The traditional Markov prediction methods of the taxi destination rely only on the previous 2 to 3 GPS points. They negelect long-term dependencies within a taxi trajectory. We adopt a Recurrent Neural Network (RNN) to explore the long-term dependencies to predict the taxi destination as the multiple hidden layers of RNN can store these dependencies. However, the hidden layers of RNN are very sensitive to small perturbations to reduce the prediction accuracy when the amount of taxi trajectories is increasing. In order to improve the prediction accuracy of taxi destination and reduce the training time, we embed suprisal-driven zoneout (SDZ) to RNN, hence a taxi destination prediction method by regularized RNN with SDZ (TDPRS). SDZ can not only improve the robustness of TDPRS, but also reduce the training time by adopting partial update of parameters instead of a full update. Experiments with a Porto taxi trajectory data show that TDPRS improves the prediction accuracy by 12% compared to RNN prediction method in literature[4]. At the same time, the prediction time is reduced by 7%.

In this paper, we modify the Legendre-Sidelnikov sequence which was defined by M. Su and A. Winterhof and consider its exact autocorrelation values. This new sequence is balanced for any p,q and proved to possess low autocorrelation values in most cases.

Due to the rapid development of small satellite technology and the advantages of LEO satellite with low delay and low propagation loss as compared with the traditional GEO satellite, the broadband LEO constellation satellite communication system has gradually become one of the most important hot spots in the field of satellite communications. Many countries and satellite communication companies in the world are formulating the project of broadband satellite communication system. The broadband satellite communication system is different from the traditional satellite communication system. The former requires a higher transmission rate. In the case of high-speed transmission, if the low elevation constellation is adopted, the satellite beam will be too much, which will increase the complexity of the satellite. It is difficult to realize the low-cost satellite. By comparing the complexity of satellite realization under different elevation angles to meet the requirement of terminal speed through link computation, this paper puts forward the conception of building broadband LEO constellation satellite communication system with high elevation angle. The constraint relation between satellite orbit altitude and user edge communication elevation angle is proposed by theoretical Eq. deduction. And the simulation is carried out for the satellite orbit altitude and edge communication elevation angle.

The 802.11n networks with MIMO technique provide a spatial degree of freedom for dealing with co-channel interference. In this letter, our proposed spatial interference coordination scheme is achieved by distributed precoding for the downlink and distributed multi-user detection for the uplink. Simulation results validate the proposed scheme in terms of the downlink and uplink maximum achievable rates at each AP.

The thermal imaging pedestrian segmentation system has excellent performance in different illumination conditions, but it has some drawbacks(e.g., weak pedestrian texture information, blurred object boundaries). Meanwhile, high-performance large models have higher latency on edge devices with limited computing performance. To solve the above problems, in this paper, we propose a real-time thermal infrared pedestrian segmentation method. The feature extraction layers of our method consist of two paths. Firstly, we utilize the lossless spatial downsampling to obtain boundary texture details on the spatial path. On the context path, we use atrous convolutions to improve the receptive field and obtain more contextual semantic information. Then, the parameter-free attention mechanism is introduced at the end of the two paths for effective feature selection, respectively. The Feature Fusion Module (FFM) is added to fuse the semantic information of the two paths after selection. Finally, we accelerate method inference through multi-threading techniques on the edge computing device. Besides, we create a high-quality infrared pedestrian segmentation dataset to facilitate research. The comparative experiments on the self-built dataset and two public datasets with other methods show that our method also has certain effectiveness. Our code is available at https://github.com/mcjcs001/LEIPNet.

Software defect prediction (SDP) plays a vital role in allocating testing resources reasonably and ensuring software quality. When there are not enough labeled historical modules, considerable semi-supervised SDP methods have been proposed, and these methods utilize limited labeled modules and abundant unlabeled modules simultaneously. Nevertheless, most of them make use of traditional features rather than the powerful deep feature representations. Besides, the cost of the misclassification of the defective modules is higher than that of defect-free ones, and the number of the defective modules for training is small. Taking the above issues into account, we propose a cost-sensitive and sparse ladder network (CSLN) for SDP. We firstly introduce the semi-supervised ladder network to extract the deep feature representations. Besides, we introduce the cost-sensitive learning to set different misclassification costs for defective-prone and defect-free-prone instances to alleviate the class imbalance problem. A sparse constraint is added on the hidden nodes in ladder network when the number of hidden nodes is large, which enables the model to find robust structures of the data. Extensive experiments on the AEEEM dataset show that the CSLN outperforms several state-of-the-art semi-supervised SDP methods.

