Search

Railway passenger comfort has been considered a growingly important field to attract more passengers from other public transports such as air flights. To allow passengers and train companies to estimate the onboard passenger comfort level, we propose a phone-based hybrid machine learning (ML) model combining pre-train convolutional neural network as a feature extractor and support vector regressor as a predictor. To better demonstrate the capacity of the proposed model, two sub-models of the hybrid model and the same hybrid model but with non-pre-train feature extractor are adopted to be benchmarks. The raw field data is acquired from a corridor between the University of Birmingham station and Birmingham International station using phones, subsequently calculated to corresponding comfort level according to UIC 513. The four models are trained by the dataset in two domains – time domain and frequency domain, then optimized by random search and validated by 10-fold cross-validation. The proposed method yields the best performance with an $R^{2}$ of 0.988 ± 0.004, a root-mean-square error (RMSE) of 0.028 ± 0.015, and a mean-absolute-error (MAE) of 0.02 ± 0.005. The results of this study underpin the possibility that the railway passenger has the access to quantify the level of comfort and the real-time assistance for the train driver to calibrate the driving style from the proposed system.

Phishing attackers spread phishing links through e-mail, text messages, and social media platforms. They use social engineering skills to trick users into visiting phishing websites and entering crucial personal information. In the end, the stolen personal information is used to defraud the trust of regular websites or financial institutions to obtain illegal benefits. With the development and applications of machine learning technology, many machine learning-based solutions for detecting phishing have been proposed. Some solutions are based on the features extracted by rules, and some of the features need to rely on third-party services, which will cause instability and time-consuming issues in the prediction service. In this paper, we propose a deep learning-based framework for detecting phishing websites. We have implemented the framework as a browser plug-in capable of determining whether there is a phishing risk in real-time when the user visits a web page and gives a warning message. The real-time prediction service combines multiple strategies to improve accuracy, reduce false alarm rates, and reduce calculation time, including whitelist filtering, blacklist interception, and machine learning (ML) prediction. In the ML prediction module, we compared multiple machine learning models using several datasets. From the experimental results, the RNN-GRU model obtained the highest accuracy of 99.18%, demonstrating the feasibility of the proposed solution.

More than half of all commercial aircraft operation accidents could have been prevented by executing a go-around. Making timely decision to execute a go-around manoeuvre can potentially reduce overall aviation industry accident rate. In this paper, we describe a cockpit-deployable machine learning system to support flight crew go-around decision-making based on the prediction of a hard landing event. This work presents a hybrid approach for hard landing prediction that uses features modelling temporal dependencies of aircraft variables as inputs to a neural network. Based on a large dataset of 58177 commercial flights, the results show that our approach has 85% of average sensitivity with 74% of average specificity at the go-around point. It follows that our approach is a cockpit-deployable recommendation system that outperforms existing approaches.

Our devices can use a wide range of communication technologies such as multiple cellular technologies (4G/5G), WiFi, and also Ethernet. At the same time, applications have a choice of a wide range of transport protocols such as QUIC and TCP that can be fine-tuned and optimized according to their needs. However, in spite of these advances, offering seamless multiconnectivity to applications continues to be a hard problem. The key factors that continue to be a roadblock towards achieving seamless multiconnectivity include a) applications cannot specify the communication technologies to be used by their flows, and b) the traditional definition of a connection endpoint was not designed to support mobile nodes. In this paper we discuss the key challenges that make this problem hard. We also present MULTI, a session layer approach that can be leveraged to address some of the key sub-problems of this problem. For instance, we observe that MULTI incurred a small overhead (less than 5% decrease in throughput) when using TCP compared to the native asyncio python library.

The noise performance of three types of n+/p-well single-photon avalanche diodes (SPADs) fabricated in a standard 180 nm CMOS technology is studied. The SPADs had different poly gate configurations: no poly gate (SPAD_NG), a dummy floating poly gate (SPAD_DG), and a field poly gate connected to the n+ cathode (SPAD_FG). The measurement results of dark count rate and afterpulsing showed that the SPAD_DG had better noise performance compared to the SPAD_NG. This is because the dummy poly gate pushed the shallow trench isolation away from the active region of the SPAD, thus reducing the dark noise generated from the Si-SiO2 interface. The measurement results also revealed that the noise performance can be further improved by connecting the poly gate to the n+ cathode. The voltage on the poly gate in SPAD_FG reduced the electric field in the n-well guard ring (GR) region, thus reducing the carriers from the GR region that can enter the active region of SPADs and initiate dark counts.

Missing data are unavoidable in the real-world application of unsupervised machine learning, and their nonoptimal processing may decrease the quality of data-driven models. Imputation is a common remedy for missing values, but directly estimating expected distances have also emerged. Because treatment of missing values is rarely considered in clustering related tasks and distance metrics have a central role both in clustering and cluster validation, we developed a new toolbox that provides a wide range of algorithms for data preprocessing, distance estimation, clustering, and cluster validation in the presence of missing values. All these are core elements in any comprehensive cluster analysis methodology. We describe the methodological background of the implemented algorithms and present multiple illustrations of their use. The experiments include validating distance estimation methods against selected reference methods and demonstrating the performance of internal cluster validation indices. The experimental results demonstrate the general usability of the toolbox for the straightforward realization of alternate data processing pipelines. Source code, data sets, results, and example macros are available on GitHub. https://github.com/markoniem/nanclustering_toolbox peerReviewed

Metamodels are simpler computer models that are designed to mimic the input-output behavior of discrete-event or other complex simulation models. They are models of models, thus the name (provided by Jack P. C. Kleijnen). This introductory tutorial will highlight uses of metamodels, commonly used metamodel types, the linkage between metamodel type and the set of simulation model runs used to fit the metamodel, and basic issues in building and validating metamodels. The tutorial ends with a brief summary of recent research in metamodel types and use, and the implications for future metamodeling applications.

