Search

Satellite image processing has been widely used in recent years in a number of applications such as land classification, Identification transfer, resource exploration, super‐resolution image, etc. Due to the orbital location, revision time, quick view angle limitations, and weather impact, the satellite images are challenging to manage. There are many types of resolution, such as spatial, spectral, and temporal. Still, in our case, we concentrated on spatial image resolution to super resolve the images from low‐resolution images. For remote sensing image super‐resolution fast wavelet‐based super‐resolution (FWSR), we propose a novel, fast wavelet‐based plexus framework that performs super‐resolution convolutional neural network (SRCNN)‐like extraction of features based on three hidden layers. First, wavelet sub‐band images are combined into a pre‐defined full‐scale data training factor, including approximation and interchangeable stand‐alone units (frequency sub‐bands). Second, to speed up image recovery, mapping the sub‐band image of the wavelet is then measured using its approximate image. Third, the added sub‐pixel layer at the end of the network model is intended to reproduce image quality using a plexus framework. The approximation sub‐band images obtained after discrete wavelet transform wavelet decomposition are used as input rather than the original image because of their high‐frequency data and preserved characteristics. Five current super‐resolution neural network approaches are compared with the proposed technique and tested on three pubic satellite image datasets and two benchmark datasets. The experimental findings are well compared qualitatively and quantitatively.

Super-resolution (SR) has received extensive attention in recent years for satellite image processing in a wide range of application scenarios, such as land classification, identification of changes, the discovery of resources, etc. Satellite images from satellite sensors are mostly low-resolution (LR) images, so they do not completely fulfill object detection and analysis criteria. SR has multiple residual network frameworks in deep learning that have improved performance and can extend thousands of layers in the system. However, each layer improves accuracy by doubling the number of layers, although training thousands of layers are too expensive, the process is slow, and there are functional recovery issues. We proposed a transferred wide residual Single Image Super-Resolution (SISR) remote sensing deep neural network model (WRSR). By increasing the width and reducing the residual network depth, the proposed approach has dramatically reduced memory costs. As a result, our model reduced memory costs by 21% in Enhanced Deep Residual Super-Resolution (EDSR) and 34% in SRResNet as a direct consequence of the in-depth reduction. The proposed architecture improves the efficiency of training loss by performing weight normalization instead of augmentation technology. We compared our method to five recent existing super-resolution (SR) deep neural network methods, tested over three public satellite image datasets and a standard reference (PRIM) dataset. Experiment analysis is evaluated in peak to signal noise ratio (PSNR) and structural similarity index measure (SSIM).

The paper considers the problem of tracking a moving target using a pair of cooperative bearing-only mobile sensors. Sensor trajectory optimisation plays the central role in this problem, with the objective to minimize the estimation error of the target state. Two approximate closed-form statistical reward functions, referred to as the Expected Rényi information divergence (RID) and the Determinant of the Fisher Information Matrix (FIM), are analysed and discussed in the paper. Being available analytically, the two reward functions are fast to compute and therefore potentially useful for longer horizon sensor trajectory planning. The paper demonstrates, both numerically and from the information geometric viewpoint, that the Determinant of the FIM is a superior reward function. The problem with the Expected RID is that the approximation involved in its derivation significantly reduces the correlation between the target state estimates at two sensors, and consequently results in poorer performance.

The object identification within an image captured during rough weather conditions (such as haze, fog) poses difficulty due to the reduction of an image. The rough weather conditions lead not only to the variation of the image's visual effect but also to the disadvantage of post‐processing of an image. Furthermore, it causes inconvenience of all types of instruments that rely on optical imaging, such as satellite remote‐sensing systems, aerial photo systems, outdoor monitoring systems, and object identification systems, respectively. Hence, the improvement and restorement of the visual effects and enhanced post‐processing are needed. This research introduces a new image enhancement approach for image dehazing based on dark channel prior and piecewise linear transformation; also, the histogram equalisation technique, i.e. contrast limited adaptive histogram equalisation is applied. A dark channel prior is well known for its simplicity and productivity. In this work, the dark channel prior to a new angle is analysed in the first step, where average patch sizes are estimated for the computation of haze densities. Furthermore, the sky is approximated up to 5–10% of the hazy images, which has a good effect in removing the haze from the image. Using the dark channel, the proposed algorithm significantly boosted the effects of the dark images as well as reduced the influence of haze and noise. Eventually, for colour correction, the piecewise linear transformation technique is applied, which enhances the colour close to the original image. Experimental results demonstrate that the proposed method significantly improves the visibility of the algorithm on dark remote‐sensing images as well as on hazy natural images.

In this work, the authors study the problem of detecting and tracking small targets using high-resolution maritime radar, where sea clutter is correlated in range, and its amplitude fluctuations are characterised by occasional spikes. To tackle this problem, they develop a Bernoulli track-before-detect filter, as the optimal recursive Bayesian detector/estimator of target state and its presence in noise. A realistic clutter model, in the form of the K -distribution with unknown distribution parameters, is adopted. Target amplitude fluctuations are also included in the model. The detection and tracking improvement are demonstrated by simulations and compared against a conventional point target tracking algorithm.

