Fixed Window Size Research Articles

A real-time aggregate data publishing scheme with adaptive <i>ω</i>-event differential privacy

Although massive real-time data collected from users can provide benefits to improve the quality of human daily lives, it is possible to expose users' privacy. $\epsilon$-differential privacy is a notable model to provide strong privacy preserving in statistics. The existing works highlight $ω$-event differential privacy with a fixed window size, which may not be suitable for many practical scenarios. In view of this issue, we explore a real-time scheme with adaptive $ω$-event for differentially private time-series publishing (ADP) in this paper. In specific, we define a novel notion, Quality of Privacy (QoP) to measure both the utility of the released statistics and the performance of privacy preserving. According to this, we present an adaptive $ω$-event differential privacy model that can provide privacy protection with higher accuracy and better privacy protection effect. In addition, we also design a smart grouping mechanism to improve the grouping performance, and then improve the availability of publishing statistics. Finally, comparing with the existing schemes, we exploit real-world and synthetic datasets to conduct several experiments to demonstrate the superior performance of the ADP scheme.

Hyperspectral Image Classification Using Joint Sparse Model and Discontinuity Preserving Relaxation

As a promising signal processing technique, a joint sparse model (JSM) has been used to integrate spatial and spectral information in the classification of remotely sensed images. This technique defines a local region of a fixed window size and assumes an equal contribution from each neighborhood pixel in the classification process of the test pixel. However, equal weighting is less reasonable for heterogeneous pixels, especially around class boundaries. Hence, a discontinuity preserving relaxation (DPR) method can be used to locally smooth the results without crossing the boundaries by detecting the discontinuities of an image in advance. In this letter, we developed a novel strategy that combines these two methods to improve the hyperspectral image classification. A JSM is first applied to obtain a posteriori probability distribution of pixels and then a DPR method is used to further improve the classification results. Experiments conducted on two benchmark data sets demonstrate that the proposed method leads to superior performance when compared with several popular algorithms.

Sliding Window Top-K Monitoring over Distributed Data Streams

Most of the traditional top-k algorithms are based on a single-server setting. They may be highly inefficient and/or cause huge communication overhead when applied to a distributed system environment. Therefore, the problem of top-k monitoring in distributed environments has been intensively investigated recently. This paper studies how to monitor the top-k data objects with the largest aggregate numeric values from distributed data streams within a fixed-size monitoring window W, while minimizing communication cost across the network. We propose a novel algorithm, which adaptively reallocates numeric values of data objects among distributed nodes by assigning revision factors when local constraints are violated and keeps the local top-k result at distributed nodes in line with the global top-k result. We also develop a framework that combines a distributed data stream monitoring architecture with a sliding window model. Based on this framework, extensive experiments are conducted on top of Apache Storm to verify the efficiency and scalability of the proposed algorithm.

Adaptive Bus Encoding for Transition Reduction on Off-Chip Buses With Dynamically Varying Switching Characteristics

This paper presents an adaptive encoding framework for the reduction of transition activity in high-capacitance off-chip data buses, since power dissipation associated with those buses can be significant for high-speed communication. The technique relies on the observation of data characteristics over fixed window sizes and formation of cluster with bit lines having highly correlated switching patterns. The proposed method utilizes redundancy in space and time to prevent loss of information while retrieving data. We present analytical and experimental analyses, which demonstrate the activity reduction of our encoding scheme for various data. The extra power cost due to the encoder and decoder circuitry along with redundancy is offset due to reduced number of off-chip transitions.

Mosdepth: quick coverage calculation for genomes and exomes

Summary Mosdepth is a new command-line tool for rapidly calculating genome-wide sequencing coverage. It measures depth from BAM or CRAM files at either each nucleotide position in a genome or for sets of genomic regions. Genomic regions may be specified as either a BED file to evaluate coverage across capture regions, or as a fixed-size window as required for copy-number calling. Mosdepth uses a simple algorithm that is computationally efficient and enables it to quickly produce coverage summaries. We demonstrate that mosdepth is faster than existing tools and provides flexibility in the types of coverage profiles produced.Availability and implementation mosdepth is available from https://github.com/brentp/mosdepth under the MIT license.Supplementary information Supplementary data are available at Bioinformatics online.