For certain sensing matrices, the Approximate Message Passing (AMP) algorithm efficiently reconstructs undersampled signals. However, in Magnetic Resonance Imaging (MRI), where Fourier coefficients of a natural image are sampled with variable density, AMP encounters convergence problems. In response we present an algorithm based on Orthogonal AMP constructed specifically for variable density partial Fourier sensing matrices. For the first time in this setting a state evolution has been observed. A practical advantage of state evolution is that Stein's Unbiased Risk Estimate (SURE) can be effectively implemented, yielding an algorithm with no free parameters. We empirically evaluate the effectiveness of the parameter-free algorithm on simulated data and find that it converges over 5x faster and to a lower mean-squared error solution than Fast Iterative Shrinkage-Thresholding (FISTA)., Comment: 5 pages, 5 figures, IEEE International Conference on Image Processing (ICIP) 2020

This article clarifies a required energy storage in a neutral-point-clamped modular multilevel converter (NPC-MMC) based on a theoretical analysis and an experimental verification to enable quantitative comparison of the size of the capacitors. The NPC-MMC consists of both a three-level structure with common dc capacitors and chopper cells. It can reduce the number of the chopper cells by half comparing to the conventional MMC. The theoretical analysis reveals that the NPC-MMC directly transfers a part of its power from the dc capacitors to the ac grid, whereas the conventional MMC transfers all of its power by way of the cells. Therefore, the NPC-MMC can reduce its required energy storage by almost half comparing to the MMC. Moreover, the NPC-MMC can further reduce its energy storage by injecting harmonic currents to its circulating current despite still smaller arm currents than the MMC. A 200-V 10-kVA experimental circuit using low-voltage MOSFET s validates the analysis and demonstrates that the NPC-MMC can achieve both downsizing and high efficiency .

Mobile crowdsourcing (MCS) has become an effective data collection method due to its mobility, low cost, and flexibility. However, since centralized MCS confronts severe security and privacy risks in reality, many researchers are devoted to building a decentralized MCS system based on blockchain. Despite the effectiveness of these schemes, they fail to offer anonymous authentication on the trust of MCS nodes, although privacy is a main concern in MCS and trust plays an important role in a series of MCS activities such as worker selection and truth discovery. Nevertheless, anonymous authentication on trust is not a trivial issue since trust evaluation usually conflicts with anonymity, which is a necessary privacy requirement in an open MCS environment. To tackle this problem, we leverage Intel Software Guard Extension (SGX) and propose a scheme to anonymously authenticate trust with trustworthy trust evaluation in a blockchain-based MCS system. The scheme employs an SGX-enabled cloud server to periodically alter user public/private key pairs and mix newly altered keys among a number of faked keys in order to ensure unlinkability. Besides, we consider the unique features of MCS and work out a novel trust evaluation method by aggregating both subjective feedback and objective behaviors. Finally, we conduct several analyses and experiments to illustrate its security and efficiency.

As AI technology advances and its use increases, efforts to incorporate machine learning for malware detection are increasing. However, for malware learning, a standardized data set is required. Because malware is unstructured data, it cannot be directly learned. In order to solve this problem, many studies have attempted to convert unstructured data into structured data. In this study, the features and limitations of each were analyzed by investigating and analyzing the method of converting unstructured data proposed in each study into structured data. As a result, most of the data conversion techniques suggest conversion mechanisms, but the scope of each technique has not been determined. The resulting data set is not suitable for use as training data because it has infinite properties.

openaire: EC/H2020/825496/EU//5G-MOBIX | openaire: EC/H2020/815191/EU//PriMO-5G The strict latency constraints of emerging vehicular applications make it unfeasible to forward sensing data from vehicles to the cloud for processing. To shorten network latency, vehicular fog computing (VFC) moves computation to the edge of the Internet, with the extension to support the mobility of distributed computing entities (a.k.a fog nodes). In other words, VFC proposes to complement stationary fog nodes co-located with cellular base stations with mobile ones carried by moving vehicles (e.g., buses). Previous works on VFC mainly focus on optimizing the assignments of computing tasks among available fog nodes. However, capacity planning, which decides where and how much computing resources to deploy, remains an open and challenging issue. The complexity of this problem results from the spatio-temporal dynamics of vehicular traffic, varying computing resource demand generated by vehicular applications, and the mobility of fog nodes. To solve the above challenges, we propose a data-driven capacity planning framework that optimizes the deployment of stationary and mobile fog nodes to minimize the installation and operational costs under the quality-of-service constraints, taking into account the spatio-temporal variation in both demand and supply. Using real-world traffic data and application profiles, we analyze the cost efficiency potential of VFC in the long term. We also evaluate the impacts of traffic patterns on the capacity plans and the potential cost savings. We find that high traffic density and significant hourly variation would lead to dense deployment of mobile fog nodes and create more savings in operational costs in the long term.

Is critical input information encoded in specific sparse pathways within the neural network? In this work, we discuss the problem of identifying these critical pathways and subsequently leverage them for interpreting the network's response to an input. The pruning objective -- selecting the smallest group of neurons for which the response remains equivalent to the original network -- has been previously proposed for identifying critical pathways. We demonstrate that sparse pathways derived from pruning do not necessarily encode critical input information. To ensure sparse pathways include critical fragments of the encoded input information, we propose pathway selection via neurons' contribution to the response. We proceed to explain how critical pathways can reveal critical input features. We prove that pathways selected via neuron contribution are locally linear (in an L2-ball), a property that we use for proposing a feature attribution method: "pathway gradient". We validate our interpretation method using mainstream evaluation experiments. The validation of pathway gradient interpretation method further confirms that selected pathways using neuron contributions correspond to critical input features. The code is publicly available., Comment: Accepted at CVPR 2021 (IEEE/CVF Conference on Computer Vision and Pattern Recognition)

This article presents a short-term decision-making model for an electricity retailer using bilevel stochastic programing. In the proposed model, a liberalized distributed renewable energy (DRE) market in which the retailer competes with other load serving entities (LSEs) for procuring DRE is proposed. The retailer, in the upper level, decides its level of involvement in the day-ahead and real-time markets, as well as the price bids offered to DRE producers for every time period, with the goal of minimizing its expected procurement cost at a predefined risk level. On the other hand, DRE producers, in the lower level, react to the price bids offered by the retailer under study and other LSEs, to maximize their total revenues. The stochastic nature of day-ahead and real-time market prices, DRE production, electricity demand, and price bids of the retailer's rival market agents (RMAs) is taken into the formulation of the proposed model. By using the Karush-Kuhn-Tucker (KKT) optimality conditions and duality theory, the bilevel problem is transformed into its equivalent single-level mixed-integer linear programming (MILP) problem. Case studies are performed to show the effectiveness of the proposed model.