We introduce the problem of anti-knowledge mining. Our goal is to create an "anti-knowledge base" that contains factual mistakes. The resulting data can be used for analysis, training, and benchmarking in the research domain of automated fact checking. Prior data sets feature manually generated fact checks of famous misclaims. Instead, we focus on the long tail of factual mistakes made by Web authors, ranging from erroneous sports results to incorrect capitals. We mine mistakes automatically, by an unsupervised approach, from Wikipedia updates that correct factual mistakes. Identifying such updates (only a small fraction of the total number of updates) is one of the primary challenges. We mine anti-knowledge by a multi-step pipeline. First, we filter out candidate updates via several simple heuristics. Next, we correlate Wikipedia updates with other statements made on the Web. Using claim occurrence frequencies as input to a probabilistic model, we infer the likelihood of corrections via an iterative expectation-maximization approach. Finally, we extract mistakes in the form of subject-predicate-object triples and rank them according to several criteria. Our end result is a data set containing over 110,000 ranked mistakes with a precision of 85% in the top 1% and a precision of over 60% in the top 25%. We demonstrate that baselines achieve significantly lower precision. Also, we exploit our data to verify several hypothesis on why users make mistakes. We finally show that the AKB can be used to find mistakes on the entire Web.

Video analytics with Deep Neural Networks (DNNs) empowers many vision-based applications. However, deploying DNN models for video analytics services must address the challenges of computational capacity, service delay, and cost. Leveraging the edge-cloud collaboration to address these problems has become a growing trend. This paper provides the multimedia research community with an open source framework named SmartEye for real-time video analytics by leveraging the edge-cloud collaboration. The system consists of 1) an edge layer which enables video preprocessing, model selection, on-edge inference, and task offloading; 2) a request forwarding layer which serves as a gateway of the cloud and forwards the offloaded tasks to backend workers; and 3) a backend worker layer that processes the offloaded tasks with specified DNN models. One can easily customize the policies for preprocessing, offloading, model selection, and request forwarding. The framework can facilitate research and development in this field. The project is released as an open source project on GitHub at https://github.com/MSNLAB/SmartEye.

In this work we study the problem of measuring the fairness of a machine learning model under noisy information. Focusing on group fairness metrics, we investigate the particular but common situation when the evaluation requires controlling for the confounding effect of covariate variables. In a practical setting, we might not be able to jointly observe the covariate and group information, and a standard workaround is to then use proxies for one or more of these variables. Prior works have demonstrated the challenges with using a proxy for sensitive attributes, and strong independence assumptions are needed to provide guarantees on the accuracy of the noisy estimates. In contrast, in this work we study using a proxy for the covariate variable and present a theoretical analysis that aims to characterize weaker conditions under which accurate fairness evaluation is possible. Furthermore, our theory identifies potential sources of errors and decouples them into two interpretable parts $\gamma$ and $\epsilon$. The first part $\gamma$ depends solely on the performance of the proxy such as precision and recall, whereas the second part $\epsilon$ captures correlations between all the variables of interest. We show that in many scenarios the error in the estimates is dominated by $\gamma$ via a linear dependence, whereas the dependence on the correlations $\epsilon$ only constitutes a lower order term. As a result we expand the understanding of scenarios where measuring model fairness via proxies can be an effective approach. Finally, we compare, via simulations, the theoretical upper-bounds to the distribution of simulated estimation errors and show that assuming some structure on the data, even weak, is key to significantly improve both theoretical guarantees and empirical results.

With the remarkable development and progress of earth-observation techniques, remote sensing data keep growing rapidly and their volume has reached exabyte scale. However, it’s still a big challenge to manage and process such huge amounts of remote sensing data with complex and diverse structures. This paper designs and realizes a distributed storage system for large-scale remote sensing data storage, access, and retrieval, called RSIMS (remote sensing images management system), which is composed of three sub-modules: RSIAPI, RSIMeta, RSIData. Structured text metadata of different remote sensing images are all stored in RSIMeta based on a set of uniform models, and then indexed by the distributed multi-level Hilbert grids for high spatiotemporal retrieval performance. Unstructured binary image files are stored in RSIData, which provides large scalable storage capacity and efficient GDAL (Geospatial Data Abstraction Library) compatible I/O interfaces. Popular GIS software and tools (e.g., QGIS, ArcGIS, rasterio) can access data stored in RSIData directly. RSIAPI provides users a set of uniform interfaces for data access and retrieval, hiding the complex inner structures of RSIMS. The test results show that RSIMS can store and manage large amounts of remote sensing images from various sources with high and stable performance, and is easy to deploy and use.

We demonstrate AggChecker, a novel tool for verifying textual summaries of relational data sets. The system automatically verifies natural language claims about numerical aggregates against the underlying raw data. The system incorporates a combination of natural language processing, information retrieval, machine learning, and efficient query processing strategies. Each claim is translated into a semantically equivalent SQL query and evaluated against the database. Our primary goal is analogous to that of a spell-checker: to identify erroneous claims and provide guidance in correcting them. In this demonstration, we show that our system enables users to verify text summaries much more efficiently than a standard SQL interface.

It has been an important technique to reduce sidelobes for processing nonzero Doppler target returns under Golay complementary waveforms. While the pointwise minimization processor in our early work shows an enhanced performance on the suppression of range sidelobes compared with existing approaches, it has a reduced detection probability to target with location uncertainties. In this paper, we present an alternative processing method which combines the radar returns in two separated pairs of Golay complementary waveforms through a pointwise addition processor. Our simulation result shows that this alternative method has a similar performance to that of the pointwise minimum processor for range sidelobes suppression and computational complexity but results in an improved target detection probability, with an acceptable decrease on the peak to peak-sidelobe ratio.

