Search

The Aerial Internet-of-Things (Aerial-IoT) systems, deploying sensors on high-altitude platforms, e.g., drones, parachutes, and aircrafts, are a crucial monitor due to its agile maneuverability and augmentation of observation, collection, and communication. As such, the measurement accuracy and requirements of Aerial-IoT are far beyond the ability of general commercial-off-the-shelf sensors, especially in the high-altitude environment, where environmental factors (air pressure, temperature, humidity, wind movement, etc.) tend to change rapidly and lead to highly deviated readings. In this article, we tackle this challenge. First, we introduce our designed measurement system for Aerial-IoT. Then, to compensate for the low data quality and calibrate the deviation data from sensors, we take into account the inherent correlations and interaction between sensor data and environmental factors, and construct a data calibration model, called data calibration based on the neural network (DC-NN). Finally, to illustrate the effectiveness of our system, we carry out a real-world implementation by deploying sensors on the surface of parachutes in a dynamic airdrop environment. Extensive experiments on temperature-humidity-material-tensile-testing (THMTT) and high-altitude airdrop are conducted to show the significant improvements of our proposed DC-NN model.

This paper presents an effective and efficient framework for Crowd-assisted Mobile Similarity Retrieval of the large-scale medical images in the resource-constraint mobile telemedicine systems (MTS), called the CMSR. The CMSR processing works as follows: when a user submits a retrieval medical image IR, a buffer checking processing is first invoked to check if the full (or partial) retrieval results have been cached in the buffer previously. After that, a parallel image data filtering and refinement processing is conducted at a master node level. Finally, the candidate images are concurrently validated by a mCrowd system to derive an answer set that is transmitted to the retrieval node. To better facilitate the effective and efficient CMSR processing, three enabling techniques, i.e., category-based image data interleaving placement scheme, hindex-support image filtering algorithm and a kNN-based buffering scheme are developed. To improve the retrieval throughput, finally, we propose an extension of the CMSR method called mCMSR to optimize the multiple CMSRs. The experimental results show that the performances of the CMSR and the mCMSR methods are: 1) effective in improving the retrieval accuracy; 2) efficient in minimizing the response time by decreasing the network transmission cost while increasing the parallelism of I/O and CPU.

Crowd flow prediction has become a strategically important task in urban computing, which is the prerequisite for traffic management, urban planning and public safety. However, due to variousness of crowd flows, multiple hidden correlations among urban regions affect the flows. Besides, crowd flows are also influenced by the distribution of Points-of-Interests (POIs), transitional functional zones, environmental climate, and different time slots of the dynamic urban environment. Thus, we exploit multiple correlations between urban regions by considering the mentioned factors comprehensively rather than the geographical distance and propose multi-graph convolution gated recurrent units (MGCGRU) for capturing these multiple spatial correlations. For adapting to the dynamic mobile data, we leverage multiple spatial correlations and the temporal dependency to build an urban flow prediction framework that uses only a little recent data as the input but can mine rich internal modes. Hence, the framework can mitigate the influence of the instability of data distributions in highly dynamic environments for prediction. The experimental results on two real-world datasets in Shanghai show that our model is superior to state-of-the-art methods for crowd flow prediction.

Many famous attacks take web browsers as transmission channels to make the target computer infected by malwares, such as watering hole and domain name hijacking. In order to protect the data transmission, the SSL/TLS protocol has been widely used to defeat various hijacking attacks. However, the existence of such encryption protection makes the security software and devices confront with the difficulty of analyzing the encrypted malicious traffic at endpoints. In order to better solve this kind of situation, this paper proposes a new efficient and transparent method for large-scale automated TLS traffic analysis, named as hyper TLS traffic analysis (HTTA). It extracts multiple types of valuable data from the target system in the hyper mode and then correlates them to decrypt the network packets in real time, so that overall data correlation analysis can be performed on the target. Additionally, we propose an aided reverse engineering method to support the analysis, which can rapidly identify the target data in different versions of the program. The proposed method can be applied to the endpoints and cloud platforms; there are no trust risk of certificates and no influence on the target programs. Finally, the real experimental results show that the method is feasible and effective for the analysis, which leads to the lower runtime overhead compared with other methods. It covers all the popular browser programs with good adaptability and can be applied to the large-scale analysis.

Can physical concepts and laws emerge in a neural network as it learns to predict the observation data of physical systems? As a benchmark and a proof-of-principle study of this possibility, here we show an introspective learning architecture that can automatically develop the concept of the quantum wave function and discover the Schrodinger equation from simulated experimental data of the potential-to-density mappings of a quantum particle. This introspective learning architecture contains a machine translator to perform the potential to density mapping, and a knowledge distiller auto-encoder to extract the essential information and its update law from the hidden states of the translator, which turns out to be the quantum wave function and the Schrodinger equation. We envision that our introspective learning architecture can enable machine learning to discover new physics in the future.

