Search

Industrial applications generate big data with redundant information that is transmitted over heterogeneous networks. The transmission of big data with redundant information not only increases the overall end-to-end delay but also increases the computational load on servers which affects the performance of industrial applications. To address these challenges, we propose an intelligent framework named Reliable and Secure multi-level Edge Computing (RaSEC), which operates in three phases. In the first phase, level-one edge devices apply a lightweight aggregation technique on the generated data. This technique not only reduces the size of the generated data but also helps in preserving the privacy of data sources. In the second phase, a multistep process is used to register level-two edge devices (LTEDs) with high-level edge devices (HLEDs). Due to the registration process, only legitimate LTEDs can forward data to the HLEDs, and as a result, the computational load on HLEDs decreases. In the third phase, the HLEDs use a convolutional neural network to detect the presence of moving objects in the data forwarded by LTEDs. If a movement is detected, the data is uploaded to the cloud servers for further analysis; otherwise, the data is discarded to minimize the use of computational resources on cloud computing platforms. The proposed framework reduces the response time by forwarding useful information to the cloud servers and can be utilized by various industrial applications. Our theoretical and experimental results confirm the resiliency of our framework with respect to security and privacy threats. [ABSTRACT FROM AUTHOR]

In this article, we address the problem of integrity of the state estimation in presence of a novel bad data injection threat. We consider persistent adversaries who inject attack vectors “silently,” i.e., they drift the results of the state estimation gradually in multiple steps, with each step bypassing the bad data detection step of state estimation. Prior works on the topic have shown how an adversary can bypass the bad data detection by constructing attack vectors as linear combinations of the column vectors of the measurement Jacobian matrix. We show here that the attack surface is much broader than implied by this assumption. We demonstrate our attack strategy using realistic load patterns from NYISO in the IEEE 14-bus system. We also propose a detection method that uses the expected energy of normalized residues and a paired t-test, and we show its effectiveness. The generality of the proposed attack and detection strategy implies that it can be used in other cyber-physical systems involving state estimation based on linearized state perturbation. [ABSTRACT FROM AUTHOR]

An introduction to the journal is presented that focuses on reference for solutions that leverage techniques and insights from the domains of artificial intelligence, internet of things, edge computing, and big data to address security, reliability, privacy, and quality challenges in industrial applications.

In today's technology, a sheer number of Internet of Things applications use hardware security modules for secure communications. The widely used algorithms in security modules, for example, digital signatures and key agreement, are based upon elliptic curve cryptography (ECC). A core operation used in ECC is the point multiplication, which is computationally expensive for many Internet of things applications. In many IoT applications, such as intelligent transportation systems and distributed control systems, thousands of safety messages need to be signed and verified within a very short time-frame. Considerable research has been conducted in the design of a fast elliptic curve arithmetic on finite fields using residue number systems (RNS). In this article, we propose an RNS-based ECC core hardware for the two families of elliptic curves that are short Weierstraß and twisted Edwards curves. Specifically, we present RNS implementations for SECP256K1 and ED25519 standard curves. We propose an RNS hardware architecture supporting fast elliptic curve point-addition (ECPA), point-doubling (ECPD), and point-tripling (ECPT). We implemented different ECC point multiplication algorithms on the Xilinx FPGA platform. The test results confirm that the performance of our fully RNS ECC point multiplication is better than the fastest ECC point multiplication cores in the literature. [ABSTRACT FROM AUTHOR]

In this article, a new structure for dual-input single-output three-phase inverters with a high voltage gain is presented. The proposed structure is based on the impedance source inverters, in which two independent input sources can share their power to supply a common load by replacing the high-frequency transformers with some inductors. The proposed structure is also a voltage booster and is suitable for applications such as connecting to hybrid renewable energy systems. In the proposed structure, to improve the efficiency and to reduce the cost and structure weight, only one power conversion stage is used. In addition, the number of used semiconductors is lower than previous structures in the literature. As renewable energy sources such as wind and solar have the nature of intermittency, the supply of load in the systems which use them as inputs may be marred by some reliability problems. To this end, supplementary sources and also a fast control algorithm could be used to overcome the reliability problem. The proposed switching method controls the ratio of the power absorbed from the input sources and the dc-link voltage through the control of two independent variables. The reliability of the load supply is improved since the controller computes the parameters very fast. The experimental results on a 310-W prototype confirm the theoretical analysis and the performance of the proposed inverter. [ABSTRACT FROM AUTHOR]