Absolute localization of a flying UAV on its own in a global-navigation-satellite-system (GNSS)-denied environment is always a challenge. In this paper, we present a landmark-based approach where a UAV is automatically locked into the landmark scene shown in a georeferenced image via a feedback control loop, which is driven by the output of an aerial image registration. To pursue a real-time application, we design and implement a speeded-up-robust-features (SURF)-based image registration algorithm that focuses efficiency and robustness under a 2D geometric transformation. A linear UAV controller with signals of four degrees of freedom is derived from the estimated transformation matrix. The approach is validated in a virtual simulation environment, with experimental results demonstrating the effectiveness and robustness of the proposed UAV self-localization system.

This paper considers the two-dimensional (2D) anchorless localization problem for sensor networks in global positioning system (GPS)-denied environments. We present an efficient method, based on the multidimensional scaling (MDS) algorithm, in order to estimate the positions of the nodes in the network using measurements of the inter-node distances. The proposed method takes advantage of the mobility of the nodes to address the location ambiguity problem, i.e., rotation and flip ambiguity, which arises in the anchorless MDS algorithm. Knowledge of the displacement of the moving node is used to produce an analytical solution for the noise-free case. Subsequently, a least squares estimator is presented for the noisy scenario and the associated closed-form solution derived. The simulations show that the proposed algorithm accurately and efficiently estimates the locations of nodes, outperforming alternative methods.

With the development of scientific big data technology, problem-oriented analysis becomes normal case. iAnalysis V1.0, an interactive analysis cloud service system, gives a unified cloud resource management service for scientific data analysis. It can not only be used directly by end-user scientists through the service portal, but also be called by other existing data systems in the form of docker container. In this paper, there are presented the key technical methods of iAnalysis V1.0, including the interactive analysis service solution based on container technology, the interactive analysis components and storage & high-performance computing services for interactive analysis. There are also introduced the specific application services of iAnalysis V1.0 such as lightweight deployment service, management and monitoring services, external application programming interface services and so on. Some applications of iAnalysis V1.0 are also presented. The basic deployment images of iAnalysis V1.0 can be download from https://hub.docker.com/repository/docker/bioinf/ianalysis.

Training and evaluation of fair classifiers is a challenging problem. This is partly due to the fact that most fairness metrics of interest depend on both the sensitive attribute information and label information of the data points. In many scenarios it is not possible to collect large datasets with such information. An alternate approach that is commonly used is to separately train an attribute classifier on data with sensitive attribute information, and then use it later in the ML pipeline to evaluate the bias of a given classifier. While such decoupling helps alleviate the problem of demographic scarcity, it raises several natural questions such as: how should the attribute classifier be trained?, and how should one use a given attribute classifier for accurate bias estimation? In this work we study this question from both theoretical and empirical perspectives. We first experimentally demonstrate that the test accuracy of the attribute classifier is not always correlated with its effectiveness in bias estimation for a downstream model. In order to further investigate this phenomenon, we analyze an idealized theoretical model and characterize the structure of the optimal classifier. Our analysis has surprising and counter-intuitive implications where in certain regimes one might want to distribute the error of the attribute classifier as unevenly as possible among the different subgroups. Based on our analysis we develop heuristics for both training and using attribute classifiers for bias estimation in the data scarce regime. We empirically demonstrate the effectiveness of our approach on real and simulated data.

Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much emphasis on how to well generalize models to new tasks. In this work, we propose an information disentanglement based regularization method for continual learning on text classification. Our proposed method first disentangles text hidden spaces into representations that are generic to all tasks and representations specific to each individual task, and further regularizes these representations differently to better constrain the knowledge required to generalize. We also introduce two simple auxiliary tasks: next sentence prediction and task-id prediction, for learning better generic and specific representation spaces. Experiments conducted on large-scale benchmarks demonstrate the effectiveness of our method in continual text classification tasks with various sequences and lengths over state-of-the-art baselines. We have publicly released our code at https://github.com/GT-SALT/IDBR., NAACL 2021

As multi-task models gain popularity in a wider range of machine learning applications, it is becoming increasingly important for practitioners to understand the fairness implications associated with those models. Most existing fairness literature focuses on learning a single task more fairly, while how ML fairness interacts with multiple tasks in the joint learning setting is largely under-explored. In this paper, we are concerned with how group fairness (e.g., equal opportunity, equalized odds) as an ML fairness concept plays out in the multi-task scenario. In multi-task learning, several tasks are learned jointly to exploit task correlations for a more efficient inductive transfer. This presents a multi-dimensional Pareto frontier on (1) the trade-off between group fairness and accuracy with respect to each task, as well as (2) the trade-offs across multiple tasks. We aim to provide a deeper understanding on how group fairness interacts with accuracy in multi-task learning, and we show that traditional approaches that mainly focus on optimizing the Pareto frontier of multi-task accuracy might not perform well on fairness goals. We propose a new set of metrics to better capture the multi-dimensional Pareto frontier of fairness-accuracy trade-offs uniquely presented in a multi-task learning setting. We further propose a Multi-Task-Aware Fairness (MTA-F) approach to improve fairness in multi-task learning. Experiments on several real-world datasets demonstrate the effectiveness of our proposed approach.

