high availability and consistency, even in the face of node failures or network partitions. By adapting the consensus mechanism based on real-time network performance and node responsiveness, CohortSync can dynamically adjust its operations to maintain system performance and data accuracy. Another key feature of CohortSync is its reconciliation process, which uses a version-controlled state reconciliation algorithm. This algorithm ensures that all nodes within a micro-cohort maintain a synchronized state, with conflicts resolved through a majority rule among the cohort members. This approach not only minimizes the risk of data divergence but also optimizes the reconciliation process to be both time-efficient and resource-conservative. CohortSync also integrates a continuous learning component that analyzes past consensus rounds to optimize future cohort formation and consensus strategies. This machine learning-driven adaptability makes the protocol robust against evolving network conditions and varying operational loads across nodes. The protocol has been tested in various simulated environments that mimic real-world distributed systems across different industries, including finance, healthcare, and e-commerce. The results demonstrate that CohortSync significantly outperforms existing consensus protocols in terms of scalability, fault tolerance, and operational efficiency. In conclusion, CohortSync presents a transformative approach to consensus and reconciliation in distributed systems. By decentralizing the consensus process into manageable micro-cohorts and integrating adaptive learning mechanisms, CohortSync offers a scalable, efficient, and robust solution that can meet the demands of contemporary distributed computing environments.
The adoption of Industry 4.0 technology in healthcare has led to increased concerns about data privacy, security, and interoperability. Traditional centralized healthcare systems are vulnerable to cybercriminal and unauthorized access; thus there is a need for secure and privacypreserving data sharing architecture. This work proposes an integration of Federated Learning (FL) with Blockchain to deliver improvements in the security, scalability, and privacy of decentralized healthcare. Florida allows hospitals to train their models locally and share them without divulging raw patient data, whereas Blockchain ensures data security, decentralized identity management, and safe access control through smart contracts. Although providing such high-level security requires the usage of advanced techniques such as Zero-Knowledge Proofs (ZKP), Homomorphic Encryption, and Proof-of-Stake (PoS) consensus, the high protection level of data is definitely on the huge-scale advantages of blockchain technology. The proposed model is in line with Industry 4.0 concepts that support automation, interoperability, and strong data ecosystems in healthcare. The resolve is to reduce security threats ensure regulatory compliance and exchange healthcare data with the highest standards of security. Experimental results show improved security, privacy, and efficiency, which make this solution a scalable and robust alternative for current decentralized healthcare data management in Industry 4.0.
Ahmed Bouteska, Taimur Sharif, Layal Isskandarani, Mohammad Zoynul Abedin
This research investigates how market-wide conditions (macro aspects) and individual cryptocurrency-specific characteristics (micro aspects) influence the efficiency of cryptocurrency markets. Macro aspects encompass the impacts of overall market liquidity, volatility, and global uncertainty events (e.g., the COVID-19 pandemic and geopolitical conflicts) on market efficiency. Micro aspects focus on cryptocurrency-specific attributes, such as liquidity and volatility levels, and their effects on price delays. Our findings reveal that rising liquidity and declining volatility enhance market efficiency at both macro and micro levels. Furthermore, we observe that during the periods of uncertainty, inefficiencies are exacerbated among less liquid and more volatile cryptocurrencies. We propose that the perceived uncertainties and substantial transaction costs associated with cryptocurrencies that lack liquidity and exhibit high volatility act as deterrents, diminishing the eagerness of active traders to participate in arbitrage trading. Consequently, this leads to inefficiencies in the market. The results of this study offer valuable insights for financial market regulators and authorities as well as investors associated with the crypto market, particularly during the times of financial turmoils.
