Federated Learning (FL) is inherently vulnerable to model poisoning attacks owing to its distributed architecture. Existing defense mechanisms typically adopt a horizontal strategy—aggregating and processing all user gradients (model updates) within each communication round to derive optimal aggregated gradients. However, such horizontal approaches fail completely under large-scale poisoning attacks involving more than 50% of participants. In this work, motivated by the observation that model convergence follows a highly predictable trajectory, we depart from conventional horizontal paradigms and reformulate the problem of optimal gradient aggregation along a vertical dimension. We introduce VERT, a novel defense framework that leverages historical gradients from previous global rounds to train a predictor, which forecasts the expected gradients for the current round. These predictions are then compared against actual submitted gradients to identify and select reliable updates for aggregation. To enhance computational efficiency, VERT incorporates a lightweight dimensionality reduction module that projects high-dimensional gradients into a lower-dimensional space without compromising representational capacity. Extensive experimental results demonstrate that VERT is both efficient and scalable, outperforming state-of-the-art (SOTA) defenses even under extreme poisoning scenarios (≥80% malicious users). Furthermore, VERT consistently achieves superior robustness across low poisoning rates (20%, 40%) and non independent and identically distributed (non-IID) data settings.

One of the main challenges in federated learning is its non-independent and identically distributed (non-IID) nature, where independent client training leads to overfitting and model deviations, negatively impacting overall performance. To address this, most research focuses on aligning local and global models to reduce client drift. However, existing algorithms use Empirical Risk Minimization (ERM) as the local optimizer, leading the global model to sharp minima, increasing bias in some clients and lowering generalization. To address these challenges, we propose GFed-HSAM, a general federated learning method that improves both local and global model generalization. GFed-HSAM uses Hybrid Sharpness-Aware Minimization (HSAM) as the local optimizer to smooth gradients with zeroth-order and first-order sharpness measures. It also includes a dynamic regularizer (DR) to align global and local models at the parameter level. Experiments show that GFed-HSAM outperforms state-of-theart methods in accuracy and generalization across different data heterogeneity settings on CIFAR10/CIFAR100.

Federated Learning (FL) is a distributed training paradigm that enables multiple devices in the Industrial Internet of Things (IIoT) to collaboratively train a global model without sharing private data. However, non-IID data in FL leads to client drift, which significantly degrades the performance of the global model in IIoT scenarios. While the primal-dual update method effectively mitigates client drift through dynamic regularization, optimizing the global model remains a significant challenge in IIoT due to the high degree of data heterogeneity. To address this challenge, we propose a novel FL method, PDFed-ALD, which effectively mitigates client drift and improves global model’s performance under high data heterogeneity. The core of PDFed-ALD is adaptive local distillation mechanism, which employs an adaptive distillation temperature based on the relative degree of data heterogeneity, dynamically correcting gradient updates, alleviating the issue of client drift. Furthermore, to reduce variance among local gradients, PDFed-ALD introduces a momentum-based minimum sharpness gradient correction method, which enhances local consistency by minimizing the variance between gradients across clients. Extensive experiments on image classification tasks using CIFAR-10, CIFAR-100 and MVTEC datasets demonstrate that PDFed-ALD outperforms state-of-the-art (SOTA) methods in terms of both accuracy and convergence speed across various settings, including client scale, participation rate, and degree of data heterogeneity.

Exploring and modeling the spreading process of rumors have shown great potential in improving rumor detection performance. However, existing propagation‐based rumor detection models often overlook the uncertainty of the underlying propagation structure and typically require a large amount of labeled data for training. To address these challenges, we propose a novel rumor detection framework, namely, the Uncertainty‐Inference Contrastive Learning (UICL) model. Specifically, UICL innovatively incorporates an edge‐wise augmentation strategy into the general contrastive learning framework, including an edge‐inference augmentation component and an EdgeDrop augmentation component, which primarily aim to capture the edge uncertainty of the propagation structure and alleviate the sparsity problem of the original dataset. A new negative sampling strategy is also introduced to enhance contrastive learning on rumor propagation graphs. Furthermore, we use labeled data to fine‐tune the detection module. Our experiments, conducted on three real‐world datasets, demonstrate that UICL can not only significantly improve detection accuracy but also reduce the dependency on labeled data compared to state‐of‐the‐art baselines.

Task scheduling in large-scale industrial Internet of Things (IIoT) is characterized by the presence of diverse resources and the requirement for efficient and synchronized processing across distributed edge clouds, raising a significant challenge. This paper proposes a task scheduling framework across edge clouds, namely LsiA3CS, which employs deep reinforcement learning (DRL) and heuristic guidance to achieve distributed, asynchronous task scheduling for large-scale IIoT. Specifically, the Markov game-based model and the asynchronous advantage actor-critic (A3C) algorithm are leveraged to orchestrate diverse computational resources, effectively balancing workloads and reducing communication latency. Moreover, the incorporation of heuristic policy annealing and action masking techniques further refines the adaptability of the proposed framework to the unpredictable requirements of large-scale IIoT systems. Real-world task datasets are utilized to conduct extensive experimental evaluations on a simulated large-scale multi-edge cloud IIoT. The results shows that LsiA3CS significantly reduces task completion times and energy consumption while managing unpredictable task arrivals and variable resource capacities.