In many screen to camera communication (S2C) systems, the barcode preprocessing method is a significant prerequisite because barcodes may be deformed due to various environmental factors. However, previous studies have focused on barcode detection under static conditions; to date, few studies have been carried out on dynamic conditions (for example, the barcode video stream or the transmitter and receiver are moving). Therefore, we present a detection and tracking method for dynamic barcodes based on a Siamese network. The backbone of the CNN in the Siamese network is improved by SE-ResNet. The detection accuracy achieved 89.5%, which stands out from other classical detection networks. The EAO reaches 0.384, which is better than previous tracking methods. It is also superior to other methods in terms of accuracy and robustness. The SE-ResNet in this paper improved the EAO by 1.3% compared with ResNet in SiamMask. Also, our method is not only applicable to static barcodes but also allows real-time tracking and segmentation of barcodes captured in dynamic situations.

For flexibility in supporting mobility and multihoming in edge networks and scalability of the backbone routing system, future Internet is expected to be based on the concept of ID/locator split. Heterogeneity Inclusion and Mobility Adaptation through Locator ID Separation (HIMALIS) has been designed as a generic future network architecture based on ID/locator split concept. It can natively support mobility, multihoming, scalable backbone routing and heterogeneous protocols in the network layer of the new generation network or future Internet. However, HIMALIS still lacks security functions to protect itself from various attacks during the procedures of storing, updating, and retrieving of ID/locator mappings, such as impersonation attacks. Therefore, in this paper, we address the issues of security functions design and implementation for the HIMALIS architecture. We present an integrated security scheme consisting of mapping registration and retrieval security, network access security, communication session security, and mobility security. Through the proposed scheme, the hostname to ID and locator mapping records can be securely stored and updated in two types of name registries, domain name registry and host name registry. Meanwhile, the mapping records retrieved securely from these registries are utilized for securing the network access process, communication sessions, and mobility management functions. The proposed scheme provides comprehensive protection of both control and data packets as well as the network infrastructure through an effective combination of asymmetric and symmetric cryptographic functions.

To secure a wireless sensor and actuator network (WSAN) in cyber-physical systems, trust management framework copes with misbehavior problem of nodes and stimulate nodes to cooperate with each other. The existing trust management frameworks can be classified into reputation-based framework and trust establishment framework. There, however, are still many problems with these existing trust management frameworks, which remain unsolved, such as frangibility under possible attacks. To design a robust trust management framework, we identify the attacks to the existing frameworks, present the countermeasures to them, and propose a hybrid trust management framework (HTMF) to construct trust environment for WSANs in the paper. HTMF includes second-hand information and confidence value into trustworthiness evaluation and integrates the countermeasures into the trust formation. We preform extensive performance evaluations, which show that the proposed HTMF is more robust and reliable than the existing frameworks.

Crack detection is a vital task to maintain a bridge's health and safety condition. Traditional computer-vision based methods easily suffer from disturbance of noise and clutters for a real bridge inspection. To address this limitation, we propose a two-stage crack detection approach based on Convolutional Neural Networks (CNN) in this letter. A predictor of small receptive field is exploited in the first detection stage, while another predictor of large receptive field is used to refine the detection results in the second stage. Benefiting from data fusion of confidence maps produced by both predictors, our method can predict the probability belongs to cracked areas of each pixel accurately. Experimental results show that the proposed method is superior to an up-to-date method on real concrete surface images.