The present study systematically reviews the cryptocurrency and financial assets literature using a three-step methodology: The data collected from the SCOPUS database applied inclusion and exclusion criteria to identify a relevant sample of 1938 articles from 2008 to 2024. The quality control criteria are based on the Australian Business Dean Council (ABDC) and Chartered Association of Business Schools (ABS) journal ranking lists. 1013 research papers were finally analyzed to recognize the most influential authors, frequently published authors, most relevant countries and institutions, most influential journals, articles, and citation trends. We have used VosViewer and Biblioshiny tools to conduct the bibliometric and network analysis. We contribute to the literature by recognizing the most prolific cryptocurrency researchers: Elie Bouri, Brian Lucey, Shaen Corbet, and David Roubaud. Finance Research Letters is the most influential journal in terms of citations and publications. Dublin City University in Ireland is the most productive institution in terms of citations, and China is the leading country in terms of the number of articles published in cryptocurrency research. The network coupling analysis results indicate that the emerging themes in cryptocurrency research are energy use, energy consumption, and sustainable development. Additionally, we performed a detailed content analysis to explore the current position of the research using the Meredith et al. (1989) framework. The outcome of our content analysis indicates that 88% of the study has been conducted using the artificial model. Further, it highlighted that mainstream researchers followed axiomatic and interpretive epistemological assumptions. Our results also suggest that behavioral theories, especially the adaptive market hypothesis, are widely used in cryptocurrency research, followed by financial, economic, and operational theories. Our findings provide new insights for future researchers to explore new paradigms, such as experimental research or event studies in cryptocurrency research.
Muhamad Abdul Fatah, Martanto Martanto, Arif Rinaldi Dikananda, Ahmad Rifa’i
Predicting erratic assets like Ethereum is difficult in the dynamic cryptocurrency market. This study uses an enhanced Support Vector Regression (SVR) algorithm to create a daily price prediction model for Ethereum. Yahoo Finance provided the data, which was preprocessed to include missing value cleaning, normalization, and feature extraction of Moving Average (MA) and Exponential Moving Average (EMA). The data was collected between August 4, 2019 and August 4, 2024. An ideal combination was obtained by parameter optimization with GridSearchCV: gamma scale, linear kernel, epsilon of 1, and C of 100. The model performed well, as evidenced by its R2 of 0.9985 and MSE of 2137.97. The model's reliability in predicting Ethereum's price movement patterns was validated via prediction graphs. A 30-day forecast indicated a stable trend, with prices slightly decreasing from $2921.31 on January 1, 2025, to $2919.83 on January 31, 2025. These results highlight the importance of data preprocessing and parameter optimization in enhancing SVR model performance.
As a theoretical foundation and overview, the paper explains how blockchain technology influences energy trade and finance through decentralized, safe, and transparent peer-to-peer transactions. It examines the current energy crisis that arises with a steep, rising curve of rather unorthodox consumption of energy and calls for cleaner, more reliable sources of energy. It also discusses how blockchain-based platforms could help eliminate persistent challenges in centralized energy systems. By combining the previous literature on distributed ledgers, smart contracts, and decentralized market mechanisms, we find that blockchain provides faster settlements, lower overheads, and enhanced resilience against single points of failure. This study will review how blockchain-enabled energy finance solutions speed transactions, build trust, and allow for innovative funding approaches, such as green bonds and energy banking. All in all, the findings support blockchain as a viable way of achieving a more flexible, customer-oriented, and environmentally sustainable energy sector while showcasing the technological, regulatory, and operational gaps that research and responsible policy actions must address. • Examines Blockchain's decentralized role in energy trade and finance. • Explores Blockchain's advantages and challenges in energy finance integration. • Reviews Blockchain models for platform, tech, privacy, and security solutions. • Highlights Blockchain's potential to enable trust and direct energy transactions. • Discusses future needs for advanced algorithms and supportive regulations.