As a distributed learning paradigm , federated learning can be effectively applied to the decentralized system since it can resolve the “data island” problem. However, it is also vulnerable to serious privacy breaches . Although existing secure aggregation technique can address privacy concerns, they also incur significant additional computation and communication costs. To address these challenges, this paper offers a C ommunication E fficient S ecure A ggregation scheme. Firstly, the central server uses the communication delay between terminals as the weight of the fully terminal-connected graph to transform it into a sparse connected graph based on the minimal spanning tree. Secondly, instead of relying on central server for key advertisement , the terminals advertise keys via a neighboring terminal forwarding approach based on sparsely graph. Thirdly, we propose using the central server for auxiliary advertising to address unexpected terminal dropout. Simultaneously, we theoretically demonstrate our scheme’s security and have lower computation and communication costs. Experiments show that CESA can reduce the running time by 28.2% without sacrificing security and model accuracy compared to conventional secure aggregation when there are 10 terminals in the system.

Federated learning is a distributed learning paradigm, which is usually combined with edge computing to meet the joint training of IoT devices. A significant challenge in federated learning lies in the statistical heterogeneity, characterized by non-independent and identically distributed (non-IID) local data across diverse parties. This heterogeneity can result in inconsistent optimization within individual local models. Although previous research has endeavored to tackle issues stemming from heterogeneous data, our findings indicate that these attempts have not yielded high-performance neural network models. To overcome this fundamental challenge, we introduce the framework called FedPKR in this paper, which facilitates efficient federated learning through knowledge review. The core principle of FedPKR involves leveraging the knowledge representation generated by the global and local model layers to conduct periodic layer-by-layer comparative learning in a reciprocal manner. This strategy rectifies local model training, leading to enhanced outcomes. Our experimental results and subsequent analysis substantiate that FedPKR effectively augments model accuracy in image classification tasks, meanwhile demonstrating resilience to statistical heterogeneity across all participating entities. Code is available athttps://github.com/jbwangnb/FedPKR.

Continual learning with neural networks, which aims to learn a sequence of tasks, is an important learning framework in artificial intelligence (AI). However, it often confronts three challenges: 1) overcome the catastrophic forgetting problem; 2) adapt the current network to new tasks; and 3) control its model complexity. To reach these goals, we propose a novel approach named continual learning with efficient architecture search (CLEAS). CLEAS works closely with neural architecture search (NAS), which leverages reinforcement learning techniques to search for the best neural architecture that fits a new task. In particular, we design a neuron-level NAS controller that decides which old neurons from previous tasks should be reused (knowledge transfer) and which new neurons should be added (to learn new knowledge). Such a fine-grained controller allows finding a very concise architecture that can fit each new task well. Meanwhile, since we do not alter the weights of the reused neurons, we perfectly memorize the knowledge learned from the previous tasks. We evaluate CLEAS on numerous sequential classification tasks, and the results demonstrate that CLEAS outperforms other state-of-the-art alternative methods, achieving higher classification accuracy while using simpler neural architectures.

The problem of trip recommendation has been extensively studied in recent years, by both researchers and practitioners. However, one of its key aspects-understanding human mobility-remains under-explored. Many of the proposed methods for trip modeling rely on empirical analysis of attributes associated with historical points-of-interest (POIs) and routes generated by tourists while attempting to also intertwine personal preferences-such as contextual topics, geospatial, and temporal aspects. However, the implicit transitional preferences and semantic sequential relationships among various POIs, along with the constraints implied by the starting point and destination of a particular trip, have not been fully exploited. Inspired by the recent advances in generative neural networks, in this work we propose DeepTrip-an end-to-end method for better understanding of the underlying human mobility and improved modeling of the POIs' transitional distribution in human moving patterns. DeepTrip consists of: a trip encoder (TE) to embed the contextual route into a latent variable with a recurrent neural network (RNN); and a trip decoder to reconstruct this route conditioned on an optimized latent space. Simultaneously, we define an Adversarial Net composed of a generator and critic, which generates a representation for a given query and uses a critic to distinguish the trip representation generated from TE and query representation obtained from Adversarial Net. DeepTrip enables regularizing the latent space and generalizing users' complex check-in preferences. We demonstrate, both theoretically and empirically, the effectiveness and efficiency of the proposed model, and the experimental evaluations show that DeepTrip outperforms the state-of-the-art baselines on various evaluation metrics.

