Data privacy and sharing has always been a critical issue when trying to\nbuild complex deep learning-based systems to model data. Facilitation of a\ndecentralized approach that could take benefit from data across multiple nodes\nwhile not needing to merge their data contents physically has been an area of\nactive research. In this paper, we present a solution to benefit from a\ndistributed data setup in the case of training deep learning architectures by\nmaking use of a smart contract system. Specifically, we propose a mechanism\nthat aggregates together the intermediate representations obtained from local\nANN models over a blockchain. Training of local models takes place on their\nrespective data. The intermediate representations derived from them, when\ncombined and trained together on the host node, helps to get a more accurate\nsystem. While federated learning primarily deals with the same features of data\nwhere the number of samples being distributed on multiple nodes, here we are\ndealing with the same number of samples but with their features being\ndistributed on multiple nodes. We consider the task of bank loan prediction\nwherein the personal details of an individual and their bank-specific details\nmay not be available at the same place. Our aggregation mechanism helps to\ntrain a model on such existing distributed data without having to share and\nconcatenate together the actual data values. The obtained performance, which is\nbetter than that of individual nodes, and is at par with that of a centralized\ndata setup makes a strong case for extending our technique across other\narchitectures and tasks. The solution finds its application in organizations\nthat want to train deep learning models on vertically partitioned data.\n
Zhaowei Ma, F. Richard Yu, Xiantao Jiang, Azzedine Boukerche
The extensive use of vehicles, especially with the emergency of autonomous driving, urges the improvement of traffic safety. Prevalent approaches, such as Global Positioning System (GPS), Internet of Things (IoT) system and Artificial Intelligence (AI), have demonstrated their strength in preventing road accidents, with the support of trustworthy data. However, in vehicular ad hoc networks (VANETs), data transmission and storage are unreliable due to various constraints such as limited physical resource and unsteady topology. Distributed schemes are widely applied in VANETs to enforce multifold protection on vehicular data. In particular, Blockchain has become a promising approach, as it implements the real-sense distributed solution with consensus algorithm and distributed ledger. To this end, we propose a novel system in this paper, which employs Blockchain technology to consolidate the traffic information sharing in VANETs and holds profound significance for intelligent applications. Our system focuses on sharing real-time visual traffic information at the frame level via Blockchain in VANETs. Integrity verification of frames based on their sequences and timestamps is imposed prior to the consensus in Blockchain, coupled with digital watermarking to protect the multimedia traffic data. Improved efficiency and reliability of sharing are achieved by the system dynamically adjusting transaction volume in terms of the frame type and number. With the fault tolerance and immutability of Blockchain, our proposal can solidly protect the traffic information sharing against vandalization in VANETs, and confidently escort the traffic with trustworthy safety guidance.
Abstract Even though there is continuous improvement in road and vehicle safety, road traffic incidents have been increasing over last few decades. There is a need to reduce traffic incidents like accidents through predictive analysis and timely warnings while at the same time data related to accidents and traffic violations need to be maintained in a tamper proof storage system that can be retrieved for forensic analysis and law enforcement at a later stage. The Secure Incident and Evidence Management Framework (SIEMF) proposed in this work address these two challenges of predictive modeling for timely warning and secure evidence management for forensics analysis in case of accidents and traffic violations. The system proposes a deep learning based predictive incident modeling with blockchain and CP-ABE based access control for the incident data stored in blockchain.
Nowadays vehicles are increasing on the road. Due to this, it is a challenge for society to manage traffic jams and road accidents all over the world. Artificial Intelligence (AI) such as Machine Learning (ML) algorithms are very helpful to improve the performance of the overall road safety management system. AI is used for many real-world applications to make any system be a smart system. The Smart Road Traffic Management System (SRTMS) easily recognizes the influence occurs for random changes on road safety. The SRTMS detects the unsafe driving patterns as well as convey the information to the respective authorities. The Internet of Things (IoT) is a boon technology to observe human activities in real-time. IoT devices or nodes are composed of sensors that are commonly utilized to identify and reply to electrical and other signals. Currently, Blockchain (BC) is the most trending technology to automate transactions, which means sharing or exchange of information between the IoT devices or nodes. BC technology facilitates for sharing of information on the network is decentralized, secure, persistent, anonymity, suitability and trustworthy manner. With consensus algorithms and smart contracts, Blockchain holds to manage communication among nodes without the involvement of a third-party or intermediary body. Simultaneously, AI has the ability to offer intelligent and decision-making machines similar to human beings' minds. This paper proposes the SRTMS model for solving the road accident, traffic jam and disseminate the information to all stakeholders. This proposed model is a combination of most trending technologies such as AI, BC, and IoT. This paper proposes the SRTMS model for solving the road accident, traffic jam and disseminate the information to all stakeholders. This proposed model is a combination of most trending technologies such as AI, BC, and IoT.