Peer-to-peer (P2P) energy trading is one of the promising approaches for implementing decentralized electricity market paradigms. In the P2P trading, each actor negotiates directly with a set of trading partners. Since the physical network or grid is used for energy transfer, power losses are inevitable, and grid-related costs always occur during the P2P trading. A proper market clearing mechanism is required for the P2P energy trading between different producers and consumers. This paper proposes a decentralized market clearing mechanism for the P2P energy trading considering the privacy of the agents, power losses as well as the utilization fees for using the third party owned network. Grid-related costs in the P2P energy trading are considered by calculating the network utilization fees using an electrical distance approach. The simulation results are presented to verify the effectiveness of the proposed decentralized approach for market clearing in P2P energy trading. Agency for Science, Technology and Research (A*STAR) Accepted version This work was supported by the Agency for Science, Technology and Research (A*STAR) through its Singapore–Germany Academic-Industry (2+2) International Collaboration under Grant A1990b0060. Paper no. TSG-01805-2019.

This article develops a novel nonlinear controller for the mitigation of drivetrain torsional oscillations of wind turbine generators following large disturbances. The key idea is to integrate differential geometry theory with an extended state observer. Differential geometry allows transforming the wind turbine generator nonlinear model into a simple second-order Brunovsky system, whereas the extended state observer can accurately estimate the states of the transformed Brunovsky system and compensate unknown disturbances. Simulation results show that, under various conditions in different test systems, the proposed controller achieves significant enhancements with respect to conventional approximate linearization-based controller and nonlinear sliding mode control-based method.

This letter presents a robust generalized correlation approach for monitoring of power system oscillatory modes. Due to the non-Gaussian nature of measurement noise, and presence of impulsive outliers, the wide-sense stationarity assumption of power system measurement data is violated even under ambient conditions thus limiting the effectiveness of conventional autocorrelation based approaches in mode metering. The fundamental definition of correlation function for power system measurements is extended to a generalized correlation function in order to incorporate higher order statistics into existing modal estimation technique. Simulations on synthetic and real-life test signals have been conducted to demonstrate the robustness of the proposed method.

Wireless communications can facilitate transfer of synchrophasor data between spatially separated phasor measurement units (PMUs) and phasor data concentrators (PDCs). However, such communication systems may impose random access delay and failure on PMU channels that lead to missing synchrophasor data frames at the output of the PDC. This paper presents a new approach for online reliability assessment and improvement of synchrophasor data communications. The proposed approach involves elaborate estimation and probabilistic prediction algorithms that trigger a prioritized handover mechanism in order to minimize the number of synchrophasor data frames that are missing over successive time stamps. Extensive simulations based on the LTE communications in a low-voltage distribution feeder confirm significant performance improvement and fast fault detection under the communication link failures. This non-intrusive approach can be adopted by network operators to ensure reliable transmission of synchrophasor data to monitoring, control, and protection applications in smart grids.

This paper presents a grid-forming control (GFC) scheme for two-stage photovoltaic (PV) systems that maintains power reserves by operating below the maximum power point (MPP). The PV plant in GFC mode behaves like a voltage source that supports the grid during disturbances in full or limited grid-forming mode as per the reserve availability. This is a model-free method that avoids the estimation of MPP power in real-time commonly done in the literature, which makes it simpler and more reliable. The proposed control also features an enhanced current limitation scheme that guarantees containment of the current overshoots during faults, which is not trivial in voltage-sourced GFC inverters. A thorough investigation is done, exploring various generation mixtures of synchronous machines (SM), GFC and grid-following (GFL) inverters, and all common disturbances, e.g., load change, faults and irradiance transients. The results show very favorable dynamic performance by the GFC inverters, far superior to GFL inverters and directly comparable to SMs. It is found that replacing SMs with GFC inverters may improve the frequency profile and terminal voltage during disturbances, despite losing out in the mechanical inertia and the strict inverter overcurrent limits.

The increasing uncertainty level caused by growing renewable energy sources (RES) and aging transmission networks poses a great challenge in the assessment of total transfer capability (TTC) and available transfer capability (ATC). In this paper, a novel data-driven sparse polynomial chaos expansion (DDSPCE) method is proposed for estimating the probabilistic characteristics (e.g., mean, variance, probability distribution) of probabilistic TTC (PTTC). Specifically, the proposed method, requiring no pre-assumed probabilistic distributions of random inputs, exploits data sets directly in estimating the PTTC. Besides, a sparse scheme is integrated to improve the computational efficiency. Numerical studies on the modified IEEE 118-bus system demonstrate that the proposed DDSPCE method can achieve accurate estimation for the probabilistic characteristics of PTTC with a high efficiency. Moreover, numerical results reveal the great significance of incorporating discrete random inputs in PTTC and ATC assessment, which nevertheless was not given sufficient attention., Comment: Accepted by IEEE Transactions on Power Systems for future publication

Development of protection scheme for microgrid is a challenging issue due to the inclusion of distributed generations (DGs). The research work for developing the primary protection scheme for microgrid is progressing continuously. This paper proposes an integrated impedance angle (IIA) based protection scheme using wide-area positive sequence components of voltages and currents. The proposed scheme uses data retrieved from the phasor measurement units (PMUs) of IEEE C37.118.1 complied standards. Furthermore, the IIA for the line is computed considering both ends PMU information, which is the key indicator for identifying the faults in the microgrid. The proposed protection scheme is extensively tested considering the different operating conditions of microgrid, variation in DG penetration and variation in fault parameters such as fault resistance, fault types, and fault location. Furthermore, cross validation on no-fault situations including section cutoff, disconnection of high penetration DG, grid-islanding resynchronization, motor starting, capacitor switching, and load encroachment are carried out. The proposed scheme is also tested for the insensitivity towards the external faults. The test results on both 15-bus and 34-bus systems clearly indicate that the proposed IIA-based wide-area scheme can be a potential protection measure for microgrid under varied operating circumstances.

