Search

The literature argues that a real digital transformation of firms requires holistic changes of the business model. Despite knowledge about this ambitious goal, understanding of how digital business model transformation can be achieved is still very limited. In this article, we explore how firms achieve digital business model transformation. We apply a case study design to investigate how incumbents have changed their respective business model dimensions during digital transformation. Our findings center on interview data and complementary archival records from 15 cases. We present a framework for digital business model transformation along the dimensions of value proposition, value creation, and value capture. Our results emphasize the importance of a preparatory phase in which the strategic course is set. Furthermore, our findings demonstrate that transforming a company's business model is most effective when a single person, namely the Chief Digital Officer, is responsible. Our findings contribute to the business model literature, by providing a more holistic view on how business model innovation can be utilized during digital transformation.

Accurate object detection requires correct classification and high-quality localization. Currently, most of the single shot detectors (SSDs) conduct simultaneous classification and regression using a fully convolutional network. Despite high efficiency, this structure has some inappropriate designs for accurate object detection. The first one is the mismatch of bounding box classification, where the classification results of the default bounding boxes are improperly treated as the results of the regressed bounding boxes during the inference. The second one is that only one-time regression is not good enough for high-quality object localization. To solve the problem of classification mismatch, we propose a novel reg-offset-cls (ROC) module including three hierarchical steps: the regression of the default bounding box, the prediction of new feature sampling locations, and the classification of the regressed bounding box with more accurate features. For high-quality localization, we stack two ROC modules together. The input of the second ROC module is the output of the first ROC module. In addition, we inject a feature enhanced (FE) module between two stacked ROC modules to extract more contextual information. The experiments on three different datasets (i.e., MS COCO, PASCAL VOC, and UAVDT) are performed to demonstrate the effectiveness and superiority of our method. Without any bells or whistles, our proposed method outperforms state-of-the-art one-stage methods at a real-time speed. The source code is available at https://github.com/JialeCao001/HSD.

Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks locally on-device. Yet the complexity of deep models needs to be trimmed down to fit in mobile storage and memory. Previous studies squeeze the redundancy within a single model. In this work, we reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to merge correlated, pre-trained deep neural networks for cross-model compression. Central in MTZ is a layer-wise neuron sharing and incoming weight updating scheme that induces a minimal change in the error function. MTZ inherits information from eachmodel and demands light retraining to re-boost the accuracy of individual tasks. MTZ supports typical network layers and applies to inference tasks with different input domains. Evaluations show that MTZ can fully merge the hidden layers of two VGG-16 network. Moreover, MTZ can effectively merge nine residual networks for diverse inference tasks and models for different input domains. Withthe joint model merged by MTZ, the latency to switch between these tasks on memory-constrained devices is reduced by 8.71.

Model-based design is an important method of addressing problems associated with designing complex control systems. For complex dynamic systems in the presence of uncertainties, the modeling process from the first principles becomes extremely tedious and simplification in mechanism and parameter measurement may result in model inaccuracy. On the contrary, machine learning has the characteristic of fitting complicated equations, which makes it widely used in the research of model identification. However, it only brings a black-box model where the design schemes based on an analytical model cannot be applied. In this article, a simple and novel scheme for modeling and control of robotic manipulators is proposed; without prior knowledge, a dynamic model in an analytical form is obtained from artificially excited training data using the symbolic regression technique, and then, a controller is designed based on the dynamic model. Due to the ingenious experimental design, on one hand, the amount of training data is far less than the system identification method by machine learning. On the other hand, a decoupling feature is used in the model that greatly simplifies controller design. The experimental results on two-degree of freedom (DOF) and 6-DOF robotic manipulator simulators verify that the scheme is feasible and effective.

With the dawn of 5G network, a new set of requirements for site spectrum monitoring, cellular planning are emerging, all of which are relying on fine-grained signal map. Although with significant importance, the traditional signal map construction could be time-consuming and labor-intensive. The state-of-the arts usually employ crowdsourcing scheme and matrix completion algorithm to solve the dilemma. However, the crowdsourcing scheme usually suffers from uneven distributed and inadequate participants. To this end, in this paper, we study how to effectively reconstruct and update the signal map in the case of partially measured signal maps with smaller cost and propose a GAN-based active signal map reconstruction method (GSMAC). Our method is mainly innovative in two parts: GSMC, GAN-based signal map construction, and ACS, an active crowdsourcing scheme. Specifically, GSMC can effectively update the signal map with only a small number of observations while updating the signal map online. ACS consists of a reinforce learning-based active query mechanism which quantitatively evaluates the most valuable measurement site for reconstruction. The simulation results and real implemented data-driven experiments demonstrate the advantages and effectiveness of our approach in both accuracy and cost.

Compressed sensing has been identified as a good candidate for user detection in grant-free non-orthogonal multiple access (NOMA) by exploiting the inherent sparsity of user activity. However, most of the existing works do not fully utilize the temporal correlation in NOMA and rely heavily on the unrealistic assumption that the number of active users is known in advance. To address these issues, we propose a temporal correlation enhanced multiuser detection scheme to achieve efficient and practical multiuser detection. Firstly, using 1 bit memory to piggyback the information whether the active users still have data to transmit, the base station can realize whether the active users in current time slot will turn to be silent or remain active. Then, to make explicit use of the temporal correlation of active user sets, a cross validation based adaptive subspace pursuit (CVASP) algorithm, is developed by utilizing the reported information on prior active users. The proposed CVASP is a highly practical algorithm that does not require any prior knowledge of the user sparsity level, as the cross validation technique could properly determine the stopping condition. Extensive simulation results demonstrate that the proposed mechanism could achieve a superier performance without requiring any prior knowledge.

