Search

In this article, quadrotor unmanned aerial vehicles (QUAVs) are organized as a two-layer structure, where the first layer is leader QUAVs and the second layer is follower QUAVs. In this structure, only the leader QUAVs can receive the desired tracking information of position and attitude. Although the followers cannot obtain the given tracking information directly, they can obtain the corresponding information from leaders and other followers through the communication network based on the graph theory. In terms of this case, a distributed formation-containment (FC) control method is proposed to handle the related flight problems. We aim to develop a formation control for the leader QUAVs and a containment control for the follower QUAVs with the graph theory. Furthermore, a neural network (NN) technique is utilized to cope with the uncertainty of each QUAV. In order to guarantee good flight performance when tracking, the finite-time stability theorem is introduced into the control design to make each QUAV achieve satisfactory tacking performance in finite time. Finally, numerical simulations are conducted in the platform of two-layer 16 QUAVs to validate the feasibility and effectiveness of the proposed NN-based finite-time FC control.

As the complexity of flight missions continues to increase, sending a timely warning or providing assistance to pilots helps to reduce the probability of operational errors and flight accidents. Monitoring pilots’ physiological data, real-time evaluation of mission load is a feasible technical way to achieve this. In this paper, a set of flight tasks including aircraft control, human-computer interaction and mental arithmetic tests are designed to simulate five mission loads at different flight difficulty levels. A sensitivity analysis method based on a comprehensive test is proposed to select a set of sensitive physiological factors. Then, based on the SVM hierarchical combination classification method, the pilot mission load real-time evaluation model is established. The test results show significant differences in EMG, respiration rate (abdomen), heart rate, blood oxygen saturation, pupil area, fixation duration, number of fixations, and saccades. The high accuracy obtained from experiments proved that the proposed real-time evaluation model is applicable to meet the requirements of real working environments. The findings can provide methodological references for mission load evaluation research in other fields.

App developers are increasingly using packing services (or packers) to protect their code against being reverse engineered or modified. However, such packing techniques are also leveraged by the malicious developers to prevent the malware from being analyzed and detected by the static malware analysis and detection systems. Though there are already studies on unpacking packed Android apps, they usually leverage the manual reverse engineered packing behaviors to unpack apps packed by the specific packers and cannot be applied to the evolving and new packers. In this paper, we propose a novel unpacking approach with the capacity of adaptively unpacking the evolving and newly encountered packers. Also, we develop a new system, named PackerGrind, based on this adaptive approach for unpacking Android packers. The evaluation with real packed apps demonstrates that PackerGrind can successfully reveal packers? protection mechanisms, effectively handle their evolution and recover Dex files with low overhead.

One important challenge in the post-genomic era is to explore disease mechanisms by efficiently integrating different types of biological data. In fact, a single disease is usually caused through multiple genes products such as protein complexes rather than single gene. Therefore, it is meaningful for us to discover protein communities from the protein-protein interaction network and use them for inferring disease-disease associations. In this article, we propose a new framework including protein-protein networks, disease-gene associations and disease-complex pairs to cluster protein complexes and infer disease associations. Complexes discovered by our approach is superior in quality (Sn, PPV and ACC) and clustering quantity than other four popular methods on three PPI networks. A systematic analysis shows that disease pairs sharing more protein complexes (such as Glucose and Lipid Metabolic Disorders) are more similar and overlapping proteins may have different roles in different diseases. These findings can provide clinical scholars and medical practitioners with new ideas on disease identification and treatment.

An important part of the human-computer interaction process is speech emotion recognition (SER), which has been receiving more attention in recent years. However, although a wide diversity of methods has been proposed in SER, these approaches still cannot improve the performance. A key issue in the low performance of the SER system is how to effectively extract emotion-oriented features. In this paper, we propose a novel algorithm, an autoencoder with emotion embedding, to extract deep emotion features. Unlike many previous works, instance normalization, which is a common technique in the style transfer field, is introduced into our model rather than batch normalization. Furthermore, the emotion embedding path in our method can lead the autoencoder to efficiently learn a priori knowledge from the label. It can enable the model to distinguish which features are most related to human emotion. We concatenate the latent representation learned by the autoencoder and acoustic features obtained by the openSMILE toolkit. Finally, the concatenated feature vector is utilized for emotion classification. To improve the generalization of our method, a simple data augmentation approach is applied. Two publicly available and highly popular databases, IEMOCAP and EMODB, are chosen to evaluate our method. Experimental results demonstrate that the proposed model achieves significant performance improvement compared to other speech emotion recognition systems.