The information and communication technology (ICT) is increasingly involved in the measurement, operation, control and protection of the cyber-physical power system (CPPS). As one of the most promising communication infrastructure projects, Starlink is a satellite Internet constellation being constructed by SpaceX for providing global Internet access, which can benefit the network service supply for the communication-enabled power system equipment in locations where the network access is unreliable, expensive, or completely unavailable. In this letter, the future applications of the Starlink space network in CPPSs are explored: the communication infrastructure and transmission parameters are discussed, and the corresponding test case was emulated in real-time on the heterogeneous co-emulation platform to validate the proposed concept of space network enhanced cyber-physical power system.

With the integration of multiple types of loads and renewable generations, the number of system states significantly grows. As a result, running optimal power flow (OPF) to analyze a myriad of system states is challenging and this seriously restricts the efficiency of the state enumeration method. To address that, this paper proposes a Lagrange Multiplier based State Enumeration (LMSE) approach to accelerate the analysis without loss of accuracy. The core idea is to directly obtain the optimal load shedding of contingency states by Lagrange multiplier-based functions, rather than the time-consuming OPF algorithms. This approach can also be conveniently integrated with the impact-increment method and the clustering technique for further efficiency enhancement. Case studies are performed on the RTS-79 and IEEE 118-bus systems considering multiple types of loads, photovoltaics (PVs), and wind turbines (WTs). Results indicate that the proposed method can significantly reduce the computing time without compromising the calculation accuracy.

Mobile Edge computing (MEC) is a new distributed computing paradigm where edge servers are deployed at, or near cellular base stations in close proximity to end-users. This offers computing resources at the edge of the network, facilitating a highly accessible platform for real-time, latency-sensitive services. A typical MEC environment is highly stochastic with random user arrivals and departures over time. Here, we address the user allocation problem from a service provider's perspective, who needs to allocate its users to the cloud or edge servers in a specific area. A user, who has a multi-dimensional resource requirement, can be allocated to either the remote cloud, which incurs a high latency, or an edge server, which results in a low latency but might require the user to wait in a queue. This study aims to achieve a controllable trade-off between performance (throughput) and several associated costs such as queuing delay and latency costs. We model this problem as a stochastic optimization problem, propose SUAC (Stochastic User AlloCation) -- an online Lyapunov optimization-based algorithm, and prove its performance bounds. The experimental results demonstrate that SUAC outperforms existing approaches, effectively allocating users with a desired trade-off while keeping the system strongly stable.

Internet of Things offers the infrastructure for smooth functioning of autonomous context-aware devices being connected towards the Cloud. Edge Computing (EC) relies between the IoT and Cloud providing significant advantages. One advantage is to perform local data processing (limited latency, bandwidth preservation) with real time communication among IoT devices, while multiple nodes become hosts of the collected data (reported by IoT devices). In this work, we provide a mechanism for the exchange of data synopses (summaries of extracted knowledge) among EC nodes that are necessary to give the knowledge on the data present in EC environments. The overarching aim is to intelligently decide on when nodes should exchange data synopses in light of efficient execution of tasks. We enhance such a decision with a stochastic optimization model based on the Theory of Optimal Stopping. We provide the fundamentals of our model and the relevant formulations on the optimal time to disseminate data synopses to network edge nodes. We report a comprehensive experimental evaluation and comparative assessment related to the optimality achieved by our model and the positive effects on EC.

In Press / En Prensa The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complexrelationship between computing and radio dynamics make vRAN resource control particularly daunting. We present vrAIn, a resourceorchestrator for vRANs based on deep reinforcement learning. First, we use an autoencoder to project high-dimensional context data(traffic and channel quality patterns) into a latent representation. Then, we use a deep deterministic policy gradient (DDPG) algorithmbased on an actor-critic neural network structure and a classifier to map contexts into resource control decisions.We have evaluated vrAIn experimentally, using an open-source LTE stack over different platforms, and via simulations over aproduction RAN. Our results show that: (i) vrAIn provides savings in computing capacity of up to 30% over CPU-agnostic methods;(ii) it improves the probability of meeting QoS targets by 25% over static policies; (iii) upon computing capacity under-provisioning,vrAIn improves throughput by 25% over state-of-the-art schemes; and (iv) it performs close to an optimal offline oracle. To ourknowledge, this is the first work that thoroughly studies the computational behavior of vRANs and the first approach to a model-freesolution that does not need to assume any particular platform or context. This work was partially supported by the European Commission through Grant No. 856709 (5Growth) and Grant No. 856950 (5G-TOURS); by Science Foundation Ireland (SFI) through Grant No. 17/CDA/4760; and AEI/FEDER through project AIM under Grant No. TEC2016-76465-C2-1-R. Furthermore, the work is closely related to the EU project DAEMON (Grant No. 101017109).

