The use of computationally intensive systems that employ machine learning algorithms is increasingly common in the field of finance. New state of the art deep learning architectures for time series forecasting are being developed each year making them more accurate than ever. This study evaluates the predictive power of the N-BEATS deep learning architecture trained on Bitcoin daily, hourly, and up-to-the-minute data in comparison with other popular time series forecasting methods such as LSTM and ARIMA. Prediction errors are measured with Mean Average Percentage Error (MAPE), and Root Mean Squared Error (RMSE). The results suggest that the developed N-BEATS model has promising predictive power compared to LSTM and ARIMA models.
Artificial neural networks are modern methods suitable for solving the problem of nonlinear dependency approximation, which is successfully applied in many fields. This paper compares the predictive capabilities of Back Propagation, Radial Basis Function, Extreme Learning Machine, and Long-Short Term Memory neural networks to determine which artificial intelligence algorithm is best for modeling the price of Bitcoin opening. The criterion for comparing network performance was the standard deviation, the mean absolute deviation, and the accuracy of predicting the direction of change of course. At the same time, in the study of time series, it is recommended to perform a comprehensive data analysis using appropriate networks, depending on the length of the series and the specificity of the database.
Adnan Iftekhar, Xiaohui Cui, Mir Hassan, Wasif Afzal
Food supply chain plays a vital role in human health and food prices. Food supply chain inefficiencies in terms of unfair competition and lack of regulations directly affect the quality of human life and increase food safety risks. This work merges Hyperledger Fabric, an enterprise-ready blockchain platform with existing conventional infrastructure, to trace a food package from farm to fork using an identity unique for each food package while keeping it uncomplicated. It keeps the records of business transactions that are secured and accessible to stakeholders according to the agreed set of policies and rules without involving any centralized authority. This paper focuses on exploring and building an uncomplicated, low-cost solution to quickly link the existing food industry at different geographical locations in a chain to track and trace the food in the market.
M. Sivaram, E. Laxmi Lydia, Irina V. Pustokhina, Denis A. Pustokhin · 7 authors
The booming applications of bitcoin Blockchain technologies made investors concerned about the return and risk of financial products. So, the return rate of bitcoin must be foreseen in prior. This research article devises an effective return rate prediction technique for Blockchain financial products based on Optimal Least Square Support Vector Machine (OLS-SVM) model. The parameter optimization of the LS-SVM model was performed using hybridization of Grey Wolf Optimization (GWO) with Differential Evolution (DE), called optimal GWO (OGWO) algorithm. The hybridization process is performed to eliminate the local optima problem of GWO and enhance the diversity of the population. To verify the goodness of the proposed model, the Ethereum (ETH) return rate was chosen as the target and experimental analysis was performed on it to verify the predictive results on the time series. The experimental outcome was analyzed in terms of two performance measures namely Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). The obtained simulation outcome infers that the OLS-SVM model yielded better predictive outcome of the return rate of financial products.
The current land registration process involves a lot of vulnerabilities and people uses it to cheat the common people and the government. This paper discusses about a secure land registry implemented using blockchain which works on the basis of majority consensus. By implementing the land registry in blockchain, the security issue is resolved to a great extent. The hash value calculated for each block will be unique as it is linked to the hash of the previous block. The algorithm that is used for hashing is SHA256. Along with SHA256, Proof Of Work(PoW) algorithm is also used which makes the information related to each transaction more secure. Message digest that is generated for each block is of fixed size and each hash represents a complete set of transaction within a given block. The proposed land registry blockchain network consists of 12 nodes which calculates the proof of work. Nodes are responsible for verifying a transaction, mining a new block and adding the new block to the blockchain. A total of 200 land transactions are recorded using the blockchain methodology which offers a tamper proof and updated version of land registry. Elliptic curve cryptographic algorithm is used for signature generation which is used for verifying whether the transaction is signed by the owner or not. Merkle tree is used for linking the transactions using hash and in turn reduces the disk usage. The proposed implementation of land registry using blockchain thus offers a 99% reduction in manual effort spent in record keeping.