This study is about the manufacturing of a personified automatic robotic lawn mower with image recognition. The system structure is that the platform above the crawler tracks is combined with the lawn mower, steering motor, slide rail, and webcam to achieve the purpose of personification. Crawler tracks with a strong grip and good ability to adapt to terrain are selected as a moving vehicle to simulate human feet. In addition, a lawn mower mechanism is designed to simulate the left and right swing of human mowing to promote efficiency and innovation, and then human eyes are replaced by Webcam to identify obstacles. A human-machine interface is added so that through the mobile phone remote operation, users can choose a slow mode, inching mode, and obstacle avoidance mode on the human-machine interface. When the length of both sides of the rectangular area is input to the program, the automatic robotic lawn mower will complete the instruction according to the specified path. The chip of a Digital Signal Processor (DSP) TMS320F2808 is used as the core controller, and Raspberry Pi is used as image recognition and human-machine interface design. This robot can reduce labor costs and improve the efficiency of mowing by remote control. In addition to the use as an automatic mower on farms, this study concept can also be used in the lawn maintenance of golf courses and school playgrounds.

We provide a construction for categorical representation learning and introduce the foundations of "$\textit{categorifier}$". The central theme in representation learning is the idea of $\textbf{everything to vector}$. Every object in a dataset $\mathcal{S}$ can be represented as a vector in $\mathbb{R}^n$ by an $\textit{encoding map}$ $E: \mathcal{O}bj(\mathcal{S})\to\mathbb{R}^n$. More importantly, every morphism can be represented as a matrix $E: \mathcal{H}om(\mathcal{S})\to\mathbb{R}^{n}_{n}$. The encoding map $E$ is generally modeled by a $\textit{deep neural network}$. The goal of representation learning is to design appropriate tasks on the dataset to train the encoding map (assuming that an encoding is optimal if it universally optimizes the performance on various tasks). However, the latter is still a $\textit{set-theoretic}$ approach. The goal of the current article is to promote the representation learning to a new level via a $\textit{category-theoretic}$ approach. As a proof of concept, we provide an example of a text translator equipped with our technology, showing that our categorical learning model outperforms the current deep learning models by 17 times. The content of the current article is part of the recent US patent proposal (patent application number: 63110906)., Comment: Fixed some typos. 16 pages. Comments are welcome

With the rapid development of the Internet, security issues in cyberspace have received more and more attention, and network security situation awareness has become a research focus. This paper proposes a network security situation awareness framework based on situation fusion, which decomposes the network security situation into two parts: the host security situation and the network attack situation. First, the host asset information and network topology information are used to calculate the weight vector of all hosts to make the weight setting more reasonable. Then using CVSS to evaluate the host security situation value. Meanwhile, security events are extracted from the alarm information of the intrusion detection system, and we designed threat downgrading rules and escalation rules based on system environment matching and the attacker’s willingness, so as to calculate the threat of network attacks, and ultimately integrated into the overall network security situation value. The results of the case analysis show that the framework proposed in this paper can quantify the security situation better.

With the popularity of unmanned aerial vehicles (UAVs) and the development of the network technology, the UAV network has become a new research hotspot. However, due to various factors such as terrain, transmission distance, and hacker attacks, UAV network needs to reconstruct the network architecture and restore data according to the actual situation. The blockchain technology can be applied to the UAV network for its high reliability and distributed characteristics. Therefore, this paper proposes a blockchain-based adaptive reconstruction technology framework for UAV networks. Also, to solve possible data damage or missing problems in UAV networks, a data recovery and update approach as well as the corresponding algorithms are given. Furthermore, this paper uses the blockchain to record the behavior of the UAV nodes in the UAV network, and proposes an algorithm to check whether the UAV is malicious or malfunctioning. So that the ground control station (GCS) can reconstruct the UAV network communication link.

With the emergency of the Internet of Things in all walks of life, its security problems are getting more attention. Different devices need to access users’ data from different platforms. However, as different platforms are developed based on different security architectures, when the security policies of different platforms are supposed to be composed, it will result in new vulnerabilities and bring security risks. To address this problem, a new cross-domain access control framework based on OAuth 2.0 is proposed in this paper. The framework realizes secure and flexible management of authentication and authorization of cross-platform access control. The security domain token is used for entities to access and share the resources of each security domain, which solves the cross-domain security problem. The proposed approach is formally modeled in Coq theorem prover, and the results show that the proposed access control mechanism satisfies the security properties.

In library applications, radio frequency indentification (RFID) technology, sensors, and wireless transmission networks have been applied to various services such as self-service checkout and return systems, electronic reader cards, intelligent bookshelves, intelligent monitoring of library premises, augmented reality (AR) interactive picture books, physical corridors, and seat reservations; in regional library alliances, real crossregional and cross-system alliance cooperation through IoT technology is also becoming increasingly important. Continuous information resource sharing is an important means to maximize the effectiveness of library information resources and meet the information needs of various users. The development of IoT technology opens new ideas and methods for information resource sharing in regional library alliances, effectively expanding the scope of information resource sharing and improving the efficiency of information resource sharing. This paper briefly presents the relationship, architecture, and key technologies of IoT technology and the definition, characteristics, and types of regional library consortium and content. Analysis of the characteristics and principles of regional library consortium information resource sharing is in the context of IoT and the corresponding studies on information sharing between regional library consortia at home and abroad. We also propose strategies to establish a specialized agency for information resource sharing, establish a sound investment mechanism for information resource sharing, ensure the security of information resource sharing of the regional library consortium, and increase the publicity and training capacity of information resource sharing of the regional library consortium.