This paper presents an approach for tolerant control and compensation of cyber attacks on the inputs and outputs of a cyber-physical system of rotary gantry type. The proposed control schemes are designed based on classic–intelligent control strategies for trajectory tracking and vibration control of a networked control system, which are developed for tip angular position control, while the system is prone to cyber attacks. The malicious attacks are assumed to be of denial of service (DoS) kind and cause packet loss with high probability in the two signals; control input and sensor output. In this paper, several classic and intelligent control strategies are studied in terms of robustness and effectiveness to attacks. Based on the results, a new hybrid control scheme is designed using linear quadratic regulation, sliding mode control, and artificial radial basis function neural network to alleviate the effect of DoS attacks and maintain the performance of the cyber-rotary gantry system in tracking applications. The neural network controller is trained during the control process. Its learning algorithm is based on the minimization of a cost function which contains the sliding surface. The hybrid control system is analyzed from the stability perspective. Moreover, the efficiency of the proposed scheme is validated by simulation on MATLAB Simulink platform. [ABSTRACT FROM AUTHOR]

DFT adjusts data pre-processing and training process, optimizes the constructing a disagreement encoding network, and expands on the recognition disagreement of pseudo-labelled samples-based training sets. Internet of things (IoT) and big data (BD) also play a critical role in the smart city infrastructures, changing the way we analyse patterns and trends in human behaviour. A smart city implies the realization of sustainable city growth enabled by technology-based intelligent solutions to give a good quality of life to its citizens. [Extracted from the article]

The energy Internet (EI) equipment may face threats that attackers poison federated learning (FL) models to disturb electricity load forecasting. To mitigate this vulnerability, it is important to study load forecasting disturbance approaches. This article proposes a side-channel analysis (SCA)-based disturbance approach. First, we design an FL SCA scheme to extract power information from the FL chip running forecasting model. Second, we propose an FL data speculation method using an optimized convolutional neural network trained with SCA information. Third, we design a label-flipping-based poisoning scheme with speculated data characteristics for load forecasting disturbance. Experimental results show attackers can successfully poison and disturb FL-based load forecasting. The average accuracy of EI load data speculation is 99.8%. This work is the first to study EI load forecasting disturbance from an SCA perspective. [ABSTRACT FROM AUTHOR]

The integration of the Internet of Things (IoT) with traditional healthcare systems has improved quality of healthcare services. However, the wearable devices and sensors used in Healthcare System (HS) continuously monitor and transmit data to the nearby devices or servers using an unsecured open channel. This connectivity between IoT devices and servers improves operational efficiency, but it also gives a lot of room for attackers to launch various cyber-attacks that can put patients under critical surveillance in jeopardy. In this article, a Blockchain-orchestrated Deep learning approach for Secure Data Transmission in IoT-enabled healthcare system hereafter referred to as "BDSDT" is designed. Specifically, first a novel scalable blockchain architecture is proposed to ensure data integrity and secure data transmission by leveraging Zero Knowledge Proof (ZKP) mechanism. Then, BDSDT integrates with the off-chain storage InterPlanetary File System (IPFS) to address difficulties with data storage costs and with an Ethereum smart contract to address data security issues. The authenticated data is further used to design a deep learning architecture to detect intrusion in HS network. The latter combines Deep Sparse AutoEncoder (DSAE) with Bidirectional Long Short-Term Memory (BiLSTM) to design an effective intrusion detection system. Experiments on two public data sources (CICIDS-2017 and ToN-IoT) reveal that the proposed BDSDT outperformed state-of-the-arts in both non-blockchain and blockchain settings and have obtained accuracy close to 99% using both datasets. [ABSTRACT FROM AUTHOR]