The vibration response of the launcher is one of the important sources of the initial disturbance of the missile launch. Based on the theory of multi-body dynamics and finite element analysis, a rigid-flexible coupling model of a vehicle-mounted missile launcher is established, and the vibration response of the launching tube is simulated. Using the method of replacing the rigid and flexible body models of the key components, the order of the main factors affecting the subsidence of the launch tube is obtained, and the conclusion that the subsidence can be reduced by increasing the rigidity of the frame and chassis is proposed.

This paper presents results of the ongoing development of a crowdsourcing platform for labelling remote sensing images. In order to perform fast spatial and temporal retrieval and read data efficiently, this paper proposes an adaptive grid design method to enable the remote sensing images being segmented into tiles, which supports parallel reading and writing, and uses Ceph cluster for storage. To guarantee crowdsourcing results' quality, a quality control mechanism combining expertsourcing and crowdsourcing is proposed. The online labelling system is designed and a prototype has been developed. Users neither have to install any software, nor download large remote sensing images. They can directly label the images by just selecting tags and drawing polygons. By providing such a platform, a large volume of training dataset for remote sensing classification can be obtained.

Hidden Markov Chains (HMCs) and, more recently, Hidden semi-Markov Chains (HsMCs) have been used by several groups of researchers to provide a model for indoor localization. A homogeneous HMC is completely determined by the state initial probability vector and the state transition probability matrix. This is also true for the HsMC provided the state duration probability is given. These parameters are often chosen heuristically but when sufficient measurement training data are available, they can be learned using the well-known Baum-Welch algorithm. Given the model parameters, approaches such as the forward-only algorithm, the forward-backwards algorithm and the Viterbi algorithm can be applied for state sequence inference under the HMC/HsMC framework. In indoor localization applications, there is often insufficient prior information to specify such parameters in advance of the application and they have to be learned from limited amounts of training data. In this paper, we endeavour to evaluate the parameter learning accuracy of the Baum-Welch algorithm using varying amounts of training data, and evaluate the influence of applying inaccurate model parameters on these typical state estimation algorithms under both the HMC and HsMC frameworks. All of the evaluations are based on received signal strength (RSS) for application to indoor localization.

We present ToTTo, an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description. To obtain generated targets that are natural but also faithful to the source table, we introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. We present systematic analyses of our dataset and annotation process as well as results achieved by several state-of-the-art baselines. While usually fluent, existing methods often hallucinate phrases that are not supported by the table, suggesting that this dataset can serve as a useful research benchmark for high-precision conditional text generation., Accepted to EMNLP 2020

NLP models are shown to suffer from robustness issues, i.e., a model's prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled Adversarial Text Generation (CAT-Gen) model that, given an input text, generates adversarial texts through controllable attributes that are known to be invariant to task labels. For example, in order to attack a model for sentiment classification over product reviews, we can use the product categories as the controllable attribute which would not change the sentiment of the reviews. Experiments on real-world NLP datasets demonstrate that our method can generate more diverse and fluent adversarial texts, compared to many existing adversarial text generation approaches. We further use our generated adversarial examples to improve models through adversarial training, and we demonstrate that our generated attacks are more robust against model re-training and different model architectures., Comment: 6 pages, accepted to EMNLP 2020

Work of Pezeshki, Calderbank and others [1, 2] has shown that choice of transmission order of Golay complementary waveforms in radar pulse trains can significantly improve Doppler resilience in detecting nonzero Doppler targets. For multiple targets a Weighted average Doppler (WD) algorithm [3] based on our earlier work has been shown to provide improvements. In this paper, we demonstrate that the Weighted Sidelobe Minimization procedure, developed in our recent work that combines the outputs of WD and the existing Binominal Design algorithms for ordering transmitted complementary waveform sequences using a point-wise minimization process (PMP), is also effective for the elimination of false target returns arising from sea clutter. A detailed analysis based on a Swerling II target model in terms of target detection probability is presented to validate the use of PMP. Our validation is strengthened by numerical simulations for both fixed and randomized scenarios.

Most mechanism contains one or more joints. However, joint clearances which cannot be dislodged make accuracy analysis become complicated. In order to seek a method to investigate the impact of joint clearances on the accuracy of a parallel robot, this paper deals with the 3-SPS-1-S spatial parallel robot’s pose error predicting and sensitivity analyzing. In this paper, a nonlinear method for evaluating the sources of the pose errors is proposed on the condition that the pose errors only come from joint clearances. Firstly, based on the nonlinear contact modes inside the joints, the error equivalent method is outlined for spherical joint and sliding pair. Then the pose error distribution over its workspace is presented. Secondly, those areas where the pose errors present abnormally changing are analyzed. Thirdly, sensitivity models are defined to evaluate how much the external variable load affects the pose errors. Finally, the simulation results, which are consistent with the structural characteristics of the 3-SPS-1-S spatial parallel robot, proved the validity of the equivalent method proposed in this paper.

In order to better standardize the process of disassembly and assembly of a certain type of surface-to-air missile co-launcher assembly frame, improve the efficiency of bomb replacement, and shorten the preparation time for combat, this paper uses Pro/E three-dimensional modeling software to perform three-dimensional modeling of the main structure of this type of co-frame launcher, and carry out the analysis of mechanical interface adaptability.