With the advancement of large-scale coordinated attacks, the adversary is shifting away from traditional distributed denial of service (DDoS) attacks against servers to sophisticated DDoS attacks against Internet infrastructures. Link flooding attacks (LFAs) are such powerful attacks against Internet links. Employing network measurement techniques, the defender could detect the link under attack. However, given the large number of Internet links, the defender can only monitor a subset of the links simultaneously, whereas any link might be attacked. Therefore, it remains challenging to practically deploy detection methods. This paper addresses this challenge from a game-Theoretic perspective, and proposes a randomized approach (like security patrolling) to optimize LFA detection strategies. Specifically, we formulate the LFA detection problem as a Stackelberg security game, and design randomized detection strategies in consideration of the adversary's behavior, where best and quantal response models are leveraged to characterize the adversary's behavior. We employ a series of techniques to solve the nonlinear and nonconvex NP-hard optimization problems for finding the equilibrium. The experimental results demonstrate the necessity of handling LFAs from a game-Theoretic perspective and the effectiveness of our solutions. We believe our study is a significant step forward in formally understanding LFA detection strategies. This work is supported in part by National Natural Science Foundation (61602371, 61772411, U1736205, 61632013), CCF-NSFOCUS KunPeng Research Fund (2018002), Hong Kong ITF (No. UIM/285) and Hong Kong RGC Project No. PolyU5389/13E, PolyU152279/16E, Natural Science Basic Research Plan in Shaanxi Province (2016JQ6034), SZSTI JCYJ20170816100819428, Special Foundation of China Postdoctoral Science (2018T111065), China Postdoctoral Science Foundation (2015M582663), the Fundamental Research Funds for the Central Universities, Shaanxi Province Postdoctoral Science Foundation, of China.

For the first time, an unsupervised learning training method was proposed for neural network (NN)-based blind equalization in intensity modulation and direct detection (IMDD) system. The whole scheme can directly train an NN-based equalizer with only the received signal rather than original symbols as reference. Besides, the unsupervised learning can also help a well-trained NN to keep its performance in face of varying system status, such as wavelength shift and bias fluctuation, in practical applications. We evaluate the performance of the proposed scheme in a 50 Gb/s IMDD system. The experimental results confirm that the proposed unsupervised learning can train fully-connected NN-based equalizer as well as convolutional neural network (CNN)-based equalizer to reach the same performance as the one trained by supervised learning. Besides, in face of signals with different bias current of the directly-modulated laser (DML), the unsupervised learning method can train the NN to keep the best performance. It can be proved that the scheme can help maintain the performance of NN-based equalizer against the continuous system parameter variations.

Aiming at the problems of cumbersome, time-consuming, inefficient and unable to create an accurate and controllable light environment for the input of the dimming system in the existing road tunnel lighting dimming quality inspection process, this paper designed a set of road tunnel lighting brightness intelligent detection system. The system fixes 5 illuminance sensors in a vehicle-mounted manner to achieve continuous measurement of longitudinal measurement points on the tunnel road surface and synchronous measurement of lateral measurement points; a programmable light source installed outside the tunnel provides a controllable brightness input for the dimming system, and uses the LoRa wireless technology completes the long-distance wireless communication with the inspection vehicle, which can realize the analysis and management of the measurement data. The whole system is convenient, efficient and intelligent, which can be applied to highway tunnel lighting quality monitoring and operation management.

Highway tunnel lighting equipment, as an important equipment to ensure traffic safety in highway tunnel, has some problems in its production, installation, commissioning and operation, such as low intelligence degree and weak man machine interaction operation. On the basis of studying the existing test methods of highway tunnel lighting equipment, this paper designs an improved test process and method of highway tunnel lighting equipment, builds a cloud management platform for test data, realizes the automatic test of highway tunnel lighting equipment by using remote client combined with Ethernet, realizes the intellectualization of test process and the standardization of test data. The database and background management software deployed on the remote server can realize the classified management of many kinds of test data. The system can improve the testing efficiency of lighting equipment for the highway tunnel lighting equipment production enterprises, and improve the management efficiency and quality for the highway tunnel lighting management department.

An anti-trackslip path tracking algorithm for steel box girder inspection robot based on model prediction (MPC) is proposed in this paper. This algorithm is oriented to the actual needs of the automatic inspection of steel box girder of super large bridges. It solves the slippage problem of the inspection robot because of the wear of driving wheels and slippery contact. The kinematic models of longitudinal and lateral slippage were established and corrected after analyzing the robot sliding control and slippage parameter estimation methods. The robot system error dynamic model and the error model based on state extension were proposed by overall considering control constraints. The robot’s optimized objective function was constructed to convert MPC problem into quadratic programming. Finally, path tracking simulations were performed on the inspection robot under pure rolling and sliding conditions, respectively, using the improved MPC (IMPC) algorithm and the front-wheel feedback algorithm. The comparison showed that the IMPC algorithm exceeded the front-wheel feedback algorithm based on geometrical tracking in tracking precision, proving the effectiveness of the proposed IMPC in anti-trackslip path tracking.