In Wireless Body Area Networks (BAN), energy consumption, energy harvesting, and data communication are the three most important issues. In this paper, we develop an optimal allocation algorithm (OAA) for sensor devices, which are carried by or implanted in human body, harvest energy from their surroundings, and are powered by batteries. Based on the optimal allocation algorithm that uses a two-timescale Lyapunov optimization approach, we design a framework for joint optimization of network service cost and network utility to study energy, communication, and allocation management at the network edge. Then, we formulate the utility maximization problem of network service cost management based on the framework. Specifically, we use OAA, which does not require prior knowledge of energy harvesting to decompose the problem into three subproblems: battery management, data collection amount control and transmission energy consumption control. We solve these through OAA to achieve three main goals: (1) balancing the cost of energy consumption and the cost of data transmission on the premise of minimizing the service cost of the devices; (2) keeping the balance of energy consumption and energy collection under the condition of stable queue; and (3) maximizing network utility of the device. The simulation results show that the proposed algorithm can actually optimize the network performance. [ABSTRACT FROM AUTHOR]

Demographic factors, statistical information, and technological innovation are prominent factors shaping energy transitions in the residential sector. Explaining these energy transitions requires combining insights from the disciplines investigating these factors. The existing literature is not consistent in identifying these factors, nor in proposing how they can be combined. In this paper, three contributions are made by combining the key demographic factors of households to estimate household energy consumption. Firstly, a mathematical formula is developed by considering the demographic determinants that influence energy consumption, such as the number of persons per household, median age, occupancy rate, households with children, and number of bedrooms per household. Secondly, a geographical position algorithm is proposed to identify the geographical locations of households. Thirdly, the derived formula is validated by collecting demographic factors of five statistical regions from local government databases, and then compared with the electricity consumption benchmarks provided by the energy regulators. The practical feasibility of the method is demonstrated by comparing the estimated energy consumption values with the electricity consumption benchmarks provided by energy regulators. The comparison results indicate that the error between the benchmark and estimated values for the five different regions is less than 8% (7.37%), proving the efficacy of this method in energy consumption estimation processes. [ABSTRACT FROM AUTHOR]

Fuzzy systems can aid in diminishing uncertainty and noise from biometric security applications by providing an intelligent layer to the existing physical systems to make them reliable. In the absence of such fuzzy systems, a little random perturbation in captured human biometrics could disrupt the whole security system, which may even decline the authentication requests of legitimate entities during the protocol execution. In the literature, few fuzzy logic-based biometric authentication schemes have been presented; however, they lack significant security features including perfect forward secrecy (PFS), untraceability, and resistance to known attacks. This article, therefore, proposes a novel two-factor biometric authentication protocol enabling efficient and secure combination of physically unclonable functions, a physical object analogous to human fingerprint, with user biometrics by employing fuzzy extractor-based procedures in the loop. This combination enables the participants in the protocol to achieve PFS. The security of the proposed scheme is tested using the well-known real-or-random model. The performance analysis signifies the fact that the proposed scheme not only offers PFS, untraceability, and anonymity to the participants, but is also resilient to known attacks using light-weight symmetric operations, which makes it an imperative advancement in the category of intelligent and reliable security solutions. [ABSTRACT FROM AUTHOR]

In this paper, a new distributed multi-agent framework based on the three layers' fog computing architecture is developed for real-time microgrid economic dispatch and monitoring. To this end, the changes of load at any time will be tracked by the proposed technique, considering unit sudden exits and entries. Moreover, to make the system more realistic, different renewable energies, including photovoltaics (PVs), wind turbines (WTs), fuel cells (FCs), and microturbines (MT) are considered in the proposed technique. To overcome the complexity of the problem, by using advantages of fog computing, a new fast consensus-based optimization algorithm is used, which is modified based on the fuzzy adaptive leader technique. Finally, the proposed technique is simulated and tested on microgrids with 6 and 14 buses, respectively. Simulation results demonstrate and validate the effectiveness of the proposed technique, as well as the capability to track the changes of load with the interactions in real-time and the fast convergence rate. • We developed a three-layer framework based on fog computing for MG. • We developed a modified distributed consensus-based technique to achieve the optimal dispatch solutions. • We simulated and analyzed the proposed model on two IEEE standard test system with two different scenarios. [ABSTRACT FROM AUTHOR]