Image dehazing is a fast-growing research area in image processing and computer vision. Due to the extreme fog, haze, and air dispersion within an environment, the hazy image raises several challenges in retrieving original image information type. However, past techniques endure massive computation complexity and even the distortion of original images such as halos and over-saturation. In this research work, a new wavelet Hybrid (Local-Global Combined) Network is proposed for single image dehazing using a convolution neural network (CNN) in the wavelet domain (WH-Net). It is observed that low-level features such as edges are more important than high-level features such as texture. So we have used 2-DWT to decompose the single image model into the frequency subbands, which performs more quickly. It is demonstrated that the estimation of wavelet sub-bands reformulates the trainable end-to-end learning with a special architecture where DWT and IDWT are the feature extraction layers instead of Conv and Deconv, distinguishing it from classical CNN networks. The WHNet method is designed to achieve multi-level representations of hazy images to provide local and global information. The proposed network prominent features are designed with fewer convolution layers without decreasing performance relative to the commonly observed deeper learning models. Compared to several state-of-the-art algorithms, our proposed WHNet neural network surpasses in visual and quantitative performances on three public datasets.

Airborne LiDAR technology is a popular technique to quickly acquire high-precision information of the ground and the objects above it. Moreover, filtering the data is one of the necessary core processing steps. In recent years, many algorithms have been derived from traditional filtering algorithms. However, when applied to LiDAR data obtained from mountainous regions, most algorithms generate numerous omissions and errors when attempting to retain steep terrain features and filter vegetation information. This paper aims to quickly and accurately extract the digital terrain model (DTM) in mountainous regions. To accomplish this goal, a filtering algorithm based on a regular mesh generation strategy is proposed. The proposed algorithm initially divides the huge amount of point cloud data into strips and selects the appropriate spacing to subdivide each strip into equidistant grid data. The grid data is used as the input to an iterative polynomial fitting process, after which the point cloud is classified based on a controlled threshold. The experimental results show that the proposed method can quickly and efficiently classify data of mountains with different characteristics while retaining terrain feature information better than other algorithms. The average accuracy of recognition is greater than 92%. In addition, this algorithm also applies to mountains with lush vegetation.

Recently, there has been increasing development of positioning technology, which enables us to collect large scale trajectory data for moving objects. Efficient processing and analysis of massive trajectory data has thus become an emerging and challenging task for both researchers and practitioners. Therefore, in this paper, we propose an efficient data processing framework for mining massive trajectory data. This framework includes three modules: (1) a data distribution module, (2) a data transformation module, and (3) a high performance I/O module. Specifically, we first design a two-step consistent hashing algorithm, which takes into account load balancing, data locality, and scalability, for a data distribution module. In the data transformation module, we present a parallel strategy of a linear referencing algorithm with reduced subtask coupling, easy-implemented parallelization, and low communication cost. Moreover, we propose a compression-aware I/O module to improve the processing efficiency. Finally, we conduct a comprehensive performance evaluation on a synthetic dataset (1.114 TB) and a real world taxi GPS dataset (578 GB). The experimental results demonstrate the advantages of our proposed framework.

In this paper, we investigate the problem of detecting and tracking small targets in sea clutter using the Bernoulli Track-Before-Detect filter. This filter is an optimal recursive Bayesian detector / estimator to determine the state of a single target and its presence in noise. Typically, clutter amplitude fluctuations are modelled using the Rayleigh distribution. This assumption, however, is not valid in the maritime domain, where sea-clutter is often spikier with a longer distribution tail. In this work, we develop the Bernoulli filter for a compound Gaussian clutter model with thermal noise and model the target with a Swerling 1 fluctuation. To demonstrate the performance improvement, we model the texture as a gamma distribution, giving an overall K plus noise distribution for the clutter plus noise. The detection and tracking improvement is then demonstrated using Monte Carlo simulation.

The detection and tracking of targets in the maritime environment can be a challenging problem. One approach to improve the tracking ability of weak targets is to use track before detect (TBD). However, different TBD algorithms have different underlying assumptions about the background clutter which are not always valid. In this paper we consider three TBD algorithms: the histogram probabilistic multi-hypothesis tracker (H-PMHT), the Bernoulli filter and the multi-Bernoulli filter. The H-PMHT inherently assumes the clutter is modelled with a distribution derived from the continuous limit of the Poisson distribution, while the two Bernoulli filters both assume Rayleigh distributed clutter. To quantify performance, we use a Monte Carlo simulation with the sea clutter generated using both Rayleigh and K-distributions. The performance is then determined using the optimal sub-pattern assignment (OSPA) distance.

Semantic segmentation in high-resolution remote-sensing (RS) images is a fundamental task for RS-based urban understanding and planning. However, various types of artificial objects in urban areas make this task quite challenging. Recently, the use of Deep Convolutional Neural Networks (DCNNs) with multiscale information fusion has demonstrated great potential in enhancing performance. Technically, however, existing fusions are usually implemented by summing or concatenating feature maps in a straightforward way. Seldom do works consider the spatial importance for global-to-local context-information aggregation. This paper proposes a Learnable-Gated CNN (L-GCNN) to address this issue. Methodologically, the Taylor expression of the information-entropy function is first parameterized to design the gate function, which is employed to generate pixelwise weights for coarse-to-fine refinement in the L-GCNN. Accordingly, a Parameterized Gate Module (PGM) was designed to achieve this goal. Then, the single PGM and its densely connected extension were embedded into different levels of the encoder in the L-GCNN to help identify the discriminative feature maps at different scales. With the above designs, the L-GCNN is finally organized as a self-cascaded end-to-end architecture that is able to sequentially aggregate context information for fine segmentation. The proposed model was evaluated on two public challenging benchmarks, the ISPRS 2Dsemantic segmentation challenge Potsdam dataset and the Massachusetts building dataset. The experiment results demonstrate that the proposed method exhibited significant improvement compared with several related segmentation networks, including the FCN, SegNet, RefineNet, PSPNet, DeepLab and GSN.For example, on the Potsdam dataset, our method achieved a 93.65% F 1 score and 88.06% I o U score for the segmentation of tiny cars in high-resolution RS images. As a conclusion, the proposed model showed potential for object segmentation from the RS images of buildings, impervious surfaces, low vegetation, trees and cars in urban settings, which largely varies in size and have confusing appearances.