A prompt and accurate assessment of buildings' damage is critical for disaster management and emergency response. With the development of high-resolution synthetic aperture radar (SAR) and deep-learning methods, more efficient damage assessment techniques based on building-units are possible. This paper proposes a new building damage assessment method using high-resolution SAR images based on semantic change detection. It utilizes a Siamese-based module for damage change detection together with an attention mechanism-based module for semantic segmentation of the damage maps. To evaluate the proposed model, a new damage assessment dataset is constructed from the SAR imagery originated from the battle of Aleppo, Syria, for model training and testing. The experiments performed on this dataset show an overall accuracy of 88.3%. The proposed method effectively identifies the damaged areas of the buildings and grade the damage condition.

Information cascade size prediction is one of the primary challenges for understanding the diffusion of information. Traditional feature-based methods heavily rely on the quality of handcrafted features, requiring extensive domain knowledge and hard to generalize to new domains. Recently, inspired by the success of deep learning in computer vision and natural language processing, researchers have developed neural network-based approaches for tackling this problem. However, existing deep learning-based methods either focused on modeling the temporal characteristics of cascades but ignored the structural information or failed to take the order-scale and position-scale into consideration in modeling structures of information propagation. This paper proposed a novel graph neural network-based model, called MUCas, to learn the latent representations of cascade graphs from a multi-scale perspective, which can make full use of the direction-scale, high-order-scale, position-scale, and dynamic-scale of cascades via a newly designed MUlti-scale Graph Capsule Network (MUG-Caps) and the influence-attention mechanism. Extensive experiments conducted on two real-world data sets demonstrate that our MUCas significantly outperforms the state-of-the-art approaches.

Most existing studies that employ social-trust information to solve the data sparsity issue in recommender systems assume that socially connected users have equal influence on each other. However, this assumption does not hold in practice since users and their friends may not have similar interests because social connections are multifaceted and exhibit heterogeneous strengths in different scenarios. Therefore, estimating the diverse levels of influence among entities (users/items/social connections) is very important in advancing social recommender systems. Towards this goal, we propose a new model named Social-Trust-Aware Variational Recommendation (SOAP-VAE). Particularly, SOAP-VAE leverages graph attention network techniques to capture the varying levels of influence and the complex interaction patterns among all the entities collectively and holistically. In doing so, heterogeneity among entities is obtained seamlessly. Consequently, we generate social-trust-aware item embedding representations in which the right level of influence has been integrated. Next, based on these rich social-trust-aware item representations, we formulate the first-ever social-trust-aware prior in literature. Unlike priors utilized in earlier VAE-based recommendation models, this novel prior aids in dealing with the issue of posterior-collapse and can effectively capture the uncertainty of latent space. In effect, the model produces better latent representations, which significantly alleviates the data sparsity issue. Finally, we empirically show that SOAP-VAE outperforms several state-of-the-art baselines on three real-world data sets.

Researchers have exerted tremendous effort in designing ways to detect and identify rumors automatically. Traditional approaches focus on feature engineering, which requires extensive manual efforts and are difficult to generalize to different domains. Recently, deep learning solutions have emerged as the de facto methods which detect online rumors in an end-to-end manner. However, they still fail to fully capture the dissemination patterns of rumors. In this study, we propose a novel diffusion-based rumor detection model, called Macroscopic and Microscopic-aware Rumor Detection, to explore the full-scale diffusion patterns of information. It leverages graph neural networks to learn the macroscopic diffusion of rumor propagation and capture microscopic diffusion patterns using bidirectional recurrent neural networks while taking into account the user-time series. Moreover, it leverages knowledge distillation technique to create a more informative student model and further improve the model performance. Experiments conducted on two real-world data sets demonstrate that our method achieves significant accuracy improvements over the state-of-the-art baseline models on rumor detection.

The ubiquity of mobile devices use has generated huge volumes of location-aware contextual data, providing opportunities enriching various location-based social network (LBSN) applications - e.g., trip recommendation, ride-sharing allocation and taxi demand prediction etc. Trajectory-based social circle inference (TSCI), which aims at inferring the social relationships among users based on the human mobility data, has received great attention in recent years due to its importance in many LBSN applications. However, existing solutions suffer from three key challenges, including (1) lack of modeling contextual feature in user check-ins; (2) cannot capture the structural information in user motion patterns; (3) and fail to consider the underlying mobility distribution. In this paper, we propose a novel framework ASCI-CAM (Adversity-based Social Circles Inference via Context-Aware Mobility) to address the above challenges. ASCI-CAM is a graph-based model taking into account the contextual information associated with check-ins which, combined with an attentive auto-encoder, allows for semantic trajectory representation. We regularize the learned trajectory embedding with an adversarial learning procedure, which allows us to better understand the user mobility patterns and personalized trajectory distribution. Our extensive experiments on real-world mobility datasets demonstrate that our model achieves significant improvement over the state-of-the-art baselines.

A prompt and accurate assessment of building damage is critical for disaster assistance and emergency monitoring. Polarimetric synthetic aperture radar (PolSAR) has become one of the most effective methods in damage assessment, owing to its all-weather/all-time observation ability and abundant polarization scattering information of target. In this study, we discussed the distribution law of Touzi decomposition polarization parameters before and after building collapse, based on the ALOS PALSAR data in the L band and the simulated SAR images in the Ku band. The experimental results show that the as1component obtained by Touzi decomposition can be used for building damage assessment, and is universal in L-band and Ku-band SAR images.