Aiming at the main problems of terminal data storage, long service delay and transmission security of (WBAN) in wireless body area network, combined with fog computing distributed computing model, this paper proposes an intelligent medical service framework in wireless body area network, which is divided into intelligent medical terminal layer, fog computing central layer and cloud computing data storage layer, and proposes a real-time encrypted transmission scheme for data transmission between each layer. Security analysis shows that the framework and scheme can reduce the cost and delay, while ensuring the security and dispersion of data transmission between layers.

The exact holographic mapping (EHM) provides an explicit duality map between a conformal field theory (CFT) configuration and a massive field propagating on an emergent classical geometry. However, designing the optimal holographic mapping is challenging. Here we introduce the neural network renormalization group as a universal approach to design generic EHM for interacting field theories. Given a field theory action, we train a flow-based hierarchical deep generative neural network to reproduce the boundary field ensemble from uncorrelated bulk field fluctuations. In this way, the neural network develops the optimal renormalization group transformations. Using the machine-designed EHM to map the CFT back to a bulk effective action, we determine the bulk geodesic distance from the residual mutual information. We apply this approach to the complex $\phi^4$ theory in two-dimensional Euclidian spacetime in its critical phase, and show that the emergent bulk geometry matches the three-dimensional hyperbolic geometry., Comment: 9 pages, 7 figures + appendix

Due to the centralization of communication in the management of data generated by diverse Internet of Thing (IoT) devices, there is a lack of reliability when data is being transferred and stored. Among errors caused by various behaviors, Silent Data Corruption (SDC) error, owing to stealthy destruction without error prompt, is one of the most difficult data consistency problems in the storage system, whether it is a traditional multi-control, distributed storage, or public cloud storage. Nowadays, for SDC error detection, extracting instruction features to analyze vulnerabilities of programs or instructions has still not been fully explored. Literature generally just count the number of possible features, without mining the inter-characteristic of the instruction and correlation between them. Thus, we propose a method of SDC-causing Error Detection based on Support Vector Regression (SED-SVR) for fully exploiting the correlation between data features. Specifically, firstly, we extract instruction features based on the SDC vulnerability of program instructions by analyzing results of fault injections. Secondly, we establish the instruction SDC vulnerability prediction model based on SVR and propose our SED-SVR model. Thirdly, according to the predicted values of SDC vulnerability, we develop some solutions for faults tolerance of target programs by different granularity of instruction redundancy. The experimental results show that our SED-SVR has higher fault detection rate with lower performance overhead.

The wideband spectrum estimation is an essential step in the wireless network. In order to avoid employing power-hungry high-rate analog-to-digital converters (ADCs), the CS-based sub-Nyquist sampling approaches are used to estimate the wideband spectrum. In this paper, we propose a sub-Nyquist sampling system based on the analog to information converter (AIC), and the proposed system is constructed by multiple parallel channels with a banks of low pass filters. The system model is constructed in the time domain. To estimate the power spectrum, we define a new power spectrum of samples with a finite length, called the circular power spectrum (CPS), served as the aim we strive to estimate. The defined CPS can clearly reflect the power of the signal varying with frequency and is also with the same length as the equivalent digital samples. The experimental results indicate that the defined CPS can be successfully estimated from samples captured by the proposed sub-Nyquist sampling system whose overall sampling rate is much lower than the Nyquist rate.

Multi-focus image fusion consists in the integration of the focus regions of multiple source images into a single image. At present, there are still some common problems in image fusion methods, such as block artifacts, artificial edges, halo effects, and contrast reduction. To address these problems, a novel, to the best of our knowledge, multi-focus image fusion method using energy of Laplacian and a deep neural network (DNN) is proposed in this paper. The DNN is composed of multiple denoising autoencoders and a classifier. The Laplacian energy operator can effectively extract the focus information of source images, and the trained DNN model can establish a valid mapping relationship between source images and a focus map according to the extracted focus information. First, the Laplacian energy operator is used to perform focus measurement for two source images to obtain the corresponding focus information maps. Then, the sliding window technology is used to sequentially obtain the windows from the corresponding focus information map, and all of the windows are fed back to the trained DNN model to obtain a focus map. After binary segmentation and small region filtering, a final decision map with good consistency is obtained. Finally, according to the weights provided by the final decision map, multiple source images are fused to obtain a final fusion image. Experimental results demonstrate that the proposed fusion method is superior to other existing ones in terms of subjective visual effects and objective quantitative evaluation.

This paper discusses the information management and service of open scientific data in university library in the big data era and analyze the open channels and application and service method of data information resource for the university library to get scientific data and information resources.