In order to make redundant robot manipulators (RRMs) track the complex time-varying trajectory, the motion-planning problem of RRMs can be converted into a constrained time-varying quadratic programming (TVQP) problem. By using a new punishment mechanism-combined recurrent neural network (PMRNN) proposed in this article with reference to the varying-gain neural-dynamic design (VG-NDD) formula, the TVQP problem-based motion-planning scheme can be solved and the optimal angles and velocities of joints of RRMs can also be obtained in the working space. Then, the convergence performance of the PMRNN model in solving the TVQP problem is analyzed theoretically in detail. This novel method has been substantiated to have a faster calculation speed and better accuracy than the traditional method. In addition, the PMRNN model has also been successfully applied to an actual RRM to complete an end-effector trajectory tracking task.

Connected and autonomous vehicles are expected to revolutionize transportation systems in the near future. Nevertheless, full autonomy still requires further development that will only be achieved through a high level of cooperation and coordination among vehicles. For the safe execution of several autonomous functions, vehicles will need to frequently communicate their current location to the Road Side Units (RSUs). However, due to information aging, it is expected that the delays from the time a message is generated until the location of the vehicle is updated will induce a tracking error. Thus, there is a tradeoff between the frequency of location updates and tracking error. Further, in order to reduce the queue-induced delays present in the system, the number of messages can be reduced by employing an event-triggered communication scheme. In this work, a family of optimization problems is proposed, utilizing the event-triggered algorithm, in order to determine the optimal triggering threshold. Both single and multiple RSU cases are considered in several simulation scenarios, demonstrating that the proposed optimization framework derives the optimal tracking accuracy. In the case of multiple RSUs, results are further optimized by assigning roads (and in turn vehicles) to RSUs if coverage areas of multiple RSUs overlap.

In this article, the exponential synchronization control issue of reaction-diffusion neural networks (RDNNs) is mainly resolved by the sampling-based event-triggered scheme under Dirichlet boundary conditions. Based on the sampled state information, the event-triggered control protocol is updated only when the triggering condition is met, which effectively reduces the communication burden and saves energy. In addition, the proposed control algorithm is combined with sampled-data control, which can effectively avoid the Zeno phenomenon. By thinking of the proper Lyapunov-Krasovskii functional and using some momentous inequalities, a sufficient condition is obtained for RDNNs to achieve exponential synchronization. Finally, some simulation results are shown to demonstrate the validity of the algorithm.

Deep reinforcement learning is confronted with problems of sampling inefficiency and poor task migration capability. Meta-reinforcement learning (meta-RL) enables meta-learners to utilize the task-solving skills trained on similar tasks and quickly adapt to new tasks. However, meta-RL methods lack enough queries toward the relationship between task-agnostic exploitation of data and task-related knowledge introduced by latent context, limiting their effectiveness and generalization ability. In this article, we develop an algorithm for off-policy meta-RL that can provide the meta-learners with self-oriented cognition toward how they adapt to the family of tasks. In our approach, we perform dynamic task-adaptiveness distillation to describe how the meta-learners adjust the exploration strategy in the meta-training process. Our approach also enables the meta-learners to balance the influence of task-agnostic self-oriented adaption and task-related information through latent context reorganization. In our experiments, our method achieves 10%-20% higher asymptotic reward than probabilistic embeddings for actor-critic RL (PEARL).

Conventionally, single phase shift control technique is used, for dual active bridge (DAB) which works efficiently at unity voltage conversion ratio and full load. However, when there is mismatch between primary voltage and reflected secondary voltage on primary side at light load, its efficiency reduces because of increased current stress and circulating power. Moreover, due to single control variable, its power flow controllability is confined. In this paper, isolated bi-directional T-type multilevel dual active bridge dc-dc converter topology is presented. It has five level voltages on both the primary and secondary side of high frequency transformer, which reduces the current stress and circulating power over wide operating range. It also has five control variables which gives extra edge for enhancing power flow controllability. Comparative analysis reveals that the proposed converter has high efficiency over wide operating range, due to reduced circulating power and current stress. Performance of the proposed T- type multilevel dual active bridge DC-DC converter topology has been verified via simulation in MATLAB.

Compared to conventional microgrids (MGs) with pre-defined and static topology, dynamic MGs feature varying electric boundaries and enhanced operational resiliency. This paper evaluates the operation stability of inverter-based dynamic MGs in terms of fulfilling the requested MGs topology change and associated network reconfiguration, which falls into the category of large-signal stability analysis. A complete nonlinear state-space model of inverter-based dynamic MGs is derived, where coordinated controls among inverters along with the effect of communication delays have been considered. In response to reconfiguration demands, an evaluation scheme is developed to determine whether the system could perform seamless topology variation without losing synchronism. Specifically, the system’s stability region is quantified by the domain of attraction (DoA) around the desired operating point using Takagi-Sugeno fuzzy modeling (T-S multimodeling). The large-signal stability of a multi-bus inverter-based dynamic MG with both interface inverters and sectionalizing switches have been analyzed. The stability regions estimated under different scenarios of topology variation have been validated using time-domain simulation in MATLAB/Simulink. The developed evaluation scheme is used to quantify the effects of control gain designs and communication delays on system large-signal stability.