Categorisation of polyphonic musical signals by using modularity community detection in audio-associated visibility network

This article proposes a method to numerically characterise the homogeneity of polyphonic musical signals through community detection in audio-associated visibility networks and to detect patterns that allow the categorisation of these signals into two types of grouping based on this numerical characterization. To implement this methodology, we first calculate the variance fluctuation series in fixed-size windows of an audio stretch. Next we map this series onto a visibility graph, where the nodes are the points of the series, and the edges are defined by the visibility between each pair of points. Then, we measure the quality of the partitions of the network using the modularity and Louvain optimisation. We observed that a greater or lesser homogeneity of the magnitudes of the signal transients is related to a higher or lower modularity of the audio-associated visibility network. We also note that these differences are related to musical choices that can establish important differences between musical styles. In this article, we show that the modularity is able to give relevant information to allow the categorisation of 120 musical signs labelled in percussive and symphonic music.

Sliding‐window forward error correction using Reed‐Solomon code and unequal error protection for real‐time streaming video

SummaryForward error correction (FEC) techniques are widely used to recover packet losses over unreliable networks in real‐time video streaming applications. Traditional frame‐level FEC encodes 1 video frame in each FEC coding window. By contrast, in the expanding‐window FEC scheme, high‐priority frames are included in the FEC processing of the following frames, so as to construct a larger coding window. In general, expanding‐window FEC improves the recovery performance of FEC, because the high‐priority frame can be protected by multiple windows and the use of a larger coding window increases the efficiency. However, the larger window size also increases the complexity of the coding and the memory space requirements. Consequently, expanding‐window FEC is limited in terms of practical applications. Sliding‐window FEC adopts a fixed window size in order to approximate the performance of the expanding‐window FEC method, but with a reduced complexity. Previous studies on sliding‐window FEC have generally adopted an equal error protection (EEP) mechanism to simplify the analysis. This paper considers the more practical case of an unequal error protection (UEP) strategy. An analytical model is derived for estimating the playable frame rate (PFR) of the proposed sliding‐window FEC scheme with a Reed‐Solomon erasure code for real‐time non‐scalable streaming applications. The analytical model is used to determine the optimal FEC configuration which maximizes the PFR value under given transmission rate constraints. The simulation results show that the proposed sliding‐window scheme achieves almost the same performance as the expanding‐window scheme, but with a significantly lower computational complexity.

Kernel based online learning for imbalance multiclass classification

In this paper, we propose a weighted online sequential extreme learning machine with kernels (WOS-ELMK) for class imbalance learning (CIL). The existing online sequential extreme learning machine (OS-ELM) methods for CIL use random feature mapping. WOS-ELMK is the first OS-ELM method which uses kernel mapping for online class imbalance learning. The kernel mapping avoids the non-optimal hidden node problem associated with weighted OS-ELM (WOS-ELM) and other existing OS-ELM methods for CIL. WOS-ELMK tackles both the binary class and multiclass imbalance problems in one-by-one as well as chunk-by-chunk learning modes. For imbalanced big data streams, a fixed size window scheme is also implemented for WOS-ELMK. We empirically show that WOS-ELMK obtains superior performance in general than some recently proposed CIL approaches on 17 binary class and 8 multiclass imbalanced datasets.

Speckle filtering of Synthetic Aperture Radar images using filters with object-size-adapted windows

ABSTRACTSpeckle degrades the radiometric quality of a Synthetic Aperture Radar (SAR) image. Previous methods for speckle reduction have used a fixed-size window for filtering the entire image. This, however, may not be effective for the entire image, as land covers of different sizes require different filtering windows. In this paper, a novel method is proposed by which each pixel in the image is filtered with a window appropriate for the size of object within it. The real in-phase and the imaginary quadrature components of the SAR images determine the best window size and the pixels in the intensity image are filtered using their own optimal windows. The proposed method is presented for both single- and multi-polarized SAR images, and the results of several common filters that were modified are presented. This approach is applied to two RADARSAT-2 images: one over San Francisco, California, USA and the other over St. John’s, Newfoundland and Labrador, Canada, producing results that were similar to, or outperformed, comparable filters while retaining details and suppressing speckle effectively. While the method was successful for single-look intensity data, it offers great potential for multi-look and amplitude data as well.