Bitcoin is a current popular cryptocurrency with a promising future. It’s like a stock market with time series, the series of indexed data points. We looked at different deep learning networks and methods of improving the accuracy, including min-max normalization, Adam optimizer and windows min-max normalization. We gathered data on the Bitcoin price per minute, and we rearranged them to reflect Bitcoin price in hours, a total of 56,832 points. We took 24 hours of data as input and output the Bitcoin price of the next hour. We compared the different models and found that the lack of memory means that Multi-Layer Perceptron (MLP) is ill-suited for the case of predicting price based on current trend. Long Short-Term Memory (LSTM) provides relatively the best prediction when past memory and Gated Recurrent Network (GRU) is included in the model.
Bin Yu, Ping Zhan, Ming Lei, Fang Zhou · 5 authors
Currently, food quality has become a major concern for the food industry. To efficiently detect food quality problems during the production process, food enterprises must build quality monitoring systems. However, in a traditional quality monitoring system, data tampering and centralized storage have become barriers to reliability. In addition, due to lack of sufficient automation, traditional quality monitoring approaches are usually inefficient. Fortunately, blockchain is a promising technology that is tamper-proof and decentralized. Moreover, smart contracts, which are executable codes on the blockchain platform, are able to conduct transactions between mutually untrusted parties and are self-executing and self-verifying. By combining smart contracts and quality evaluation models, this paper presents an intelligent quality monitoring system for fruit juice production. This system has the characteristics of high automation and high reliability. In this system, response surface models are established based on preproduction data, and the optimal production condition for each stage is identified. During the actual production process, smart contracts are executed to record production data on a blockchain. These data serve as the inputs for evaluation models. Based on the evaluation outcome, smart contracts will decide whether the production process can be resumed or not. To evaluate the feasibility of the presented system, a prototype version of the quality monitoring system for flat peach juice production is implemented based on the Ethereum platform and executed in the Remix IDE.
Bitcoin is considered to be most valuable and expensive currency in the world. Besides being first decentralized digital currency, its value has also experienced a steep increase, from around 1 dollar in 2010 to around 18000 in 2017. In recent years, it has attracted considerable attention in a diverse set of fields, including economics, finance and computer science. In economics, the primary focus has always been on studying how it affects the market, determining reasons behinds its price fluctuations, and predicting its future prices. In computer science, the focus is on its vulnerabilities, scalability, and other techno-cryptoeconomic issues. Firstly, we are going to collect the historical data of Bitcoin prices over the years 2013 to 2019 and do prediction for the year 2020. We have aimed to justify the usefulness of traditional Autoregressive Integrative Moving Average (ARIMA) model for predicting bitcoin prices. We have predicted the closing price of bitcoin for first seven days of January 2020. Further, we have created web services using ASP.NET to make the predictions on bitcoin price online and lastly, we have plotted the results in a responsive chart using Highcharts.
Günümüzde kripto para birimlerinin önemi gittikçe artmaktadır. Kripto para birimleri sanal oyun platformlarında kullanılırken, şu an pek çok kurum ve kuruluş tarafından ödeme aracı olarak kullanılmaktadır. Güvenlik risklerine karşı blockchain (Blok Zinciri) adı verilen algoritması ile üretimi sağlanmaktadır. Kripto para fiyatlarının doğru olarak tahmin edilmesi yatırımcı ve karar vericiler açısından büyük önem taşımaktadır. Bu çalışma kapsamında en çok kullanılan dört kripto para birimine (Bitcoin, Ethereum, Ripple, Litecoin) ait fiyat değerleri tahmin edilmiştir. Çoklu kırılma testinden yararlanılarak her seriye ait kırılmalar belirlenerek analiz genişletilmiştir. Ele alınan sanal para değerlerini doğru bir şekilde tahmin etmek amacıyla hem klasik zaman serisi modellerinden hem de üç farklı tür yapay sinir ağı modelinden faydalanılmıştır. Ayrıca elde edilen tahminler üzerinde basit birleştirilme teknikleri uygulanmıştır. Rassal yürüyüşün egemen olduğu bu seriler arasından, özellikle işlem hacmi ve bilinilirliği en fazla olan Bitcoin sanal parasında rassal yürüyüş modelinden daha iyi sonuçlar elde edildiği gözlemlenmiştir.
