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.
Machine-learning algorithms have shown outstanding image recognition performance for computer vision applications. While these algorithms are modeled to mimic brain-like cognitive abilities, they lack the remarkable energy-efficient processing capability of the brain. Recent studies in neuroscience reveal that the brain resolves the competition among multiple visual stimuli presented simultaneously...
Static program analysis is a technique to analyse code without executing it, and can be used to find bugs in source code. Many open source and commercial tools have been developed in this space over the past 20 years. Scalability and precision are of importance for the deployment of static code analysis tools - numerous false positives and slow runtime both make the tool hard to be used by development,...
Online social message classification is an important task for E-Commerce companies to mine and classify the customer opinions. In this paper, we have proposed a first of its kind of an efficient message classification algorithm which is independent of tweet content and considers the set of followers who will retweet during the retweet peaks. By including the followers who will retweet during retweet...
With the emergence of a knowledge driven economy, these are times of brisk business for institutions providing training to professionals. The flipside of this is that there is an ever increasing demand on them to create a growing number of new courses, and serve an ever increasing flow of customers ata faster and faster pace. In its various flavours, this problem is faced by MOOC/online course providers,...
Dynamic selection (DS) is a mechanism to select one or an ensemble of competent classifiers from a pool of base classifiers, in order to classify a specific test sample. The size of this pool is user defined and yet crucial to control the computational complexity and performance of a DS. An appropriate pool size depends on the choice of base classifiers, the underlying DS method used, and more importantly,...
This paper addresses the problem of determining whether an observed subject has already been seen in a stream of biometric samples. Given a new sample, unlike the common practice of comparing a related match score to a constant threshold, this work introduces a function which takes as input the match score and the position of that sample in the stream, and produces as output a duplicate/non-duplicate...
In millimeter-wave massive multiple-input multiple-output systems, to decrease the large training overhead of traditional channel estimation techniques, compressive sensing (CS) is advocated for channel estimation by exploiting the channels' sparse nature. However, existing CS-based channel estimation (CSCE) methods have to deal with a large-size reconstruction problem for sparse channel recovery,...
This paper explores the supervised pattern recognition problem based on feature partitioning. This formulation leads to a new problem in computational geometry. The supervised pattern recognition problem is formulated as an heuristic good clique cover problem satisfying the k-nearest neighbors rule. First it is applied a heuristic algorithm for partitioning a graph into a minimal number of cliques...
Multiverse networks were recently proposed as a method for promoting more effective transfer learning. While an extensive analysis was proposed, this analysis failed to capture two main aspects of these networks: (i) the rank of the representation is much lower than the rank predicted by the analysis; and (ii) the contribution of increased multiplicity in such networks diminishes quickly. In this...
A+ aka Adjusted Anchored Neighborhood Regression - is a state-of-the-art method for exemplar-based single image super-resolution with low time complexity at both train and test time. By robustly training a clustered regression model over a low-resolution dictionary, its performance keeps improving with the dictionary size - even when using tens of thousands of regressors. However, this can pose a...
Complexity is a double-edged sword for learning algorithms when the number of available samples for training in relation to the dimension of the feature space is small. This is because simple models do not sufficiently capture the nuances of the data set, while complex models overfit. While remedies such as regularization and dimensionality reduction exist, they themselves can suffer from overfitting...
Efficient detection of three dimensional (3D) objects in point clouds is a challenging problem. Performing 3D descriptor matching or 3D scanning-window search with detector are both time-consuming due to the 3-dimensional complexity. One solution is to project 3D point cloud into 2D images and thus transform the 3D detection problem into 2D space, but projection at multiple viewpoints and rotations...
Multi-label classification (MLC), allowing instances to have multiple labels, has been received a surge of interests in recent years due to its wide range of applications such as image annotation and document tagging. One of simplest ways to solve MLC problems is label-power set method (LP) that regards all possible label subsets as classes. LP validates traditional multi-classification classifiers...
Outlier detection algorithms are often computationally intensive because of their need to score each point in the data. Even simple distance-based algorithms have quadratic complexity. High-dimensional outlier detection algorithms such as subspace methods are often even more computationally intensive because of their need to explore different subspaces of the data. In this paper, we propose an exceedingly...
This work attempts to find the most optimal setting for shallow artificial neural network (ANN) for Bengali digit dataset. Recognition of handwritten Bengali numerals has recently gained much interest among researchers due to significant performance gain found in the recognition of English numerals using artificial neural network. In this work, a new dataset of 70,000 samples were created first by...
It is known that Linear Chain Conditional Random Fields have quadratic time and space complexity in terms of the output tags set cardinality. This fact poses a prohibitive performance penalty when the tag set is large, such as in language applications where the language has a rich set of morphosyntactic tags. However, knowledge of the allowed tag bigramcombinations can lead to significant speedup...
The HEVC(H.265) has brought in significant improvements in terms of coding efficiency. However, the reduction in bitrates comes along with an increment in computational complexity. This paper presents a data mining approach to reduce the complexity of inter partition modes in HEVC. Determining the CU-splitting in inter partition modes requires substantial resources, so the goal of the work is to terminate...
The condensed nearest neighbor algorithm(CNN) is susceptible to pattern read sequence, abnormal patterns and so on. To deal with the above problems, through the analysis of the relationship between the whole dataset and the individual patterns, a new prototype selection algorithm is proposed based on the extended near neighbor relationship and the affinity changes. First, the proposed algorithm can...
In this paper, an information fusion system for tree species recognition through leaves is proposed. This approach consists in training sub-classifiers (Random forests) with attributes extracted from leaf photos. The database is incomplete, partial and some data is conflicting. A hierarchical fusion system based on Belief functions theory allows the fusion of data provided by different sub-classifiers...
In the face of technological advancements, serious games are becoming more widely recognized as effective educational tools. This paper presents a serious game that teaches a complex subject in a simplified and easy to understand manner-Communication and collaboration during post-disaster operations. The game is multiplayer where each player works through a simulated disaster using an incident management...
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.