The Internet of Things (IoT) aims to connect everyday physical objects to the internet. These objects will produce a significant amount of data. The traditional cloud computing architecture aims to process data in the cloud. As a result, a significant amount of data needs to be communicated to the cloud. This creates a number of challenges, such as high communication latency between the devices and the cloud, increased energy consumption of devices during frequent data upload to the cloud, high bandwidth consumption, while making the network busy by sending the data continuously, and less privacy because of less control on the transmitted data to the server. Fog computing has been proposed to counter these weaknesses. Fog computing aims to process data at the edge and substantially eliminate the necessity of sending data to the cloud. However, combining the Service Oriented Architecture (SOA) with the fog computing architecture is still an open challenge. In this paper, we propose to decompose services to create linked-microservices (LMS). Linked-microservices are services that run on multiple nodes but closely linked to their linked-partners. Linked-microservices allow distributing the computation across different computing nodes in the IoT architecture. Using four different types of architectures namely cloud, fog, hybrid and fog+cloud, we explore and demonstrate the effectiveness of service decomposition by applying four experiments to three different type of datasets. Evaluation of the four architectures shows that decomposing services into nodes reduce the data consumption over the network by 10% - 70%. Overall, these results indicate that the importance of decomposing services in the context of fog computing for enhancing the quality of service., Comment: IEEE TRANSACTIONS SUSTAINABLE COMPUTING, 2019

Learning an advanced skill in sports requires a huge amount of practice and players also have to overcome both physical difficulties and the dullness of repetitive training. Returning a fast spin shot in table tennis could be taken as an example, as athletes need to judge the spin type and decide the racket pose within a second, which is difficult for beginners. Therefore, in this paper, we show how to design an intuitive training system to acquire this specific skill using different cues in Virtual Reality (VR). Using VR, we can easily provide visual information, attach haptic devices, and distort the speed of time, however, it is difficult to decide which types of information could benefit the training. In an initial study, by comparing real world training with VR training, we showed the effect of VR training and obtained some insights about augmentation for training spin shots. The training system was then improved by adding three new conditions using different visualizations and temporal distortions, as well as a haptic racket for creating realistic feedback. Finally, we performed a detailed experiment, which suggest a significant improvement of skill for each condition compared to the baseline, while a qualitative evaluation indicates that both users' motivation and their understanding of spin are increased by using our system.

Unpaired image-to-image (I2I) translation has received considerable attention in pattern recognition and computer vision because of recent advancements in generative adversarial networks (GANs). However, due to the lack of explicit supervision, unpaired I2I models often fail to generate realistic images, especially in challenging datasets with different backgrounds and poses. Hence, stabilization is indispensable for GANs and applications of I2I translation. Herein, we propose Augmented Cyclic Consistency Regularization (ACCR), a novel regularization method for unpaired I2I translation. Our main idea is to enforce consistency regularization originating from semi-supervised learning on the discriminators leveraging real, fake, reconstructed, and augmented samples. We regularize the discriminators to output similar predictions when fed pairs of original and perturbed images. We qualitatively clarify why consistency regularization on fake and reconstructed samples works well. Quantitatively, our method outperforms the consistency regularized GAN (CR-GAN) in real-world translations and demonstrates efficacy against several data augmentation variants and cycle-consistent constraints., Comment: Accepted to ICPR2020

Describing orally what we are seeing is a simple task we do in our daily life. However, in the natural language processing field, this simple task needs to be bridged by a textual modality that helps the system to generalize various objects in the image and various pronunciations in speech utterances. In this study, we propose an end-to-end Image2Speech system that does not need any textual information in its training. We use a vector-quantized variational autoencoder (VQ-VAE) model to learn the discrete representation of a speech caption in an unsupervised manner, where discrete labels are used by an image-captioning model. This self-supervised speech representation enables the Image2Speech model to be trained with the minimum amount of paired image-speech data while still maintaining the quality of the speech caption. Our experimental results with a multi-speaker natural speech dataset demonstrate our proposed text-free Image2Speech system’s performance close to the one with textual information. Furthermore, our approach also successfully outperforms the most recent existing frameworks with phoneme-based and grounding-based Image2Speech systems.

Perimeter models, which provide access control for protecting resources on networks, make authorization decisions using the source network of access requests as one of critical factors. However, such models are problematic because once a network is intruded, the attacker gains access to all of its resources. To overcome the above problem, a Zero Trust Network (ZTN) is proposed as a new security model in which access control is performed by authenticating users who request access and then authorizing such requests using various information about users and devices called contexts. To correctly make authorization decisions, this model must take a large amount of various contexts into account. However, in some cases, an access control mechanism cannot collect enough context to make decisions, e.g., when an organization that enforces access control joins the identity federation and uses systems operated by other organizations. This is because the contexts collected using the systems are stored in individual systems and no federation exists for sharing contexts. In this study, we propose the concept of a Zero Trust Federation (ZTF), which applies the concept of ZTN under the identity federation, and a method for sharing context among systems of organizations. Since context is sensitive to user privacy, we also propose a mechanism for sharing contexts under user control. We also verify context sharing by implementing a ZTF prototype.

The development of a low-cost high-performance secure hash algorithm (SHA)-256 accelerator has recently received extensive interest because SHA-256 is important in widespread applications, such as cryptocurrencies, data security, data integrity, and digital signatures. Unfortunately, most current researches have focused on the performance of the SHA-256 accelerator but not on a system level, in which the data transfer between the external memory and accelerator occupies a large time fraction. In this paper, we solve the state-of-art problem with a novel SHA-256 architecture named the multimem SHA-256 accelerator that achieves high performance at the system on chip (SoC) level. Notably, our accelerator employs three novel techniques, the pipelined arithmetic logic unit (ALU), multimem processing element (PE), and shift buffer in shift buffer out (SBi-SBo), to reduce the critical path delay and significantly increase the processing rate. Experiments on a field-programmable gate array (FPGA) and an application-specific integrated circuit (ASIC) show that the proposed accelerator achieves significantly better processing rate and hardware efficiency than previous works. The accelerator accuracy is verified on a real hardware platform (FPGA ZCU102). The accelerator is synthesized and laid out with 180 nm complementary metal oxide semiconductor (CMOS) technology with a chip sized $8.5\,mm \times 8.5\,mm$ , consumes 1.86 W, and provides a maximum processing rate of 40.96 Gbps at 80 MHz and 1.8 V. With FPGA Xilinx 16 nm FinFET technology, the accelerator processing rate is as high as 284 Gbps.