Increasing adoption of electric vehicles (EVs) and the expansion of EV charging infrastructure present opportunities for enhancing sustainable transportation within smart cities. However, the interconnected nature of EV charging stations (EVCSs) exposes this infrastructure to various cyber threats, including false data injection, man-in-the-middle attacks, malware intrusions, and denial of service attacks. Financial attacks, such as false billing and theft of credit card information, also pose significant risks to EV users. In this work, we propose a Hyperledger Fabric-based blockchain network for EVCSs to mitigate these risks. The proposed blockchain network utilizes smart contracts to manage key processes such as authentication, charging session management, and payment verification in a secure and decentralized manner. By detecting and mitigating malicious data tampering or unauthorized access, the blockchain system enhances the resilience of EVCS networks. A comparative analysis of pre- and post-implementation of the proposed blockchain network demonstrates how it thwarts current cyberattacks in the EVCS infrastructure. Our analyses include performance metrics using the benchmark Hyperledger Caliper test, which shows the proposed solution’s low latency for real-time operations and scalability to accommodate the growth of EV infrastructure. Deployment of this blockchain-enhanced security mechanism will increase user trust and reliability in EVCS systems.
The rapid expansion of the Internet of Things (IoT) ecosystem has transformed various sectors but has also introduced significant cybersecurity challenges. Traditional centralized security methods often struggle to balance privacy preservation and real-time threat detection in IoT networks. To address these issues, this study proposes a Federated Learning-Driven Cybersecurity Framework designed specifically for IoT environments. The framework enables decentralized data processing by training models locally on edge devices, ensuring data privacy. Secure aggregation of these locally trained models is achieved using homomorphic encryption, allowing collaborative learning without exposing sensitive information. The proposed framework utilizes recurrent neural networks (RNNs) for anomaly detection, optimized for resource-constrained IoT networks. Experimental results demonstrate that the system effectively detects complex cyber threats, including distributed denial-of-service (DDoS) attacks, with over 98% accuracy. Additionally, it improves energy efficiency by reducing resource consumption by 20% compared to centralized approaches. This research addresses critical gaps in IoT cybersecurity by integrating federated learning with advanced threat detection techniques. The framework offers a scalable and privacy-preserving solution adaptable to various IoT applications. Future work will explore the integration of blockchain for transparent model aggregation and quantum-resistant cryptographic methods to further enhance security in evolving technological landscapes.
Manuel Naviglio, Francesco Tarantelli, Fabrizio Lillo
Blockchain technology has revolutionized financial markets by enabling decentralized exchanges (DEXs) that operate without intermediaries. Uniswap V2, a leading DEX, facilitates the rapid creation and trading of new tokens, which offer high return potential but exposing investors to significant risks. In this work, we analyze the financial impact of newly created tokens, assessing their market dynamics, profitability and liquidity manipulations. Our findings reveal that a significant portion of market liquidity is trapped in honeypots, reducing market efficiency and misleading investors. Applying a simple buy-and-hold strategy, we are able to uncover some major risks associated with investing in newly created tokens, including the widespread presence of rug pulls and sandwich attacks. We extract the optimal sandwich amount, revealing that their proliferation in new tokens stems from higher profitability in low-liquidity pools. Furthermore, we analyze the fundamental differences between token price evolution in swap time and physical time. Using clustering techniques, we highlight these differences and identify typical patterns of honeypot and sellable tokens. Our study provides insights into the risks and financial dynamics of decentralized markets and their challenges for investors.
Carlos Melo, Glauber Gonçalves, Francisco A. Silva, André Soares
Hyperledger Fabric is a platform for permissioned blockchain networks that enables secure and auditable distributed data storage for enterprise applications. There is a growing interest in applications based on this platform, but its use requires the configuration of different blockchain parameters. Various configurations impact the system's non-functional qualities, especially performance and cost. In this article, we propose a Stochastic Petri Net to model the performance of the Hyperledger Fabric platform with different blockchain parameters, computer capacity, and transaction rates. We also present a set of case studies to demonstrate the feasibility of the proposed model. This model serves as a practical guide to help administrators of permissioned blockchain networks find the best performance for their applications. The proposed model allowed us to identify the block size that leads to a high mean response time (ranging from 1 to 25 seconds) caused by a change in the arrival rate.