In this work we propose DeepTrip -- an end-to-end method for better understanding of the underlying human mobility and improved modeling of the POIs' transitional distribution in human moving patterns. DeepTrip consists of: a Trip Encoder to embed a given route into a latent variable with a recurrent neural network (RNN); and a Trip Decoder to reconstruct this route conditioned on an optimized latent space. Simultaneously, we define an Adversarial Net composed of a generator and critic, which generates a representation for a given query and uses a critic to distinguish the trip representation generated from Trip Encoder and query representation obtained from Adversarial Net. DeepTrip enables regularizing the latent space and generalizing users' complex check-in preference. We demonstrate the effectiveness and efficiency of the proposed model, and the experimental evaluations show that DeepTrip outperforms the state-of-the-art baselines on various evaluation metrics.

Effectively predicting the size of an information cascade is critical for many applications spanning from identifying viral marketing and fake news to precise recommendation and online advertising. Traditional approaches either heavily depend on underlying diffusion models and are not optimized for popularity prediction, or use complicated hand-crafted features that cannot be easily generalized to different types of cascades. Recent generative approaches allow for understanding the spreading mechanisms, but with unsatisfactory prediction accuracy. To capture both the underlying structures governing the spread of information and inherent dependencies between re-tweeting behaviors of users, we propose a semi-supervised method, called Recurrent Cascades Convolutional Networks (CasCN), which explicitly models and predicts cascades through learning the latent representation of both structural and temporal information, without involving any other features. In contrast to the existing single, undirected and stationary Graph Convolutional Networks (GCNs), CasCN is a novel multi-directional/dynamic GCN. Our experiments conducted on real-world datasets show that CasCN significantly improves the prediction accuracy and reduces the computational cost compared to state-of-the-art approaches.

Effectively modeling and predicting the information cascades is at the core of understanding the information diffusion, which is essential for many related downstream applications, such as fake news detection and viral marketing identification. Conventional methods for cascade prediction heavily depend on the hypothesis of diffusion models and hand-crafted features. Owing to the significant recent successes of deep learning in multiple domains, attempts have been made to predict cascades by developing neural networks based approaches. However, the existing models are not capable of capturing both the underlying structure of a cascade graph and the node sequence in the diffusion process which, in turn, results in unsatisfactory prediction performance. In this paper, we propose a deep multi-task learning framework with a novel design of shared-representation layer to aid in explicitly understanding and predicting the cascades. As it turns out, the learned latent representation from the shared-representation layer can encode the structure and the node sequence of the cascade very well. Our experiments conducted on real-world datasets demonstrate that our method can significantly improve the prediction accuracy and reduce the computational cost compared to state-of-the-art baselines.

An important task in Location based Social Network applications is to predict mobility - specifically, user's next point-of-interest (POI) - challenging due to the implicit feedback of footprints, sparsity of generated check-ins, and the joint impact of historical periodicity and recent check-ins. Motivated by recent success of deep variational inference, we propose VANext (Variational Attention based Next) POI prediction: a latent variable model for inferring user's next footprint, with historical mobility attention. The variational encoding captures latent features of recent mobility, followed by searching the similar historical trajectories for periodical patterns. A trajectory convolutional network is then used to learn historical mobility, significantly improving the efficiency over often used recurrent networks. A novel variational attention mechanism is proposed to exploit the periodicity of historical mobility patterns, combined with recent check-in preference to predict next POIs. We also implement a semi-supervised variant - VANext-S, which relies on variational encoding for pre-training all current trajectories in an unsupervised manner, and uses the latent variables to initialize the current trajectory learning. Experiments conducted on real-world datasets demonstrate that VANext and VANext-S outperform the state-of-the-art human mobility prediction models.

Learning explicit and implicit patterns in human trajectories plays an important role in many Location-Based Social Networks (LBSNs) applications, such as trajectory classification (e.g., walking, driving, etc.), trajectory-user linking, friend recommendation, etc. A particular problem that has attracted much attention recently - and is the focus of our work - is the Trajectory-based Social Circle Inference (TSCI), aiming at inferring user social circles (mainly social friendship) based on motion trajectories and without any explicit social networked information. Existing approaches addressing TSCI lack satisfactory results due to the challenges related to data sparsity, accessibility and model efficiency. Motivated by the recent success of machine learning in trajectory mining, in this paper we formulate TSCI as a novel multi-label classification problem and develop a Recurrent Neural Network (RNN)-based framework called DeepTSCI to use human mobility patterns for inferring corresponding social circles. We propose three methods to learn the latent representations of trajectories, based on: (1) bidirectional Long Short-Term Memory (LSTM); (2) Autoencoder; and (3) Variational autoencoder. Experiments conducted on real-world datasets demonstrate that our proposed methods perform well and achieve significant improvement in terms of macro-R, macro-F1 and accuracy when compared to baselines.