In Internet-of-Vehicles (IoV) ecosystems, intelligent toll gates (ITGs) connect nearby metropolitan cities through smart highways. At ITGs, existing solutions integrate blockchain (BC) and deep-learning schemes to leverage trusted and responsive analytics support for connected smart vehicles (CSVs) at ITGs. BC eliminates third-party intermediaries, and secures payments between vehicle owners (VO) and governing authorities (GA). Deep-Learning, on the other hand, facilitates accurate predictions for diverse and complex urban traffic conditions. However, due to fixed toll pricing schemes based on connected smart vehicles (CSV) type, VOs suffer from variable delays at different lanes due to dynamic congestion scenarios. To address the research gaps of such a fixed pricing schemes, we propose a BC-envisioned scheme DwaRa, that operates in three phases. In the first phase, future traffic is predicted based on Markov queues to balance the congestion at different lanes at ITGs efficiently. Then, we propose a novel spatially induced-long-short term memory (SI-LSTM) model to predict current traffic and weather based on historical repositories. Second, based on inputs by the Markov model, SI-LSTM, lane type, and vehicle type, a dynamic pricing algorithm is presented to improve the quality of experience (QoE) of the VO. Finally, based on dynamic price fixation between the VO and the GA, smart contracts (SCs) are executed and transactional data is secured through BC. The proposed scheme is compared against parameters like average mean-squared error (MSE), predicted traffic, scalability, interplanetary file system (IPFS) storage, computation (CC), and communication cost (CCM). At n = 100 test samples, and arrival rate β = 80, the obtained MSE is 0.0012, with a peak average value of 0.00526. The overall CC is 45.88 milliseconds (ms) and CCM is 53 bytes that indicate the proposed scheme efficacy against conventional approaches.
Santiago Figueroa-Lorenzo, Jon Goya, Javier Añorga, Iñigo Adín · 6 authors
The European Union is moving toward the “smart” era having as one of the key topics the smart mobility. What is more, the European union (EU) is moving toward Mobility as a Service (MaaS). The key concept behind MaaS is the capability to offer both the traveler's mobility and goods' transport solutions based on travel needs. For example, unique payment methods, intermodal tickets, passenger services, freight transport services, etc. The introduction of new services implies the integration of many Internet-of-Things (IoT) sensors. At this point, security gains a key role in the railway sector. Considering an environment where sensor data are monitored from sensor events, and alarms are detected and emitted when events contain an anomaly, this document proposes the development of an alarms collection system, which ensures both traceability and privacy of these alarms. This system is based on Ethereum blockchain events-log, as an efficient storage mechanism, which guarantees that any railway entity can participate in the network, ensuring both entity security and information privacy.
As manufacturing, operations and maintenance become increasingly complex in the aviation sector, a digital transformation is underway toward Blockchain technology, an open source digital architecture for related data and their histories. From maintenance, repair and overhaul to protection against global positioning system spoofing, Blockchain technology is making a major impact in aviation industry. This paper analyzes possible implementation of Blockchain technology within the realm of Aviation Cybersecurity Framework.
The exponential surge in the number of vehicles on the road has aggravated the traffic congestion problem across the globe. Several attempts have been made over the years to predict the traffic scenario accurately and consequently avoiding further congestion. Crowdsourcing has come forward as one of the most adopted methods for predicting traffic intensity using live data. However, the privacy concerns and the lack of motivation for the live users to help in the traffic prediction process have rendered existing crowdsourcing models inefficient. Towards this end, we present an advanced blockchain-based secure crowdsourcing model. Not only does our model ensure privacy preservation of the users, but by incorporating a revenue model, it also provides them with an incentive to participate in the traffic prediction process willingly. For accurate and efficient traffic jam probability estimation, our work proposes a neural network-based smart contract to be deployed onto the blockchain network. The results reveal that the proposed model is highly efficient in terms of attaining high participation and consequently obtaining highly accurate predictions.
