Vincent W.J. van Gerven Oei, Pieter Effendy, Lili Ayu Wulandhari, Islam Nur Alam
Cryptocurrencies have recently become popular among many people, young and old, with various backgrounds. The popularity of cryptocurrency shines due to several things, one of which is Bitcoin, the largest cryptocurrency ever to exist. However, even though Bitcoin is well-known and considered as the largest cryptocurrency, Bitcoin still experienced major price fluctuations over the years, seen in daily trades and yearly valuations. It is because in this digital era, the whole market can be said to be vulnerable because news and social media posts can easily be accessed on the internet. Therefore, it can create sentiments and trends across society. Due to the possibility that sentiment and trends can influence the volatility movements of cryptocurrencies such as Bitcoin, this research wants to see whether the use of sentiment analysis and trends in one of Machine Learning algorithms, namely Random Forest, can predict the Bitcoin price action well.
The application of Ethereum Blockchain within IoT-based weather monitoring systems presents substantial potential for enhancing data security, integrity, transparency, and trust. This study is focused on the design, implementation, and evaluation of Ethereum Blockchain as a robust data security mechanism in an IoT weather monitoring system. The system is configured to monitor environmental parameters, specifically temperature and humidity, using DHT22 sensors, with data securely stored and processed through smart contracts on a locally deployed Ethereum network. The research utilizes the Proof of Authority consensus mechanism, assessing data transmission and storage latency across varying mining intervals. The findings reveal minimal transmission delays, whereas storage delays on the blockchain exhibit variability, influenced by the duration of the mining period. Specifically, longer mining intervals contribute to increased delays in data storage. These results underscore the necessity of optimizing the mining interval to ensure complete and synchronized data storage, thereby enhancing the accuracy and reliability of the weather monitoring system. This study demonstrates the efficacy of Ethereum Blockchain in addressing critical challenges related to data security and integrity within IoT applications, highlighting its potential as a promising solution for secure data management.
This paper proposes a new blockchain-based transaction verification infrastructure for co-payment and data verification for multi-modal public transportation systems.Our solution offers a decentralized platform that ensures secure copayments and data integrity while addressing interoperability, data security and transactional transparency.With a private blockchain, transportation providers act as nodes and validated, consensus-approved transactions increase trust and transparency.A standardized data format and robust algorithms for data contribution by transport operators are developed as well as a model for operators, assets, and transactions.Including zero-knowledge proofs improves user privacy by allowing secure authentication without revealing sensitive data.We believe that this research may lead a closer collaboration between public transport operators and provide an enhanced user experience while enabling transport transaction security and data verification.
The rapid increase in the number of electric vehicles (EVs) has resulted in huge fuel tax losses for governments every year. Many countries have levied taxes based on the annual or monthly travel record (TR) submitted by the EV. On the one hand, TR contains important private information, such as the time, locations, and trajectories of EV owners. On the other hand, EV owners may forge TR to reduce taxes. Therefore, the verification protocol of TR requires extremely high security and effectiveness. To solve this outstanding issue, this paper proposes a V2I-SNARK protocol that combines vehicle-to-infrastructure communications (V2I) and zk-SNARK for TR verification of EVs. V2I -SNARK is divided into two stages, the trusted setup stage and the TR verification stage. In the former stage, a trusted authority (TA) will generate the proof key and verification key for verification and store them on the verification server (Verifier). In the latter stage, EV will use the proof key to generate a randomized proof, and the verifier will use the verification key to verify the proof. Regarding the performance of the V2I -SNARK protocol, we first provide security proofs for completeness, soundness, and zero-knowledge properties. Furthermore, we compare the verification efficiency, energy consumption, computational complexity, and other performance of V2I-SNARK with the benchmark protocols. The results show that the proposed V2I-SNARK protocol outperforms other protocols in terms of verification efficiency and energy consumption.
As a crucial component of the digital economy, the market price fluctuations of Non-Fungible Tokens (NFTs) are influenced by various factors, making accurate prediction extremely important. This paper leverages a Graph Neural Network (GNN) model to analyze features such as user interaction frequency, user influence, and the popularity of discussion topics within social networks, aiming to predict the volatility of NFT market prices. Experimental results demonstrate that the GNN model achieves a prediction accuracy of 92%, significantly outperforming traditional time series models and linear regression models in key metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), and R². The study finds that high-influence users and trending discussion topics in social networks are the primary drivers of price volatility. This research not only validates the effectiveness of the GNN model in processing complex social network data but also provides new theoretical insights and practical references for understanding and predicting market behaviors in the digital asset space. The findings offer a solid foundation for the design and optimization of price prediction models in the future digital economy.