Directly-modulated laser (DML) is widely employed in intensity modulation and direct detection (IMDD) system due to its low cost and high output power. However, the corresponding frequency chirp is regarded as one of the main disadvantages for its application in passive optical networks (PONs). In this paper, we theoretically analyze the frequency response evolution of DML based system under different chirp and dispersion conditions, proving that the system bandwidth can be improved by interactions between negative dispersion and DML chirp. Based on this concept, we experimentally demonstrated downstream 50 Gb/s PAM4 signal transmission over 20 km single-mode fiber (SMF) access based on the 10 Gb/s DML operating at 1310 nm and avalanche photodiode (APD). A dispersion-shifted fiber (DSF) providing -150 ps/nm dispersion at 1310 nm in the optical line terminal (OLT) is used to pre-equalize the frequency response of bandwidth-limited directly modulated signals in the optical domain. Thanks to our proposed dispersion-supported equalization (DSE) technique, the system bandwidth can be improved by 5 GHz. Feed-forward equalization (FFE), decision feedback equalization (DFE) and Volterra filter are employed to evaluate the signal performance improvement, respectively. By evaluating the receiver sensitivity, the DSE combined with FFE scheme shows 2 dB improvement than the complex Volterra algorithm, indicating its potential to reduce the complexity of digital signal processing (DSP) and therefore a lower cost and power consumption in PON.

In the underlay cognitive radio networks, the power spectrum maps (PSMs) estimation is the main challenge in sensing the idle wireless radio resources. Traditional deep learning-based algorithms achieve good estimation performance, under the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the PSMs in the target region. However, collecting the PSMs training data is not an easy task, which is time-consuming and requires a numerous number of sensing devices. For this reason, we propose a two-phase transfer learning generative adversarial network (TPTL-GAN) for the PSMs reconstruction task. The proposed algorithm relaxes the i.i.d. assumption in traditional deep learning-based algorithms, allowing us to estimate the PSMs based on the simulated or previously collected training data, which share similar rather than strictly identical distribution with the target data. In the first phase of the TPTL-GAN algorithm, we design a domain projecting (DP) framework to project the source domain to the adjacent domain. In the second phase, we propose a domain completing (DC) framework, which extracts helpful radio environment features from the adjacent domain and reconstructs the PSMs in the target domain. Through the above two phases, the proposed algorithm provides a more accurate PSMs reconstruction performance than the traditional methods, as verified by the simulation results.

The purpose of this paper is to build an efficiency evaluation model based on efficiency drivers. Building technique, resource ability and management level are the three main driving factors in production efficiency of shipbuilding. Two-stage internal production efficiency structure analysis model (ESAM) firstly decomposes the shipbuilding system efficiency into three dimensions of subsystem efficiency structures to express the driving effect of the three driving factors of technique, operation and management. Secondly, ESAM uses system efficiency function and dimension structure efficiency function to express the relationships between the efficiency of each level and its subordinate efficiency. The contribution of subsystems to system efficiency is represented by the regression coefficient while the driving relationship between the efficiency of the subsystems and the efficiency of the system is expressed by the moving average trend curves of the system efficiency and the structural efficiency of each dimension. The empirical analysis shows that the case shipyard inner production is inefficient, which implies that most Chinese shipyards may be in the same condition, or even worse. It also shows that operation efficiency has the greatest driving effect on shipbuilding system efficiency while the driving effect of technique efficiency is not obvious, which means that improving management efficiency and technique efficiency should be the main direction taken to improve Chinese shipbuilding efficiency.

In recent years, a series of serious catastrophic traffic accidents, such as the Chongqing bus crash and Wuxi Road bridge collapse, revealed some serious issues in the mobile vehicle safety and emergency response mechanisms. The advent of 5G communication has undoubtedly created some great opportunities for solving these issues. In order to fulfill the requirements of serious traffic accident prevention and forensic analysis, this paper proposes an event-based mobile vehicle cyber-physical security governance framework based on 5G communication technology. The proposed framework aims to resolve the issues of mobile vehicle security, including the availability of network resources in high-speed motion and the complexity of security objectives within cyber-physical systems. Relying on precise perception of insecure events at the physical, communication, and society layers, this paper constructs an integrated intelligent safety response strategy for physical equipment information security, state vehicle security, environmental vehicle security, and network security by intelligent perception, edge-cloud computing, and other technologies. The proposed framework achieves the goals of real-time event prediction before the event, immediate alarm during the event, and replay for evidence forensics after the event.

Defect prediction assists the rational allocation of testing resources by detecting the potentially defective software modules before releasing products. When a project has no historical labeled defect data, cross project defect prediction (CPDP) is an alternative technique for this scenario. CPDP utilizes labeled defect data of an external project to construct a classification model to predict the module labels of the current project. Transfer learning based CPDP methods are the current mainstream. In general, such methods aim to minimize the distribution differences between the data of the two projects. However, previous methods mainly focus on the marginal distribution difference but ignore the conditional distribution difference, which will lead to unsatisfactory performance. In this work, we use a novel balanced distribution adaptation (BDA) based transfer learning method to narrow this gap. BDA simultaneously considers the two kinds of distribution differences and adaptively assigns different weights to them. To evaluate the effectiveness of BDA for CPDP performance, we conduct experiments on 18 projects from four datasets using six indicators (i.e., F-measure, g-means, Balance, AUC, EARecall, and EAF-measure). Compared with 12 baseline methods, BDA achieves average improvements of 23.8%, 12.5%, 11.5%, 4.7%, 34.2%, and 33.7% in terms of the six indicators respectively over four datasets.