One-to-many transfers in a fast and efficient manner are essential to meet the growing need for duplicating, migrating, or sharing bulk data among servers in a datacenter and across geographically distributed datacenters. Some existing works utilize multiple multicast trees for a one-to-many transfer request to increase network link utilization and its transfer throughput. However, since those schemes do not fully utilize the max-flow value of transmission from a single sender to each recipient, there is room for each recipient to retrieve data more quickly. Therefore, assuming fully-controlled networks with full-duplex links, we pose a problem to find a set of multicast flows with an allocation of block-wise transmissions by which each of multiple recipients with diverse max-flow values from the sender can utilize its own max-flow value. Based on that, assuming a sender-side coding capability on file blocks, we design a schedule of block transmissions over multiple phases by which each recipient can achieve a lower-bound of its file retrieval completion time, i.e., the file size divided by its own max-flow value. This paper presents the coded Multipath Multicast (Coded-MPMC) for one-to-many transfers with heuristic procedures to find a desired set of multicast flows on which block transmissions are scheduled. Through extensive simulations on large-scale real-world network topologies and different types of randomly-generated synthetic topologies, the proposed method is shown to design a desired schedule efficiently. A preliminary implementation on OpenFlow is also reported to show the fundamental feasibility of Coded-MPMC.

The rapid development of Internet in recent years has led to a proliferation of social media networks as people who can gather online to share information, knowledge, and opinions. However, the network public opinion tends to generate strongly misleading and a large number of messages can cause shocks to the public once major emergencies appear. Therefore, we need to make correct prediction regarding and timely identify a potential crisis in the early warning of network public opinion. In view of this, this study fully considers the features of development and the propagation characteristics, so as to construct a network public opinion early warning index system that includes 4 first-level indicators and 13 second-level indicators. The weight of each indicator is calculated by the “CRITIC” method, so that the comprehensive evaluation value of each time point can be obtained and the early warning level of internet public opinion can be divided. Then, the Back Propagation neural network based on Genetic Algorithm (GA-BP) is used to establish a network public opinion early warning model. Finally, the major public health emergency, COVID-19 pandemic, is taken as a case for empirical analysis. The results show that by comparing with the traditional classification methods, such as BP neural network, decision tree, random forest, support vector machine and naive Bayes, GA-BP neural network has a higher accuracy rate for early warning of network public opinion. Consequently, the index system and early warning model constructed in this study have good feasibility and can provide references for related research on internet public opinion.

COVID-19 is an extremely dangerous disease because of its highly infectious nature. In order to provide a quick and immediate identification of infection, a proper and immediate clinical support is needed. Researchers have proposed various Machine Learning and smart IoT based schemes for categorizing the COVID-19 patients. Artificial Neural Networks (ANN) that are inspired by the biological concept of neurons are generally used in various applications including healthcare systems. The ANN scheme provides a viable solution in the decision making process for managing the healthcare information. This manuscript endeavours to illustrate the applicability and suitability of ANN by categorizing the status of COVID-19 patients’ health into infected (IN), uninfected (UI), exposed (EP) and susceptible (ST). In order to do so, Bayesian and back propagation algorithms have been used to generate the results. Further, viterbi algorithm is used to improve the accuracy of the proposed system. The proposed mechanism is validated over various accuracy and classification parameters against conventional Random Tree (RT), Fuzzy C Means (FCM) and REPTree (RPT) methods.

Network resource management is one of the key technologies needed to ensure that multiple applications in edge networks provide reliable and stable performance. Although throughput has previously been seen as the primary network performance metric, recent applications do not focus on throughput alone. Instead, Quality of Experience (QoE) is attracting significant attention as an indicator of network resource management performance because it allows a wide variety of applications to be compared within a single metric. In this study, we tackle QoE measurements for a video streaming service as a way to evaluate QoE-based network management. However, there are several problems related to measuring QoE. For example, in-network components are difficult to measure because QoE is normally measured at end-points, and several properties that are deeply related to application settings are required for those calculations. Additionally, the measurements set forth in the International Telecommunication Union’s ITU-T G.1071 standard require a certain duration, which is too long for network resource management evaluations. Therefore, this paper proposes a two-staged in-network QoE estimation method for video flows that can resolve these issues. In the first stage, we focus on producing a fast and rough QoE estimate to start forwarding the arriving flow onto an appropriate route as soon as possible. Next, the second stage is designed to produce precise QoE estimations based on careful long-duration measurements. In both stages, the proposed method uses a parameter estimation process that converts in-network information to end-point information for QoE calculations by following ITU-T G. 1071 and corrects measurement errors reducing QoE calculation errors to the greatest extent possible. Through experimental evaluations, we then demonstrate that the QoEs of all flows can be maximized by selecting appropriate routes based on the predicted QoE at the first stage, and that the accuracy of the QoE estimation at the second stage can be improved in real-time even when packet losses occur.

Data races have become one of the severe issues affecting the correctness of concurrent programs. Existing detection tools for data races have many false positives and false negatives. To improve the correctness, this paper proposes a context-sensitive approach to detect data races in concurrent programs. Several program analysis techniques are conducted to reduce false positives and false negatives. First, control-flow analysis is used to construct call graphs, in which escape analysis is employed to find escaped objects among threads. Second, context-sensitive alias analysis is employed to find alias objects. Finally, happens-before analysis is conducted to reduce false positives and false negatives. We develop a prototype tool ConRacer based on WALA and evaluate it on several benchmarks. We also compare ConRacer with existing static and dynamic tools. The experimental results show that ConRacer can effectively detect data races and reduce false positives and false negatives.

This paper proposes a novel adaptive range composite differential evolution (ARCoDE) algorithm to efficiently and accurately solve optimal reactive power dispatch (ORPD) problem. Because of a novel adaptive range strategy for control parameters, the proposed ARCoDE possesses superior exploration and exploitation capabilities that can efficiently handle the ORPD problem involving complicated constraints and discrete and continuous variables. This has been demonstrated in case studies using the IEEE optimal power flow testbeds considering complex wind and demand scenarios. The superior performance of ARCoDE has been further validated through comparisons with several award-winning algorithms in 2014 IEEE Competition on “Application of Modern Heuristic Optimization Algorithms for Solving Optimal Power Flow Problems”, given limited iterations of in evolutionary optimization process. Energy Market Authority (EMA) Published version This work was supported in part by the National Key Research and Development Program of China under Grant 2019YFB1505400, and inpart by the Energy Market Authority and National Science Foundation Singapore under Grant NRF2017EWT-EP003-038.