Exploiting Unlabeled Data for Neural Grammatical Error Detection

Identifying and correcting grammatical errors in the text written by non-native writers have received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical error detection and correction approaches, they are still limited in terms of quantity and coverage because human annotation is labor-intensive, time-consuming, and expensive. In this work, we propose to utilize unlabeled data to train neural network based grammatical error detection models. The basic idea is to cast error detection as a binary classification problem and derive positive and negative training examples from unlabeled data. We introduce an attention-based neural network to capture long-distance dependencies that influence the word being detected. Experiments show that the proposed approach significantly outperforms SVM and convolutional networks with fixed-size context window.

Local Competition-Based Superpixel Segmentation Algorithm in Remote Sensing.

Remote sensing technologies have been widely applied in urban environments’ monitoring, synthesis and modeling. Incorporating spatial information in perceptually coherent regions, superpixel-based approaches can effectively eliminate the “salt and pepper” phenomenon which is common in pixel-wise approaches. Compared with fixed-size windows, superpixels have adaptive sizes and shapes for different spatial structures. Moreover, superpixel-based algorithms can significantly improve computational efficiency owing to the greatly reduced number of image primitives. Hence, the superpixel algorithm, as a preprocessing technique, is more and more popularly used in remote sensing and many other fields. In this paper, we propose a superpixel segmentation algorithm called Superpixel Segmentation with Local Competition (SSLC), which utilizes a local competition mechanism to construct energy terms and label pixels. The local competition mechanism leads to energy terms locality and relativity, and thus, the proposed algorithm is less sensitive to the diversity of image content and scene layout. Consequently, SSLC could achieve consistent performance in different image regions. In addition, the Probability Density Function (PDF), which is estimated by Kernel Density Estimation (KDE) with the Gaussian kernel, is introduced to describe the color distribution of superpixels as a more sophisticated and accurate measure. To reduce computational complexity, a boundary optimization framework is introduced to only handle boundary pixels instead of the whole image. We conduct experiments to benchmark the proposed algorithm with the other state-of-the-art ones on the Berkeley Segmentation Dataset (BSD) and remote sensing images. Results demonstrate that the SSLC algorithm yields the best overall performance, while the computation time-efficiency is still competitive.

Extracting reference text from citation contexts

Information from the textual context of citations in scientific articles has been studied and used in many applications by the research community. For example, it has been used in topic modeling, sentiment analysis, scientific paper summarization and information retrieval. However, these applications suffer the problem of right identification of citation context window and alternately use the text in a fixed size window around the citation mention. In this way, citation contexts may contain terms or other text that is not used for describing the citation and should not be included in the citation context. Identifying such non-reference text in the citation context is a non-trivial task, yet significant. In this paper, it is attempted to identify and remove the non-reference text from the citation contexts by developing a heuristic algorithm based on pruning the transition-based dependency parse tree. Evaluating the accuracy of our algorithm, results showed 77% macro-precision, 83% macro-recall and 80% F-macro for 88 research articles of testing dataset having varying number of citations. Additionally, we find that for many of the cited articles in our testing dataset, the number of objective citation contexts is more than subjective ones.

Evolving, dynamic clustering of spatio/spectro-temporal data in 3D spiking neural network models and a case study on EEG data