Anandkumar Balasubramaniam, Malik Junaid Jami Gul, Varun G. Menon, Anand Paul
Intelligent Transportation System (ITS) is gaining attention but at the same time, road accidents, congestion, delays, etc. have also increased. Relative information about such events is vital. Such information can be presented in legal processes as digital proof. Availability of the information is not a problem as multidimensional data have been recorded all the time by ITS. Recording all the information in ITS arises the problem of fetching relevant information and removing other facts and figure that are not required to describe certain situations such as an accident. To address this issue, we analyze road accident data and reduce various dimensions with Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Non-negative Matrix Factorization (NMF). We conduct comparative analysis with three datasets where error rate for PCA is 32% with Dataset1. Likewise, error rate for LDA and NMF are 36% and 35%, receptively. While keeping in mind that such reduced data is helpful in many legal processes, we introduce Blockchain in the framework. Blockchain can make data immutable thus can be considered as digital proof. Blockchain also requires a smart contract in this situation between insurance companies to collect data in case of any uncertain situation. Such analysis can offer a different point of views and trends in data. Information can be more explainable to define the situation and helps to develop a friendly environment for day-to-day customers. The proposed framework provides dimensionality reduction of data that eventually reduce the data dimension to store in Blockchain.
European buildings are producing a massive amount of data from a wide spectrum of energy-related sources, such as smart meters’ data, sensors and other Internet of things devices, creating new research challenges. In this context, the aim of this paper is to present a high-level data-driven architecture for buildings data exchange, management and real-time processing. This multi-disciplinary big data environment enables the integration of cross-domain data, combined with emerging artificial intelligence algorithms and distributed ledgers technology. Semantically enhanced, interlinked and multilingual repositories of heterogeneous types of data are coupled with a set of visualization, querying and exploration tools, suitable application programming interfaces (APIs) for data exchange, as well as a suite of configurable and ready-to-use analytical components that implement a series of advanced machine learning and deep learning algorithms. The results from the pilot application of the proposed framework are presented and discussed. The data-driven architecture enables reliable and effective policymaking, as well as supports the creation and exploitation of innovative energy efficiency services through the utilization of a wide variety of data, for the effective operation of buildings.
Railway traffic conflicts are common in the day‐to‐day operation of trains due to the limited track capacity, the varying priority of trains, localised weather conditions, maintenance operations etc. The conventional conflict resolution strategy focuses on delaying the trains by considering the braking distance of a preceding train, cancellation or intermediate stopping of the trains etc. This strategy can solve the problem of railway operators than the passenger's problem of missed connecting trains, missed business opportunities or personal appointments etc. To ensure both operator and passenger satisfaction, this paper proposes a novel blockchain‐enabled virtual coupling of automatic train operation fitted mainline trains for railway traffic conflicts. The immutable blockchain databases of the trains and track infrastructures help to forecast the traffic conflicts in real time. Seven variants of virtual coupling strategies are described in this study. Based on the chosen strategy, the reference model of the automatic train operation of mainline trains is virtually coupled or synchronised. Finally, the simulation results and theoretical analyses using several case studies are carried out to confirm the sufficiency of the proposed system and method. The major advantage of the proposed study is that it can be an overlay to the existing European Railway Traffic Management System Level‐2.
Shirshak Raja Maskey, Shahriar Badsha, Shamik Sengupta, Ibrahim Khalil
With the rise of smart cities, transportation systems are getting smarter every day. An Intelligent Transportation System (ITS) should be secure, autonomous, capable of discerning safeness levels at the roads, and provide services to improve human experience. To reach the gold standard, the ITS faces several issues such as centralization, trust, and data integrity. The Transportation System and the data generated from the vehicles can be intercepted, manipulated and corrupted with coordinated attacks. Moreover, every system might have bad actors who want to manipulate the system or data to his or her favor by exploiting the system. In order to guarantee data integrity, immutability, and availability for the ITS, we propose Blockchain based architecture with outlier detection to prevent malicious activity by the vehicles while preserving integrity in sharing information. The Outlier Detection is designed to reside before the consensus process, to identify and prevent participation of malicious vehicles in consensus process or block mining. In our proposed Blockchain based Intelligent Transportation system with Outlier Detection for Smart City (BITS), we used machine learning to detect the anomaly in the data. The proposed model can be used in various applications of ITS such as traffic monitoring, criminal activity profiling, accident detection and reporting, etc.