Trajectory-User Linking (TUL) is an essential task in Geo-tagged social media (GTSM) applications, enabling personalized Point of Interest (POI) recommendation and activity identification. Existing works on mining mobility patterns often model trajectories using Markov Chains (MC) or recurrent neural networks (RNN) -- either assuming independence between non-adjacent locations or following a shallow generation process. However, most of them ignore the fact that human trajectories are often sparse, high-dimensional and may contain embedded hierarchical structures. We tackle the TUL problem with a semi-supervised learning framework, called TULVAE (TUL via Variational AutoEncoder), which learns the human mobility in a neural generative architecture with stochastic latent variables that span hidden states in RNN. TULVAE alleviates the data sparsity problem by leveraging large-scale unlabeled data and represents the hierarchical and structural semantics of trajectories with high-dimensional latent variables. Our experiments demonstrate that TULVAE improves efficiency and linking performance in real GTSM datasets, in comparison to existing methods.

Computational Radio Frequency Identification (CRFID) tags operate solely on harvested energy and have emerged as viable platforms for a variety of ubiquitous sensing and computation applications. Due to their battery-less nature, these tags can be permanently deployed in hard-to-reach places where the possibility of tag access is eliminated. In such scenarios, maintaining and upgrading the tag’s firmware becomes infeasible because programming tools, including wired interface and PC-based software, are required to erase, modify, or reprogram the microcontroller unit’s memory. Such limitations necessitate the demand for an over-the-air (OTA) scheme, which can wirelessly reprogram or upgrade the firmware in CRFID tags. In this article, we present R 3 —a reliable OTA reprogramming scheme that is compliant with EPC protocol and requires no hardware upgrade to RFID reader or CRFID tag. We demonstrate our scheme on three platforms, which include both software-defined as well as chip-based CRFID tags, that is, WISP5.1 and Optimized WISP (Opt-WISP), and Spider tag, respectively. The selection also includes both the FLASH- and FRAM-based microcontrollers. We extensively evaluate our scheme in terms of several metrics, including overall system delay, time and energy overhead, and success rate in line with interrogation range. We foresee our endeavor to offer the viability of OTA reprogramming and firmware upgrade for CRFID tokens under practical situations.

Electronic Health Records sharing is extremely healthful for medical data analysis while preserving of patients' privacy also play a major role. While cloud computing and the emergence of big data phenomena presents significant opportunity for health care, they also elicit privacy concerns during the sharing of data for analysis and research. The privacy of the patients are at risk while using the electronic healthcare system for the submission of healthcare data through the internet for analysis. The leakage of personal health information can easily be compromise for medical insurance fraud or medical identity theft. These concerns indicate the need to ensure privacy protection when collecting medical data for analyzing or publishing. This study presents a mathematical model for identity based encryption protocol for privacy preservation of the patient during the collection of patient health data for analysis. This has become an integral part of human daily life in which health data are submitted for analysis. The model delinks the patient's identity from the examined data during data submission for the preservation of the patient's privacy.

Understanding human trajectory patterns is an important task in many location based social networks (LBSNs) applications, such as personalized recommendation and preference-based route planning. Most of the existing methods classify a trajectory (or its segments) based on spatio-temporal values and activities, into some predefined categories, e.g., walking or jogging. We tackle a novel trajectory classification problem: we identify and link trajectories to users who generate them in the LBSNs, a problem called Trajectory-User Linking (TUL). Solving the TUL problem is not a trivial task because: (1) the number of the classes (i.e., users) is much larger than the number of motion patterns in the common trajectory classification problems; and (2) the location based trajectory data, especially the check-ins, are often extremely sparse. To address these challenges, a Recurrent Neural Networks (RNN) based semi-supervised learning model, called TULER (TUL via Embedding and RNN) is proposed, which exploits the spatio-temporal data to capture the underlying semantics of user mobility patterns. Experiments conducted on real-world datasets demonstrate that TULER achieves better accuracy than the existing methods.

Rice fields occupy a land area of more than 100 million ha in Asia, feed about 3.5 billion people worldwide. There is a significant interest in the information provided by remote sensing about rice fields in a timely and efficient manner. Information on phenological development is a fundamental key to rice monitoring because it describes the actual state of the rice plants and their relation with the pedoclimatic conditions. As part of an ongoing effort to explore the use of polarimetric SAR data in rice monitoring, this study proposed an automated method of rice phenology retrieval using a feature optimization strategy integrated support vector machine (SVM) and sequential forward selection (SFS). The optimal polarimetric variables for each phenological stage were acquired, based on which eight rice phenological stages were retrieved automatically. The accuracies were higher than 90% except for the dough stage and the transition period between two stages.

Aerodynamic roughness is an important parameter for urban meteorological and climate studies. Buildings in urban areas alter the surface roughness and the drag effect of urban surfaces, which in turn affects urban boundary layer dynamics. Polarimetric Synthetic Aperture Radar is considered to be an effective means for aerodynamic roughness retrieval because polarimetric parameters are sensitive to the surface roughness and geometric structure of a given target. In this paper, the correlation between radar polarimetric parameters and aerodynamic roughness in urban areas are analyzed. And then the optimal polarimetric parameter for the aerodynamic roughness calculation was determined. Finally a quantitative relationship was set up to retrieve the aerodynamic roughness length in urban areas from polarimetric SAR data.