With the massive deployment of the Internet of things (IoT) devices, many data analysis applications emerge for the large amount of data accumulated by IoT. Federated learning (FedL) on IoT devices is an appealing mode to train a precise data analysis model. However, existing federated learning schemes either take expensive computation costs (e.g., public key cryptographic operations) or a large number of interactions among participants. Obviously, these schemes are unsuitable for IoT devices due to the limited computational and communication resources. In this work, we propose a lightweight privacy-preserving federated learning scheme for IoT devices. To protect the privacy of individual local data, we add masks to intervening parameters. An effective secret sharing scheme is adopted to ensure that masks can be eliminated accurately. Considering that FedL involves multiple iterations and mask generation for each iteration costs a large number of interactions among users for privacy guarantee, we also design a secure mask reusing mechanism for large-scale FedL tasks. We prove that our scheme is secure against the honest-but-curious model. In addition, we also expand our scheme to deal with the collusion attack. Extensive experiments on real IoT devices demonstrate the accuracy and efficiency of our work.

The huge amount of data produced in the 6G networks not only brings new challenges to the reliability and efficiency of mobile devices but also drives rapid development of new storage techniques. With the benefits of fast access speed and high reliability, NAND flash memory has become a promising storage solution for the 6G networks. In this paper, we investigate a protograph-coded bit-interleaved coded modulation with iterative detection and decoding (BICM-ID) utilizing irregular mapping (IM) in the NAND flash-memory systems. First, we propose an enhanced protograph-based extrinsic information transfer (EPEXIT) algorithm to facilitate the analysis of protograph codes in the IM-BICM-ID systems. With the use of EPEXIT algorithm, a simple design method is conceived for the construction of a family of high-rate protograph codes, called irregular-mapped accumulate-repeat-accumulate (IMARA) codes, which possess excellent decoding thresholds and linear-minimum-distance-growth property. Furthermore, motivated by the voltage-region iterative gain characteristics of IM-BICM-ID systems, a novel read-voltage optimization scheme is developed to acquire accurate read-voltage levels, thus minimizing the decoding thresholds (in dB) of protograph codes. Analyses and simulations indicate that the proposed IMARA-aided IM-BICM-ID scheme and read-voltage optimization scheme remarkably improve the convergence and decoding performance of flash-memory systems. Thus, the proposed protograph-coded IM-BICM-ID can be viewed as a reliable and efficient storage solution for the new-generation mobile networks, such as Internet of Vehicles.

Non-Euclidean property of graph structures has faced interesting challenges when deep learning methods are applied. Graph convolutional networks (GCNs) can be regarded as one of the successful approaches to classification tasks on graph data, although the structure of this approach limits its performance. In this work, a novel representation learning approach is introduced based on spectral convolutions on graph-structured data in a semisupervised learning setting. Our proposed method, COnvOlving cLiques (COOL), is constructed as a neighborhood aggregation approach for learning node representations using established GCN architectures. This approach relies on aggregating local information by finding maximal cliques. Unlike the existing graph neural networks which follow a traditional neighborhood averaging scheme, COOL allows for aggregation of densely connected neighboring nodes of potentially differing locality. This leads to substantial improvements on multiple transductive node classification tasks.

The future communication technologies like 6G are capable to provide higher mobility and better quality of service requirements to Internet of Things (IoT). To ensure mobility, the 6G technologies need more reliable and scalable solutions, which are capable to integrate large scale heterogeneous IoT networks. In a heterogeneous environment, seamless mobility along with the demands of IP addresses requires a proxy mobile IPv6 (PMIPv6) protocol that provides cost-effective solutions in next generation IoT networks. The PMIPv6 has been exploited for resource efficiency in IoT-enabled next generation networks. In this paper, we have proposed a demand-based resource-efficient location-aware PMIPv6 extension for seamless mobility in the next generation IoT networks. The proposed approach efficiently utilizes the network resources using location information and received signal strength (RSS). This solution enhances the performance of PMIPv6 protocol in terms of signaling cost, and load on network entities. Furthermore, mathematical models are derived in terms of signaling cost, load distribution. The proposed solution is compared with the existing RSS-based PMIPv6 extension protocols. The results show that the proposed scheme enhances the performance and is a resource-friendly for the next generation large scale IoT networks.

This paper introduces a new modular cascaded multilevel inverter (MLI) which is composed of a cascaded connection of submodules (SMs). The combination of basic cells (BCs) with polarity changer H-Bridge produces the SMs, which is the basis of the introduced inverter. Owing to its high modularity, the proposed inverter can be extended to reach higher voltage levels. Hence, two extensions are suggested: 1) Extension based on cascading more BCs within each SM, and 2) Extension based on cascading more SMs. Using a set of algorithms, the magnitude of DC voltage sources is determined to synthesize the proper AC side voltage waveform. Furthermore, the proposed topology is optimized in different ways to achieve the desired purposes, such as maximizing the number of voltage levels, minimizing the number of switches and DC sources, and providing the least total standing voltage on the switches. Therefore, in each of the mentioned optimization goals, the optimal structure is obtained. A prototype of the presented MLI is defined and its performance is verified through several simulation studies in MATLAB/Simulink and experimental tests. Besides, a comprehensive comparison is made with the best performance of the existing alternatives to demonstrate the merits and superiorities of the proposed MLI.