Clustering is a fundamental data processing technique. While clustering of static (vector based) data and of fixed window size time series have been well explored, dynamic clustering of spatiotemporal data has been little researched if at all. Especially when patterns of changes (events) in the data across space and time have to be captured and understood. The paper presents novel methods for clustering of spatiotemporal data using the NeuCube spiking neural network (SNN) architecture. Clusters of spatiotemporal data were created and modified on-line in a continuous, incremental way, where spatiotemporal relationships of changes in variables are incrementally learned in a 3D SNN model and the model connectivity and spiking activity are incrementally clustered. Two clustering methods were proposed for SNN, one performed during unsupervised and one—during supervised learning models. Before submitted to the models, the data is encoded as spike trains, a spike representing a change in the variable value (an event). During the unsupervised learning, the cluster centres were predefined by the spatial locations of the input data variables in a 3D SNN model. Then clusters are evolving during the learning, i.e. they are adapted continuously over time reflecting the dynamics of the changes in the data. In the supervised learning, clusters represent the dynamic sequence of neuron spiking activities in a trained SNN model, specific for a particular class of data or for an individual instance. We illustrate the proposed clustering method on a real case study of spatiotemporal EEG data, recorded from three groups of subjects during a cognitive task. The clusters were referred back to the brain data for a better understanding of the data and the processes that generated it. The cluster analysis allowed to discover and understand differences on temporal sequences and spatial involvement of brain regions in response to a cognitive task.

Adaptive background model registration for moving cameras

We propose a framework for adaptively registering background models with an image for background subtraction with moving cameras. Existing methods search for a background model using a fixed window size, to suppress the number of false positives when detecting the foreground. However, these approaches result in many false negatives because they may use inappropriate window sizes. The appropriate size depends on various factors of the target scenes. To suppress false detections, we propose adaptively controlling the method parameters, which are typically determined heuristically. More specifically, the search window size for background registration and the foreground detection threshold are automatically determined using the re-projection error computed by the homography based camera motion estimate. Our method is based on the fact that the error at a pixel is low if it belongs to background and high if it does not. We quantitatively confirmed that the proposed framework improved the background subtraction accuracy when applied to images from moving cameras in various public datasets.

Image classification for detection of winter grapevine buds in natural conditions using scale-invariant features transform, bag of features and support vector machines

In viticulture, there are several applications where bud detection in vineyard images is a necessary task, susceptible of being automated through the use of computer vision methods. A common and effective family of visual detection algorithms are the scanning-window type, that slide a (usually) fixed size window along the original image, classifying each resulting windowed-patch as containing or not containing the target object. The simplicity of these algorithms finds its most challenging aspect in the classification stage. Interested in grapevine buds detection in natural field conditions, this paper presents a classification method for images of grapevine buds ranging 100–1600 pixels in diameter, captured in outdoor, under natural field conditions, in winter (i.e., no grape bunches, very few leaves, and dormant buds), without artificial background, and with minimum equipment requirements. The proposed method uses well-known computer vision technologies: Scale-Invariant Feature Transform for calculating low-level features, Bag of Features for building an image descriptor, and Support Vector Machines for training a classifier. When evaluated over images containing buds of at least 100 pixels in diameter, the approach achieves a recall higher than 0.9 and a precision of 0.86 over all windowed-patches covering the whole bud and down to 60% of it, and scaled up to window patches containing a proportion of 20–80% of bud versus background pixels. This robustness on the position and size of the window demonstrates its viability for use as the classification stage in a scanning-window detection algorithms.

Adaptive local window for level set segmentation of CT and MRI liver lesions.

We propose a novel method, the adaptive local window, for improving level set segmentation technique. The window is estimated separately for each contour point, over iterations of the segmentation process, and for each individual object. Our method considers the object scale, the spatial texture, and the changes of the energy functional over iterations. Global and local statistics are considered by calculating several gray level co-occurrence matrices. We demonstrate the capabilities of the method in the domain of medical imaging for segmenting 233 images with liver lesions. To illustrate the strength of our method, those lesions were screened by either Computed Tomography or Magnetic Resonance Imaging. Moreover, we analyzed images using three different energy models. We compared our method to a global level set segmentation, to a local framework that uses predefined fixed-size square windows and to a local region-scalable fitting model. The results indicate that our proposed method outperforms the other methods in terms of agreement with the manual marking and dependence on contour initialization or the energy model used. In case of complex lesions, such as low contrast lesions, heterogeneous lesions, or lesions with a noisy background, our method shows significantly better segmentation with an improvement of 0.25 ± 0.13 in Dice similarity coefficient, compared with state of the art fixed-size local windows (Wilcoxon, p < 0.001).