Summary Both distance fraud attacks and relay attacks threaten radio‐frequency identification (RFID) applications but are hard to prevent. Existing approaches can neither avoid tags to response the rouge reader's challenges nor have the simultaneous feature to defend the two kinds of attacks. In a first step, this paper presents an improved distance‐bounding protocol that a tag deduces the distance to a reader and reports if the reader is honest or malicious through the output of trust values that can defend distance fraud. When multiple readers are synchronized and scheduled, we just logically threat them as one. So our solutions fix a flaw in prior work that may be leveraged by attackers to increase the successful rate of discovering relay attack. Secondly, we deploy trusted third party architecture to provide anonymity for tags in anonymous RFID systems without requiring tag identifiers. Existing distance‐based attack detection methods are not applicable in anonymous RFID systems because of the requirement of awareness of tag identifiers. This insight inspires Distance‐Bounding Trust Protocol (DBTP), which is for both distance fraud and relay attacks detection in anonymous RFID systems. DBTP can make correct decisions through trust values in accepting or rejecting a reader's challenge by establishing collaborations and trust relationship between one reader (verifier) and active tags (provers). We evaluate the performance of DBTP through theoretical analysis and extensive simulations. The results show that DBTP can detect both distance fraud and relay attacks, and it is effective to guarantee security for anonymous RFID systems. Copyright © 2015 John Wiley & Sons, Ltd.

Processing huge amounts of network data is one of the largest challenges for network-based intrusion detection system (IDS). Usually these data contain lots of irrelevant or redundant features. To improve the efficiency of IDS, relevant features are necessary to be extracted from original data via feature selection approaches. In this paper, an effective feature selection approach based on Bayesian Network classifier is proposed. And with the same intrusion detection benchmark dataset (NSL-KDD), the performance of the proposed approach is evaluated and compared with other commonly used feature selection methods. It is shown by empirical results that features selected by our approach have decreased the time to detect attacks and increased the classification accuracy as well as the true positive rates significantly.

China is the largest rice producer in the world. Guizhou province is an important rice growing area in the southwest of China. However, rice monitoring with remote sensing data has great difficulties in this region due to its perennial cloud-coverage weather and undulating terrain. With the emergence of polarimetric SAR data and state of art methods for polarization information extraction, rice monitoring in this region is more promising. In this study, multi-temporal RADARSAT-2 polarimetric SAR data set was acquired in Guizhou, China. The Freeman-Durden, Cloude-Pottier and the Touzi decompositions were used for classification and rice scattering mechanism analysis.

The discrepancies caused by different cluster merging algorithms in fully polarimetric SAR classification are analyzed here. There are two often-used merging schemes, i.e., merging first to desirable cluster numbers and then iterative clustering and, the agglomerative hierarchical clustering, both using three different between-cluster distance measures herein. One sub-image of RadarSat-2 SAR SLC image is used here. The results illustrate that (1) The choice of between-cluster distance measures in merging scheme one affects the merging results obviously. (2) the agglomerative hierarchical clustering, the merging scheme two can significantly alleviate these discrepancies caused by different between-cluster distance measures and get almost the same merging results. (3) the agglomerative hierarchical clustering also will gain the stability of merging sequence when Pct is small enough.

This paper investigates the S-band backscattering variation of wheat in its four growing seasons, with the purpose of providing a reliable method for wheat identification and monitoring using satellite S-band synthetic aperture radar (SAR) data. The study is based on the tower-based scatteromerer experiment conducted on the wheat fields at the remote sensing test site of Institute of remote sensing applications Chinese academy of sciences. During the entire growing season, we carried out four experiments and got a great amount of backscatter data including the HH and VV polarization. Synchronously, a wide range of plant parameters, such as biomass, soil moisture and canopy height were measured. This paper describes these experiments and analyzes wheat temporal backscattering variation at S-band with corresponding ground parameters.

In the southwest of China, Synthetic aperture radar (SAR) is anticipated to provide an important tool for forestry inventory because of its all weather capabilities. In this paper, Zhazuo area in Guizhou Province of southwest China, with typical Karst landform, was selected as the test site, and six RADARSAT-2 polarimetric images were used for experiments. Methods for forest mapping based on polarimetric decomposition and multi-temporal polarimetric SAR data fusion were proposed. Experiments showed that polarimetric signatures of forest were significantly different with other targets, and fusion of multi-temporal RADARSAT-2 images can effectively improve image quality and enhance forest and deforestation information.