Rapid building damage identification plays a vital role in rescue operations when disasters strike, especially when rescue resources are limited. In the past years, supervised machine learning has made considerable progress in building damage identification. However, the usage of supervised machine learning remains challenging due to the following facts: 1) the massive samples from the current damage imagery are difficult to be labeled and thus cannot satisfy the training requirement of deep learning, and 2) the similarity between partially damaged and undamaged buildings is high, hindering accurate classification. Leveraging the abundant samples of auxiliary domains, domain adaptation aims to transfer a classifier trained by historical damage imagery to the current task. However, traditional domain adaptation approaches do not fully consider the category-specific information during feature adaptation, which might cause negative transfer. To address this issue, we propose a novel domain adaptation framework that individually aligns each category of the target domain to that of the source domain. Our method combines the variational autoencoder (VAE) and the Gaussian mixture model (GMM). First, the GMM is established to characterize the distribution of the source domain. Then, the VAE is constructed to extract the feature of the target domain. Finally, the Kullback-Leibler (KL) divergence is minimized to force the feature of the target domain to observe the GMM of the source domain. Two damage detection tasks using post-earthquake and post-hurricane imageries are utilized to verify the effectiveness of our method. Experiments show that the proposed method obtains improvements of 4.4% and 9.5%, respectively, compared with the conventional method.

Nowadays, malware is a serious threat to the Internet. Traditional signature-based malware detection method can be easily evaded by code obfuscation. Therefore, many researchers use the high-level structure of malware like function call graph, which is impacted less from the obfuscation, to find the malware variants. However, existing graph match methods rely on approximate calculation, which are inefficient and the accuracy cannot be effectively guaranteed. Inspired by the successful application of graph convolutional network in node classification and graph classification, we propose a novel malware similarity metric method based on graph convolutional network. We use graph convolutional network to compute the graph embedding vectors, and then we calculate the similarity metric of two graph based on the distance between two graph embedding vectors. Experimental results on the Kaggle dataset show that our method can applied to the graph based malware similarity metric method, and the accuracy of clustering application with our method reaches to 97% with high time efficiency.

In this letter, we propose a novel discriminative representation for patterned fabric defect inspection when only limited negative samples are available. Fisher criterion is introduced into the loss function of deep learning, which can guide the learning direction of deep networks and make the extracted features more discriminating. A deep neural network constructed from the encoder part of trained autoencoders is utilized to classify each pixel in the images into defective or defectless categories, using as context a patch centered on the pixel. Sequentially the confidence map is processed by median filtering and binary thresholding, and then the defect areas are located. Experimental results demonstrate that our method achieves state-of-the-art performance on the benchmark fabric images.

Aiming at the problem of non-line of sight (NLOS) signal recognition for Ultra Wide Band (UWB) positioning, we utilize the concepts of Neural Network Clustering and Neural Network Pattern Recognition. We propose a classification algorithm based on self-organizing feature mapping (SOM) neural network batch processing, and a recognition algorithm based on convolutional neural network (CNN). By assigning different weights to learning, training and testing parts in the data set of UWB location signals with given known patterns, a strong NLOS signal recognizer is trained to minimize the recognition error rate. Finally, the proposed NLOS signal recognition algorithm is verified using data sets from real scenarios. The test results show that the proposed algorithm can solve the problem of UWB NLOS signal recognition under strong signal interference. The simulation results illustrate that the proposed algorithm is significantly more effective compared with other algorithms.

In this paper, a real-valued reweighted l1 norm minimization method based on data reconstruction in monostatic multiple-input multiple-output (MIMO) radar is proposed. Exploiting the special structure of the received data, and through the received data reconstruction approach and unitary transformation technique, a one-dimensional real-valued received data matrix can be obtained for recovering the sparse signal. Then a weight matrix based on real-valued MUSIC spectrum is designed for reweighting l1 norm minimization to enhance the sparsity of solution. Finally, the DOA can be estimated by finding the non-zero rows in the recovered matrix. Compared with traditional l1 norm-based minimization methods, the proposed method provides better angle estimation performance. Simulation results are presented to verify the effectiveness and advantage of the proposed method.

Aperiodic quadriphase Z-complementary sequences, which include the conventional complementary sequences as special cases, are introduced. It is shown that, the aperiodic quadriphase Z-complementary pairs are normally better than binary ones of the same length, in terms of the number of Z-complementary pairs, and the maximum zero correlation zone. New notions of elementary transformations on quadriphase sequences and elementary operations on sets of quadriphase Z-complementary sequences are presented. In particular, new methods for analyzing the relations among the formulas relative to sets of quadriphase Z-complementary sequences and for describing the sets are proposed. The existence problem of Z-complementary pairs of quadriphase sequences with zero correlation zone equal to 2, 3, and 4 is investigated. Constructions of sets of quadriphase Z-complementary sequences and their mates are given.