In cognitive radio, Reinforcement Learning (RL) has been widely applied to the construction of cognition engine. However, two crucial challenges remain to be resolved: First, it takes long time to interact with the environment before reaching intelligent decision. Second, agents improve their performance through trial and error, but some applications in Cognitive Radio Networks (CRN) cannot afford the extensive latency and energy expenditure. An apprenticeship learning scheme based on expert demonstrations is adopted for solving above problems. Firstly, the reinforcement responsibility rating is introduced to enhance the efficiency of power allocation by allowing multi-level transition for the transmit power. In order to avoid the failure of expert node identification due to SU’s remote location, an adaptive radius Bregman Ball model is presented. Furthermore, the Multi-Teacher Deep Q-learning from Demonstrations (MT-DQfD) is proposed to accelerate the learning procedure by sharing demonstrations derived from multiple expert nodes. Our experiments illustrate that the proposed cross-layer routing protocol reduces the training period while improves transmission quality compared to the traditional algorithms. Moreover, the newly-joined nodes can achieve better performance than the experts.

The second-order consensus problem depends on not only the topology condition but also the coupling strength of the relative positions and velocities between neighboring agents. This paper seeks to solve the finite-time consensus problem of second-order multi-agent systems by games with special structures. Potential game and weakly acyclic game were applied for modeling the second-order consensus problem with different topologies. Furthermore, this paper introduces the event-triggered asynchronous cellular learning automata algorithm for optimizing the decision making process of the agents, which facilitates a convergence with the Nash equilibrium. Finally, numerical examples illustrate the effectiveness of the models.

In this paper, a study of control for an uncertain 2-degree of freedom &#x0028 DOF &#x0029 helicopter system is given. The 2-DOF helicopter is subject to input deadzone and output constraints. In order to cope with system uncertainties and input deadzone, the neural network technique is introduced because of its capability in approximation. In order to update the weights of the neural network, an adaptive control method is utilized to improve the system adaptability. Furthermore, the integral barrier Lyapunov function &#x0028 IBLF &#x0029 is adopt in control design to guarantee the condition of output constraints and boundedness of the corresponding tracking errors. The Lyapunov direct method is applied in the control design to analyze system stability and convergence. Finally, numerical simulations are conducted to prove the feasibility and effectiveness of the proposed control based on the model of Quanser &#x02BC s 2-DOF helicopter.

Responding to the growing bandwidth demand by emerging applications, such as fixed-mobile convergence for fifth generation (5G) and beyond 5G, 100 Gb/s/ λ access network becomes the next research focus of passive optical network (PON) roadmap. Intensity modulation and direct detection (IMDD) technology is still considered as a promising candidate for 100 Gb/s/ λ PON attributed to its low cost, low power consumption, and small footprint. In this paper, we achieve 100 Gb/s/ λ IMDD PON by using 20G-class optical and electrical devices due to its commercial availability. To mitigate the system linear and nonlinear distortions, neural network (NN) based equalizer is used and the performance is compared with feedforward equalizer (FFE) and Volterra nonlinear equalizer (VNE). We introduce the rules to train and test the data while using NN-based equalizer to guarantee a fair comparison with FFE and VNE. Random data have to be used for training, but for test, both random data and pseudorandom bit sequence are applicable. We found that the NN-based equalizer has the same performance with FFE and VNE in the case of linear distortion, but outperforms them in a strong nonlinearity case. In the experiment, to improve the loss budget, we increase the launch power to 18 dBm, achieving a 30-dB loss budget for 33 GBd/s PAM8 signal at the system frequency response of 16.2 GHz, attributed to the strong nonlinear equalization capability of NN.

For performance and compatibility reasons, developers tend to use native code in their applications (or simply apps). This makes a bidirectional data flow through multiple contexts, i.e., the Java context and the native context, in Android apps. Unfortunately, this interaction brings serious challenges to existing dynamic analysis systems, which fail to capture the data flow across different contexts. In this paper, we first performed a large-scale study on apps using native code and reported some observations. Then, we identified several scenarios where data flow cannot be tracked by existing systems, leading to uncaught information leakage. Based on these insights, we designed and implemented NDroid , an efficient dynamic taint analysis system that could track the data flow between both Java context and native context. The evaluation of real apps demonstrated the effectiveness of NDroid in identifying information leakage with reasonable performance overhead.

Android packers have been widely adopted by developers to protect apps from being plagiarized. Meanwhile, various unpacking tools unpack the apps through direct memory dumping. To defend against these off-the-shelf unpacking tools, packers start to adopt virtual machine (VM) based protection techniques, which replace the original Dalvik bytecode (DCode) with customized bytecode (PCode) in memory. This defeats the unpackers using memory dumping mechanisms. However, little is known about whether such packers can provide enough protection to Android apps. In this paper, we aim to shed light on these questions and take the first step towards demystifying the protections provided to the apps by the VM-based packers. We proposed novel program analysis techniques to investigate existing commercial VM-based packers including a learning phase and a deobfuscation phase.We aim at deobfuscating the VM-protection DCode in three scenarios, recovering original DCode or its semantics with training apps, and restoring the semantics without training apps. We also develop a prototype named Parema to automate much work of the deobfuscation procedure. By applying it to the online VM-based Android packers, we reveal that all evaluated packers do not provide adequate protection and could be compromised.