Policy-based chameleon hash (PCH) is one of the techniques used for rewriting transaction-level data stored in blockchains. This technique integrates the access policy of the attribute-based encryption (ABE) in the transactions and only allows users with attributes set satisfying the access policy to modify the transactions. However, some operations in the PCH-based rewritable blockchain solution require high computational cost which may impact the performance of user systems, especially on resource-constrained devices. To solve this problem, we propose an online/offline rewritable blockchain with auditable outsourced computation (OO-RB-AOC) scheme. We utilize the ring signature to ensure the credibility of multiple attribute authorities, and adopt the online/offline technique for generating the hash of the rewritable transaction. In addition, expensive computations (e.g., pairings) required for rewriting the transactions can be outsourced to the clouds. The users can rest assured that the computations from the clouds are correct with the audit mechanism of the proposed scheme. On the other hand, the proposed scheme offers a desirable feature for commercial application where the clouds can limit the number of outsourced requests according to the subscription of the users. We also prove the security of the proposed OO-RB-AOC scheme. Finally, we present a theoretical comparison and experimental analysis of the proposed scheme.

The increasing popularity of remote Cloud File Sharing (CFS) has become a major concern for privacy breach of sensitive data. Aiming at this concern, we present a new resource sharing framework by integrating enterprise-side Attribute-Based Access Control/eXtensible Access Control Markup Language (ABAC/XACML) model, client-side Ciphertext-Policy Attribute-Based Encryption (CP-ABE) scheme, and cloud-side CFS service. The framework workflow is provided to support the encrypted-file writing and reading algorithms in accordance with ABAC/XACML-based access policy and attribute credentials. However, an actual problem of realizing this framework is that policy matrix, derived from access policy, seriously affects the performance of existing CP-ABE from Lattice (CP-ABE-L) schemes. To end it, we present an optimal generation algorithm of Small Policy Matrix (SPM), which only consists of small elements, and generates an all-one reconstruction vector. Based on SPM, the improved CP-ABE-L scheme is proposed to reduce the cumulative errors to the minimum. Furthermore, we give the optimal estimation of system parameters to implement a valid Error Proportion Allocation (EPA). Our experiments indicate that our scheme has short size of parameters and enjoys efficient computation and storage overloads. Thus, our new framework with optimization methods is conducive to enhancing the security and efficiency of remote work on CFS.

We study the problem of multi-user dynamic searchable symmetric encryption (DMUSSE) where a data owner stores its encrypted documents on an untrusted remote server and wishes to selectively allow multiple users to access them by issuing keyword search queries. Specifically, we consider the case where some of the users may be corrupted and colluding with the server to extract additional information about the dataset (beyond what they have access to). We provide the first formal security definition for the dynamic setting as well as forward and backward privacy definitions. We then propose SE, the first provably secure DMUSSE scheme and instantiate it in two versions, one based on oblivious data structures and one based on update queues, with different performance trade-offs. Furthermore, we extend SE to support verifiability of results. To achieve this, users need a secure digest initially computed by the data owner and changed after every update. We efficiently accommodate this, without relying on a trusted third party, by adopting a blockchain-based approach for the digests dissemination and deploy our schemes over the permissioned Hyperledger Fabric blockchain. We prototype both versions and experimentally evaluate their practical performance, both as stand-alone systems and running on top of Hyperledger Fabric.

We propose a flexible low complexity design (FLCD) of coded distributed computing (CDC) with empirical evaluation on Amazon Elastic Compute Cloud (Amazon EC2). CDC can expedite MapReduce like computation by trading increased map computations to reduce communication load and shuffle time. A main novelty of FLCD is to utilize the design freedom in defining map and reduce functions to develop asymptotic homogeneous systems to support varying intermediate values (IV) sizes under a general MapReduce framework. Compared to existing designs with constant IV sizes, FLCD offers greater flexibility in adapting to network parameters and significantly reduces the implementation complexity by requiring fewer input files and shuffle groups. The FLCD scheme is the first proposed low-complexity CDC design that can operate on a network with an arbitrary number of nodes and computation load. We perform empirical evaluations of the FLCD by executing the TeraSort algorithm on an Amazon EC2 cluster. This is the first time that theoretical predictions of the CDC shuffle time are validated by empirical evaluations. The evaluations demonstrate a 2.0 to 4.24x speedup compared to conventional uncoded MapReduce, a 12% to 52% reduction in total time, and a wider range of operating network parameters compared to existing CDC schemes., 13 pages, 4 figures

Weakly supervised object detection (WSOD aims to train object detectors by using only image-level annotations. Many recent works on WSOD adopt multiple instance detection networks (MIDN, which usually generate a certain number of proposals and regard proposal classification as a latent model learning within image classification. However, these methods tend to detect salient object, salient object parts and clustered objects due to lack of instance-level annotations during training. Thus a core issue is how to guarantee that the network learn as many objects with precise bounding boxes as possible. In this paper, we address this issue by exploiting the potential of proposal scores during training. We propose an adaptive instance refinement (AIR framework with three novel designs, which can be integrated with MIDN into a single network. Specifically, adaptive instance mining attempts to discover all positive instances according to the score distribution of proposals and their spatial similarity. Adaptive score modulation dynamically adjusts proposal scores to make the network focus more on instances with different difficulties in different training iterations. Adaptive knowledge refinement distills important information from all previous stages by the weighted average of proposal scores. The experimental results on the PASCAL VOC 2007 and 2012 benchmarks and the MS COCO benchmark demonstrate that AIR significantly improves the performance of the original MIDN and achieves the state-of-the-art results.