In the Architecture, Engineering, construction and Operations (AEcO) there is a growing interest in the use of the building Information modelling (bIm). Through integration of information and processes in a digital model, bIm can optimise resources along the lifecycle of a physical asset. Despite the potential savings are much higher in the operational phase, bIm is nowadays mostly used in design and construction stages and there are still many barriers hindering its implementation in Facility management (Fm). Its scarce integration with live data, i.e. data that changes at high frequency, can be considered one of its major limitations in Fm. The aim of this research is to overcome this limit and prove that buildings or infrastructures operations can benefit from a digital model updated with live data. The scope of the research concerns the optimisation of Fm operations. The optimisation of operations can be further enhanced by the use of maintenance smart contracts allowing a better integration between users' behaviour and maintenance implementation. In this case study research, the Image recognition (Imr), a type of Artificial Intelligence (AI), has been used to detect users' movements in an office building, providing real time occupancy data. This data has been stored in a bIm model, employed as single reliable source of information for Fm. This integration can enhance maintenance management contracts if the bIm model is coupled with a smart contract. Far from being a comprehensive case study, this research demonstrates how the transition from bIm to the Asset Information model (AIm) and, finally, to the Digital Twin (i.e. a near-real-time digital clone of a physical asset, of its conditions and processes) is desirable because of the outstanding benefits that have already been measured in other industrial sectors by applying the principles of Industry 4.0.
We present a new Bitcoin coin selection algorithm, "coin selection with leverage", which aims to improve upon cost savings than that of standard knapsack like approaches. Parameters to the new algorithm are available to be tuned at the users discretion to address other goals of coin selection. Our approach naturally fits as a replacement for the standard knapsack ingredient of full coin selection procedures.
In the modernized world like digital world, traditional way of payments through banks and other third parties are out of sphere. To meet the digital competency digital token like bitcoin based crypto currency payment is required. Lots of business persons are moving towards the digital way of secure payment. Intruders like hackers hamper the digital token and make immortality in the transaction which in turn create the double spend. Double spend is a serious threat in the Bitcoin network. Our research work focuses on double spend detection of transaction before it gets confirmed and added to the block by the miners. The proposed new architecture for detecting double spend using Dual Payout based on Lost Agreement Amount (DPL2A) will identify one of the ways that double spend attack occur before it is added to the blockchain. This architecture gives the clear identification of double spend attack and their full details of transaction occurrence so that when it is broadcasted into the peer-to-peer network, the network nodes will use this architecture to detect double spend, its occurrence is fully prevented and only the genuine transaction will be added to the blockchain.
The red-hot crypto currency is a bitcoin which occupies first position in the capital investment of financial world which is assaulted by various factors like wallet attacks, network attacks, mining attacks and double spending attacks. Double spending is the major attack in which the attacker tries to cheat the network nodes and use the same coin for more than one set of transactions. Of this the original transaction identification from the set of transactions is a challenging one. In this paper we propose a solution for identifying the primary transaction from the set of double spended or multi spended transactions. The proposed approach finds the authentic transaction from the list of double spended transactions using transaction hash value, which is primarily used for every transaction in the Bitcoin network. Transaction hash value is used as transaction identifier for each bitcoin transaction. By comparing the transaction hash value with the existing pool of unconfirmed input pool, transhash pool and utxopool one can identify the genuine transaction from the flawed transaction list. The firsthand transaction is then added to the Confirmed input pool which is then entered into the newly added block of the blockchain. This architecture will prevent the double spend of bitcoin further in the network which facilitates the network nodes as well as minimize the miners task for verification and validation of transaction.
Bitcoin has recently received a lot of attention from the media and the public due to its recent price surge and crash. Correspondingly, many researchers have investigated various factors that affect the Bitcoin price and the patterns behind its fluctuations, in particular, using various machine learning methods. In this paper, we study and compare various state-of-the-art deep learning methods such as a deep neural network (DNN), a long short-term memory (LSTM) model, a convolutional neural network, a deep residual network, and their combinations for Bitcoin price prediction. Experimental results showed that although LSTM-based prediction models slightly outperformed the other prediction models for Bitcoin price prediction (regression), DNN-based models performed the best for price ups and downs prediction (classification). In addition, a simple profitability analysis showed that classification models were more effective than regression models for algorithmic trading. Overall, the performances of the proposed deep learning-based prediction models were comparable.