In order to reduce the energy consumption in the cloud data center, it is necessary to make reasonable scheduling of resources in the cloud. The accurate prediction for cloud computing load can be very helpful for resource scheduling to minimize the energy consumption. In this paper, a cloud load prediction model based on weighted wavelet support vector machine(WWSVM) is proposed to predict the host load sequence in the cloud data center. The model combines the wavelet transform and support vector machine to combine the advantages of them, and assigns weight to the sample, which reflects the importance of different sample points and improves the accuracy of load prediction. In order to find the optimal combination of the parameters, we proposed a parameter optimization algorithm based on particle swarm optimization(PSO). Finally, based on the WWSVM model, a load prediction algorithm is proposed for cloud computing using PSO-based weighted support vector machine. The Google cloud computing data set is used to verify the algorithm proposed in this paper by experiments. The experiment results indicate that comparing with the wavelet support vector machine, autoregressive integrated moving average, adaptive network-based fuzzy inference system and tuned support vector regression, the proposed algorithm is superior to the other four prediction algorithms in prediction accuracy and efficiency.

Community discovery is a leading research topic in social network analysis. In this paper, we present an ego-network probabilistic graphical model (ENPGM) which encodes users’ feature similarities and the causal dependencies between users’ profiles, communities, and ego networks. The model comprises three parts: a profile similarity probabilistic graph, social circle vector, and relationship probabilistic vector. Using Bayesian networks, the profile similarity probabilistic graph considers information about both the features of individuals and network structures with low memory usage. The social circle vector is proposed to describe both the alters belonging to a community and the features causing the community to emerge. The relationship probabilistic vector represents the probability that an ego network forms when given a set of user profiles and a set of circles. We then propose a parameter-learning algorithm and the ego-network probabilistic criterion (ENPC) for extracting communities from ego networks with some missing feature values. The ENPC score balances both the positive and negative impacts of social circles on the probabilities of forming an ego network. Experimental results using Facebook, Twitter, and Google+ datasets indicate that the ENPGM and community learning algorithms can predict social circles with similar quality to the ground-truth communities.

As a key component of building management and security, occupancy inference through smart sensing has attracted a lot of research attention for nearly two decades. Recently, a cutting edge technique visible light sensing (VLS) that utilizes the LED luminaires as light sensors has shown its promising application potentials in occupancy inference as it piggybacks on pervasive lighting infrastructure without extra equipment deployment. Although existing inference algorithms based on the VLS data set can achieve high accuracy, the performance degrades when the occupants are moving. This paper focuses on the occupancy inference issue and presents an ensemble learning algorithm to improve the inference accuracy. We use heterogeneous learning algorithms to generate diverse learners. Consequently, we adopt forward sequential pruning to enhance the ensemble that pursues inference error minimization. We conduct extensive experiments based on the field data. The experiment results show that the proposed algorithm is able to improve inference accuracy, especially for highly dynamic occupancy data set. Published version

To address the problem of detecting malicious codes in malware and extracting the corresponding evidences in mobile devices, we construct a consortium blockchain framework, which is composed of a detecting consortium chain shared by test members and a public chain shared by users. Specifically, in view of different malware families in Android-based system, we perform feature modeling by utilizing statistical analysis method, so as to extract malware family features, including software package feature, permission and application feature, and function call feature. Moreover, for reducing false-positive rate and improving the detecting ability of malware variants, we design a multi-feature detection method of Android-based system for detecting and classifying malware. In addition, we establish a fact-base of distributed Android malicious codes by blockchain technology. The experimental results show that, compared with the previously published algorithms, the new proposed method can achieve higher detection accuracy in limited time with lower false-positive and false-negative rates.

The widespread adoption of smart contracts demands strong security guarantees. Our work is motivated by the problem of statically checking potential information tampering in smart contracts. This paper presents a security type verification framework for smart contracts based on type systems. We introduce a formal calculus for reasoning smart contract operations and interactions and design a lightweight type system for checking secure information flow in Solidity (a popular high-level programming language for writing smart contracts). The soundness of our type system is proved w.r.t. non-interference. In addition, a type verifier based on our type system is proposed to assist users to automatically find an optimal secure type assignment for state variables, which makes contracts well-typed. We also prove that finding the optimal secure type assignment is theoretically a NP-complete problem. We develop a prototype implementation of the Solidity Type Verifier ( STV ) including the Solidity Type Checker ( STC ) based on the K-framework, and demonstrate its effectiveness on real-world smart contracts.

Cloud computing is growing in popularity among computing paradigms, but in practice the energy consumption of the cloud data centers is very high. In this paper, we build the resource model of the cloud data center and the dynamic power model of the physical machine, and then propose a three-dimensional virtual resource scheduling method for energy saving in cloud computing (TVRSM), in which the process of virtual resource scheduling are divided into three stages: virtual resource allocation, virtual resource scheduling and virtual resource optimization. For the different objective of each stage, we design three different algorithms, respectively. The simulation results prove that the TVRSM is able to efficiently allocate and manage the virtual resources in the cloud data center. And compared with other traditional algorithms, the TVRSM can effectively reduce the energy consumption of the cloud data center and significantly minimize the amount of violations of Service Level Agreement (SLA). We propose a three-dimensional virtual resource (VR) scheduling method.We present a bin packing problem based heuristics VR allocation algorithm.We demonstrate a multi-dimensional power-aware based VR scheduling algorithm.We put forward a VR optimization algorithm to reduce energy consumption.The simulation results demonstrate the effectiveness of the proposed method.