Workflow scheduling in cloud environments has become a significant topic in both commercial and industrial applications. However, it is still an extraordinarily challenge to generate effective and economical scheduling schemes under the deadline constraint especially for the large scale workflow applications. To address the issue, this paper investigates the cloud workflow scheduling problem with the aim of minimizing the whole cost of workflow execution whereas maintaining its execution time under a predetermined deadline. A novel knowledge-based adaptive discrete water wave optimization (KADWWO) algorithm is developed based on the problem-specific knowledge of cloud workflow scheduling. In the proposed KADWWO, a discrete propagation operator is designed based on the idle time knowledge of hourly-based cost model to adaptively explore the huge search space. The adaptive refraction operator is employed to avoid stagnation and expand the available resource pool. Meanwhile, the dynamic grouping based breaking operator is designed to exploit the excellent block structure knowledge of task allocation scheme and corresponding resource to intensify the local region and accelerate convergence. Extensive simulation experiments on the well-known scientific workflow demonstrate that the KADWWO approach outperforms several recent state-of-the-art algorithms.

Fusion and interaction of multimodal features are essential for video question answering. Structural information composed of the relationships between different objects in videos is very complex, which restricts understanding and reasoning. In this paper, we propose a quaternion hypergraph network (QHGN) for multimodal video question answering, to simultaneously involve multimodal features and structural information. Since quaternion operations are suitable for multimodal interactions, four components of the quaternion vectors are applied to represent the multimodal features. Furthermore, we construct a hypergraph based on the visual objects detected in the video. Most importantly, the quaternion hypergraph convolution operator is theoretically derived to realize multimodal and relational reasoning. Question and candidate answers are embedded in quaternion space, and a Q&A reasoning module is creatively designed for selecting the answer accurately. Moreover, the unified framework can be extended to other video-text tasks with different quaternion decoders. Experimental evaluations on the TVQA dataset and DramaQA dataset show that our method achieves state-of-the-art performance.

Musculoskeletal simulations are useful in biomechanics to investigate the causes of movement disorder, to estimate non-measurable physiological quantities or to study the optimality of human movement. We introduce Bioptim, an easy-to-use Python framework for biomechanical optimal control, handling musculoskeletal models. Relying on algorithmic differentiation and the multiple shooting formulation, Bioptim interfaces nonlinear solvers to quickly provide dynamically consistent optimal solutions. The software is both computationally efficient (C++ core) and easily customizable, thanks to its Python interface. It allows to quickly define a variety of biomechanical problems such as motion tracking/prediction, muscle-driven simulations, parameters optimization, multiphase problems, etc. It is also intended for real-time applications such as moving horizon estimation and model predictive control. Six contrasting examples are presented, comprising various models, dynamics, objective functions and constraints. They include data-driven simulations (i.e., a multiphase muscle driven gait cycle and an upper-limb real-time moving horizon estimation of muscle forces) and predictive simulations (i.e., a muscle-driven pointing task, a twisting somersault with a quaternion-based model, a position controller using external forces, and a multiphase torque-driven maximum-height jump motion).

Constrained operations for autonomous vehicles have been extensively studied in the literature over the recent years. However, to the best of the authors knowledge, all of the existing works address only constant or time-varying constraint functions. In this work, we study path-dependent constraint requirements, which explicitly depend on the path parameter, instead of depending on the time variable directly. This approach is more practical in reality, where the constraint requirements are often shaped by the environment boundaries. From the system users perspectives, it is also much easier to define constraint functions based on the path parameter. A modified version of the universal barrier function is used in the analysis of pathdependent constraint requirements. We show that under the proposed novel control scheme, the vehicles line-of-sight distance and angle error terms can converge into small sets near the equilibrium with a fixed-time convergence rate, while the pathdependent constraint requirements are satisfied at all time. A simulation and an experiment study further demonstrate the efficacy of the proposed scheme.

Smart grid is a typical application of industrial cyber-physical systems (ICPS) in the electric power industry. Due to the exposure to different kinds of uncertainties and unpredictable faults, how to reliably assess the short-term voltage stability (SVS) of smart grids to prevent the occurrence of large-scale blackouts is still of primary concern. To tackle this challenging problem, this article develops a novel machine learning scheme to achieve accurate and interpretable online SVS assessment in two steps. First, it utilizes time-series shapelet transform to extract key dynamics and convert the postfault time series into flat features. Second, it designs a graph convolutional network (GCN) to incorporate these features with topology information for SVS assessment. The GCN explores the spatial-temporal dynamics of power system via graph convolution and introduces a system layer to derive the final assessment result. Compared with conventional methods, this novel scheme makes full use of the spatial-temporal information in SVS dynamics, resulting in higher assessment accuracy and stronger adaptability. Besides, it is capable of discovering certain valuable underlying rules and patterns related to SVS. Test results on the IEEE 39-bus system and real-world Guangdong Power Grid in South China verify the effectiveness of the proposed scheme.