Blockchains were initially introduced in 2009, and since then, they have evolved into a revolutionary technology that has affected, not only the digital world but also our everyday lives and activities. Blockchain systems and architectures continue to grow at a fast rate, constantly introducing innovative solutions across multiple research topics. However, despite their wide adoption by the research community, the technology is still not mature enough to address the problems of business use cases. Issues like scalability, complexity, cryptocurrencies' market fluctuations etc. prevent the proposed solutions from being widely accepted. Based on this observation this paper introduces an innovative solution to enable Big Data analysis of private information using blockchains. This solution is based on the Hyperledger Fabric blockchain and is able support the strict privacy and security requirements of operational and business environments.
Based on daily data about Bitcoin and six other major financial assets (stocks, commodity futures (commodities), gold, foreign exchange (FX), monetary assets, and bonds) in China from 2013 to 2017, we use a VAR-GARCH-BEKK model to investigate mean and volatility spillover effects between Bitcoin and other major assets and explore whether Bitcoin can be used either as a hedging asset or a safe haven. Our empirical results show that (i) only the monetary market, i.e., the Shanghai Interbank Offered Rate (SHIIBOR) has a mean spillover effect on Bitcoin and (ii) gold, monetary, and bond markets have volatility spillover effects on Bitcoin, while Bitcoin has a volatility spillover effect only on the gold market. We further find that Bitcoin can be hedged against stocks, bonds and SHIBOR and is a safe haven when extreme price changes occur in the monetary market. Our findings provide useful information for investors and portfolio risk managers who have invested or hedged with Bitcoin.
After Bitcoin Introduced around the world, many Cryptocurrencies was created that followed the standard of bitcoin. The use of Bitcoin or other Cryptocurrency as a currency is also an interesting study from an Islamic economic perspective. They tried to use gold with value back by gold , which gold itself is famous for its exchange rate stability. From abu bakar There is a need for monitoring organization of the cryptocurrency, to controlling from Riba (Interest), Maysir (gambling) and ghahar (Uncertainty). To solve this problem there is a need a tool that can predict with certainty based on valid historical data, to produce accurate prediction results and produce Economic value estimations that are close to Gold real value. With the results we can monitoring day by day, see next day value and continuously based on Cryptocurrency with value back by gold, and see what other impact influences the value by looking the factor negative or positive with sentiment analysis. In the last section we discuss and provide method that we analyse from previous work to produce method to estimate value cryptocurrency value back by gold.
Lukman Adewale Ajao, James Agajo, Emmanuel Adewale Adedokun, Loveth Karngong
This research work proposes a method for the securing and monitoring of petroleum product distribution records in a decentralized ledger database using blockchain technology. The aim of using this technique is to secure the transaction of distributed ledgers in a database and to protect records from tampering, fraudulent activity, and corruption by the chain participants. The blockchain technology approach offers an efficient security measure and novel advantages, such as in the transaction existence and distribution ledger management between the depot, transporter, and retailing filling station. Others advantages are transparency, immunity to fraud, insusceptibility to tampering, and maintaining record order. The technique adopted for this secure distributed ledger database is crypto hash algorithm-1 (SHA-1)-based public permissioned blockchain and telematics, while this telematics approach is an embedded system integrated into an in-vehicle model for remote tracking of geolocation (using Global Positioning System (GPS)), monitoring, and far-off data acquisition in a real-time. The scope of the data in the secure distributed ledger database (using blockchain) developed are identification (ID) of the tanker operator, Depot name, Source station ID, Destination station ID, Petroleum product volume, Transporter ID, and Geographic automobiles location. This system proved to be efficient, secure, and easy to maintain as it does not permit any individual for records tampering, but supports agreement of ~75% of participants in the chain to make changes.