In this paper, a model-driven software collaborative modeling method is proposed, and a software collaborative modeling framework on model assembly and model updating is established. The composability of models, the integrity of model assembly and the consistency of model updating are studied from two aspects: model assembly mechanism and model updating mechanism. The collaborative modeling protocol is defined, and six collaborative relationship stereotypes are introduced to add collaborative semantics to the model based on the extensible mechanism of UML. The algorithm of model assembly and integrity checking is proposed and the collaborative modeling of multiple clients is implemented. The algorithm of model updating and consistency checking is proposed to solve the problem of model updating in collaborative modeling.

Objective. To explore the mechanism of action of Bu-Fei-Yi-Shen formula (BFYSF) in treating chronic obstructive pulmonary disease (COPD) based on network pharmacology analysis and molecular docking validation. Methods. First of all, the pharmacologically active ingredients and corresponding targets in BFYSF were mined by the Traditional Chinese Medicine Systems Pharmacology (TCMSP) database, the analysis platform, and literature review. Subsequently, the COPD-related targets (including the pathogenic targets and known therapeutic targets) were identified through the TTD, CTD, DisGeNet, and GeneCards databases. Thereafter, Cytoscape was employed to construct the candidate component-target network of BFYSF in the treatment of COPD. Moreover, the cytoHubba plug-in was utilized to calculate the topological parameters of nodes in the network; then, the core components and core targets of BFYSF in the treatment of COPD were extracted according to the degree value (greater than or equal to the median degree values for all nodes in the network) to construct the core network. Further, the Autodock vina software was adopted for molecular docking study on the core active ingredients and core targets, so as to verify the above-mentioned network pharmacology analysis results. Finally, the Omicshare database was applied in enrichment analysis of the biological functions of core targets and the involved signaling pathways. Results. In the core component-target network of BFYSF in treating COPD, there were 30 active ingredients and 37 core targets. Enrichment analysis suggested that these 37 core targets were mainly involved in the regulation of biological functions, such as response to biological and chemical stimuli, multiple cellular life processes, immunity, and metabolism. Besides, multiple pathways, including IL-17, Toll-like receptor (TLR), TNF, and HIF-1, played certain roles in the effect of BFYSF on treating COPD. Conclusion. BFYSF can treat COPD through the multicomponent, multitarget, and multipathway synergistic network, which provides basic data for intensively exploring the mechanism of action of BFYSF in treating COPD.

With the widespread use of mobile embedded devices in the Internet of Things, mobile office, and edge computing, security issues are becoming more and more serious. Remote attestation, one of the mobile security solutions, is a process of verifying the identity and integrity status of the remote computing device, through which the challenger determines whether the platform is trusted by discovering an unknown fingerprint. The remote attestation on the mobile terminal faces many security challenges presently because there is a lack of trusted roots, devices are heterogeneous, and hardware resources are strictly limited. To ARM’s mobile platform, we propose a mobile remote attestation scheme based on ARM TrustZone (TZ-MRAS), which uses the highest security authority of TrustZone to implement trusted attestation service. Compared with the existing mobile remote attestation scheme, it has the advantages of wide application, easy deployment, and low cost. To defend against the time-of-check-to-time-of-use (TOC-TOU) attack, we propose a probe-based dynamic integrity measurement model, ProbeIMA, which can dynamically detect unknown fingerprints that generate during kernel and process execution. Finally, according to the characteristics of the improved dynamic measurement model, that is, the ProbeIMA will expand the scale of the measurement dataset, an optimized stored measurement log construction algorithm based on the locality principle (LPSML) is proposed, which has the advantages of shortening the length of the authentication path and improving the verification efficiency of the platform configuration. As a proof of concept, we implemented a prototype for each service and made experimental evaluations. The experimental results show the proposed scheme has higher security and efficiency than some existing schemes.

To protect core functions, applications often utilize the countermeasure techniques such as antidebugging to avoid analysis by outsiders, especially the malware. Dynamic binary instrumentation is commonly used in the analysis of binary programs. However, it can be easily detected and has stability and applicability problems as it involves program rewriting and just-in-time compilation. This paper proposes a new lightweight analysis method for binary programs with the assistance of hardware features and the operating system kernel, named BAHK, which can automatically analyze the target program by stealth and has wide applicability. With the support of underlying infrastructures, this paper designs several optimization strategies and specific analysis approaches at instruction level to reduce the impact of fine-grained analysis on the performance of target program so that it can be well applied in practice. The experimental results show that the proposed method has good stealthiness, low memory consumption, and positive user experience. In some cases, it shows better analysis performance than the traditional dynamic binary instrumentation method. Finally, the real case studies further show its feasibility and effectiveness.

The complexity and diversity of cloud computing bring about cloud faults, which affect the quality of services. Existing fault detection methods suffer problems such as low efficiency and low accuracy. In order to improve the reliability of the cloud data center, a fault detection algorithm based on weighted one-class support vector machine (WOCSVM) is proposed to detect and identify the host faults in the cloud data center. Specifically, first, we conduct correlation analysis among monitoring metrics and select key ones for reducing the complexity. Second, for imbalanced monitoring dataset, one-class support vector machine is used to detect and identify host faults, and a weight allocation strategy is proposed to assign weights to the samples, which describes the importance of different sample points in order to improve detection accuracy on potential faults. Finally, for the purpose of increasing the accuracy further, the parameters are set via a parameter optimization algorithm based on quantum-behaved particle swarm optimization (QPSO). Furthermore, experiments by comprising with similar algorithms, demonstrate the superiority of our algorithm under different classification indicators.