As the backbone of Industry 4.0, industrial cyber-physical systems (ICPSs) that are geographically dispersed, federated, cooperative, and security-critical systems become the center of interest from both industry and academia. In ICPS, there are huge amounts of devices, such as sensors and actuators, which are embedded and networked together to improve the performance of real-time monitoring and control. Reliability and temperature are two important concerns of these embedded and networked devices in ICPS due to their stringent requirement of reliable execution and long lifespan. In this article, we study the problem of maximizing soft-error reliability of CPU- and GPU-integrated embedded platforms deployed in ICPS under the temperature constraint. To speed up the estimation of soft-error rate (SER) and temperature, we train an artificial neural network (ANN) that is able to quickly and accurately derive the system's SER and temperature. To solve the temperature-constrained reliability optimization problem, we propose a feedback control-based task scheduling scheme that adaptively determines the number of tasks admitted in the system and the number of replicas for the admitted tasks. We perform a series of simulation experiments to verify the efficacy of our scheme. The experimental results demonstrate that: 1) the estimated SER and temperature derived by our ANN-based method are very close to the ground-truth data and 2) our proposed feedback control-based task scheduling method can improve system reliability by up to 184.2% with a lower peak temperature when compared with one baseline and two state-of-the-art methods.

To reduce the cost of human and material resources and improve the collaborations among medical systems, research laboratories and insurance companies for healthcare researches and commercial activities, electronic medical records (EMRs) have been proposed to shift from paperwork to friendly shareable electronic records. To take advantage of EMRs efficiently and reduce the cost of local storage, EMRs are usually outsourced to the remote cloud for sharing medical data with authorized users. However, cloud service providers are untrustworthy. In this paper, we propose an efficient, secure, and flexible EMR sharing system by introducing a novel cryptosystem called dual-policy revocable attribute-based encryption and tamper resistance blockchain technology. Our proposed system enables EMRs to be shared at a fine-grained level and allows data users to detect any unauthorized manipulation. Moreover, the key generation center can revoke malicious users without affecting the honest users. We provide the formal security model as well as the concrete scheme with security analysis. The experimental simulation and experimental analysis of our proposed scheme demonstrate that our proposed system has superior performances to the most relevant solutions.

Deep learning methods have achieved significant progress in the presence of correctly annotated datasets in instance segmentation. However, object classes in large-scale datasets are sometimes ambiguous, which easily causes confusion. Besides, limited experience and knowledge of annotators can lead to mislabeled object semantic classes. To solve this issue, a novel method is proposed in this paper, which considers different roles of noisy class labels in different sub-tasks. Our method is based on two basic observations: firstly, the foreground-background annotation of a sample is correct even though its class label is noisy. Secondly, symmetric loss benefits the model robustness to noisy labels but harms the learning of hard samples, while cross entropy loss is the opposite. Based on the two basic observations, in the foreground-background sub-task, cross entropy loss is used to fully exploit correct gradient guidance. In the foreground-instance sub-task, symmetric loss is used to prevent incorrect gradient guidance provided by noisy class labels. Furthermore, we apply contrastive self-supervised loss to update features of all foreground, to compensate for insufficient guidance provided by partially correct labels especially in the highly noisy setting. Extensive experiments conducted with three popular datasets (i.e., Pascal VOC, Cityscapes and COCO) have demonstrated the effectiveness of our method in a wide range of noisy class label scenarios.

In this paper, a new dataset, the driver emotion facial expression (DEFE) dataset for drivers spontaneous emotions analysis is introduced. The dataset includes facial expression recordings from 60 participants during driving. After watching a selected video-audio clip to elicit a specic emotion, each participant completed the driving tasks in the same driving scenario and rated his/her emotional responses during the driving processes from the aspects of dimensional emotion method and discrete emotion method. The study also conducted classication experiments to recognize the scales of arousal, valence, dominance, as well as the emotion category and intensity to establish baseline results for the proposed dataset. Furthermore, this paper compared emotion recognition results difference through facial expressions between dynamic driving and static life scenarios. The results showed signicant differences in the AUs presence of facial expressions between dynamic driving and static life scenarios, Therefore, to accurately recognize the drivers emotions to establish a reliable emotion-aware human-machine interaction system, thereby improving driving safety and comfort, publishing a human emotion dataset specically for the driver is necessary. The proposed dataset will be publicly available so that researchers worldwide can use it to develop and examine their driver emotion analysis methods.