La blockchain propose un système d'enregistrement décentralisé, immuable et transparent. Elle offre un réseau de nœuds sans entité de gouvernance centralisée, ce qui la rend "indéchiffrable" et donc plus sûr que le système d'enregistrement centralisé sur papier ou centralisé telles que les banques. L’approche traditionnelle basée sur l’enregistrement ne fonctionne pas bien avec les relations numériques où les données changent constamment. Contrairement aux canaux traditionnels, régis par des entités centralisées, blockchain offre à ses utilisateurs un certain niveau d'anonymat en leur permettant d'interagir sans divulguer leur identité personnelle et en leur permettant de gagner la confiance sans passer par une entité tierce. En raison des caractéristiques susmentionnées de la blockchain, de plus en plus d'utilisateurs dans le monde sont enclins à effectuer une transaction numérique via blockchain plutôt que par des canaux rudimentaires. Par conséquent, nous devons de toute urgence mieux comprendre comment ces opérations sont gérées par la blockchain et combien de temps cela prend à un nœud du réseau pour confirmer une transaction et l’ajouter au réseau de la blockchain. Dans cette thèse, nous visons à introduire une nouvelle approche qui permettrait d'estimer le temps il faudrait à un nœud de la blockchain Ethereum pour accepter et confirmer une transaction sur un bloc tout en utilisant l'apprentissage automatique. Nous explorons deux des approches les plus fondamentales de l’apprentissage automatique, soit la classification et la régression, afin de déterminer lequel des deux offrirait l’outil le plus efficace pour effectuer la prévision du temps de confirmation dans la blockchain Ethereum. Nous explorons le classificateur Naïve Bayes, le classificateur Random Forest et le classificateur Multilayer Perceptron pour l’approche de la classification. Comme la plupart des transactions sur Ethereum sont confirmées dans le délai de confirmation moyen (15 secondes) de deux confirmations de bloc, nous discutons également des moyens pour résoudre le problème asymétrique du jeu de données rencontré avec l’approche de la classification. Nous visons également à comparer la précision prédictive de deux modèles de régression d’apprentissage automatique, soit le Random Forest Regressor et le Multilayer Perceptron, par rapport à des modèles de régression statistique, précédemment proposés, avec un critère d’évaluation défini, afin de déterminer si l’apprentissage automatique offre un modèle prédictif plus précis que les modèles statistiques conventionnels.
Jul 17, 2019·Proceedings of the International Conferences ICT, Society, and Human Beings 2019; Connected Smart Cities 2019; and Web Based Communities and Social Media 2019
In the University setting, part of management recorded all education transaction since the students register until theygraduate. In this point, the transaction raises several new and crucial challenges. At a closer look, the concerns appeareddue
Bitcoin is a popular cryptocurrency that records all transactions in an allotted append-handiest public ledger referred to as a blockchain. The security of Bitcoin heavily relies on the motivation-suitable proof-of-work (PoW) founded dispensed consensus protocol, which is run with the aid of the community nodes known as miners. Because of its inception, blockchain technological know-how has proven promising application possibilities. The spectrum of blockchain functions stages from financial, healthcare, automobile, hazard administration, internet of matters (IoT) to public and social offerings. Several reports focal point on utilizing the blockchain information structure in various applications. These vulnerabilities result in the execution of different security threats to the ordinary functionality of Bitcoin. We then examine the feasibility and robustness of the brand new safety solutions. Moreover, we discuss the current anonymity concerns in Bitcoin and the privatenessrelated threats to Bitcoin customers together with the evaluation of the comprehensive privacy-keeping solutions.
Dhyanendra Jain, Ashu Jain, Amit Pandey, Jogender Kumar
Abstract Bitcoin is one of the crypto currencies and is most unpredictable currencies. In the world of crypto currencies, the value of a coin can unpredictably upgrade or degrade. In this study, the model has been trained to predict the value of Bitcoin in USD at any given time stamp. For this prediction, three algorithms of machine learning - Linear Regression (LR), Support Vector Regression (SVR) and Neural Network Regression (NNR) have been used. The model is trained using the collected dataset. After the collection of data set, we first applied SVR algorithm, then we used LR and then NNR to calculate the error compared to the actual value. Root mean squared error (RMSE) is used as the predictive measure. Out of the three algorithms, LR was found out to be more accurate for predicting the value of bitcoin.