Aiming at the problem of host load forecasting in mobile cloud computing, the Long Short Term Memory networks (LSTM) is introduced, which is suitable for the complex and long-time series data of the cloud environment and a load forecasting algorithm based on Glowworm Swarm Optimization LSTM neural network is proposed. Specifically, we build a mobile cloud load forecasting model using LSTM neural network, and the Glowworm Swarm Optimization Algorithm (GSO) is used to search for the optimal LSTM parameters based on the research and analysis of host load data in the mobile cloud computing data center. Finally, the simulation experiments are implemented and similar prediction algorithms are compared. The experimental results show that the prediction algorithms proposed in this paper are superior to similar prediction algorithms in prediction accuracy.

Aiming at the problem of insufficient memory in the real-time processing of SAR imaging on embedded TX2, this paper studies a design optimization scheme of fixed-point imaging algorithm on TX2. In order to ensure the accuracy, this paper only performs fixed-point processing on the FFT. According to the characteristics of the algorithm, the memory multiplexing method is adopted to effectively reduce the occupation of the work area buffer. A large number of registers are used to improve computing performance. The results show that the fixed-point FFT processing scheme can achieve a hundred times faster than the Intel Xeon CPU, and the memory footprint is less.

Autonomous navigation systems on unmanned aerial vehicles (UAVs) equipped with multiple sensors are essential to various applications in the smart city and intelligent transportation. However, the general autonomous navigation models are markedly influenced by the prior knowledge from training environments, which in turn are not applicable in unknown environments. To address this issue, we propose an online autonomous UAV navigation system named as multi-sensor data-fusion-based autonomous navigation (MDFAN) system for unknown flight environments, including the collision avoidance and path planning. Specifically, first, the newly MDFAN system formulates the navigation problem as a decision-making path planning problem to reduce the dependence of prior knowledge of the flight environment. Secondly, we develop a multi-sensor data-fusion-based method to extract more effective local environment information for mining the inherent inter-relationship between the local environment information and the current state of the UAV. Thirdly, we propose a deep reinforcement learning method for handling uncertain situations of the unknown environment. Finally, we validated our method both on the simulated and real-world environments.

With the rapid development and popularization of cloud computing, how to reduce the energy consumption of cloud computing data centers and improve the utility of data centers is one of the urgent problems to be solved. In this paper, focusing on four dimensions of CPU, memory, network bandwidth, and disk, we establish a virtual machine(VM) scheduling model based on multi-objective optimization, which can minimize the data center energy consumption and maximize data center utility. And we propose a VM scheduling algorithm based on improved particle swarm optimization(PSO) to solve the model. The improvement includes adaptive parameter adjustment. Finally, the effectiveness of the proposed algorithm is verified by simulation experiments. The experimental results show that the adaptive VM scheduling algorithm based on improved PSO can improve the efficiency of the data center while reducing energy consumption.

The quantum neural network is one of the promising applications for near-term noisy intermediate-scale quantum computers. A quantum neural network distills the information from the input wavefunction into the output qubits. In this Letter, we show that this process can also be viewed from the opposite direction: the quantum information in the output qubits is scrambled into the input. This observation motivates us to use the tripartite information, a quantity recently developed to characterize information scrambling, to diagnose the training dynamics of quantum neural networks. We empirically find strong correlation between the dynamical behavior of the tripartite information and the loss function in the training process, from which we identify that the training process has two stages for randomly initialized networks. In the early stage, the network performance improves rapidly and the tripartite information increases linearly with a universal slope, meaning that the neural network becomes less scrambled than the random unitary. In the latter stage, the network performance improves slowly while the tripartite information decreases. We present evidences that the network constructs local correlations in the early stage and learns large-scale structures in the latter stage. We believe this two-stage training dynamics is universal and is applicable to a wide range of problems. Our work builds bridges between two research subjects of quantum neural networks and information scrambling, which opens up a new perspective to understand quantum neural networks., 6 pages, 4 figures + 9 pages of supplemental material

In order to improve the fault monitoring performance of grounding electrode lines in high voltage DC (HVDC) transmission systems, a new grounding electrode line protection based on multi-band voltage amplitude integration is proposed in this paper. Firstly, the voltage spectrum under normal operation and fault were analyzed. It was found that the voltage under different frequency bands will change greatly after fault occurred in grounding electrode line. Based on this, a new fault identification criterion using the voltage amplitude integration is proposed in this paper. A large number of simulation experiments based on PSCAD/EMTDC show that this method can effectively identify various faults on the grounding electrode line, which is less affected by the fault resistance and has a good application prospect.