Many blockchains such as Ethereum execute all incoming transactions sequentially significantly limiting the potential throughput. A common approach to scale execution is parallel execution engines that fully utilize modern multi-core architectures. Parallel execution is then either done optimistically, by executing transactions in parallel and detecting conflicts on the fly, or guided, by requiring exhaustive client transaction hints and scheduling transactions accordingly. However, recent studies have shown that the performance of parallel execution engines depends on the nature of the underlying workload. In fact, in some cases, only a 60% speed-up compared to sequential execution could be obtained. This is the case, as transactions that access the same resources must be executed sequentially. For example, if 10% of the transactions in a block access the same resource, the execution cannot meaningfully scale beyond 10 cores. Therefore, a single popular application can bottleneck the execution and limit the potential throughput. In this paper, we introduce Anthemius, a block construction algorithm that optimizes parallel transaction execution throughput. We evaluate Anthemius exhaustively under a range of workloads, and show that Anthemius enables the underlying parallel execution engine to process over twice as many transactions.
Blockchain technology, characterized by its immutability, decentralization, transparency, security, and traceability, has shown vast potential for applications in secure IoT communications and data protection through its deployed smart contracts. While machine learning-based code generation systems aim to automate high-quality programming solutions, they face significant challenges when addressing blockchain-related issues. This paper analyzes the limitations of machine learning in identifying vulnerabilities within blockchain smart contracts and proposes robust solutions. To achieve this, this paper suggests organizing multiple security experts for labeling, developing efficient labeling tools, employing semi-supervised learning to reduce dependency on labeled data, and establishing a continuous update mechanism for labeled datasets to adapt to evolving threat landscapes. To address the scarcity of training samples in the blockchain domain, this paper introduces a method for generating additional Solidity smart contract training samples using data augmentation techniques. Given that traditional data augmentation methods are not suitable for Solidity, the approach involves converting Solidity contracts into Python code for processing, then reverting them back to Solidity post-augmentation, with provided code examples. Furthermore, leveraging established non-blockchain code to train blockchain-related models enhances model performance and generalization capabilities. These strategies effectively tackle the issue of insufficient training samples in the blockchain field and offer new perspectives on the conversion between Solidity and Python.
Digital product passports (DPPs) will become a reality for several regulated products in Europe. The topic is still in its infancy but will significantly impact product information and the infrastructure required by manufacturing in increasingly agile and circular supply chains. This paper presents the results of a two-year design science research to develop an end-to-end blockchain-based DPP prototype instantiated in the textile industry. On the one hand, the upstream supply chain involves physical product transformations from the early stages of production, requiring a robust traceability architecture. On the other hand, multiple events occur during downstream phases that need to be easily accessible by different stakeholders. Our results confirm the suitability of blockchain-based DPPs and define the information flow within the product life cycle. This paper advances the literature on sustainable product identification, ensuring tamper-proof and transparent information in the supply chain. Although aiming at the end consumers, the DPP will majorly impact production, requiring proper industry planning. For practitioners, this paper provides one of the first DPP instantiations in different segments of the textile supply chain, highlighting the requirements that the industry should be aware of for the coming years. Eleven design principles for blockchain-based DPPs are proposed.
This comprehensive article explores the technological foundations, implementation frameworks, and future implications of smart contracts in blockchain technology.The article examines the core features of smart contracts, including their automated execution mechanisms, security architectures, and cost efficiency through disintermediation.Through detailed analysis of real-time execution environments and Preethi Ravisankar
The financial applications of the blockchain technology are gaining increasing attention in the regulatory sphere both for their growing relevance and for the several scandals and failures of the past months. The regulatory landscape is quickly and non-linearly evolving, resulting in the impossibility to capture a nitid snapshot of the international regulatory regime from a comparative perspective. Therefore, this chapter takes a functional approach, investigating the sources and dynamics of regulatory convergence and divergence in the area of cryptocurrencies and stablecoins. The chapter focuses mostly, but not exclusively, on the regulatory regime of the EU, UK and US. This chapter adds to the literature on the regulation of crypto finance as it provides a functional framework to approach an area whose regulation is quickly evolving. Moreover, it also adds to the comparative law literature, looking at the sources and dynamics of divergence in the regulation of innovative technologies.