Landslides have posed a huge threat to the ecological environment and human society all over the world. As the most conventional reinforcement method, anti-slide piles are widely used in the reinforcement of slopes. Currently, more and more attentions have been paid to the low-cost and high-efficiency optimal design of anti-slide piles. However, limitations in the method of the optimization design for slope reinforced with piles still exist. In this paper, a new multi-objective comprehensive optimization method was proposed for the optimization of the slope reinforced with anti-slide piles. The factor of safety, internal force and deflection of piles were selected as the optimization indexes and the optimization index weight was determined by integrating the subjective and objective weight. The influence of the pile location, pile length and pile spacing on the reinforcement effect was analyzed by the numerical simulation. Through the simulation case analysis, the proposed model had achieved good effects on the optimization design of anti-slide piles, which could effectively reduce the engineering costs. The optimization results showed that the best reinforcement effect for the homogeneous slope could be obtained when the anti-slide piles with the critical pile length and small pile spacing was located in the middle of the slope. This provides a new solution for the optimization design of other types of complex slopes, and has broad application prospects.

N etwork space mimicry defense constructs heterogeneous redundant configuration of execution pool through software and hardware diversification technology, and forms multi-mode output vector through scheduler. Although it can provide a point to surface fusion defense mechanism independent of traditional security means, the execution scheduler, which plays a key role, can still sniff or guess through retransmission attack because of its single and static algorithm. The basic principle of the scheduling algorithm is detected to increase the chance of mimicry escape. This paper designs a dynamic scheduling mechanism with diversified algorithms, which increases the complexity and dynamics of the scheduling mechanism, and can effectively reduce the risk of the scheduler being sniffed. Experimental results show that, compared with the traditional scheduling mechanism, the proposed diversified and dynamic scheduling scheme can significantly reduce the risk of the scheduler being attacked, and further improve the security of the mimicry defense system.

Since the global education industry has transformed from informatization to intellectualization, teaching mode is facing subversive innovation and changes. Guided by the constructivism theory, this paper analyzed the educational design with learning as the center, studied the instructional design strategy for integrating art and technology, and constructed an integrated learning innovation model with learners as the core. Based on the quantitative experiment of Kansei Engineering, combined with Pearson correlation analysis, the subjects evaluated the satisfaction of eight teaching modes by the 7-point Likert scale, obtained the Pearson correlation coefficient of learning innovation model elements by SPSS software and the learning innovation model elements that have the greater impact on students’ satisfaction by comparing the value of the coefficient. Finally, this paper constructed the teaching model of art and technology integration innovation based on constructivism and realized the optimization and reform of the teaching innovation mode of art and technology integration.

Speech emotion recognition is an important part of the human-computer interaction process, which has been receiving more attention in recent years. However, although a wide diversity of methods had been proposed in decades, these approaches still cannot improve the performance. The main reason for the low accuracy of emotion recognition system is how to effectively extract emotion-oriented features. In this paper, we propose a novel autoencoder architecture, two-stream emotion-embedded autoencoder, to extract deep emotion feature. The input is projected to two latent representations in our method. One of them is meant to learn the best representation of the input which contains all information of speech; whereas the other is used to capture emotion-independent information. Next, the difference between two latent representations is considered as the deep emotion feature. Furthermore, the deep emotion feature is concatenated with global acoustic features obtained by openSMILE toolkit. Finally, based on the concatenated feature vector, fully connected network is adopted to conduct emotion classification. Besides, to improve generalization of our method, a simple data augmentation approach is applied. IEMOCAP that is a publicly available and highly popular databases is chosen to evaluate our method. Experimental results demonstrate that the proposed model achieves significant performance improvement compared to other speech emotion recognition systems.

Facial makeup significantly changes the perceived appearance of the face and reduces the accuracy of face recognition. To adapt to the application of smart cities, in this study, we introduce a novel joint subspace and low-rank coding method for makeup face recognition. To exploit more discriminative information of face images, we use the feature projection technology to find proper subspace and learn a discriminative dictionary in such subspace. In addition, we use a low-rank constraint in the dictionary learning. Then, we design a joint learning framework and use the iterative optimization strategy to obtain all parameters simultaneously. Experiments on real-world dataset achieve good performance and demonstrate the validity of the proposed method.

We experimentally demonstrate 100G PAM-4 passive optical network using DML-based intensity modulation and direct detection with 3-dB system bandwidth of 15 GHz in O-band. Combining nonlinear Tomlinson-Harashima precoding at the transmitter and 2nd-order Volterra at the receiver enables 34-dB power budget for PON downstream.