In cloud data sharing systems, Searchable Encryption (SE) schemes ensure data confidentiality with retrieving, but it faces several issues in practice. First, most of the previous Ciphertext-Policy Attribute-Based Keyword Search (CP-ABKS) systems enable users to initiate search requests with a single keyword, which results in many inaccurate results to be returned, thereby wasting computing and bandwidth resources. Second, untrusted cloud servers may return a small portion of incomplete search results to compress communication overhead. Besides, most CP-ABKS schemes only support an unshared multi-owner setting, which incurs a large amount of computational and storage overhead. Furthermore, when the keyword space is a polynomial, most of the previous schemes suffer from offline keyword guessing attacks. To address these issues, we focus on a multi-keyword search scheme which supports the verification of search results without losing efficiency by combining Ciphertext Policy Attribute-Based Encryption (CP-ABE) technology under the shared multi-owner mechanism. We show the security of our scheme, which achieves selective security against offline keyword guessing attacks and guarantees the unforgeability of signatures. The comparison of experimental results illustrates that our scheme is effective and enjoys superior functionalities than the most relevant solutions.

Machine learning (ML) models are increasingly trained with distributed workers possessing heterogeneous resources. In such scenarios, model training efficiency may be negatively affected by \emph{stragglers}---workers that run much slower than others. Efficient model training requires eliminating such stragglers, yet for modern ML workloads, existing load balancing strategies are inefficient and even infeasible. In this paper, we propose a novel strategy, called \emph{semi-dynamic load balancing}, to eliminate stragglers of distributed ML workloads. The key insight is that ML workers shall be load-balanced at \emph{iteration boundaries}, being non-intrusive to intra-iteration execution. Based on it we further develop LB-BSP, an integrated worker coordination mechanism that adapts workers' load to their instantaneous processing capabilities---by right-sizing the sample batches at the synchronization barriers. We have designed distinct load tuning algorithms for ML in CPU clusters, in GPU clusters as well as in federated learning setups, based on their respective characteristics. LB-BSP has been implemented as a Python module for ML frameworks like TensorFlow and PyTorch. Our EC2 deployment confirms that LB-BSP is practical, effective and light-weight, and is able to accelerating distributed training by up to $54\%$ .

We here investigate the secure control of networked control systems developing a new dynamic watermarking (DW) scheme. First, the weaknesses of the conventional DW scheme are revealed, and the tradeoff between the effectiveness of false data injection attack (FDIA) detection and system performance loss is analyzed. Second, we propose a new DW scheme, and its attack detection capability is interrogated using the additive distortion power of a closed-loop system. Furthermore, the FDIA detection effectiveness of the closed-loop system is analyzed using auto/cross-covariance of the signals, where the positive correlation between the FDIA detection effectiveness and the watermarking intensity is measured. Third, the tolerance capacity of FDIA against the closed-loop system is investigated, and theoretical analysis shows that the system performance can be recovered from FDIA using our new DW scheme. Finally, the experimental results from a networked inverted pendulum system demonstrate the validity of our proposed scheme.

In mobile crowdsensing, location-based task recommendation requires each data requester to submit a task-related geometric range to crowdsensing service providers such that they can match suitable workers within this range. Generally, a trusted server (i.e., database owner) should be deployed to protect location privacy during the process, which is not desirable in practice. In this paper, we propose the location privacy-preserving task recommendation (PPTR) schemes with geometric range query in mobile crowdsensing without the trusted database owner. Specifically, we first propose a PPTR scheme with linear search complexity, named PPTR-L, based on a two-server model. By leveraging techniques of polynomial fitting and randomizable matrix multiplication, PPTR-L enables the service provider to find the workers located in the data requester's arbitrary geometric query range without disclosing the sensitive location privacy. To further improve query efficiency, we design a novel data structure for task recommendation and propose PPTR-F to achieve faster-than-linear search complexity. Through security analysis, it is shown that our schemes can protect the confidentiality of workers locations and data requesters' queries. Extensive experiments are performed to demonstrate that our schemes can achieve high computational efficiency in terms of geometric range query.

Federated Learning (FL) is a promising machine learning paradigm to cooperatively train a global model with highly distributed data located on mobile devices. Aiming to optimize the communication efficiency for gradient aggregation and model synchronization among large-scale devices, we propose a relay-assisted FL framework. By breaking the traditional transmission-order constraint and exploiting the broadcast characteristic of relay nodes, we design a novel synchronization scheme named Partial Synchronization Parallel (PSP), in which models and gradients are transmitted simultaneously and aggregated at relay nodes, resulting in traffic reduction. We prove that PSP has the same convergence rate as the sequential synchronization approaches via rigorous analysis. To further accelerate the training process, we integrate PSP with any unbiased and error-bounded compression technologies and prove that the convergence properties of the resulting scheme still hold. Extensive experiments are conducted in a distributed cluster environment with real-world datasets and the results demonstrate that our proposed approach reduces the training time up to 37\% compared to state-of-the-art methods.

Fake check scam is one of the most common attacks used to commit fraud against consumers. This fraud is particularly costly for victims because they generally lose thousands of dollars as well as being exposed to judicial proceedings. Currently, there is no existing solution to authenticate checks and detect fake ones instantly. Instead, banks must wait for a period of more than 48 h to detect the scam. In this context, we propose a blockchain-based scheme to authenticate checks and detect fake check scams. Moreover, our approach allows the revocation of used checks. More precisely, our approach helps the banks to share information about provided checks and used ones, without exposing the banks’ customers’ personal data. We demonstrate a proof of concept of our proposed approach using Namecoin and Hyperledger blockchain technologies.