The paper presents the results of comparative studies of the transport management application blockchain technology. The accuracy of the use Quick Road System (QRS) in intelligent transport systems (ITS) may be the service of getting free passage is shown. This service is aimed at creation of decentralized network of road lane sharing in real time. Based on model studies it was found that, depending If a driver is in a hurry or wants to get priority in using the speed lane, then, having established a special status, he shares his place in the lane with other vehicles moving along the same route by exchanging incentives through the blockchain with other private car owners. The paper estimates the probability of with the development of Internet of Things (IoT) technology, the number of connected devices in ITS is growing extremely fast. Therefore, the optimal use of large arrays of collected data is the main focus of research and the Internet of Vehicles (IoV) is one of the most targeted branches of integration of the existing IoT technologies with the growing transport needs in order to solve the problem of intellectual traffic.
Nowadays, commuting by personal vehicles and public road transport is widely common and mostly cost-effective. In this regard, globally there is traffic congestion in megacities and inevitably road collisions take place, which leads to people's injuries and a rise in traffic jams. Many governments are scrambling to decrease the number of accidents and are trying to introduce the latest technologies in the road infrastructure. It might be possible if these technologies are used correctly and reasonably. This paper proposes two blockchain-based accident detection models aiming at improving the ease of law violation detection and related measures. In particular, authors introduce a new technology, called offline-detection, relating to the detection of accidents in the absence of communication and Internet access. Blockchain technology itself may become a solution to improve honesty, openness, and truthfulness in cases of road-related issues. It allows restoring the road situation in details including location, vehicles, and surrounding infrastructure involvement due to blockchain property of immutability.
In view of the security risks and centralized structure of traditional intelligent transportation system, we propose a novel scheme of secure data sharing and customized services based on the consortium blockchain (DSCSCB). The ciphertext-policy attribute-based proxy re-encryption algorithm has the function of keyword searching by dividing the key into an attribute key and a search key, which not only solves the problem that proxy re-encryption algorithm cannot retrieve data, but also realizes data sharing and data forwarding. Moreover, the algorithm effectively controls the access permission of data, and provides a secure communication environment for the vehicular ad-hoc network (VANET). Service sectors, such as insurance companies, the traffic police and maintenance suppliers, obtain the corresponding ciphertext and then apply the smart contract to provide customized services for the onboard unit after decryption. Security analysis and performance evaluation demonstrate that our scheme not only meets the requirements of data sharing in the security and confidentiality, but also has obvious advantages in the overhead of computing and communication.
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.
Due to the long train marshaling and complex line conditions, the operating modes in heavy haul rail systems frequently change when trains travel. Improper traction or braking operation made by drivers will increase the longitudinal impact force to trains and causes the train decoupling, severely affecting the safe operations of trains. It is quite desirable to replace the manual control with intelligent control in heavy haul rail systems. Traditional machine learning-based intelligent control methods suffer from insufficient data. Due to lacking effective incentives and trust, data from different rail lines or operators cannot be shared directly. In this paper, we propose an approach on blockchain-based federated learning to implement asynchronous collaborative machine learning between distributed agents that own data. This method performs distributed machine learning without a trusted central server. The blockchain smart contract is used to realize the management of the entire federated learning. Using the historical driving data collected from real heavy haul rail systems, the learning agent in the federated learning method adopts a support vector machine (SVM) based intelligent control model. To deal with the imbalanced traction and braking data, we optimize the classic SVM model via assigning different penalty factors to the majority and minority classes. The data set are mapped to a high dimension using kernel functions to make it linearly separable. We construct a mixing kernel function composed of polynomial and radial basis function (RBF) kernel functions, which uses a dynamic weight factor changing with train speeds to improve the model accuracy. The simulation results demonstrate the efficiency and accuracy of our proposed intelligent control method.