Modern search engines increasingly incorporate tabular content, which consists of a set of entities each augmented with a small set of facts. The facts can be obtained from multiple sources: an entity's knowledge base entry, the infobox on its Wikipedia page, or its row within a WebTable. Crucially, the informativeness of a fact depends not only on the entity but also the specific context(e.g., the query).To the best of our knowledge, this paper is the first to study the problem of contextual fact ranking: given some entities and a context (i.e., succinct natural language description), identify the most informative facts for the entities collectively within the context.We propose to contextually rank the facts by exploiting deep learning techniques. In particular, we develop pointwise and pair-wise ranking models, using textual and statistical information for the given entities and context derived from their sources. We enhance the models by incorporating entity type information from an IsA (hypernym) database. We demonstrate that our approaches achieve better performance than state-of-the-art baselines in terms of MAP, NDCG, and recall. We further conduct user studies for two specific applications of contextual fact ranking-table synthesis and table compression-and show that our models can identify more informative facts than the baselines.

Modern search engines provide contextual information surrounding query entities beyond ten blue links in the form of information cards. Among the various attributes displayed about entities there has been recent interest in providing fun facts. Obtaining such trivia at a large scale is, however, non-trivial: hiring professional content creators is expensive and extracting statements from the Web is prone to uninteresting, out-of-context and/or unreliable facts. In this paper we show how fun facts can be mined from superlative tables in Wikipedia, whose rows are ranked according to some statistics, to provide a large volume of reliable and interesting content. We employ a template-based approach to semi-automatically generate natural language statements as fun facts. We show how to bootstrap and streamline the process for faster and cheaper task completion. However, the content contained in these tables is dynamic. Therefore, we address the problem of automatically maintaining the pairing of templates to tables as the tables are updated over time. Fun facts produced by our work is now part of Google's production search results.

A design of scientific analysis service based on container technology in data cloud is presented: resource nodes are scaled up by means of automatic registration; resource nodes can be physical hosts or virtual hosts. When the utilization rate of computing resources reaches the threshold, the management node starts resource registration, subsequently, a resource host is to be registered and the available container instances are into the pool. The health of the container instance pool is maintained inside of the host. The instance lifecycle management is performed according to the maximum usage time and maximum silent time from each instance. A user can not only do analysis jobs through the interactive component, the interactive programming component or the interactive application component, which is in a separate container instance for efficient isolation of the resources, but also use data storage clusters and the high-performance computing clusters in data cloud.

How can we build recommender systems to take into account fairness? Real-world recommender systems are often composed of multiple models, built by multiple teams. However, most research on fairness focuses on improving fairness in a single model. Further, recent research on classification fairness has shown that combining multiple "fair" classifiers can still result in an "unfair" classification system. This presents a significant challenge: how do we understand and improve fairness in recommender systems composed of multiple components? In this paper, we study the compositionality of recommender fairness. We consider two recently proposed fairness ranking metrics: equality of exposure and pairwise ranking accuracy. While we show that fairness in recommendation is not guaranteed to compose, we provide theory for a set of conditions under which fairness of individual models does compose. We then present an analytical framework for both understanding whether a real system's signals can achieve compositional fairness, and improving which component would have the greatest impact on the fairness of the overall system. In addition to the theoretical results, we find on multiple datasets -- including a large-scale real-world recommender system -- that the overall system's end-to-end fairness is largely achievable by improving fairness in individual components., Comment: WSDM 2021

The launch of the new Google News in 2018 (https://www.blog.google/products/news/new-google-news-ai-meets-human-intelligence/.) introduced the Frequently asked questions feature to structurally summarize the news story in its full coverage page. While news summarization has been a research topic for decades, this new feature is poised to usher in a new line of news summarization techniques. There are two fundamental approaches: mining the questions from data associated with the news story and learning the questions from the content of the story directly. This paper provides the first study, to the best of our knowledge, of a learning based approach to generate a structured summary of news articles with question and answer pairs to capture salient and interesting aspects of the news story. Specifically, this learning-based approach reads a news article, predicts its attention map (i.e., important snippets in the article), and generates multiple natural language questions corresponding to each snippet. Furthermore, we describe a mining-based approach as the mechanism to generate weak supervision data for training the learning based approach. We evaluate our approach on the existing SQuAD dataset (https://rajpurkar.github.io/SQuAD-explorer/.) and a large dataset with 91K news articles we constructed. We show that our proposed system can achieve an AUC of 0.734 for document attention map prediction, a BLEU-4 score of 12.46 for natural question generation and a BLEU-4 score of 24.4 for question summarization, beating state-of-art baselines.