Smartphone vendors are using multiple methods to kill processes of Android apps to reduce the battery consumption. This motivates developers to find ways to extend the liveness time of their apps, hence the name diehard apps in this paper. Although there are blogs and articles illustrating methods to achieve this purpose, there is no systematic research about them. What's more important, little is known about the prevalence of diehard apps in the wild. In this paper, we take a first step to systematically investigate diehard apps by answering the following research questions. First, why and how can they circumvent the resource-saving mechanisms of Android? Second, how prevalent are they in the wild? In particular, we conduct a semi -automated analysis to illustrate insights why existing methods to kill app processes could be evaded, and then systematically present 12 diehard methods. After that, we develop a system named DiehardDetector to detect diehard apps in a large scale. The experimental result of applying DiehardDetector to more than 80k Android apps downloaded from Google Play showed that around 21 % of apps adopt various diehard methods. Moreover, our system can achieve high precision and recall.

Deep learning systems are known to be vulnerable to adversarial samples, which are implemented to change the prediction results by adding small perturbations to benign samples. It is significant to defend against an adversarial attack in critical fields such as automatic drive. In this paper, we propose an interpretation area-guided detection method of adversarial samples, which can improve the performance of the typical feature squeezing method by combining the generated interpretation results. Specifically, we divide the input image into two main parts, the interpretation part, and the non-interpretation part. Then we only squeeze the non-interpretation part, which can reduce the side-effect for benign samples. We evaluate our approach on two widely used datasets, and the results demonstrate that our approach outperforms the original feature squeezing method.

Track jamming can cause disorder in radar data processing process by generating false target trace points, which has low implementation difficulty in actual combat conditions and receives good interference effect. This paper analyzes the interference mechanism of track jamming, makes simulated analysis on the influence of track jamming on radar in the process of radar data processing involving links of track initiation, data correlation and tracking filtering. Experiments show that after the radar is disturbed by track jamming, a lot of resources will be consumed at the initiation and termination of the track, and there will be target data association error, making it impossible to establish or maintain accurate and stable tracking.

Electric water heaters have time-accumulating effect due to the ability to store energy, which makes them attract much attention in the field of smart homes. The load scheduling problem of an electric water heater is challenging due to the uncertainty of future electricity prices and the applicability of different types of electric water heaters. This paper formulates the problem as a Markov decision process (MDP) and uses deep reinforcement learning (DRL) to obtain the optimal scheduling policy. Specifically, Long Short-Term Memory (LSTM) is applied to forecast the future prices. Then adopt Deep Q Network (DQN) to determine the optimal strategy for this problem. LSTM can deal with the uncertainty of future prices. This model-free approach can handle the applicability of different types of electric water heaters. Simulation results indicate that the proposed algorithm can minimize the cost of electricity and dissatisfaction. In addition, the electricity cost and user dissatisfaction can be balanced by introducing a balance parameter according to user preferences.

The convolutional neural network (CNN) shows excellent performances in various applications at the cost of huge storage and calculation overheads. To compress and accelerate the CNN, conventional methods usually prune the unimportant filters under the pre-selected standards, which should be artificially and carefully designed according to the specific application scenarios. In this paper, we propose a general CNN accelerating and compressing method, i.e., the parasitic mechanism (PAM)-based filter pruning algorithm. First, the parasitic layer is constructed on the basis of the convolutional structure and the gate module. Then, the parasitic layers are attached to the original CNN, which carry out the pruning process for the filters in each layer. The above attaching and pruning process is named as the parasitic mechanism. Compared with the traditional filter pruning methods which pre-select the pruning standards artificially, the PAM method intelligently learns the pruning standard in the training process, and prunes the unimportant filters under the constraint of maintaining the performance of the original CNN. As verified by simulations, the proposed PAM algorithm has a better pruning performance than the conventional filter pruning methods.

Based on the analysis of the reactive power regulation capability of wind farm with DFIGs, this paper proposes a method of active power scheduling that maximizes the reactive power limit of wind farms. When the predicted value of the active power output of the wind farm is less than the active dispatch instruction issued by the control center station, power generation is performed according to the principle of maximum wind energy tracking; when the predicted value of the active output is greater than the dispatch instruction, the Lagrangian function method is used to prove that the average distributed active power At power, the reactive power limit of the wind farm with DFIGs is the largest. According to this principle, the active power is distributed, so as to maximize the reactive power regulation capacity of the wind farm. Finally, a simulation analysis is carried out, and the feasibility and effectiveness of the proposed method are verified by comparing with the traditional active scheduling method.

The integration of large-scale wind power into the power grid poses serious challenges to the safe and stable operation of the power grid. Wind farm participation in system frequency control is one of the important countermeasures. Based on the integrated frequency regulation control strategy of the wind turbine (WT), this paper proposes a frequency regulation control strategy for wind farms under complex wind speed conditions. Based on the total wind speed conditions, a coordinated distribution factor of deloading power is established, so that the wind farm will allocate the total deloadingpower to each WT in accordance with the established distribution factor. This method can maintain sufficient stability when the power system is disturbed, and at the same time can reduce the regulating pressure of the synchronous generator. A four-machine two-region model is established on the Digsilent/Powerfactory simulation platform. Through simulation analysis, it is concluded that the proposed control method can make good use of wind energy of different sizes in response to system changes and provide dynamic support for the power grid.