Anber Abraheem Shlash Mohammad, Ammar Mohammad Al-Ramadan, Suleiman Ibrahim Mohammad, Badrea Al Oraini · 8 authors
Sustainability in food supply chains is a critical global challenge, particularly in resource-constrained regions like Jordan, where operational inefficiencies and environmental concerns are prevalent. This study explores the integration of blockchain and artificial intelligence (AI) technologies to enhance metadata management, forecast sustainability metrics, and support decision-making in Jordan’s food supply chains. Blockchain's ability to improve metadata accuracy, standardization, and traceability, combined with AI’s predictive capabilities, offers a powerful solution for addressing sustainability challenges.MethodsThe research employed a mixed-methods approach, combining real-time data from blockchain transaction logs, AI-generated forecasts, and stakeholder surveys. Blockchain data from platforms like Hyperledger Fabric and Ethereum provided insights into metadata accuracy and traceability. AI models were developed using machine learning techniques, such as linear regression, to forecast food waste reduction, carbon footprint reduction, and energy efficiency. Multi-Criteria Decision Analysis (MCDA), using AHP and TOPSIS, was applied to evaluate trade-offs among sustainability goals.ResultsThe results revealed significant improvements in metadata accuracy (from 83% to 96.66%) and reductions in traceability time (from 4.0 to 2.35 hours) following blockchain implementation. AI models demonstrated high predictive accuracy, explaining 88%, 81%, and 76% of the variance in food waste reduction, carbon footprint reduction, and energy efficiency, respectively. ConclusionThis study underscores the transformative potential of blockchain and AI technologies in achieving sustainability goals. By fostering transparency, predictive insights, and data-driven decision-making, these innovations can address key challenges in Jordan’s food supply chains, offering actionable strategies for stakeholders.
Ahmad Anwar Zainuddin, Farah Mazlan, Nur Faizah Omar, Nik Nor Muhammad Saifudin Nik Mohd Kamal
Most conventional contract systems have issues with middlemen, drawn-out implementation procedures, fraud risk, and human error. Considering this, the project uses smart contract technology to provide a decentralized, automated, and safe solution in an effort to address such inefficiencies and the trust issues they raise. Smart contracts enable self-execution of contracts whose conditions are expressed explicitly in lines of code by presenting solutions using blockchain technology. The concept behind a smart contract is that each party may carry out their portion of the duties without depending on a third party and the contract will automatically execute in the meantime. This automation significantly reduces transaction costs while simultaneously improving security and transparency. With the use of this underlying technology, smart contracts may be used to directly code parties' compliance with their duties under the agreement and the blockchain will keep an immutable record of every transaction. For smooth and dependable transactions, smart contracts offer a dependable and effective substitute for conventional contract methods. Furthermore, integrating smart contracts with cutting-edge technologies like machine learning and artificial intelligence could improve decision-making and accelerate operations in a variety of sectors. Their application extends beyond financial transactions to areas such as supply chain management, energy trading, and healthcare, showcasing their versatility. Despite these advantages, issues like energy consumption, scalability, and regulatory compliance still need creative solutions. Ongoing research and development aim to address these issues, fostering the evolution of smarter, more sustainable contract systems. By leveraging these advancements, smart contracts keep opening the door for a revolution in the digital economy that will increase productivity and confidence.
