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.
For text clustering task, distinctive text features selection is important due to feature space high dimensionality. It is essential to reduce the feature space dimension to increase accuracy and decrease processing time. In this work, for text clustering task, we introduce a novel hybrid feature selection model. This method measures the term importance based on the correlation coefficient among four...
In trying to understand the big picture of how users learn to program in App Inventor, we want to be able to represent projects in a way suitable for large scale learning analytics. Here I present different representations of projects that could potentially be used to identify App Inventor projects that have structural similarities to each other, e.g., projects created by users following tutorials...
Contrast is a very important characteristic for visual perception of image quality. Some No-Reference Image Quality Assessment Algorithm NR-IQA metrics for Contrast-Distorted Images (CDI) have been proposed in the literature, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and NR-IQA for Contrast-Distorted Images (NR-IQACDI). Here, we intend to improve the assessment...
Multitrack audio mixing is an essential part of music production and one of the first steps consist on processing individual stems from raw recordings. In this paper, we investigate this stage as a content-based transformation. We explore which audio features are relevant to interpret this specific process and which set of features gets modified by the mixing of stems in the most consistent way. We...
Person re-identification is important and challenging parts in a non-overlapping camera network. In this paper, we propose the person re-identification framework which consists of kernel size into convolutional layers considering the person ratio and relationship matrix that train the relationship information related to neighborhoods. Our framework deals with global feature extracted from the whole...
This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks. The main challenge that vision systems face in this context is catastrophic forgetting: as they tend to adapt to the most recently seen task, they lose performance on the tasks that were learned previously. Our method aims at preserving the knowledge of the previous tasks while learning...
Growing complexity in modern software is making signature-based intrusion detection an increasing challenge. Many recent intrusion detection systems rely on accurate recovery of application semantics from memory. In this paper, we approach the problem from a different angle. We observe that the user applications in corporate network often run in identical system environments due to standardized IT...
We propose a model that adapts to CNN trained by non-rotated images even for rotated images by evaluating the feature map obtained from the convolution part of CNN. The additional network for rotation angle estimation is able to correct the rotation angle using the feature map in the MNIST data-set. It is possible to cope with the rotation without changing the original network by adding a network...
Instead of using HOG feature on cells or blocks, the extraction of HOG features on corner points is proposed for multiple object visual tracking system in which single or multiple moving objects could be classified. Background subtraction and extraction of corner feature are applied to track and classify the moving objects. Firstly, moving objects will be detected in the form of regions from background...
The classification of different odontocetes using écholocation clicks plays a significant role in tracking and detecting animals for research and protection purposes. Echolocation clicks were detected by an automatic method based on the Teager-Kaiser Energy Operator (TKEO). Then, these clicks were represented by their FFT magnitude spectrum. To reduce the influence of high similar clicks among species,...
Faster R-CNN (R corresponds to “Region”) which combined the RPN network and the Fast R-CNN network is one of the best ways to object detection of R-CNN series based on deep learning. The proposal obtained by RPN is directly connected to the ROI Pooling layer, which is a framework for CNN to achieve end-to-end object detection. The feasibility of Faster R-CNN implementation of ResNet101 network and...
Many of today's machine learning (ML) systems are composed by an array of primitive learning modules (PLMs). The heavy use of PLMs significantly simplifies and expedites the system development cycles. However, as most PLMs are contributed and maintained by third parties, their lack of standardization or regulation entails profound security implications. In this paper, for the first time, we demonstrate...
Risk recognition training is an important training in construction companies to avoid work-related accidents. The existing risk recognition training is usually conducted on an illustration including explicit risks. However, it is difficult to express dynamic scenarios and surroundings of the scene due to the still illustration. In this study, a video based risk recognition training tool with an eye...
This paper presents a novel method of image classification for trend prediction based on integration of visual and fNIRS features. It is expected that classification of images in the same object category in terms of generation enables trend prediction. However, since images in the same object category have similar visual features, a limit of accuracy exists for image classification by using only visual...
A life log is a record of human life and behavior as digital data. In recent years, it has become possible to collect easily life logs by wearable devices. There is reflection of information as one of usage of these life logs. Among them, reflection by images is easy to understand. However, when recording for a long time by automatic photographing, the number of images becomes enormous, and it is...
Over a decade of continual expansion in networking and cloud computing has naturally created an increased demand for cybersecurity solutions. Due to the large number of communication devices and content, it is ideal that these cybersecurity solutions are automated. Unfortunately, malicious content and/or activity is often designed to “look” normal and new malicious attacks are repeatedly being developed...
The task of Sparse Symmetric Nonnegative Matrix Factorization(SSNMF) is formulated as optimization problem and solved numerically with the method of projected gradients descent. The adjustable sparsity level allows to emphasize the most significant object features. Clustering of the Yale Faces data set shows that SSNMF provides the same level of quality as common clustering approaches.
When performing feature location tasks, developers often need to explore a large number of program elements by following a variety of clues (such as program element location, dependency, and content). As there are often complex relationships among program elements, it is likely that some relevant program elements are omitted, especially when the implementations for a feature or concern scatter across...
In order to study the feature and extraction methods of series arc fault, the series arc fault experiments under different current conditions were carried out with the motor load and inverter respectively. A method of feature extraction based on improved singular value decomposition was proposed, and arc faults were distinguished by support vector machine (SVM). SVM was optimized by genetic algorithm...
Image co-segmentation is the problem of extracting the common objects from multiple images. Foreground segmentation is always effected by the diverse objects and complex background. However, the existing methods didn't pay much attention to images' background as object, especially the similar background. To address the similar scene co-segmentation problems, a method which considers the foreground...
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.