Our paper aims at learning from imbalance data based on ensemble learning. At the stage, the main solution is to combine under-sampling, oversampling or cost sensitivity learning with ensemble learning. However, these feature space-based methods fail to reflect the transformation of distribution and are usually accompanied with high computational complexity and risk of overfitting. In this paper, we propose a dynamic cluster algorithm based on coefficient of variation (or entropy), which learns the local spatial distribution of data and hierarchically clusters the majority. This algorithm has low complexity and can dynamically adjust the cluster according to the iteration of AdaBoost, adaptively synchronized with changes caused by sample weight changes. Then, we design an index to measure the importance of each cluster. Based on this index, a dynamic sampling algorithm based on maximum weight is proposed. The effectiveness of the sampling algorithm is proved by visual experiments. Finally, we propose a cost-sensitive algorithm based on Bagging, and combine it with the dynamic sampling algorithm to propose a multi-fusion imbalanced ensemble learning algorithm. In experimental research, our algorithms have been validated on three artificial datasets, 22 KEEL datasets and two gene expression cancer datasets, and have shown ideal or better performance than SOTA in terms of AUC, indicating that our algorithms are not only effective imbalance algorithms, but also provide potential for building a reliable biological cyber-physical system. [ABSTRACT FROM AUTHOR]

Due to the rapid developments in intelligent transportation systems, modern vehicles have turned into intelligent transportation means which are able to exchange data through various communication protocols. Today's vehicles portray best example of a cyber-physical system because of their integration of computational components and physical systems. As the IoT and data remain intrinsically linked together, the evolving nature of the transportation network comes with a risk of virtual vehicle hijacking. In this paper, we propose a combination of machine learning techniques to mitigate the relay attacks on Passive Keyless Entry and Start (PKES) systems. The proposed algorithm uses a set of key fob features that accurately profiles the PKES system and a set of driving features to identify the driver. First relay attack detection is performed, and if a relay attack is not detected, the vehicle is unlocked and algorithm proceeds to gain the driving features and use neural networks to identify whether the current driver is whom he/she claims to be. To assess the machine learning model, we compared the decision tree, SVM, and KNN method using a three-month log of a PKES system. Our test results confirm the effectiveness of the proposed method in recognizing relayed messages. The proposed methods achieve 99.8% accuracy rate. We used a Long Short-Term Memory recurrent neural network for driver identification based on the real-world driving data, which are collected from a driver who drives the vehicles on several routes in real-world traffic conditions. [ABSTRACT FROM AUTHOR]

Human activity recognition has been a topic of attraction among researchers and developers because of its enormous usage in widespread region of human life. The varied human activities and the way they are executed at individual level are the main challenges to be recognized in human behavior modeling. This paper proposes a novel methodology that recognizes human activities from the behavior of individuals in a smart home environment. The dataset considered in this work is captured using Bluetooth low energy, a popular technology for indoor localization. The proposed framework is a binary cuckoo search-based stacking model that collectively exploits multiple base learners for human activities recognition from the gathered accelerometer sensors data mounted on wearable and mobile devices. The work is tested on the newly developed SPHERE dataset to recognize user activities in smart home environment. The experimental results confirm the effectiveness of the proposed approach, which outperforms MLP, DT, KNN, SGD, NB, RF, LR and SVM classifiers on the dataset and gives a high predictive accuracy value of 93.77% via a tenfold cross-validation. The proposed approach gives a better performance at the expense of more computation time, that is, due to the integration of cuckoo search metaheuristic algorithm. [ABSTRACT FROM AUTHOR]