In recent years, under the background that the rapid development of traffic volume makes the current traffic lights far from meeting the urban traffic demand, intelligent traffic lights based on the centralized architecture began to appear. However, in the traffic network with complex structure and private data flow, there are many malicious attacks against the centralized architecture, such as Sybil and ghost car attacks, which undoubtedly brings great security risks to the traditional intelligent traffic lights. Blockchain technology is a popular security framework nowadays. Based on its outstanding characteristics in the distributed architecture and the development of Edge Intelligence (EI) technology, this paper proposes a distributed security architecture scheme based on blockchain technology for the existing intelligent traffic light system. At the same time, based on the model cutting technology proposed by EI, the smart contract is improved to achieve redundant cutting of ledger data in the process of block consensus, which greatly reduces the pressure of blockchain ledger data transmission. In the end of this paper, the superiority of this scheme compared with the traditional intelligent traffic light scheme in communication cost and time cost is demonstrated by simulation experiment.
Yuze Li, Shangrong Jiang, Xuerong Li, Shouyang Wang
Abstract In recent years, Bitcoin has received substantial attention as potentially high-earning investment. However, its volatile price movement exhibits great financial risks. Therefore, how to accurately predict and capture changing trends in the Bitcoin market is of substantial importance to investors and policy makers. However, empirical works in the Bitcoin forecasting and trading support systems are at an early stage. To fill this void, this study proposes a novel data decomposition-based hybrid bidirectional deep-learning model in forecasting the daily price change in the Bitcoin market and conducting algorithmic trading on the market. Two primary steps are involved in our methodology framework, namely, data decomposition for inner factors extraction and bidirectional deep learning for forecasting the Bitcoin price. Results demonstrate that the proposed model outperforms other benchmark models, including econometric models, machine-learning models, and deep-learning models. Furthermore, the proposed model achieved higher investment returns than all benchmark models and the buy-and-hold strategy in a trading simulation. The robustness of the model is verified through multiple forecasting periods and testing intervals.
Hye-Yeong Shin, Daeyong Kim, Soohoon Maeng, Kiyoung Lee · 5 authors
Most of the existing platform for Bitcoin data analysis or visualization, they perform data collection from one node in the main-net. Thus we can notice some differences in their provided data. In this research, and in order to provide global data visualization, we collect both the historical and realtime Bitcoin data. Our monitoring system is comprised of three main components; multiple full Bitcoin nodes were used to collect data, the analysis of data was done by the Analytic Engine, while the webserver was used to visualize both row-data and analyzed data.
Qilei Ren, Ka Lok Man, Muqing Li, Bingjie Gao · 5 authors
With the continuous development of Internet of things, all kinds of smart systems are quickly evolving to make our day-to-day life smoother and safer. Like many other sectors, transportation has entered a period of rapid change. Intelligent Traffic System is one of the fastest-growing fields within the smart systems, which is expected to increase road safety, mitigate traffic congestion, and enable fuel efficiency. The main functionalities of Intelligent Traffic System are as follows: (1) monitoring real-time traffic conditions in specific areas, (2) locating traffic emergencies (i.e. traffic accidents) in specific areas, and (3) dynamic monitoring and managing the continuous use in public transit services (i.e. change in car lanes) that may lead to changes in macro traffic conditions. This article will use the above-mentioned functionalities of the Intelligent Traffic System as underlying simulative scenarios, to design and to implement a smart transportation system based on Internet of things and blockchain—both share inherent distributed technology characteristics—combining both Internet of things sensor nodes and distributed ledger technology, to (1) record the changes in intelligent transportation systems and (2) set up a credit-token mechanism for paying the use and misuses in public transit services accordingly. The Intelligent Traffic System described in this article is intended to be used as experimental project only, given the terms and conditions as depicted in the simulated scenario. In real-life traffic scenarios, it may generate more complex system and data security issues, which will be elaborated and analyzed at the end of this article. Intelligent Traffic System is a comprehensive smart system; it can significantly change and reinvent the wheel for traffic conditions. Based on the system development as discussed in this article, there are still a lot of demands and challenges that need to be addressed in the future. Such topic scope will be explored in depth in our subsequent research.