As sharing of accounts is quite common, the design of efficient recommender schemes for shared accounts has raised much attention recently. Generally speaking, after each login, recommender systems should identify the current user behind and leverage this information to make recommendations. One naive approach is first to identify the identity of the current user and then make recommendations. However, this two-stage based approach may not achieve satisfactory performance. The key is that the recommended items favoring identifying users in the first stage may not be interesting to the users, which can deplete the user's patience quickly and cause early termination of users. To address the problem, we propose a novel recommendation scheme that makes a tradeoff between recommending discriminating items (helpful for identifying the user) and recommending interesting ones to the user (helpful for increasing the number of clicks). Under this scheme, we develop a patience model to capture the user's patience during the recommendation process. Moreover, we incorporate mobile sensor data into our approach to improve the performance of the system. We implemented the above system in an App on mobile devices and carried out extensive experiments. The results demonstrate that our proposed scheme outperforms the existing state-of-the-art approaches.

We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary view. We do so by reformulating view consistency using a differentiable ray consistency (DRC) term. We show that this formulation can be incorporated in a learning framework to leverage different types of multi-view observations e.g. foreground masks, depth, color images, semantics etc. as supervision for learning single-view 3D prediction. We present empirical analysis of our technique in a controlled setting. We also show that this approach allows us to improve over existing techniques for single-view reconstruction of objects from the PASCAL VOC dataset., Comment: To appear at CVPR 2017. Project webpage : https://shubhtuls.github.io/drc/

As the controller parameter adjustment process is simplified significantly by using learning algorithms, the studies about learning-based control attract a lot of interest in recent years. This article focuses on the intelligent servo control problem using learning from desired demonstrations. Compared with the previous studies about the learning-based servo control, a control policy using the broad learning system (BLS) is developed and first applied to a microrobotic system, since the advantages of the BLS, such as simple structure and no-requirement for retraining when new demos' data is provided. Then, the Lyapunov theory is skillfully combined with the complex learning algorithm to derive the controller parameters' constraints. Thus, the final control policy not only can obtain the movement skills of the desired demonstrations but also have the strong ability of generalization and error convergence. Finally, simulation and experimental examples verify the effectiveness of the proposed strategy using MATLAB and a microswimmer trajectory tracking system.

Recent developments in collection, computation and communication have expanded the way of data reporting in intelligent Internet of Things (IoT). However, diversity and complexity of data sources also impose new trust challenge in data collection process since untrust reporters tend to report false or even malicious data, which highlights the need to develop a novel methodology to solve such challenge. Thus, based on this domain, inspired by deterrence theory, this paper proposes a blockchain-based trust system with assistant of drones to deter malicious data reporting in intelligent IoT. Specifically, to deter malicious data reporting, based on blockchain technology, the data sensed by fully-trusted drones is public published on blockchain showing participants the data standards, named as malicious deterrence scheme. This scheme provides a barrier for malicious reporters to arbitrarily publish false data to blockchain, since the false data can be easily detected while they cannot deny. Secondly, to further reduce malicious data reporting, a strict penalty mechanism is proposed to punish malicious reporters who have reported false data to blockchain to reduce the mali-cious data reporting in the following task through punishment. Thirdly, note that the sensing of data standard generates addi-tional costs, therefore, a drone flight route scheme based on a simper Deep Reinforcement Learning with Multi-head Attention mechanism (MA-DRL) is designed to reduce the flight distance for drones. Finally, extensive experiments demonstrate efficiency of our proposed system in terms of reducing malicious data reporting in advance as well as reducing drone flight distance.

At present, under the condition of privacy-preserving, vertical federated learning (VFL) has played an important role in training the machine learning models in the application scenarios, such as medical prediction, fraud detection, in which the data is distributed vertically. Random forest is one of the most widely used machine learning methods in VFL, which has the advantages of strong predictive performance, availability, and the ability to parallel tasks. However, current research on privacy-preserving of vertical federated random forest is limited, and none of them can achieve the application level of security, that is, in a system where users are dynamically changing, not only privacy can be preserved, but also data integrity can be verified. Therefore, we propose a verifiable privacy-preserving scheme (VPRF) based on vertical federated random forest, in which the users are dynamic change. Firstly, we design homomorphic comparison and voting statistics algorithms based on multi-key homomorphic encryption for privacy preservation. Then, we propose a multi-client delegated computing verification algorithm to make up for the disadvantage that the above algorithms cannot verify data integrity. Finally, we used the datasets in UCI machine learning warehouse to evaluate the propose scheme. The experiment results indicate that our scheme is more efficient than the existing ones that can achieve the same security level.

This paper presents the field programmable gate array (FPGA) implementation of a particle swarm optimization (PSO) based nonlinear model predictive control (NMPC) for applications with millisecond timescales and resource-constrained embedded systems. A custom hardware circuit architecture of NMPC controller, which mainly includes phase locking loop (PLL) clock, universal asynchronous receiver transmitter (UART) interface, trigonometric function, random number generator, objective function, PSO solver modules, is implemented on FPGA based on a hardware description language (HDL) specification. It employs parallelism, pipelining, and specialized numerical formats to enhance the online computation performance of NMPC. And the partial parallel expansion calculations of fitness (objective) function and particle position update are adopted for trading off the computational performance against resource usage. The hardware-in-the-loop experimental results through controlling a wheeled mobile robot model demonstrate that the design is capable of computing the required control action in real-time by using a midrange FPGA, while still offering good control performance.