In the state-of-the-art methods for (large) image transmission, no user interaction behaviors (e.g., user tapping) can be actively involved to affect the transmission performance (e.g., higher image transmission efficiency with relatively poor image quality). So, to effectively and efficiently reduce the large image transmission costs in resource-constraint mobile wireless networks (MWN), we design a content-based and bandwidth-aware Interactive large Image Transmission method in MWN, called the I it. To the best of our knowledge, this is the first study on the interactive image transmission. The whole transmission processing of the I it works as follows: before transmission, a preprocessing step computes the optimal and initial image block (IB) replicas based on the image content and the current network bandwidth at the sender node. During transmission, in case of unsatisfied transmission efficiency, the user’s anxiety to preview the image can be implicitly indicated by the frequency of tapping the screen. In response, the transmission resolutions of the candidate IB replicas can be dynamically adjusted based on the user anxiety degree (UAD). Finally, the candidate IB replicas are transmitted with different priorities to the receiver for reconstruction and display. The experimental results show that the performance of our approach is both efficient and effective, minimizing the response time by decreasing the network transmission cost while improving user experiences.

To effectively and efficiently reduce the transmission costs of large medical image in (mobile) telemedicine systems, we design and implement a professionally user-adaptive large medical image transmission method called UMIT. Before transmission, a preprocessing step is first conducted to obtain the optimal image block (IB) replicas based on the users’ professional preference model and the network bandwidth at a master node. After that, the candidate IBs are transmitted via slave nodes according to the transmission priorities. Finally, the IBs can be reconstructed and displayed at the users’ devices. The proposed method includes three enabling techniques: (1) user’s preference degree derivation of the medically useful areas, (2) an optimal IB replica storage scheme, and (3) an adaptive and robust multi-resolution-based IB replica selection and transmission method. The experimental results show that the performance of our proposed UMIT method is both efficient and effective, minimizing the response time by decreasing the network transmission cost.

Risk assessment at the early stage of software development can effectively reduce potential security flaws in the software, thus reduce the cost of testing and maintenance. However, there are very few standardized risk assessment methods toward the design models of security-critical RTESs (real-time embedded systems). This paper defines a formal model called OMR (Object-Message-Role) using Z notation for the security-critical RTESs. Comparing with the existing models for RTESs, OMR is able to specify both the functional and security aspects of the system as an integrated model, which directly provides the input for risk assessment. A risk assessment method RAMES (risk assessment method for embedded systems) based on OMR is then proposed. RAMES is complianced with the risk management process standardized by ISO 31000. To perform the risk analysis in RAMES, an algorithm RAOMR is designed based on the analysis of the message flows and security constraints in OMR. The illustration of a case study shows that RAMES is able to evaluate the risk level of the system model, and locate the high-risky objects and messages.

In this paper, we study the optimal design of weakly secure linear network coding (WSLNC) against wiretapping attack. Specifically, given a set of wiretapped links, we investigate how to maximize the weakly secure transmission rate of multiple unicast streams between a pair of source and destination nodes, and how to minimize the size of the required finite field, over which the WSLNC can be implemented. In our study, we apply a novel approach that integrates the WSLNC design and the transmission topology construction. We first provide theoretical analysis and prove that the problem of finding the optimal transmission topology is NP-hard. We then develop efficient algorithms to find optimal and sub-optimal topologies in different scenarios. With the transmission topology, we design WSLNC schemes and theoretically analyze the relationships between the transmission topology and two important system factors: (1) the size of the finite field, and (2) the probability that a random linear network coding is weakly secure. Based on the relationships, we further improve our algorithms to address the two system factors, while keeping the same maximal STR. Extensive simulation results show that the proposed heuristic algorithms can achieve good performance in various scenarios.

Wireless sensor networks (WSNs) are increasingly deployed for mission-critical applications such as emergency management and health care, which impose stringent requirements on the communication performance of WSNs. To support these applications, it is crucial to model and measure the effect of wireless interference, which is the major factor that limits WSN performance. Accurate modeling and measurement of interference faces two key challenges. First, as shown in our experimental results, interference yields considerable spatial and temporal variations of WSN performance, which poses a major challenge for measurement at rum-time. Second, in the unlicensed band, the communication of WSN is interfered by coexisting wireless devices such as smartphones and laptops equipped with 802.11 radios, which lead to cross-technology interference that are difficult to characterize due to the heterogeneous PHY. To tackle these challenges, this paper presents a novel accuracy-aware approach to interference modeling and measurement for WSNs. First, we propose a new regression-based interference model and analytically characterize its accuracy based on statistics theory. Second, we develop a novel protocol called accuracy-aware interference measurement for measuring the proposed interference model with assured accuracy at run time. Third, building on interference modeling, we propose an algorithm that accurately forecasts the performance of WSNs in the presence of cross-technology interference. Our extensive experiments on a testbed of 17 TelosB motes show that the proposed approaches achieve high accuracy of interference modeling and WSN performance forecasting with significantly lower overhead than state-of-the-art approaches.

A digital signal acquisition system consists of two steps: sampling and quantization. Sampling maps a continuous signal to a digital signal, which then is quantized into a finite number of bits. Generally, a high sampling rate can ensure robustness to noise, while high resolution means less distortion. However, an analog-to-digital converter (ADC) cannot provide a high sampling rate and high resolution simultaneously. The bit rate is constrained, and there is a tradeoff between sampling rate and resolution. In this paper, we investigate the signal reconstruction in the framework of a compressed sensing based sub-Nyquist sampling system. We also study the noise introduced in the sampling stage and the quantization stage and evaluate the recovered signal-to-noise ratio (RSNR) with respect to the sampling rate and resolution. Considering potential application, we study the tradeoff involved in choosing the sampling rate and number of quantization bits according to the input SNR. Finally, we derive a relationship between RSNR and signal sparsity order, sampling rate, and number of quantization bits.