With the increasing complexity of today’s battlefield environment, the workload level of the pilots greatly affects the smooth execution of flight tasks. When a pilot’s workload is too high, it can cause his ability to sense the surrounding environment to be reduced, and even cause extremely dangerous flight accidents. Based on experiments and statistics, the sensitivity of the pilot’s EEG (electroencephalography) and physiological factors under different flight tasks is analyzed, and a pilot workload evaluation model is established based on the SVM (support vector machines) classifier.

Due to the limitation of less information in a single image, it is very difficult to generate a high-precision 3D model based on the image. There are some problems in the generation of 3D voxel models, e.g., the information loss at the upper level of a network. To solve these problems, we design a 3D model generation network based on multi-modal data constraints and multi-level feature fusion, named as 3DMGNet. Moreover, 3DMGNet is trained by self-supervised method to achieve 3D voxel model generation from an image. The image feature extraction network (2DNet) and 3D feature extraction network (3D auxiliary network) are used to extract the features of the image and 3D voxel model. Then, feature fusion is used to integrate the low-level features into the high-level features in the 3D auxiliary network. To extract more effective features, each layer of the feature map in feature extraction network is processed by an attention network. Finally, the extracted features generate 3D models by a 3D deconvolution network. The feature extraction of 3D model and the generation of voxelization play an auxiliary role in the training of the whole network for the 3D model generation based on an image. Additionally, a multi-view contour constraint method is proposed, to enhance the effect of the 3D model generation. In the experiment, the ShapeNet dataset is adapted to prove the effect of the 3DMGNet, which verifies the robust performance of the proposed method.

In this paper, an optimal tracking control scheme is proposed to solve the infinite-horizon linear quadratic tracking (LQT) problem using iterative adaptive dynamic programming (ADP) algorithm. The reference trajectory is assumed to be produced by a linear command generator. First, via system transformation, an augmented system composed of controlled system and command generator is constructed. Then we derive the Bellman equation in terms of the transformed system with discount factor in cost function. In order to avoid requirement for knowledge of system dynamics, the iterative ADP algorithm is introduced to solve the Bellman equation with convergence analysis. A novel approach based on controllability and observability analysis is presented to show the stability of tracking error. For facilitating the implementation of this iterative approach, three neural networks (NNs) are employed as parametric structures to identify the unknown system dynamics, approximate performance function and search control policy, respectively. Finally, a simulation example is included to verify the effectiveness of the proposed scheme.

A new class of target link flooding attacks (LFAs) can cut off the Internet connections of a target area without being detected, because they employ legitimate flows to congest selected links. Although new mechanisms for defending against LFA have been proposed, the deployment issues limit their usage, since they require either additional modules to enhance routers or using the software-defined network to replace the traditional routers. In this paper, we propose a novel framework that employs both the end-to-end and hop-by-hop network measurement techniques to capture the abnormal path performance degradation for detecting LFA and then locate the target links or areas whenever possible, and develop a prototype of the framework named LinkScope . Although using network measurement to capture network anomaly is not new, we tackle a number of challenging issues, such as conducting large-scale Internet path monitoring via non-cooperative measurement so that users do not need to install LinkScope on every host, profiling the performance of asymmetric Internet paths and detecting LFA. The extensive evaluation in a testbed and the Internet shows that with limited bandwidth and computational overhead, LinkScope can achieve timely detection and diagnosis of LFA with high detection rate and low false positive rate.

The positional error of aviation drilling robot has a great influence on the strength and lives of aircrafts in the aircraft assembly. In order to improve the position accuracy of aviation drilling robot, an error compensation method based on co-kriging is proposed in this paper. The error similarity based on the kinematic of drilling robot is proposed firstly. Then, the positional errors of a set of points in the workspace are measured by using precision laser tracker. The measurement data are used to fit the cross-variogram of positional error. After the cross-variogram is obtained, the predicted positional errors of verification points can be estimated based on co-kriging. The positions after compensation are given to the drilling robot. The proposed method is carried out on an aviation drilling robot for practical compensation to verify the correctness and effectiveness of the error compensation method. The experimental results show that the average absolute positional error is reduced to 0.1150 mm from 0.7168 mm, and that the maximum absolute positional error is reduced to 0.2664 mm from 1.3073 mm. The experimental results also demonstrate that the proposed method can improve the absolute position accuracy of aviation robot and could meet the requirement of aircraft assembly.

Various type of deep convolution neural network (CNN) have been successfully applied to synthetic aperture radar (SAR) image despeckling. However, the model is limited by the length of network stru...

Linear approximate segmentation and data compression of moving target spatio-temporal trajectory can reduce data storage pressure and improve the efficiency of target motion pattern mining. High quality segmentation and compression need to accurately select and store as few points as possible that can reflect the characteristics of the original trajectory, while the existing methods still have room for improvement in segmentation accuracy, reduction of compression rate and simplification of algorithm parameter setting. A trajectory segmentation and compression algorithm based on particle swarm optimization is proposed. First, the trajectory segmentation problem is transformed into a global intelligent optimization problem of segmented feature points, which makes the selection of segmented points more accurate; then, a particle update strategy combining neighborhood adjustment and random jump is established to improve the efficiency of segmentation and compression. Through experiments on a real data set and a maneuvering target simulation trajectory set, the results show that compared with the existing typical methods, this method has advantages in segmentation accuracy and compression rate.

