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.
We first examine the generalization issue with the noise samples used in training nonlinear mapping functions between noisy and clean speech features for deep neural network (DNN) based speech enhancement. Then an empirical proof is established to explain why the DNN-based approach has a good noise generalization capability provided that a large collection of noise types are included in generating...
Keystroke dynamics, which is a biometric characteristic that depends on typing style of users. In the past thirty years, dozens of classifiers have been proposed for distinguishing people using keystroke dynamics; many have obtained excellent results in evaluation. However, a more common case is that only normal instances are available and none of the rare classes are observed. It leads us to use...
In this paper, we present Genetic Algorithm based optimized feature selections for intrusion detection systems. We used one-point crossover for the Genetic Algorithm parameters instead of two-point crossover used by the previous research as it one-point crossover is faster. For evaluations, we used the NSL-KDD Cup 99 data set and we modified the data set by looking into to the recent attacks, hence...
Part of speech tagging has some different methods or techniques to the problem in assigning each word of a text with a part-of-speech tag. In this paper, we conducted some part-of-speech tagging techniques for Bahasa Indonesia experiments using statistical approach (Unigram, Hidden Markov Models) and Brill's tagger. In this study, we used Supervised POS Tagging approach requiring a large number of...
Traditional machine learning approaches are based on the premise that the training and testing samples come from a common probability distribution. Transfer learning refers to situations where this assumption does not necessarily hold. Integrating biological data measured on diverse platforms is a major challenge. Transfer learning is a natural candidate for achieving such integration. In this paper,...
We present and compare two approaches to detect the presence of bird calls in audio recordings using convolutional neural networks on mel spectrograms. In a signal processing challenge using environmental recordings from three very different sources, only two of them available for supervised training, we obtained an Area Under Curve (AUC) measure of 89% on the hidden test set, higher than any other...
This paper proposes a novel method based on the archetypal analysis (AA) for bird activity detection (BAD) task. The proposed method extracts a convex representation (frame-wise) by projecting a given audio signal on to a learned dictionary. The AA based dictionary is trained only on bird class signals, which makes the method robust to background noise. Further, it is shown that due to the inherent...
The use of statistical and machine learning approaches, such as Markov chains, for procedural content generation (PCG) has been growing in recent years in the field of Game AI. However, many of these level generation approaches account for only the structural properties of the levels. We developed multi-layered representations of levels, where each layer is designed to capture distinct gameplay information...
The performance of automatic speech recognition systems under noisy environments still leaves room for improvement. Speech enhancement or feature enhancement techniques for increasing noise robustness of these systems usually add components to the recognition system that need careful optimization. In this work, we propose the use of a relatively simple curriculum training strategy called accordion...
The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving privacy. However, older ideas about privacy may well remain valid and useful. This note reviews two recent works on privacy in the light of the wisdom of some of the early literature, in particular the principles distilled by...
Network traffic classification technique is currently a key part of network security systems. In recent years, some network traffic classification algorithms using machine learning based on packet and flow level features have been proposed, yet the results are frequently disappointing. On the one hand, obtaining a large, representative, training data set that is fully labeled to train a classifier...
A variety of applications (App) installed on mobile systems such as smartphones enrich our lives, but make it more difficult to the system management. For example, finding the specific Apps becomes more inconvenient due to more Apps installed on smartphones, and App response time could become longer because of the gap between more, larger Apps and limited memory capacity. Recent work has proposed...
Overhead depth map measurements capture sufficient amount of information to enable human experts to track pedestrians accurately. However, fully automating this process using image analysis algorithms can be challenging. Even though hand-crafted image analysis algorithms are successful in many common cases, they fail frequently when there are complex interactions of multiple objects in the image....
Among dependency parsing algorithms available in MALTParser and MSTParser, the best accuracy for parsing Indonesian language is achieved by Chu-Liu-Edmonds algorithm. This is due to the long distance relation between head and dependent in Indonesian sentences. Most of inaccuracy parsing results is caused by the non-verb sentence root score where there are many cases in Indonesian sentence having a...
In recent years, the machine translation system based on neural network, called Neural Machie Translation, have attracted much attention, in which the entire translation steps are implemented in a single large neural network. In this framework, dealing with a large vocabulary size on its input (source) and output (target) often make the training computationally intractable. Therefore, the most frequent...
We propose a method for optimizing an acoustic feature extractor for anomalous sound detection (ASD). Most ASD systems adopt outlier-detection techniques because it is difficult to collect a massive amount of anomalous sound data. To improve the performance of such outlier-detection-based ASD, it is essential to extract a set of efficient acoustic features that is suitable for identifying anomalous...
Research shows that speech dereverberation (SD) with Deep Neural Network (DNN) achieves the state-of-the-art results by learning spectral mapping, which, simultaneously, lacks the characterization of the local temporal spectral structures (LTSS) of speech signal and calls for a large storage space that is impractical in real applications. Contrarily, the Convolutional Neural Network (CNN) offers a...
Color is one of the attributes that play a role in identifying specific objects, color processing including the extraction of information about the spectral properties of the object's surface and look for the best similarity of a set of descriptions which have been known to do an introduction. Therefore, the classification is needed right fuji apples to obtain good quality fruit. Fuzzy model is one...
With the evolution of large computer data, every corner of the society is filled with a variety of text information. Indeed, large data information that need manage by people has been unable to meet the rapid development of society. Therefore, the technology of efficient management and accurate positioning of vast quantities of text information has become a hot topic in the research community. In...
Supervised event-based NILM systems usually require a large set of labeled training data to achieve high classification accuracies. To minimize the cost of labeling a sufficient amount of events, active learning can be employed. By using only a small set of labeled samples for initial training followed by selecting only the most informative samples to be labeled, the total number of labeled training...
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.