Synthetic Aperture Radar (SAR) has the penetration of the drying dielectric layer, which can detect subsurface targets and buried characteristics. It took fully polarimetric SAR datasets of the subsurface in Lop Nur Palaeo-lacustrine basin for example to compute Shannon entropy parameter and analyze its image features, and then compare those with the other polarization parameters and polarization decomposition results from scattering mechanism and image features. The results show that the introduced Shannon entropy can describe the actual situation and express the image features more obvious in study area, so it has an important reference value for subsurface targets detection and buried characteristics extraction.

The new spaceborne high resolution synthetic aperture radar (SAR) sensors on board the TerraSAR-X satellites can achieve spatial resolution up to 1m. In high resolution SAR image, signature of urban buildings can be identified and extracted. Due to the side-looking character of SAR, building usually presents as L-shaped bright linear feature caused by the two sides that facing the radar sensor, while echoes from the other two sides' lost. It's clear that multi aspect image will be helpful for this problem. This paper deals with building footprint extraction from dual-aspect high-resolution SAR images acquired from ascending and descending orbits. Firstly, the dimension and position of building is estimated from single aspect image separately by several combined methodologies. Then through fusing estimates from each aspect image, more complete footprint of buildings can be obtained. Field measurements proved that building footprint extracted from dual-aspect SAR images is more reliable than that from single aspect SAR image.

Because of side looking illumination, terrain undulations affect the geometric and radiometric quality of synthetic aperture radar images. The correction of these effects becomes indispensable when quantitative image analysis is performed with respect to the derivation of geo- and biophysical parameters. In this paper a newly dual-aspect geometric and radiometric terrain correction method based on RD (Range Doppler) is put forward for geometric and radiometric correction of SAR images. This method is based on a pair of SAR images acquired from dual aspects. First either of the dual-aspect SAR image is ortho-rectified and radiometric slope corrected after the imaging geometry is reconstructed using a DEM (digital elevation model). This process could correct terrain caused geometric distortions and distorted backscatter coefficient caused by foreshortening. Then one image was used to compensate the lost information in shadow and layover areas in the other image. The resulting backscattering images are fully terrain corrected. At last an optimal SAR incidence angle pair selection plan based on SAR simulation was given and this method could help the users to order the SAR data which would achieve the best compensation result.

The bloom of algae called Enteromorpha prolifera posed a potential threat to the Olympic sailing competition in June 2008. Synthetic Aperture Radar (SAR) technology plays an irreplaceable role in algal blooming monitoring. Based on the analysis of various influence factors, a procedure for E.P. detection is proposed. In this paper, multi-temporal SAR images especially with short time interval, currents datum from buoys and wind products retrieved from SeaWinds scatterometer have been employed for E.P. dynamic monitoring and drift trend analysis. The result of analysis shows SAR, currents and wind datum are available for forecasting the trend of the E.P. drift.

High resolution SAR (Synthetic Aperture Radar) will provide an innovative tool for urban area applications. Nevertheless, interpretation of SAR image in urban area is far from solved by the increase of spatial resolution. It is usually difficult to establish a determined relationship between scattering centers in high resolution SAR images and the basic units of building targets. In order to thoroughly understand the backscattering behaviour of building targets in high resolution SAR images, a method of high resolution SAR imaging simulation based on electromagnetic model is proposed in this paper, which mainly includes 3-D model establishment for the building target, triangular facets partition, RCS prediction for each facet, and SAR imaging through coherent superposition of echo from each triangular facet. Through comparison of the simulated and the original SAR image, building scatter mechanisms in high resolution SAR images can be well interpreted.

This paper aims to get the relationship between drought and crop growth. By investigating synthetic aperture radar (SAR) backscattering coefficients, HH- and VV- polarization were found different due to influence from canopy, because of strong attenuation of the VV- polarization by the vertically oriented wheat stems. In small incidence angle, HH is sensitive to soil moisture, while VV is more sensitive to canopy. Two classes of crop with low and high soil moisture are investigated by ¿water-cloud¿ model with vegetation descriptor vegetation water mass (VWM). Parameters of the model show that in drought the crop growth will be worse. This research presents that it is possible to study the influence of drought to wheat growth with small incidence angle of C-band SAR.

As the high resolution radar satellite's has been successfully launched, its ability of the typical target's recognition monitor enhances a lot. This article mainly does analysis based on the RADARSAT2 quad-polarimetric data, compared scattering properties of typical target feature with two temporal full polarized data, and used the measured data to drive MIMICS (Michigan Microwave Canopy Scattering model) model and carry on the multi-wave band full polarization backscattering simulation about the farmland and forest. Then we carried on the comparison between X, C band SAR image gain's actual scattering value and simulation value in order to infer the typical target feature' scattering properties rule of S band. With anticipation of HJ-1-C satellite soon launched by China and then we can carrry on the comparison with the fact. Along with the full polarized data's development, the typical target feature's scattering properties analysis will be more perfect.