Optimal trajectories for two platforms with similar dynamics are calculated using a game theoretic formulation. Each platform makes noisy observations of the kinematic state of the other. The objective of each is to maximise observable information about the other while minimising the information the other is able to acquire about it. That is to say, each platform maximises the mutual information between the expected future measurement of the opposing platform and the current likelihood of the state whilst minimising the estimated mutual information between potential measurements of itself by the other and its actual state. The multi-objective optimisation problem for each platform is converted to a single optimisation using the Pareto parameter to weigh the relative importance of the two information measures. The relationship between the two Pareto parameters, and different initial track initialisations is investigated. Remarkably this complex coupled system of two platforms exhibits, for suitably chosen values of the Pareto parameters, interesting cyclical behaviours that are worthy of further exploration.

Multipath propagation makes the use of received signal strength (RSS) unreliable as a signal propagation model for localization of a radio source based on RSS data. An approach to mitigation of this problem is the use of a Hidden Markov model (HMM) to represent the relationship between RSS and the radio source location by incorporating an environment prior and RSS source dynamics. The HMM structure forces a geometric form for the distribution for the sojourn time. This, combined with missing data problems, reduces confidence in location estimation. It is found, in this paper, that Hidden semi-Markov Models (HsMMs), with a more flexible sojourn time distribution are more able to represent source dynamics while retaining the advantages of HMMs for environmental constraints and improving resilience to missing measurements. The performance of the proposed HsMM algorithm is compared with a standard HMM via experiments and simulations involving indoor radio source localization using RSS data. Simulations use a ray tracing software-based simulator and the experiments for transmitter localization with RSS data are collected by software defined radios.

In this work, we study the case of tracking a moving sensor using the radio interferometric positioning system measurements. The system consists of four wireless network nodes and it measures the sum of signal phase differences between two receivers while the other two are transmitting sine waves at close frequencies. With the locations of three sensors known, we can estimate the fourth sensor moving trajectory from a sequence of phase measurements using a nonlinear filter. Two nonlinear filters, a natural gradient Kalman filter and a extended Kalman filter, are investigated and implemented for this moving sensor tracking problem. The performances of them are compared in a computer simulated tracking experiment.

Diverse storage formats, archive dispersal, and inconsistent naming make it difficult for researchers and the general public to find and access remote sensing data. To facilitate the use of remote sensing data, this paper provides an integrated framework for direct reading remote sensing data in a widely compatible and analysis-ready format, NumPy ndarray. The framework is composed of two main components. One is the raster data processing and storage model. All the operational gridded remote sensing data are split into tiles, and reorganized in n-dimensional array. Then the N-Dimensional data array is serialized into netCDF and stored into distributed file system. The other is the spatiotemporal filter to achieve parallel query, and it has been encapsulated into Internet-accessible application programming interfaces (APIs). The scenario of calculating NDVI of a specified spatiotemporal range given at last illustrate the efficiency and convenience of our platform provided for remote sensing data analysis.

This paper considers the joint recursive estimation of the dynamic state and the time-varying process noise covariance for a linear state space model. The conjugate prior on the process noise covariance, the inverse Wishart distribution, provides a latent variable. A variational Bayesian inference framework is then adopted to iteratively estimate the posterior density functions of the dynamic state, process noise covariance and the introduced latent variable. The performance of the algorithm is demonstrated with simulated data in a target tracking application.

The Chinese Remainder Theorem (CRT) enables phase unwrapping for measurement of a distance using multiple wrapped phases of sinusoidal transmissions, such as in radar, sonar, or wireless geolocation. In the presence of measurement noise, the existing CRT algorithm assumes that the correct number of wrapping wavelengths can be obtained after a round off operation by ignoring the received signal noise. In this paper, additional hypotheses for the output of the round off process are formulated and a modified CRT algorithm for range estimation is proposed. We show that an improved distance reconstruction rate over the existing CRT algorithm is achieved from both analytical calculations and numerical simulations.

We present a novel natural language query interface, the AggChecker, aimed at text summaries of relational data sets. The tool focuses on natural language claims that translate into an SQL query and a claimed query result. Similar in spirit to a spell checker, the AggChecker marks up text passages that seem to be inconsistent with the actual data. At the heart of the system is a probabilistic model that reasons about the input document in a holistic fashion. Based on claim keywords and the document structure, it maps each text claim to a probability distribution over associated query translations. By efficiently executing tens to hundreds of thousands of candidate translations for a typical input document, the system maps text claims to correctness probabilities. This process becomes practical via a specialized processing backend, avoiding redundant work via query merging and result caching. Verification is an interactive process in which users are shown tentative results, enabling them to take corrective actions if necessary. Our system was tested on a set of 53 public articles containing 392 claims. Our test cases include articles from major newspapers, summaries of survey results, and Wikipedia articles. Our tool revealed erroneous claims in roughly a third of test cases. A detailed user study shows that users using our tool are in average six times faster at checking text summaries, compared to generic SQL interfaces. In fully automated verification, our tool achieves significantly higher recall and precision than baselines from the areas of natural language query interfaces and fact-checking., Comment: 18 pages, 13 figures, 11 tables

With the support of major search platforms such as Google and Bing, fact-checking articles, which can be identified by their adoption of the schema.org ClaimReview structured markup, have gained widespread recognition for their role in the fight against digital misinformation. A claim-relevant document is an online document that addresses, and potentially expresses a stance towards, some claim. The claim-relevance discovery problem, then, is to find claim-relevant documents. Depending on the verdict from the fact check, claim-relevance discovery can help identify online misinformation. In this paper, we provide an initial approach to the claim-relevance discovery problem by leveraging various information retrieval and machine learning techniques. The system consists of three phases. First, we retrieve candidate documents based on various features in the fact-checking article. Second, we apply a relevance classifier to filter away documents that do not address the claim. Third, we apply a language feature based classifier to distinguish documents with different stances towards the claim. We experimentally demonstrate that our solution achieves solid results on a large-scale dataset and beats state-of-the-art baselines. Finally, we highlight a rich set of case studies to demonstrate the myriad of remaining challenges and that this problem is far from being solved.