• Deploys AIoT and DLT to create novel business models for improved data driven services in smart cities. • Provides understanding on the integration of AIoT and DLT in achieving intelligent mobility services in smart cities. • Bridges the gap between theory and practice by providing insights on the potential benefits of converging AIoT and DLT. • Grounded on the TOE framework this study presents the factors that impacts the convergence of AIoT and DLT in smart cities. • Present use cases on the applicability of AIoT and DLT to support intelligent mobility services in smart cities. The society is witnessing an accelerated large-scale adoption of technology with transformative effects on daily transport operations, with cities now depending on data driven mobility services. Disruptive technologies such as Artificial Intelligence (AI), the Internet of Things (IoT), and decentralized technologies for example Distributed Ledger Technologies (DLT) are being deployed in smart cities. However, AI is faced with data security and privacy issues due to its centralized mode of deployment. Conversely, DLT which employs a decentralized architecture can be converged with AI to provide a secure data sharing across various IoT thereby overcoming the existing setbacks faced in deploying AI in smart cities. Evidently, the convergence of AI and IoT as AIoT and DLT have great potential to create novel business models for improved data driven services such as intelligent mobility in smart cities. Although research on the convergence of AI, IoT and DLT exists, our understanding of its integration in achieving intelligent mobility services in smart cities remains fragmented as current research in this area remains scarce. This study bridges the gap between theory and practice by providing researchers and practitioners with insights on the potential benefits of converging AIoT and DLT. Grounded on the Technology Organization Environment (TOE) framework this study presents the technological, organizational, and environmental factors that impacts the convergence of AIoT and DLT in smart cities. Additionally, findings from this study present use cases on the applicability of AIoT and DLT to support intelligent mobility services in smart cities.
The article examines the issue of insufficiently efficient forecasting mechanism of cash flow and liquidity status on the boiler accounts of local budgets, which led to the revision of liquidity management practices. In the context of financial decentralization, local financial authorities have faced numerous challenges, including the need to ensure sufficient cash balances in the accounts of local budgets to guarantee financing and payment of obligations with minimal associated costs. In addition, effective management of cash reserves and forecasting of the revenue base of local budgets is necessary. The authors emphasize the importance of applying modern forecasting methods, such as machine learning and neural networks, which allow faster and more accurate analysis of financial data and more accurate forecasts. special attention assigned processes previous processing and automation data, algorithm selection, training models and estimates productivity. The article also investigated the concept management liquidity developed by the Ministry of finance of Ukraine for 2020-2023, and its impact on improvement of management practices state finances. Thus, in the article is highlighted necessity implementation effective methods forecasting and management liquidity for security stability and efficiency financial systems at both the local and state levels.
When analyzing Bitcoin users' balance distribution, we observed that it follows a log-normal pattern. Drawing parallels from the successful application of Gibrat's law of proportional growth in explaining city size and word frequency distributions, we tested whether the same principle could account for the log-normal distribution in Bitcoin balances. However, our calculations revealed that the exponent parameters in both the drift and variance terms deviate slightly from one. This suggests that Gibrat's proportional growth rule alone does not fully explain the log-normal distribution observed in Bitcoin users' balances. During our exploration, we discovered an intriguing phenomenon: Bitcoin users tend to fall into two distinct categories based on their behavior, which we refer to as ``poor" and ``wealthy" users. Poor users, who initially purchase only a small amount of Bitcoin, tend to buy more bitcoins first and then sell out all their holdings gradually over time. The certainty of selling all their coins is higher and higher with time. In contrast, wealthy users, who acquire a large amount of Bitcoin from the start, tend to sell off their holdings over time. The speed at which they sell their bitcoins is lower and lower over time and they will hold at least a small part of their initial holdings at last. Interestingly, the wealthier the user, the larger the proportion of their balance and the higher the certainty they tend to sell. This research provided an interesting perspective to explore bitcoin users' behaviors which may apply to other finance markets.
The integration of machine learning (ML), blockchain, and the Internet of Things (IoT) in smart cities represents a pivotal advancement in urban innovation. This convergence addresses the complexities of modern urban environments by leveraging ML’s data analytics and predictive capabilities to enhance the intelligence of IoT systems, while blockchain provides a secure, decentralized framework that ensures data integrity and trust. The synergy of these technologies not only optimizes urban management but also fortifies security and privacy in increasingly connected cities. This survey explores the transformative potential of ML-driven blockchain-IoT ecosystems in enabling autonomous, resilient, and sustainable smart city infrastructure. It also discusses the challenges such as scalability, privacy, and ethical considerations, and outlines possible applications and future research directions that are critical for advancing smart city initiatives. Understanding these dynamics is essential for realizing the full potential of smart cities, where technology enhances not only efficiency but also urban sustainability and resilience.