Logic Encryption is a hardware security technique that protects integrated circuit designs that are fabricated at untrusted pure play foundries from being pirated or maliciously modified. In the technique, logic gates are added to the design that are driven by an added key input bus, such that the correct behavior of the circuit is recovered with only the exact correct key input pattern. However, the power, performance, and area (PPA) cost of implementing logic encryption has often been ignored in the literature in favor of increasing the level of security provided. This has proved to be a significant hurdle in transitioning the method to use in commercial-grade designs and a systematic methodology of constraining the cost of logic encryption is needed. In this paper, we propose a generalized Constraint-Directed Logic Encryption (CDLE) methodology. In CDLE, the potential design space of encrypted versions of a circuit is searched to apply logic encryption under PPA constraints. Two example CDLE methods are proposed. The first is a concurrent tree search method which uses commercial tools to sample designs for their PPA cost and determine the optimal encryption strategy. In this method, PPA cost is accurately analyzed at the cost of heavy runtime. The second is a machine learning approach which estimates the PPA cost to predict the optimal encryption strategy. The machine learning model developed in this work is limited, but the results are promising as a direction for study in logic encryption. Detailed experimental results evaluating both methods are presented.

In this paper, we designed a registration framework that can be used to develop augmented reality environments, where all the real (including the users) and virtual elements are co-localized and registered in a common reference frame. The software is provided together with this paper, to contribute to the research community. The developed framework allows us to perform a quantitative assessment of interaction and egocentric perception in Augmented Reality (AR) environments. We assess perception and interaction in the peripersonal space through a 3D blind reaching task in a simple scenario and an interaction task in a kitchen scenario using both video (VST) and optical see-through (OST) head-worn technologies. Moreover, we carry out the same 3D blind reaching task in real condition (without head-mounted display and reaching real targets). This provides a baseline performance with which to compare the two augmented reality technologies. The blind reaching task results show an underestimation of distances with OST devices and smaller estimation errors in frontal spatial positions when the depth does not change. This happens with both OST and VST devices, compared with the real-world baseline. Such errors are compensated in the interaction kitchen scenario task. Thanks to the egocentric viewing geometry and the specific required task, which constrain the position perception on a table, both VST and OST have comparable and effective performance. Thus, our results show that such technologies have issues, though they can be effectively used in specific real tasks. This does not allow us to choose between VST and OST devices. Still, it provides a baseline and a registration framework for further studies and emphasizes the specificity of perception in interactive AR.

The multi-energy system is a promising energy-efficient technology to supply electric and thermal energy to end-users simultaneously, which can realize the energy cascade utilization. However, it is challenging to optimize the operation of multi-energy systems due to their inherent structural complexity, as well as the highly coupled nature of multiple energy flows and the uncertainty of renewable energy generation. This paper proposed a collaborative demand-controlled operation strategy for a multi-energy system, which consists of an upper-level model and a lower-level model. In the upper-level model, a robust linear optimization method is adopted to optimize the system operation in a day-ahead stage. In the lower-level model, a stochastic rolling optimization method is applied to achieve a dynamic adjustment to cope with the fluctuation in both renewable electricity generation and electric load. The multiple energy demand-controlled strategy is also applied in the optimal operation strategy to achieve load shifting and to create flexibility in energy demand despite the “source-load” imbalance power fluctuation. A case study is carried out and simulation results verify the effectiveness and correctness of the proposed model of the coordinated operation framework.

Owing to its high spectrum efficiency (SE), two-way relaying has aroused tremendous research interests. In this paper, the spectrum-energy efficiency (SE-EE) trade-off in decode-and-forward (DF) two-way multi-relay networks is studied by considering non-ideal power amplifiers and non-negligible circuit. Firstly, we consider the scenario of several relay nodes. To achieve better performance, the relay node with the highest energy efficiency (EE) is selected as the optimal one. Secondly, we design the optimal power allocation method to allocate each node with the optimal transmission power to enhance EE and SE. Finally, we evaluate the performance of our method and additionally analyze how the change of relay nodes’ relative position influences the EE and SE. Simulation results show that: 1) the proposed method can achieve higher SE than optimal relay equal power allocation, random relay equal power allocation, and optimal power allocation only; 2) the proposed method can achieve higher EE than optimal relay equal power allocation, random relay equal power allocation, and optimal power allocation only; and 3) EE and SE increase at first and then decrease when relay nodes move from the middle of the source node and destination node to both ends.

In artificial neural networks, activation functions play a significant role in the learning process. Choosing the proper activation function is a major factor in achieving a successful learning performance. Many activation functions are sufficient universal approximators, but their performance is lacking. Thus, many efforts have been directed toward activation functions to improve the learning performance of artificial neural networks. However, the learning process involves many challenges, such as saturation, dying, and exploding/vanishing the gradient problems. The contribution of this work resides in several axes. First, we introduce two novel activation functions: absolute linear units and inverse polynomial linear units. Both activation functions are augmented by an adjustable parameter that controls the slope of the gradient. Second, we present a comprehensive study and a taxonomy of various types of activation functions. Third, we conduct a broad range of experiments on several deep neural architecture models with consideration of network type and depth. Fourth, we evaluate the proposed activation functions’ performance in image and text classification tasks. For this purpose, several public benchmark datasets are utilized to evaluate and compare the performance of the proposed functions with that of a group of common activation functions. Finally, we deeply analyze the impact of several common activation functions on deep network architectures. Results reveal that the proposed functions outperform most of the popular activation functions in several benchmarks. The statistical study of the overall experiments on both classification categories indicates that the proposed activation functions are robust and superior among all the competitive activation functions in terms of average accuracy.