In this paper, we present a method for estimating the location of a WiFi transmitter by a receiver using the radio resource and knowledge of the indoor room structure. We derive a three-ray path propagation model for the received radio signal in a known indoor environment. We show that the position of the transmitter could be localized using the received radio signal measurements. The likelihood under this model exhibits multiple local peaks when only few frequencies are used, which leads to the location ambiguities under the Maximum Likelihood criterion. We observed in simulation that the ambiguous locations under the Maximum Likelihood estimation vary with the WiFi radio frequency used but the ground truth location is always presented as a peak. Therefore, we use multiple WiFi frequency bands to resolve the localization ambiguity. A subspace based method is applied in combination with Maximum Likelihood method utilizing the same set of measurements to improve localization efficiency. Simulation using commercial ray tracing software presents promising result.

Hydrometeor classification methods using polarimetric radar variables rely on probability density functions (PDFs) or membership functions derived empirically or by using electromagnetic scattering calculations. This paper describes an objective approach based on cluster analysis to deriving the PDFs. An iterative procedure with K-means clustering and expectation–maximization clustering based on Gaussian mixture models is developed to generate a series of prototypes for each hydrometeor type from several radar scans. The prototypes are then grouped together to produce a PDF for each hydrometeor type, which is modeled as a Gaussian mixture. The cluster-based method is applied to polarimetric radar data collected with the CP-2 S-band radar near Brisbane, Queensland, Australia. The results are illustrated and compared with theoretical classification boundaries in the literature. Some notable differences are found. Automated hydrometeor classification algorithms can be built using the PDFs of polarimetric variables associated with each hydrometeor type presented in this paper.

In this paper, we investigate cooperative passive sensor trajectory planning for tracking a target where the tracking error is sensor trajectory dependent. We consider the problem under a scenario of tracking a moving target using two unmanned bearings-only sensors. The basic idea is to maximise the target information acquired from the processing measurements of the two sensors by cooperatively scheduling their future trajectories at which sensor measurements will be taken. In the literature this problem is modeled by a partially observed Markov decision process and optimal action which maximises an expected reward function is sought. Three reward functions, namely, the Expected Reward, the Determinant, and Trace of the associated Fisher Information Matrix (FIM) for the underlying problem are analysed and discussed. These rewards may only be evaluated practically through various approximations. We show that the correlation between two sensor states is weakened significantly for the Expected Reward due to linearisation and thus the closed-form Expected Reward as well as the Trace of FIM are inappropriate for this sensor trajectory scheduling problem. Finally, we present simulation results which are based on the example of a non-cooperative target chasing via two cooperative bearing-only sensors.

The Radio Frequency Identification (RFID) is a rapidly developing technology with growing applications in several fields. One of the key applications is the localisation of tagged objects using signal phase difference information via dual-frequency technology. In this application, unwrapping signal phases to acquire the range between the reader and RFID tag is the major issue that has typically been addressed in the literature using either the Chinese Remainder Theorem or Lattice Theory. In this paper, a lattice-based method robust to phase measurement noise is presented to resolve the wrapped range. The proposed algorithm is shown to be more robust and efficient than existing approaches in terms of the reconstruction probability. Simulations are presented to illustrate the performance of the proposed algorithm.

Search engines make significant efforts to recognize queries that can be answered by structured data and invest heavily in creating and maintaining high-precision databases. While these databases have a relatively wide coverage of entities, the number of attributes they model (e.g., GDP, CAPITAL, ANTHEM) is relatively small. Extending the number of attributes known to the search engine can enable it to more precisely answer queries from the long and heavy tail, extract a broader range of facts from the Web, and recover the semantics of tables on the Web. We describe Biperpedia, an ontology with 1.6M (class, attribute) pairs and 67K distinct attribute names. Biperpedia extracts attributes from the query stream, and then uses the best extractions to seed attribute extraction from text. For every attribute Biperpedia saves a set of synonyms and text patterns in which it appears, thereby enabling it to recognize the attribute in more contexts. In addition to a detailed analysis of the quality of Biperpedia, we show that it can increase the number of Web tables whose semantics we can recover by more than a factor of 4 compared with Freebase.

Temperature, solar radiation and water are major important variables in ecosystem models which are measurable via wireless sensor networks (WSN). Effective data analysis is necessary to extract significant spatial and temporal information. In this work, information regarding the long term variation of seasonal field environment conditions is explored using Hilbert-Huang transform (HHT) based analysis on the wireless sensor network data collection. The data collection network, consisting of 36 wireless nodes, covers an area of 100 square kilometres in Yanqing, the northwest of Beijing CBD, in China and data collection involves environmental parameter observations taken over a period of three months in 2011. The analysis used the empirical mode decomposition (EMD/EEMD) to break a time sequence of data down to a finite set of intrinsic mode functions (IMFs). Both spatial and temporal properties of data explored by HHT analysis are demonstrated. Our research shows potential for better understanding the spatial-temporal relationships among environmental parameters using WSN and HHT.