Behkish Nassirzadeh, Albert Heinle, Stefanos Leonardos, Anwar Hasan · 5 authors
Blockchain integration in industries like online advertising is hindered by its connectivity limitations to off-chain data. These industries heavily rely on precise counting systems for collecting and analyzing off-chain data. This requires mechanisms, often called oracles, to feed off-chain data into smart contracts. However, current oracle solutions are ill-suited for counting systems since the oracles do not know when to expect the data, posing a significant challenge. To address this, we present CountChain, a decentralized oracle network for counting systems. In CountChain, data is received by all oracle nodes, and any node can submit a proposition request. Each proposition contains enough data to evaluate the occurrence of an event. Only randomly selected nodes participate in a game to evaluate the truthfulness of each proposition by providing proof and some stake. Finally, the propositions with the outcome of True increment the counter in a smart contract. Thus, instead of a contract calling oracles for data, in CountChain, the oracles call a smart contract when the data is available. Furthermore, we present a formal analysis and experimental evaluation of the system's parameters on over half a million data points to obtain optimal system parameters. In such conditions, our game-theoretical analysis demonstrates that a Nash equilibrium exists wherein all rational parties participate with honesty.
An artificial neural network is a model from the field of machine learning that was inspired by the structure and function of the brain.Whilst deep learning involves neural networks with multiple layers between the input and output layers.This paper shows how neural networks work, and describes various features.Backpropagation is explained in detail, and the common issues that one can face whilst training a neural network are described.Methods of mitigating these issues are also given.Finally, a neural network is employed to build a daily Bitcoin trading system.The results were inferior to multiple linear regression.The neural network likely suffered from overfitting, but regularisation using dropout helped to mitigate this.
Shuchen Zhou, Lei Yu, Yinling Wang, Sami Dhahbi · 6 authors
In this paper, we utilise blockchain technology (BT) and circular q -rung orthopair fuzzy sets ( C q -ROFS) to address practical issues related to urban transportation and supply chain management (SCM). Recognising the weaknesses of earlier approaches such as circular intuitionistic fuzzy sets (C-IFS), we work C q -ROFS to better accommodate imprecise input. Novel approaches that use into metaverse settings are being investigated as a means of addressing the complex problems associated with urban mobility. This study use the SWARA-AROMAN approach to evaluate potential blockchain integration possibilities for metaverse urban mobility. Sensitivity analysis and comprehensive evaluation yield powerful insights into the robustness and adaptability of solutions. With these findings at their disposal, policymakers will be more equipped to take on unpredictability and take advantage of opportunities for sustainable urban mobility. To enhance urban transportation solutions in the dynamic metaverse, future strategies should concentrate on improving processes and exploring novel technology. Ultimately, this research emphasises how critical it is to foster interdisciplinary collaboration and ongoing innovation if we hope to influence the patterns of urban mobility in the metaverse.
S. Gopalakrishnan, E. D. Kanmani Ruby, D. Hemanand, R. Anitha · 6 authors
The incorporation or combination of Artificial Intelligence (AI) and blockchain technology into Mobile Ad Hoc Networks (MANETs) shows important factor for modern and advance smart city infrastructure and autonomous vehicular networks. This paper describes the complementary potential of the technologies to help the built-in difficulties of MANETs includes flexibility, protection, and data integrity. AI techniques such as machine learning and reinforcement learning, are emphasized to improve routing protocols to optimize data transmission rates, and decrease latency. Blockchain technology using Practical Byzantine Fault Tolerance (PBFT) and other consensus mechanisms, gives a tight and decentralized architecture for data handling assuring trust and integrity amidst network nodes. The appeal of these incorpoarted technologies is especially related for smart cities which depand on collection of data and evaluation for effective handling of urban operations such as flow of traffic, environmental observing, and consumption of energy. Autonomous vehicular networks needing rigd and strong communication and data transfer between vehicles and infrastructure, also help from the enhanced network functions and security provided by AI and blockchain incorpoaration. Experimental evaluation denotes improvements in crucial performance metrics. Sensor 2 persists the highest data transmission rate of 12 Mbps. Sensor 4 had the decreased at 9 Mbps. Latency measurements observed that Sensor 2 recorded the lowest latency at 45 ms, with Sensor 3 having the highest at 55 ms.