We are researching a mobile and sensor access platform network for the future called NerveNet, which accommodates ubiquitous sensors and provides services in local areas. The realization of reliable and accountable information collection, processing and provision over NerveNet poses a challenging and fundamental issue in promotion of the sensor business field. As a first step toward a reliable NerveNet, we investigate privacy preservation and the collection of reliable sensor information for prospective personalized sensor applications. The privacy requirement impels the logic separation between sensor networks and the communication platform in the design of NerveNet architecture. To enable sensor network users (SNUs) to reliably interact with sensors managed by different sensor network owners (SNOs), we designed a secure sensor sharing framework (S3F) based on two business models – the Ad Hoc Sales Model (AHSM) and Shopping Center Sales Model (SCSM). With S3F-AHSM, an SNU acquires permission from an SNO each time she wants to obtain information from a sensor. On the other hand, with S3F-SCSM, an SNU can obtain the access privilege to a flexible set of sensors based on the queried preferences via a third party called a sensor network service provider (SNSP). In S3F-SCSM, SNSPs that share the sensors owned by various SNOs have the ability to search the preferred sensors and provide the authorization certificate to the SNUs.

Grey model (abbreviated as GM), which is based on Deng's grey theory, has been established as a prediction model. At present, it has been widely applied in many research fields to solve efficiently the predicted problems of uncertainty systems. However, this model has irrational problems concerning the calculation of derivative and background value z since the predicted accuracy of GM is unsatisfying when original data shows great randomness. In particular, the predicted accuracy falls in case of higher-order derivative or multivariate greatly. In this paper, the new calculation methods of derivative and background value z are first proposed to enhance the predicted power according to cubic spline function. The newly generated model is defined as 3spGM. To further improve predicted accuracy, Taylor approximation method is then applied to 3spGM model. We call the improved version as T-3spGM. Finally, the effectiveness of the proposed model is validated with three real cases.

Information-Centric or Content-Centric Networking (ICN/CCN) is a promising novel network architecture that naturally integrates in-network caching, multicast, and multipath capabilities, without relying on centralized application-specific servers. Software platforms are vital for researching ICN/CCN; however, existing platforms lack a focus on extensibility and lightweight implementation. In this paper, we introduce a newly developed software platform enabling CCN, named Cefore. In brief, Cefore is lightweight, with the ability to run even on top of a resource-constrained device, but is also easily extensible with arbitrary plugin libraries or external software implementations. For large-scale experiments, a network emulator (Cefore-Emu) and network simulator (Cefore-Sim) have also been developed for this platform. Both Cefore-Emu and Cefore-Sim support hybrid experimental environments that incorporate physical networks into the emulated/simulated networks. In this paper, we describe the design, specification, and usage of Cefore as well as Cefore-Emu and Cefore-Sim. We show performance evaluations of in-network caching and streaming on Cefore-Emu and content fetching on Cefore-Sim, verifying the salient features of the Cefore software platform.

Signed networks are ubiquitous in the real world. It is of great significance to study the problem of community detection in signed networks. In general, the behaviors of nodes in a signed network are rational, which coincide with the players in the theory of game that can be used to model the process of the community formation. Unlike unsigned networks, signed networks include both positive and negative edges, representing the relationship of friends and foes respectively. In the process of community formation, nodes usually choose to be in the same community with friends and between different communities with enemies. Based on this idea, we proposed a game theory model to address the problem of community detection in signed networks. Taking nodes as players, we build a gain function based on the numbers of positive edges and negative edges inside and outside a community, and prove the existence of Nash equilibrium point. In this way, when the game reaches the Nash equilibrium state, the optimal strategy space for all nodes is the result of the final community division. To systematically investigate the performance of our method, elaborated experiments on both synthetic networks and real-world networks are conducted. Experimental results demonstrate that our method is not only more accurate than other existing algorithms, but also more robust to noise.