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.
One pass learning updates a model with only a single scan of the dataset, without storing historical data. Previous studies focus on classification tasks with a fixed class set, and will perform poorly in an open dynamic environment when new classes emerge in a data stream. The performance degrades because the classifier needs to receive a sufficient number of instances from new classes to establish...
In this study, we introduce an ensemble-based approach for online machine learning. Here, instead of working on the original data, several Hoeffding tree classifiers classify and are updated on the lower dimensional projected data generated from originality by random projections. Since random projection is unstable, from one example, many diverse training data can be created to train the set of Hoeffding...
Successful ECG monitoring algorithms often rely on learned models to describe the heartbeats morphology. Unfortunately, when the heart rate increases the heartbeats get transformed, and a model that can properly describe the heartbeats of a specific user in resting conditions might not be appropriate for monitoring the same user during everyday activities. We model heartbeats by dictionaries yielding...
This work presents a Virtual Reality training environment for upper limb amputees. Based on principles of a serious game, the training environment aims to condition the patient to use a prosthesis before it is manufactured. Studies show that the time of adjustment for use of a real prosthesis is considerably high. This often brings immense dismay to those patients who are already psychologically depressed...
The success of deep neural networks usually relies on a large number of labeled training samples, which unfortunately are not easy to obtain in practice. Unsupervised domain adaptation focuses on the problem where there is no labeled data in the target domain. In this paper, we propose a novel deep unsupervised domain adaptation method that learns transferable features. Different from most existing...
The paper presents an overview of contemporary approaches to application of virtual reality systems for training of operating personnel for man-machine systems. Special emphases are made on application issues of virtual and alternate reality systems connected with probable cognitive dissonance in operation of real physical objects. The prospects of virtual reality application in professional training...
Extending from limited domain to a new domain is crucial for Natural Language Generation in Dialogue, especially when there are sufficient annotated data in the source domain, but there is little labeled data in the target domain. This paper studies the performance and domain adaptation of two different Neural Network Language Generators in Spoken Dialogue Systems: a gating-based Recurrent Neural...
We present the Region of Interest Autoencoder (ROIAE), a combined supervised and reconstruction model for the automatic visual detection of objects. More specifically, we augment the detection loss function with a reconstruction loss that targets only foreground examples. This allows us to exploit more effectively the information available in the sparsely populated foreground training data used in...
Automatic image aesthetics rating has received a growing interest with the recent breakthrough in deep learning. Although many studies exist for learning a generic or universal aesthetics model, investigation of aesthetics models incorporating individual user’s preference is quite limited. We address this personalized aesthetics problem by showing that individual’s aesthetic preferences exhibit strong...
A novel method for personalized tweet recommendation based on Field-aware Factorization Machines (FFMs) with adaptive field organization is presented in this paper. The proposed method realizes accurate recommendation of tweets in which users are interested by the following two contributions. First, sentiment factors such as opinions, thoughts and feelings included in tweets are newly introduced into...
This paper proposes the design of an adaptive e- learning system with gamification elements. In the context of the increasing need to keep learners motivated among so many distractions, our project aims to help a user acquire knowledge at his own pace, in a captivating environment and as flexible as possible. To achieve that the solution focuses on the course model, adaptive questions and a reward...
We propose an algorithm to separate simultaneously speaking persons from each other, the “cocktail party problem”, using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is descriptive of independent speakers. Such a vector space can embed empirically determined speaker characteristics and is optimized by distinguishing between speaker masks...
Moving object tracking with discriminative model is very popular in recent years, which focuses on online selecting highly informative features to maximize the separability between object and background. An adapted particle filter tracker with online learning and inheriting discriminative model is proposed in this paper. Top-ranked discriminative features are selected into appearance model by Online...
Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attempts to align them have traditionally resulted in works reducing the domain shift by introducing appropriate loss terms, measuring the discrepancies between source and target distributions,...
We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source domain. Our training scheme follows the paradigm that in order to effectively derive class labels for the target domain, a network should produce statistically domain...
Riding on the waves of deep neural networks, deep metric learning has achieved promising results in various tasks by using triplet network or Siamese network. Though the basic goal of making images from the same category closer than the ones from different categories is intuitive, it is hard to optimize the objective directly due to the quadratic or cubic sample size. Hard example mining is widely...
Data diversity in terms of types, styles, as well as radiometric, exposure and texture conditions widely exists in training and test data of vision applications. However, learning in traditional neural networks (NNs) only tries to find a model with fixed parameters that optimize the average behavior over all inputs, without using data-specific properties. In this paper, we develop a meta-level NN...
The hand segmentation is the critical pre-processing of the gesture recognition application. Nowadays, to achieve a robust hand segmentation under cluttered background is still challenging. Advanced research in model-driven approach based on the depth information has obtained impressive performance. However, it is unable to deal with the hand very close to the body part. Also, a large number of marked...
Advances in modeling and knowledge representation, data mining, semantic Internet, analytical methods and open data are the basis for new models of knowledge analysis. The growth of information and data exceeds the ability of organizations to analyze them. This problem is particularly expressed in terms of knowledge and learning processes. Analytical methods can be successfully applied in studying...
Recently, in the field of speech processing, I-Vector modeling has been appealed a great deal of interest. I-Vector has shown its benefits in modeling of intra and inter-domain variabilities to a single low dimension space for speaker identification tasks. This paper presents the usage of I-Vector in camera identification as a new approach in image forensics domain. In our approach, image texture...
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.