Abstract In Web3 social platforms, i.e. social web applications that rely on blockchain technology to support their functionalities, interactions among users are usually multimodal, from common social interactions such as following, liking, or posting, to specific relations given by crypto-token transfers facilitated by the blockchain. In this dynamic and intertwined networked context, modeled as a financial network, our main goals are (i) to predict whether a pair of users will be involved in a financial transaction, i.e. the transaction prediction task , even using textual information produced by users, and (ii) to verify whether performances may be enhanced by textual content. To address the above issues, we compared current snapshot-based temporal graph learning methods and developed T3GNN, a solution based on state-of-the-art temporal graph neural networks’ design, which integrates fine-tuned sentence embeddings and a simple yet effective graph-augmentation strategy for representing content, and historical negative sampling. We evaluated models in a Web3 context by leveraging a novel high-resolution temporal dataset, collected from one of the most used Web3 social platforms, which spans more than one year of financial interactions as well as published textual content. The experimental evaluation has shown that T3GNN consistently achieved the best performance over time and for most of the snapshots. Furthermore, through an extensive analysis of the performance of our model, we show that, despite the graph structure being crucial for making predictions, textual content contains useful information for forecasting transactions, highlighting an interplay between users’ interests and economic relationships in Web3 platforms. Finally, the evaluation has also highlighted the importance of adopting sampling methods alternative to random negative sampling when dealing with prediction tasks on temporal networks.
Recent advancements in vehicular traffic sensing have significantly enhanced traffic information collection for the platform. However, this approach encounters two primary challenges: balancing the freshness of traffic information in the long term with the costs of vehicle recruitment and ensuring the privacy of participating vehicles. To address these challenges, we introduce a smart-contract-based incentive mechanism that recruits vehicles for traffic sensing. Our approach is structured as a two-stage game. In Stage I, the platform designs the incentive mechanism. In Stage II, vehicles independently decide their participation in the sensing process. Despite the inherent challenges of dealing with different time scales and the lack of future information, our framework effectively transforms the long-term problem into a solvable short-term one with a closed-form solution. Additionally, our implementation of the incentive mechanism through a blockchain-based smart contract offers a unique advantage: it enables vehicles to anonymously upload sensing data and receive payments, thereby safeguarding their privacy. Numerical analysis demonstrates the efficacy of the proposed method in fulfilling long-term information freshness requirements. Furthermore, the proposed method reduces the platform's time-average cost by 59.6%, 24.6%, 28.5%, and 25.8%, compared with other benchmarks.
Huong Q. Nguyen, Tri Nguyen, Lauri Lovén, Susanna Pirttikangas
This paper presents a fully coupled blockchain-assisted federated learning architecture that effectively eliminates single points of failure by decentralizing both the training and aggregation tasks across all participants. Our proposed system offers a high degree of flexibility, allowing participants to select shared models and customize the aggregation for local needs, thereby optimizing system performance, including accurate inference results. Notably, the integration of blockchain technology in our work is to promote a trustless environment, ensuring transparency and non-repudiation among participants when abnormalities are detected. To validate the effectiveness, we conducted real-world federated learning deployments on a private Ethereum platform, using two different models, ranging from simple to complex neural networks. The experimental results indicate comparable inference accuracy between centralized and decentralized federated learning settings. Furthermore, our findings indicate that asynchronous aggregation is a feasible option for simple learning models. However, complex learning models require greater training model involvement in the aggregation to achieve high model quality, instead of asynchronous aggregation. With the implementation of asynchronous aggregation and the flexibility to select models, participants anticipate decreased aggregation time in each communication round, while experiencing minimal accuracy trade-off.
