The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, a method for reducing coding artifacts introduced by lossy image compression is proposed. The method is similar to sample adaptive offset (SAO) which is adopted in the H.265/HEVC video coding standard as one of in-loop filtering tools. In the SAO, samples of the reconstructed image are classified into several categories based on some simple algorithms, and an optimum offset value is...
Context: Software Bug Severity Classification can help to improve the software bug triaging process. However, severity levels present a high-level of data imbalance that needs to be taken into account. Aim: We investigate cost-sensitive strategies in multi-class bug severity classification to counteract data imbalance. Method: We transform datasets from three severity classification papers to a common...
Recognizing secondary structures in proteins can be a highly computationally expensive task that may not always yield good results. Using Restricted Boltzmann Machines (RBM) we were able to train a simple neural network to recognize an alpha-helix with a good degree of accuracy. Modifying the RBM implementation to be much simpler and more efficient than the standard implementation we are able to see...
In this paper, we present artificial neural network (ANN) models to predict hard and soft-responses of three configurations of arbiter based physical unclonable functions (PUFs): standard, feed-forward (FF) and modified feed-forward (MFF). The models are trained using data extracted from 32-stage arbiter PUF circuits fabricated using IBM 32 nm HKMG process. The contributions of this paper are two-fold...
The goals of this paper were twofold: to continue and refine previous research in the topic of tree cover type classification by harnessing modern machine learning models, and to extend the conclusions of that work to demonstrate that results gained from such models can be used to assist U.S. land management agencies in current challenges they face. Using the same dataset as the past study, an artificial...
Detecting bird sounds in audio recordings automatically, if accurate enough, is expected to be of great help to the research community working in bio- and ecoacoustics, interested in monitoring biodiversity based on audio field recordings. To estimate how accurate the state-of-the-art machine learning approaches are, the Bird Audio Detection challenge involving large audio datasets was recently organized...
The vulnerability of automatic speaker verification (ASV) systems against spoofing attacks is an important security concern about the reliability of ASV technology. Recently, various countermeasures have been developed for spoofing detection. In this paper, we propose to use features derived from linear prediction (LP) residual signal for spoofing detection using simple Gaussian mixture model (GMM)...
We present a probabilistic framework for both (i) determining the initial settings of kernel adaptive filters (KAFs) and (ii) constructing fully-adaptive KAFs whereby in addition to weights and dictionaries, kernel parameters are learnt sequentially. This is achieved by formulating the estimator as a probabilistic model and defining dedicated prior distributions over the kernel parameters, weights...
With the wide spread of SNS (including Twitter, Facebook, and Flickr), there is a great demand for analyzing the associated Web contents consisting of a vast amount of opinions posted from anonymous users. Such opinions usually have explicit or implicit polarities. The polarity determination for short texts like Twitter is, however, very difficult. In this paper, we propose a method for sentiment...
Attention Deficit Hyperactivity Disorder (ADHD) is a disorder of performance with core symptoms of inattention, hyperactivity or impulsivity. In adults, hyperactivity may decrease, but struggles with inattention or impulsivity may continue. Neurofeedback game can be used as an alternative approach to enhance attention. In this pilot study, we developed a neurofeedback game for attention training in...
Artificial neural networks (ANN) have revolutionized the field of machine learning by providing impressive human-like performance in solving real-world tasks in computer vision, speech recognition, or complex strategic games. There is a significant interest in developing non-von Neumann coprocessors for the training of ANNs, where resistive memory devices serve as synaptic elements. However, interdevice...
This paper proposes a statistical method to detection of Topological Charges (TCs) based on calculating the similarity factor (SF) between the instantaneous crosstalk distribution and the standard crosstalk distributions. The values of SF are time-varying, and we set a threshold to recognize TCs. Then, the probability density function (PDF) of the SF is obtained to estimate error rate of TC detection...
In this paper we propose a cluster based version of the anomaly detection methodology based on signal reconstruction, using Auto Associative Kernel Regression (AAKR), combined with residuals analysis, using Sequential Probability Ratio Test (SPRT). We demonstrate how the proposed cluster based methodology can be successfully applied for anomaly detection on a marine diesel engine in operation. Furthermore,...
Feature representation plays an important role in text classification. Feature mapping based on labels information is an algorithm suitable for Binary Relevance. Compared with the conventional text representation, it makes the dimension of the text under control by means of word embedding. More importantly, it takes full advantage of the general characteristics of the label on text representation...
Traffic anomaly detection is primarily concerned with identifying malicious traffic patterns in a much larger stream of benign traffic. Traditionally, this is achieved by selecting a very specialized set of traffic-based features that are used for both training a model, as well as for detection at runtime. This paper introduces a novel method of anomaly detection that breaks the assumption that the...
Deep neural networks (DNNs) achieve excellent performance on standard classification tasks. However, under image quality distortions such as blur and noise, classification accuracy becomes poor. In this work, we compare the performance of DNNs with human subjects on distorted images. We show that, although DNNs perform better than or on par with humans on good quality images, DNN performance is still...
Object detectors have hugely profited from moving towards an end-to-end learning paradigm: proposals, fea tures, and the classifier becoming one neural network improved results two-fold on general object detection. One indispensable component is non-maximum suppression (NMS), a post-processing algorithm responsible for merging all detections that belong to the same object. The de facto standard NMS...
Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs or triplets of samples. Many of these relations are unreliable and mutually contradicting, implying inconsistencies when trained without supervision information...
Pooling second-order local feature statistics to form a high-dimensional bilinear feature has been shown to achieve state-of-the-art performance on a variety of fine-grained classification tasks. To address the computational demands of high feature dimensionality, we propose to represent the covariance features as a matrix and apply a low-rank bilinear classifier. The resulting classifier can be evaluated...
Training convolutional networks (CNNs) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is still no effective method for training large networks that do not fit in the memory of a few GPU cards, or for parallelizing CNN training. In this work we show that a simple hard mixture of experts model can be efficiently trained to good effect...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.