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.
This paper firstly analyzes the shortcoming of a self-organizing incremental neural network (SOINN), then proposes a novel online similarity metric and online adaptive kernel density estimator to handle 2 basic problems of unsupervised learning: clustering and density estimation. Our approach is an extension of the standard Gaussian process, online density estimator and SOINN; not only does it fully...
Classification is one of the most researched issues in Machine Learning. In this study, the Lorentzian Support Vector Machine (LSVM) method is proposed that performs classification in Lorentzian space. This proposed new classifier forms a hyperplane separating the classes based on the Lorentzian metric and maximize margins between nearest points to the hyperplane according to the Lorentzian distance...
Sentiment Analysis (SA) is the task of detecting people's emotions from their written text. Many algorithms have been studied for that purpose, with different authors claiming one or the other as better by a given metric. In recent years, the focus of SA has shifted to online text and microblog text, messages so short that good analysis becomes difficult that the choice of algorithm becomes critical...
In this paper, we provide a novel regression algorithm based on a Gaussian random field (GRF) indexed by a Riemannian manifold (M, g). We utilize both the labeled and unlabeled data sets to exploit the geometric structure of M. We use the recovered heat (H) kernel as the covariance function for the GRF (HGRF). We propose a Monte Carlo integral theorem on Riemannian manifolds and derive the corresponding...
In this paper, we propose a neural network based distance metric learning method for a better discrimination in the sequence-matching based keyword search (KWS). In this technique, we conduct a version of Dynamic Time Warping (DTW) based similarity search on the speaker independent posteriorgram space. With this, we aim to compensate for the scarcity of the resources and overcome the out-of-vocabulary...
Person re-identification remains a challenging problem due to large variations of poses, occlusions, illumination and camera views. To learn both feature representation and similarity metric simultaneously, deep metric learning methods using triplet convolutional neural network have been applied in person re-identification. In this paper, we propose a body structure based triplet convolutional neural...
Predicting change-prone object-oriented software using source code metrics is an area that has attracted several researchers attention. However, predicting change-prone web services in terms of changes in the WSDL (Web Service Description Language) Interface using source code metrics implementing the services is a relatively unexplored area. We conduct a case-study on change proneness prediction on...
This paper shows that many applications exhibit execution-phase-specific sensitivity towards approximation of the internal subcomputations. Therefore, approximation in certain phases can be more beneficial than others. Further, this paper presents Opprox, a novel system for application's execution-phase-aware approximation. For a user provided error budget and target input parameters, Opprox identifies...
Automatically recognising facial emotions has drawn increasing attention in computer vision. Facial landmark based methods are one of the most widely used approaches to perform this task. However, these approaches do not provide good performance. Thus, researchers usually tend to combine more information such as textural and audio information to increase the recognition rate. In this paper we propose...
Although the design of low-level local spatiotemporal features has recently led to significant improvement of performance in many action recognition applications, much less attention has been given to the equally important problem how to organize such low-level features extracted from the videos into a higher-level representation suitable to represent and discriminate between many different action...
Pushing supply voltages in the near-threshold region is today one of the main avenues to minimize power consumption in digital integrated circuits. This works well with logic units, but memory operations on standard six-transistor static RAM (6T-SRAM) cells become unreliable at low voltages. Standard cell memory (SCM) works fully reliably at near-threshold voltages, but has much lower area density...
Does a hearing-impaired individual's speech reflect his hearing loss, and if it does, can the nature of hearing loss be inferred from his speech? To investigate these questions, at least four hours of speech data were recorded from each of 37 adult individuals, both male and female, belonging to four classes: 7 normal, and 30 severely-to-profoundly hearing impaired with high, medium or low speech...
This paper discusses the Correntropy Induced Metric (CIM) based Growing Neural Gas (GNG) architecture. CIM is a kernel method based similarity measurement from the information theoretic learning perspective, which quantifies the similarity between probability distributions of input and reference vectors. We apply CIM to find a maximum error region and node insert criterion, instead of euclidean distance...
Configuring an Evolutionary Algorithm (EA) can be a haphazard and inefficient process. An EA practitioner may have to choose between a plethora of search operator types and other parameter settings. In contrast, the goal of EA principled design is a more streamlined and systematic design methodology, which first seeks to better understand the problem domain, and only then uses such acquired insights...
In this paper, we propose a nonlinear metric learning framework to boost the performance of semi-supervised learning (SSL) algorithms. Constructed on top of Laplacian SVM (LapSVM), the proposed method learns a smooth nonlinear feature space transformation that makes the input data points more linearly separable. Coherent point drifting (CPD) is utilized as the geometric model with the consideration...
Person re-identification aims to match people across non-overlapping camera views. One of the challenges in re-identification is cross view matching, where the gallery and query data belong to different views. This problem is difficult because the person's appearance varies greatly due to significant viewpoint and poses changes. In this paper, we perform Kernel Canonical Correlation Analysis (KCCA)...
On-line questionnaires are today widely used for various tasks, from census data collection to knowledge testing in job interviews. However, there is currently no automated system that can help us decide if the answers from the questionnaires are reliable or estimate how reliable the are. Deception is a part of everyday human behavior and deception is also present when answering on-line questionnaires...
In this paper, we propose a parallel block-based Viterbi decoder (PBVD) on the graphic processing unit (GPU) platform for the decoding of convolutional codes. The decoding procedure is simplified and parallelized, and the characteristic of the trellis is exploited to reduce the metric computation. Based on the compute unified device architecture (CUDA), two kernels with different parallelism are designed...
Recently, several effective features were proposed for person re-identification, such as Weight Histograms of Overlapping Stripes (WHOS) and Local Maximal Occurrence (LOMO), but it still need to explore new effective feature to improve the precision for person re-identification. So, in this paper, we proposed a new Dual Channel Gradient feature, which can be fused with WHOS and LOMO by directly concatenating...
Convolution Neural Networks today provide the best results for many image detection and image recognition problems. The network accuracy increase in the past years is obtained through an increase in complexity of the structure and amount of parameters of the deep networks. Memory bandwidth and power consumption constraints are limiting the deployment of such state-of-the-art architecture in low power...
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.