Moch Panji Agung Saputra, Riza Andrian Ibrahim, Renda Sandi Saputra
The increasing use of cryptocurrencies has changed the dynamics of investment, presenting both opportunities and challenges for investors. Although various studies have compared the performance of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) in predicting financial asset prices, there are still differences in results regarding which model is superior. Therefore, this study aims to compare the performance of LSTM and GRU in predicting Ethereum prices using a hyperparameter tuning approach. The data used is historical data of Ethereum (ETH) shares from 2020 to 2025. The research methodology includes data preprocessing using Min-Max scaling, model development with various layer configurations, and comprehensive evaluation using several performance metrics. The results show that the GRU Model provides superior performance with a lower Root Mean Squared Error (RMSE) of 0.0234 and Mean Absolute Error (MAE) of 0.0168, compared to LSTM's RMSE of 0.0265 and MAE of 0.0193. While LSTM exhibits a slightly better Mean Absolute Percentage Error (MAPE) of 18.08% compared to GRU at 18.17%, the GRU model achieves a higher R² Score of 0.9442 compared to LSTM at 0.9282. Visual analysis of the prediction patterns and residual distributions further demonstrates GRU’s more consistent and accurate performance in capturing Ethereum price movements. These findings suggest that while both models are effective for cryptocurrency price prediction, GRU offers slightly better overall performance and stability, especially in maintaining consistent prediction accuracy across different market conditions.
Anna Maria Fink, Johanna Nattenmüller, Stephan Rau, Alexander Rau · 10 authors
OBJECTIVES: This study evaluated the effect of enhancing a GPT-4 model with retrieval-augmented generation on its ability to diagnose and classify traumatic injuries based on radiology reports. MATERIALS AND METHODS: In this prospective proof-of-concept study, we used retrieval-augmented generation as a zero-shot learning approach to provide expert knowledge from the RadioGraphics top ten reading list for trauma radiology to the GPT-4 model, creating the context-aware TraumaCB. Radiological report findings of 50 traumatic injuries were independently generated by two radiologists. The performance of the TraumaCB compared to the generic GPT-4 was evaluated by three board-certified radiologists, assessing the accuracy and trustworthiness of the chatbot responses in the 100 reports created. RESULTS: The TraumaCB achieved 100% correct diagnoses, 96% correct classification, and 87% correct grading, outperforming the generic GPT-4 with 93% correct diagnoses, 70% correct classification, and 48% correct grading. TraumaCB sources consistently achieved a median rating of 5.0 for explanation and trust. Challenges encountered mainly involved traumatic injuries lacking widely accepted classification systems. CONCLUSION: Augmenting a commercial GPT-4 model with retrieval-augmented generation improves its diagnostic and classification capabilities, positioning it as a valuable tool for efficiently assessing traumatic injuries across various anatomical regions in trauma radiology. KEY POINTS: Question Retrieval-augmented generation has the potential to enhance generic chatbots with task-specific knowledge of emergency radiology. Findings The TraumaCB excelled in accuracy, particularly in injury classification and grading, and provided explanations along with the sources used, increasing transparency and facilitating verification. Clinical relevance The TraumaCB provides accurate, fast, and transparent access to trauma radiology classifications, potentially increasing the efficiency of image interpretation in emergency departments and enabling customized reports based on local or individual preferences.
Open access
Artificial Intelligence in Healthcare and Education
Abstract Decentralized Autonomous Organizations (DAOs) are attracting interest from various disciplines, particularly business and economics, and computer science. However, much like the parable of the blind men and the elephant, where each observer sees only part of the phenomenon, DAO research has largely remained fragmented across disciplines, limiting a comprehensive understanding of the potential of DAOs. This paper investigates to which extent DAO scholarship has achieved meaningful interdisciplinary integration. We address this question through an analysis of knowledge flows between Business and Economics and Computer Science, using citation network analysis, topic modelling, and outlet analysis. We find that while DAOs generate vibrant interdisciplinary discourse, the interactions remain predominantly applied and case-driven, with limited theoretical integration. By mapping interdisciplinary exchanges, we highlight key gaps and opportunities for greater synthesis across fields. We argue that strengthening the alignment between organizational and technical insights is crucial for advancing DAO research and fostering a more cohesive interdisciplinary framework.