The iterated prisoner U+02BC s dilemma U+0028 IPD U+0029 is an ideal model for analyzing interactions between agents in complex networks. It has attracted wide interest in the development of novel strategies since the success of tit-for-tat in Axelrod U+02BC s tournament. This paper studies a new adaptive strategy of IPD in different complex networks, where agents can learn and adapt their strategies through reinforcement learning method. A temporal difference learning method is applied for designing the adaptive strategy to optimize the decision making process of the agents. Previous studies indicated that mutual cooperation is hard to emerge in the IPD. Therefore, three examples which based on square lattice network and scale-free network are provided to show two features of the adaptive strategy. First, the mutual cooperation can be achieved by the group with adaptive agents under scale-free network, and once evolution has converged mutual cooperation, it is unlikely to shift. Secondly, the adaptive strategy can earn a better payoff compared with other strategies in the square network. The analytical properties are discussed for verifying evolutionary stability of the adaptive strategy.

In recent years, with the “Internet ” action plan put forward by the state, “Internet industry” has been widely used in various industries, especially in the country. With the encouragement of the “Internet traffic” innovative form, the Internet rental car industry is developing rapidly. Therefore, the establishment of a network-based car rental management system is conducive to improving the operational capacity of enterprises to meet the needs of industry development. The system is mainly based on j2EE, mainly using struts 2 Spring hibernate and other frameworks, using MyEclipse as a development tool, MYSQL as a database, Macromedia Dreamweaver as a tool for interface beautification, and using JAVA language development. The page adopts JSP dynamic page development technology. The system has simple interface, easy operation and easy maintenance.

A privacy policy is a statement informing users how their information will be collected, used, and disclosed. Failing to provide a correct privacy policy may result in a fine. However, writing privacy policy is tedious and error-prone, because the author may not understand the source code well as it could have been written by others (e.g., outsourcing), or the author does not know the internal working of third-party libraries used. In this paper, we propose and develop a novel system named AutoPPG to automatically construct correct and readable descriptions to facilitate the generation of privacy policy for Android applications (i.e., apps). Given an app, AutoPPG first conducts static code analysis to characterize its behaviors related to users’ personal information, and then applies natural language processing techniques to generating correct and accessible sentences for describing these behaviors. The experimental results using real apps and crowdsourcing indicate that: 1) AutoPPG creates correct and easy-to-understand descriptions for privacy policies; 2) the privacy policies constructed by AutoPPG usually reveal more operations related to users’ personal information than existing privacy policies; and 3) most developers, who reply us, would like to use AutoPPG to facilitate them.

Purpose The paper aims to build the connections between game theory and the resource allocation problem with general uncertainty. It proposes modeling the distributed resource allocation problem by Bayesian game. During this paper, three basic kinds of uncertainties are discussed. Therefore, the purpose of this paper is to build the connections between game theory and the resource allocation problem with general uncertainty. Design/methodology/approach In this paper, the Bayesian game is proposed for modeling the resource allocation problem with uncertainty. The basic game theoretical model contains three parts: agents, utility function, and decision-making process. Therefore, the probabilistic weighted Shapley value (WSV) is applied to design the utility function of the agents. For achieving the Bayesian Nash equilibrium point, the rational learning method is introduced for optimizing the decision-making process of the agents. Findings The paper provides empirical insights about how the game theoretical model deals with the resource allocation problem uncertainty. A probabilistic WSV function was proposed to design the utility function of agents. Moreover, the rational learning was used to optimize the decision-making process of agents for achieving Bayesian Nash equilibrium point. By comparing with the models with full information, the simulation results illustrated the effectiveness of the Bayesian game theoretical methods for the resource allocation problem under uncertainty. Originality/value This paper designs a Bayesian theoretical model for the resource allocation problem under uncertainty. The relationships between the Bayesian game and the resource allocation problem are discussed.

In order to facilitate the development of product image design, the research proposes the optimized product image design integrated decision system based on Kansei Engineering experiment. The system consists of two sub-models, namely product image design qualitative decision model and quantitative decision model. Firstly, using the product image design qualitative decision model, the influential design elements for the product image are identified based on Quantification Theory Type I. Secondly, the quantitative decision model is utilized to predict the product total image. Grey Relation Analysis (GRA)&ndash, Fuzzy logic sub-models of influential design elements are built up separately. After that, utility optimization model is applied to obtain the multi-objective product image. Finally, the product image design integrated decision system is completed to optimize the product image design in the process of product design. A case study of train seat design is given to demonstrate the analysis results. The train seat image design integrated decision system is constructed to determine the product image. This shows the proposed system is effective and for predicting and evaluating the product image. The results provide meaningful improvement for product image design decision.