As a fundamental preprocessing technique, remote sensing image motion deblurring is important for visual understanding tasks. Most conventional approaches formulate the image motion deblurring task as a kernel estimation. Because the kernel estimation is a highly ill-posed problem, many priors have been applied to model the images and kernels. Even though these methods have obtained relatively better performances, they are usually time-consuming and not robust for different conditions. To address this problem, we propose a multitask learning mechanism for remote sensing image motion deblurring in this article, which contains an image restoration subtask and an image texture complexity recognition one. First, we consider the image motion deblurring problem as a domain transformation problem, from the blurred domain to a clear one. Specifically, the blurred domain represents the data space consisted of blurring images, and the definition of clear domain is similar. Second, we design a novel weighted attention map loss to enhance the reconstruction capability of the restoration subbranch for difficult local regions. Third, based on the restoration subbranch, a recognition subbranch is incorporated into the framework to guide the deblurring process, which provides the auxiliary texture complexity information to help the optimization of restoration subbranch. Additionally, in order to optimize the proposed network, we construct three large-scale datasets, and each sample in the dataset contains a clear image, a blurred image, and its texture label obtained by corresponding texture complexity. Finally, the experimental results on three constructed datasets demonstrate the robustness and the effectiveness of the proposed method.

This paper addresses a novel fuzzy-based distributed behavioural control with the wall-following strategy for robot swarm navigation in arbitrary-shaped environments. Instead of avoiding large-sized obstacles during the swarm navigation, the proposed fully distributed control enables the robot swarm to transform from aggregation configuration to one-chain configuration and follow the obstacle boundary to overcome it. The wall-following strategy and one-chain configuration empower the swarm navigation to avoid local minima caused by obstacles and connectivity maintenance without dealing with the alignment control of swarm behaviours. The fuzzy-logic control is applied to calculate the parameters of the distributed control strategies. The proposed method is examined and evaluated in both simulation and real experiments.

Fog-to-cloud computing has now become a new cutting-edge technique along with the rapid popularity of Internet of Things (IoT). Unlike traditional cloud computing, fog-to-cloud computing needs more entities to participate in, including mobile sinks and fog nodes except for cloud service provider (CSP). Hence, the integrity auditing in fog-to-cloud storage will also be different from that of traditional cloud storage. In the recent work of Tian et al., they took the first step to design public auditing system for fog-to-cloud computing. However, their scheme becomes very inefficient since they uses intricate public key cryptographic techniques, including bilinear mapping, proof of knowledge etc. In this paper, we design a general and more efficient auditing system based on MAC and HMAC, both of which are popular private key cryptographic techniques. By implementing MAC and HMAC, we give a concrete instantiation of our auditing system. Finally, the theoretical analysis and experiment results show that our proposed system has more efficiency in terms of communication and computational costs.

Robust watermarking is a valuable methodology used in protecting the copyright and securing digital images. In this paper, new fractional-order multi-channel orthogonal exponent moments (MFrEMs) and their invariants to geometric transformations are derived for the first time. We utilized these highly accurate moments to construct a new robust watermarking algorithm for color images. This algorithm consists of three phases. First, the bits of the binary watermark scrambled by using a 1D Sine chaotic map. Second, the fractional-order MFrEMs are calculated from the host color image. Finally, a quantization process is performed, where the scrambled bits of the binary watermark embedded into the host color image. Various experiments were conducted to test the proposed watermarking algorithm and compare it with the existing robust watermarking algorithms for color images. The obtained results ensure the proposed robust watermarking algorithm’s superiority over existing algorithms regarding the visual imperceptibility and robustness against various attacks.

Lithium-Ion battery packs are an essential component for electric vehicles (EVs). These packs are configured from hundreds of series and parallel connected cells to provide the necessary power and energy for the vehicle. An accurate, adaptable battery management system (BMS) is essential to monitor and control such a large number of cells. Series and parallel connected cells also experience different production and operational conditions, which makes it challenging for the BMS to ensure the safe operation of each individual cell. The main functions of the BMS include battery state estimation, cell balancing, thermal management, and fault diagnosis. Robust estimation of the state of charge (SOC) is crucial for providing the driver with an accurate indication of the remaining range. This paper presents the state of art of battery pack SOC estimation methods along with the impact of cell inconsistency on pack performance and SOC estimation. Cell balancing methods, which are necessary due to cell inconsistencies, are discussed as well. Four categories of pack SOC estimation methods are presented, including individual cell, lumped cell, reference cell, and mean cell and difference estimation methods. The SOC estimation methods are compared in terms of algorithm type, computational load, and engineering effort to help practitioners decide which method best fits their application.

Power Domain Non Orthogonal Multiple Access (PD-NOMA) is a multiple access technique that offers spectral efficiency, low latency and user fairness in 5G networks. This paper evaluates the performance of multi-user downlink PD-NOMA in suburban environments under SUI fading channels. Baseband modulated user signals with phase shifts are allocated power levels in accordance with users distance before the superposition coding is performed at the base station. A multi-level successive interference cancellation (SIC) is performed at the receivers. Bit error rate (BER) performance against signal-to-noise ratio (SNR) for up to four users per cluster is compared for all the SUI models corresponding to different suburban terrains with varying vegetation densities. An upper limit on number of users per cluster that are supported at a benchmark BER and SNR values is also evaluated.

Vehicular ad hoc network is a kind of mobile ad hoc networks which provides wireless communication between vehicles. In most cases, multi-hop communication is needed, because of the limited range of wireless transmission. The multi-hop communication among nodes strictly relies on the forwarding functionality of intermediate nodes. Due to resource limitation, the intermediate nodes may exhibit selfishness and refuse to bear forwarding tasks for others. In this article, we defined two types of selfish nodes, namely static selfish nodes and dynamic selfish nodes. The impact of the two types of selfish nodes are quantitatively investigated from various aspects including mobilities, proportions, densities, and combinations. We conducted exhaustive simulations on an integrated simulation platform which consists of OMNeT++, SUMO, INET, and Veins. The experimental results indicate that the static selfish nodes have more harmful impacts on the performance of vehicular ad hoc networks in terms of average packet delivery ratios and end-to-end delays. Moreover, the results also imply that the impact of node selfishness should be evaluated by a comprehensive consideration of mobilities, proportions, densities, and combinations of selfish nodes.