Point cloud classification is an important task in point cloud data analysis. Traditional point cloud classification is conducted primarily on the basis of specific handcrafted features with a specific classifier and is often capable of producing satisfactory results. However, the extraction of crucial handcrafted features hinges on sufficient knowledge of the field and substantial experience. In contrast, while powerful deep learning algorithms possess the ability to learn features automatically, it normally requires complex network architecture and a considerable amount of calculation time to attain better accuracy of classification. In order to combine the advantages of both the methods, in this study, we integrated the handcrafted features, whose benefits were confirmed by previous studies, into a deep learning network, in the hopes of solving the problem of insufficient extraction of specific features and enabling the network to recognise other effective features through automatic learning. This was done to achieve the performance of a complex model by using a simple model and fulfil the application requirements of the remote sensing domain. As indicated by the experimental results, the integration of handcrafted features into the simple and fast-calculating PointNet model could generate a classification result that bore comparison with that generated by a complex network model such as PointNet++ or KPConv.

Android applications (apps) are ubiquitous, operate in complex environment. Managing their risk at the early stage of software development can effectively reduce potential security flaws, testing and maintenance cost, thus becomes an important challenge in model-based development (MBD). This paper introduces a Permission-based Hybrid Risk Management framework for Android apps (PHRiMA), which is a novel guided framework to perform risk management on Android apps by evaluating the permission-based software design. This framework customizes the standard risk management process of ISO/IEC 27005 :2018 as a hybrid of the semi-formal modeling phase and the formal analysis phase. In the semi-formal phase, a Risk Analysis and Modeling (RAM) package based on UML/MARTE is proposed to construct risk context, which can not only describe the permission-based structures, behaviors (communications) and security policies in the Android apps, but also specify criteria for managing permission-induced risks on Android apps. Semi-formal risk context can generate a RAM-based Z specification (RAMZ) by model transformation in PHRiMA formal phase, including RAMZSystem formal model and RAMZManagement formal algorithm. According to the specified risk criteria, the RAMZManagement algorithm can conduct risk management activities on the RAMZSystem model and obtain a formal model with acceptable risk values. We realized a prototype of PHRiMA : Phrima and demonstrated its effectiveness by applying it in common permission-induced risk scenarios for Android apps.

Efficient resource allocation which aims to maximize the network utility under energy neural operation is well known as a key issue in energy harvesting wireless sensor networks (EHWSNs). However, as the energy resource is unstable in practical systems, it's challenging to tackle the uncertainty in harvested energy profile. Instead of designing sophisticated harvested energy prediction model, we directly make uncertainty involved in the resource allocation design. Considering the uncertainty of harvested energy profile, a flexible network utility optimization approach is proposed that can achieve high network utility and robustness against uncertain harvested energy. We firstly formulate the network utility maximization problem subject to energy constraints involving uncertainty. We then introduce a flexible uncertainty model to describe the harvested energy and transform the network utility maximization with uncertainties into a traditional optimization problem. Our experimental results demonstrate the proposed approach is able to provide flexible energy allocation and achieve robustness.

Software-based network service chains in Network Function Virtualization (NFV) need to be dynamically allocated and scaled on hardware resources. This is because the resource demand of virtual network functions (VNFs) typically varies as a results of network flow volume. NFV elastic solutions by coarse-grained horizontal scaling or fine-grained vertical scaling have been investigated in recent years. However, none of the existing solutions can achieve both efficiency and scalability. To address this challenge, we propose elastic network service chain (ENSC), which utilizes a fine-grained hybrid scaling method to achieve both NFV efficiency and scalability. We systematically compare horizontal scaling with vertical scaling from six aspects and determine the priority within hybrid scaling. We formulate the resource allocation problem in the cloud datacenter as an integer linear programming (ILP) model and develop a heuristic algorithm called Rubik. Our evaluation results show that ENSC achieves higher acceptance ratios and resource utilization than horizontal scaling and vertical scaling methods.

Faced with various malicious intrusions, the design of intrusion detection system (IDS) has always being important in the area of network security. Recently, machine learning methods using network status data as input features are widely used to detect abnormality in the network. However, existing work does not consider the variance of the intrusions and thus is not robust to detect new types of intrusions. Therefore, considering the statistical properties of the status data change over time in unforeseen ways if intrusions occur, we propose a concept drift based ensemble incremental learning approach in IDS (CDIL). Concept drift detection technology is firstly used to detect the variance of the statistical properties of the status data in real time, and then an incremental learning is triggered to diagnose if an intrusion happens. In this way, CDIL can adapt the learning model to the changing input network status data in real time. We conduct extensive experiments on real-world network intrusion experimental data set and verify the effectiveness and real-time performance of the proposed CDIL; the accuracy of intrusion detection reaches up to 94.91%.