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.
Terrorism becomes more severe these days, especially the attacks sponsored by Islamic State of Iraq and Syria (ISIS) or Daesh. They are experts of using social network for propaganda and recruitment, thus predicting their activities through big social network data will help to predict and avoid more serious attacks. In this paper, we analyze over 17k Twitter records of pro-ISIS fanboys over a year...
To improve the performance of the convolutional neural networks, it is normally done by increase the deepness or put more layers to the network. By doing such, the number of parameters is increased. In this paper, NU-InNet, which was developed from GoogLeNet, is modified by adding more layers to the network in order to improve the accuracy of the network while keeping the number of the parameters...
Peak ground acceleration (PGA) is equal to the maximum ground acceleration that occurred during earthquake shaking at a location and the design basis earthquake ground motion is often defined in terms of PGA. In this paper, three intelligent methods are proposed for predicting of PGA in regions where PGA value is greater than 0.5g. These knowledge base methods are Adaptive Network Based Fuzzy Inference...
We propose a method to improve speaker verification performance when a test utterance is very short. In some situations with short test utterances, performance of ivector/probabilistic linear discriminant analysis systems degrades. The proposed method transforms short-utterance feature vectors to adequate vectors using a deep neural network, which compensate for short utterances. To reduce the dimensionality...
This paper presents a new system for singing melody transcription from polyphonic songs. Instead of operating solely on polyphonic audio of each song to be processed (as most existing systems do), our system takes as inputs additionally multiple monophonic recordings of people singing the song. To transcribe the singing melody in a song, our system first tracks the singing pitch from polyphonic audio...
Epithelium-stroma classification is always considered as an important preprocessing step for morphological quantitative analysis in image-based histological researches of oncologic diseases. However, large-scale accurate ground-truth labeling is expensive in histopathological image analysis, thus the classification performances will still be limited with the insufficient labeled training samples....
As high-resolution fingerprint images are becoming more common, the pores have been found to be one of the promising candidates in improving the performance of automated fingerprint identification systems (AFIS). This paper proposes a deep learning approach towards pore extraction. It exploits the feature learning and classification capability of convolutional neural networks (CNNs) to detect pores...
This paper develops a new combination model incorporating three excellent classification algorithms to solve the bank customer credit rating problem. Computational results on well-known credit records from German, Australian, Chinese and Japan banks show that, compared with other state-of-the-art classification algorithms, the proposed algorithm has higher efficiency and better evaluation results...
This paper presents a new approach of Extreme Learning Machine (ELM) ensembles that use majority voting with the q-Gaussian Activation function Circular Extreme Learning Machine (QCELM) to make the final decision for classification problems. For each QCELM is work on the CELM using q-Gaussian activation functions based on Tsallis distribution that varies the different parameter q values (called the...
Convolution neural networks (CNNs) are the heart of deep learning applications. Recent works PRIME [1] and ISAAC [2] demonstrated the promise of using resistive random access memory (ReRAM) to perform neural computations in memory. We found that training cannot be efficiently supported with the current schemes. First, they do not consider weight update and complex data dependency in training procedure...
Metamorphic testing has been successfully used in many different fields to solve the test oracle problem. However, how to find a set of appropriate metamorphic relations for metamorphic testing remains a complicated and tedious task. Recently some machine learning approaches have been proposed to predict metamorphic relations. These approaches predicting single label metamorphic relation can alleviate...
As Convolutional Neural Networks continue to produce state of the art results, more types of data are being used to see the results that would be produced. Using the heart rate data that was collected using sensors from various subjects who consumed alcohol, we converted it from the 1D waveform into a set of spectrograms. The spectrograms were fed into two pretrained CNNs, CaffeNet and AlexNet, to...
This paper studied automatic identification of malaria infected cells using deep learning methods. We used whole slide images of thin blood stains to compile an dataset of malaria-infected red blood cells and non-infected cells, as labeled by a group of four pathologists. We evaluated three types of well-known convolutional neural networks, including the LeNet, AlexNet and GoogLeNet. Simulation results...
Cardiac allograft rejection is one major limitation for long-term survival for patients with heart transplants. The endomyocardial biopsy is one gold standard to screen heart rejection for patients that have heart transplantation. However, manual identification of heart rejection is expensive and time-consuming. With the development of imaging processing techniques and machine learning tools, automatic...
Deep learning tools such as the convolutional neural network (CNN) are extensively used for image analysis and interpretation tasks but they become relatively expensive to use for a corresponding analysis in videos by requiring memory provision for the additional temporal information. Crowd video analysis is one of the subareas in video analysis that has recently gained notoriety. In this paper we...
Regression testing is an important activity performed to ensure thatchanges in the baseline version of the system do not influence thealready tested part of the system. It becomes difficult to run the entiretest suite due to constrained or limited resources. A subset of test casesthat is as efficient as the original test suite is searched as optimal suite.Computational intelligence approaches has...
This work presents results of effectiveness analyses of using deep neural networks models for syntactic parsing of SynTagRus dataset. A set of modular neural network topologies based on composition of Stack long short-term memory layers, multilayer perceptron has been compared with widely used algorithms of classification on base of Gradient boosting trees and Support vector machine. Results allow...
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI). These dynamic images are constructed from a sequence of depth maps using bidirectional rank pooling to effectively capture the spatial-temporal information. Such image-based...
The recognition system when concerned with high-security, authentication of authorized person and invalidation of an imposter is a vital task for the system. The system based on iris feature is considered as highly secure and most reliable system due to the intrinsic property of an iris. This paper presents an efficient iris recognition approach based on the fusion of modular neural network output...
Identifying arbitrary power grid topologies in real time based on measurements in the grid is studied. A learning based approach is developed: binary classifiers are trained to approximate the maximum a-posteriori probability (MAP) detectors that each identifies the status of a distinct line. An efficient neural network architecture in which features are shared for inferences of all line statuses...
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.