D. Obasuyi, Rume Elizabeth Yoro, Margaret Dumebi Okpor, A.M Ifioki · 13 authors
As competitive market and globalization continue to ripple a range of issues across the asset chain (i.e. safety, quality, tracing, and overall management efficiency). Pandemics are bound to occur without warning and has revealed the unpreparedness of many nations. Thus, the Nigerian Government aiming to shore up revenue/monetization via customs exercise duties to augment the nosedive in revenue of the oil sector – must formulate policies and adapt technology to harness its inherent benefits therein. Study advances a sensor-based blockchain NiCuSBlockIoT, which will provision a decision-support scheme for cargo goods traceability and asset movement on a value-chain by first ensuring that accurate records of cargo goods are registered, tagged and reported using the sensor-based units. These are then broadcasted on to the NiCuSBlockIoT as record and/or blocks via a P2P chain on the network as a decentralized framework executed on a distributed hyper-ledger fabric via smart-contract transaction logic. Result show model eliminate fraud that often accompanies a centralized scheme via its sensor-layered model that reports all such errors as data on NiCuSBlockIoT supply value chain. Keywords: BlockChain, Food supply chain, Nigerian Customs Service, NISBlockIoT framework CISDI Journal Reference Format Obasuyi, D.A., Yoro, R.E., Okpor, M.D., Ifioki, A.., Brizimor, S.., Ojugo, A.A., Odiakaose, C.C., Emordi, F.U., Ako, R.E., Geteloma, V.C., Abere, R.A., Atuduhor, R.R. & Akiakeme, E. (2024): NiCuSBlockIoT: Sensor-based Cargo Assets Management and Traceability Blockchain Support for Nigerian Custom Services. Computing, Information Systems, Development Informatics & Allied Research Journal. Vol 15 No 2, Pp 45-64. dx.doi.org/10.22624/AIMS/CISDI/V15N2P4. Available online at www.isteams.net/cisdijournal
Object-based modeling has become an integral and more preferred design approach as against two-dimensional (2D) design representation. This is evident in the increased use of building information modeling (BIM) for building design and city information modeling (CIM) for city planning and development. However, the development and management of object-based city models are often siloed and do not coexist in a virtual environment. Urban infrastructure is often designed in isolation, yet it forms part of an integrated network of assets in real life. Blockchain is one of several technologies that has been integrated with BIM because of its transparent and tamper-proof features. This research proposes a framework for the lifecycle management of buildings and other urban assets by integrating blockchain technology (BCT) into a heterogenous CIM of multiowned assets using a nested, multilevel data environment. First, the BIM is synchronized into a GIS scene for geospecificity, then the BIM metadata is written onto a blockchain protocol distributing the model information across a network of project collaborators using a common data environment (CDE). The resultant CIM is then shared through an outer layered city level CDE. Use case scenarios are presented to validate the functionality of the proposed approach, and research limitations are discussed. The framework enables the critical interproject or interasset communication which is otherwise impossible in traditional approaches where individual assets are designed as stand-alone models.
In the volatile cryptocurrency market, accurately forecasting Bitcoin prices is crucial yet challenging, carrying significant economic implications. This paper presents a novel hybrid model that merges the predictive capabilities of Long Short-Term Memory (LSTM) networks with the computational efficiency of Gated Recurrent Units (GRU). This integration is designed to simultaneously capture long-term dependencies and short-term fluctuations inherent in Bitcoin price dynamics, thus providing a comprehensive analysis framework. The model utilizes a meticulous architecture starting with an input layer that normalizes data to address price variability, followed by LSTM layers that interpret long-term trends, and GRU layers that refine insights based on short-term variations. Evaluated using a dataset divided into training, validation, and testing phases and optimized with the Adam algorithm, the model’s performance surpasses traditional forecasting methods and standalone neural networks. Metrics such as RMSE, MAE, and R2confirm its superior predictive accuracy, with significant improvements over benchmarks like ARIMA, standalone LSTM, and GRU models. This breakthrough highlights the Hybrid LSTM-GRU model’s potential as a transformative tool for investors and analysts navigating the complexities of the cryptocurrency market.
Collin Meese, Hang Chen, Wanxin Li, Danielle Lee · 7 authors
Managing urban traffic dynamics is critical in Intelligent Transportation Systems (ITS), where short-term traffic prediction is vital for effective congestion management and vehicle routing. While existing centralized deep learning (DL) models have achieved high prediction accuracy, their applicability is limited in decentralized ITS environments. The increasing use of connected vehicles and mobile sensors has led to decentralized data generation in ITS, presenting an opportunity to improve traffic prediction through collaborative machine learning. Recently, blockchain technology has shown promise in improving ITS efficiency, security, and reliability. In conjunction with blockchain, Federated Learning (FL) is a suitable approach to leverage online data streams in ITS; however, most research on FL for traffic prediction focuses on offline learning scenarios. This paper researches a blockchain-enhanced architecture for training online traffic prediction models using FL. The proposed approach enables decentralized model training at the edge of the ITS network, and extensive experiments used dynamically collected arterial traffic data shards as a case study to evaluate online learning performance. The results demonstrate that our online FL approach outperforms the per-device, non-federated baseline models for most sensors while maintaining a suitable execution time and latency for real-world deployment.