A Spectral-Texture Kernel-Based Classification Method for Hyperspectral Images

Classification of hyperspectral images always suffers from high dimensionality and very limited labeled samples. Recently, the spectral-spatial classification has attracted considerable attention and can achieve higher classification accuracy and smoother classification maps. In this paper, a novel spectral-spatial classification method for hyperspectral images by using kernel methods is investigated. For a given hyperspectral image, the principle component analysis (PCA) transform is first performed. Then, the first principle component of the input image is segmented into non-overlapping homogeneous regions by using the entropy rate superpixel (ERS) algorithm. Next, the local spectral histogram model is applied to each homogeneous region to obtain the corresponding texture features. Because this step is performed within each homogenous region, instead of within a fixed-size image window, the obtained local texture features in the image are more accurate, which can effectively benefit the improvement of classification accuracy. In the following step, a contextual spectral-texture kernel is constructed by combining spectral information in the image and the extracted texture information using the linearity property of the kernel methods. Finally, the classification map is achieved by the support vector machines (SVM) classifier using the proposed spectral-texture kernel. Experiments on two benchmark airborne hyperspectral datasets demonstrate that our method can effectively improve classification accuracies, even though only a very limited training sample is available. Specifically, our method can achieve from 8.26% to 15.1% higher in terms of overall accuracy than the traditional SVM classifier. The performance of our method was further compared to several state-of-the-art classification methods of hyperspectral images using objective quantitative measures and a visual qualitative evaluation.

Adaptive sliding window segmentation for physical activity recognition using a single tri-axial accelerometer

Previous studies on physical activity recognition have utilized various fixed window sizes for signal segmentation targeting specific activities. Naturally, an optimum window size varies depending on the characteristics of activity signals and fixed window size will not produce good segmentation for all activities. This paper presents a novel approach to activity signal segmentation for physical activity recognition. Central to the approach is that the window size is adaptively adjusted according to the probability of the signal belongs to a particular activity to achieve the most effective segmentation. In addition, an activity transition diagram for activity recognition is developed to validate the activity transition and improve recognition accuracy. The adaptive sliding window segmentation algorithm and the role of activity transition diagram are described in the context of physical activity recognition. The approach recognizes not only well defined static and dynamic activities, but also transitional activities. The presented approach has been implemented, evaluated and compared with an existing state-of-the-art approach by using internal and public datasets which contains activity signals of dynamic, static and transitional activities. Results have shown that the proposed adaptive sliding window segmentation achieves overall accuracy of 95.4% in all activities considered in the experiments compared to the existing approach which achieved an overall accuracy of 89.9%. The proposed approach achieved an overall accuracy of 96.5% compared to 91.9% overall accuracy with the existing approach when tested on the public dataset.

Adaptive data processing for real-time nutrition monitoring.

The issue of time-series segmentation refers to the division of continuous sensor data into discrete windows, each of which are processed individually and assigned a class label. Unlike offline data processing scenarios, segmentation for low-power wearable devices must balance the juxtaposed aims of accuracy and computational efficiency. In this paper, we propose a novel scheme for segmentation of sparse sensor data using an adaptive window size approach. Our results are benchmarked on an audio-based nutrition monitoring dataset, and show a reduction in processing overhead of 68% compared to the baseline with fixed window sizes.

Probabilistic segmentation of time-series audio signals using Support Vector Machines

To allow health tracking, patient monitoring, and provide timely user interventions, sensor signals from body sensor networks need to be processed in real-time. Time subdivisions of the sensor signals are extracted and fed into a supervised learning algorithm, such as Support Vector Machines (SVM), to learn a model capable of distinguishing different class labels. However, selecting a short-duration window from the continuous data stream is a significant challenge, and the window may not be properly centered around the activity of interest. In this work, we address the issue of window selection from a continuous data stream, using an optimized SVM-based probability model. To evaluate the effectiveness of our approach, we apply our algorithm to audio signals acquired from a wearable nutrition-monitoring necklace. Our optimized algorithm is capable of correctly classifying 86.1% of instances, compared to a baseline of 73% which segments the time-series data with fixed-size non-overlapping windows, and an exhaustive-search approach with an accuracy of 92.6%.11This work is funded by the National Science Foundation AIR Option 1: Award Number 1312310.