Wenchuan Earthquake has caused many huge landslides in the rivers in Sichuan Province. Synthetic Aperture Radar (SAR) technology played an irreplaceable role in rapid response to Wenchuan Earthquake monitoring and damage assessment. In this paper, Tangjiashan Dammed Lake was taken as a case study area for fast extracting and change detection with continuously acquired multi-temporal high-resolution SAR images. By June 12, 2008, we had identified dozens of dammed lakes in the area heavily affected by the Wenchuan Earthquake using high-resolution SAR images. In order to make a scientific evaluation of the disaster situation and provide efficient and instantaneous rescue action in the future, an effective method was developed for rapid extraction and change detection of dammed lakes.

Karst forest physiognomy occupy a large area of Guizhou, southwest China. It is a rare forest resource in the earth and urgently needed to carry out protection. Due to synthetic aperture radar (SAR) data's ability to acquire images through clouds, it was tested as an alternative to optical data to map changes of land use/land cover, to estimate biophysical parameters of vegetation types, and to detect deforestation. The main goal of this paper is to analyze the potential of the spaceborne full polarimetric data in distinguishing the different types of forest in southwest China. Different polarimetric target decompositions, such as eigenvetor-based decomposition (Cloude-Pottier's decomposition and Touzi Decomposition) and scattering model-based decomposition (Freeman decomposition), were used in this paper to extract forested areas from the scene. To further divide the extracted forested area into deciduous and coniferous forest., Supervised polarimetric classification procedures based on Freeman decomposition is presented in this paper.

In the south of China, synthetic aperture radar (SAR) provides a powerful tool for forestry inventory because of its all-weather and all-day capabilities. Nevertheless previous single or dual polarization SAR data cannot meet the requirements of forest type classification. Polarimetric SAR data contained more information of targets and in this paper we investigated the capability of polarimetric Radarsat 2 data for forest type discrimination. Taking Zhazuo forest farm of Guizhou Province as study area, an 8-temporal field experiment was designed and used for polarimetric backscattering signatures analysis based on MIMICS model. Then two-temporal polarimetric Radarsat 2 data was analyzed to extract polarimetric variables for forest species discrimination, and then polarimetric decomposition and classification were carried out. Experiments prove that forest type can be discriminated using polarimetric Radarsat 2 data, but it is not very effective for forest species identification mainly due to the spatial resolution limitation. Polarimetric SAR data with higher resolution and more complicated classification methods are needed in the future.

Rice is a major food supply in the southeast of China, which is very important for this region's rapid and sustainable development. Synthetic Aperture Radar (SAR) provides a powerful tool for rice monitoring in these regions because of its all-weather, day-and-night imaging and canopy penetration capabilities. HJ-1 small satellite constellation of China has been designed for environment and disaster monitoring, and HJ-1-C satellite has a SAR system working in S-band with incidence varying from 31° to 40°, VV polarization. Scattering model is helpful to better understand the temporal behavior of rice backscatter in S-band before HJ-1 SAR satellite is launched. In this paper, Zhaoqing test site in Guangdong province was selected as the test site, and 9-temporal field measurements acquired during the rice growing period in 1997 were used for analysis. Then rice backscattering and seasonal variation in S-band and VV polarization were simulated and analyzed based on radiative transfer model and ground measurements.

On the 7thof December 2007, the 146,000-ton oil tanker, Hebei Spirit, was wrecked and leaked more than 10,000 ton crude oil onto the sea off the west coast of the South Korea. In this paper, the monitoring of the oil spills in this pollution accident using multi-temporal Synthetic Aperture Radar (SAR) and microwave scatterometer (QSCAT and ASCAT) data was illustrated. The impact of this oil spill pollution on the China's marine environment was evaluated. The result shows the capability and the effectiveness of microwave remote sensing data in oil spill monitoring and forecasting.

Forestry inventory in southwest of China often suffers from the cloudy cover, and Synthetic Aperture Radar (SAR) can play an important role because of its all-weather and all-day capabilities. In this paper, we studied the potential of polarimetric SAR data for forest mapping in heavy cloud prone and rainy areas with polarimetric TerraSAR-X, Radarsat 2 data and how to improve the forestry classification accuracy through integration of SPOT 5 image and polarimetric SAR data. Field works were carried out in late August of 2007, and parameters were collected using a ground based Lidar and field measurements. For the high relief condition at the test site, a geometric correction strategy using two side looking direction SAR images and high resolution digital elevation model was proposed to overcome the geometric distortion of SAR image such as foreshortening, layover and shadow in hilly areas. Neural net method was suggested for classification of the SAR and SPOT images.

Oil spill pollution is a major environmental threat for many countries in the world, which can cause serious damage to marine environment. Synthetic aperture radar (SAR) has become a valuable tool for marine oil spill monitoring, because of its all-weather and all-day capabilities. However, interpretation of marine SAR imagery is often ambiguous, and some other look-alike features often pose a fundamental challenge to the identification of oil spills and make the discrimination between oil spills and the look-alikes become a necessary procedure. In this paper, co-occurrence matrix method is employed to extract textural features of marine SAR image first, then these features are analyzed and optimized, and then support machine vector (SVM) method is used to identify oil spills in SAR images. Experiments on several SAR images show that method proposed in this paper can improve the detection and identification of oil spill in SAR images.