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 propose a deep network architecture for the pan-sharpening problem called PanNet. We incorporate domain-specific knowledge to design our PanNet architecture by focusing on the two aims of the pan-sharpening problem: spectral and spatial preservation. For spectral preservation, we add up-sampled multispectral images to the network output, which directly propagates the spectral information to the...
The development of a deep (stacked) convolutional auto-encoder in the Caffe deep learning framework is presented in this paper. We describe simple principles which we used to create this model in Caffe. The proposed model of convolutional auto-encoder does not have pooling/unpooling layers yet. The results of our experimental research show comparable accuracy of dimensionality reduction in comparison...
Nowadays, deep learning is a technique that takes place in many computer vision related applications and studies. While it is put in the practice mostly on content based image retrieval, there is still room for improvement by employing it in diverse computer vision applications. In this study, we aimed to build a Convolutional Neural Network (CNN) based Facial Expression Recognition System (FER),...
Problems associated with cell biochemistry are nowadays of general concern. In particular, much attention is being paid to the problem of changes in cytosolic ATP Levels. ATeam, a genetically encoded fluorescence resonance energy transfer (FRET)-based biological indicator, can monitor the fluorescence emission ratio against ATP concentration. Up to now, change curve has always acted as a bridge between...
The object detection based on deep learning is an important application in deep learning technology, which is characterized by its strong capability of feature learning and feature representation compared with the traditional object detection methods. The paper first makes an introduction of the classical methods in object detection, and expounds the relation and difference between the classical methods...
In today's financial markets, where most trades are performed in their entirety by electronic means and the largest fraction of them is completely automated, an opportunity has risen from analyzing this vast amount of transactions. Since all the transactions are recorded in great detail, investors can analyze all the generated data and detect repeated patterns of the price movements. Being able to...
In this work, we have extended the current success of deep learning and reinforcement learning to process control problems. We have shown that if reward hypothesis functions are formulated properly, they can be used for industrial process control. The controller setup follows the typical reinforcement learning setup, whereby an agent (controller) interacts with an environment (process) through control...
Neural networks have been traditionally considered robust in the sense that their precision degrades gracefully with the failure of neurons and can be compensated by additional learning phases. Nevertheless, critical applications for which neural networks are now appealing solutions, cannot afford any additional learning at run-time. In this paper, we view a multilayer neural network as a distributed...
Deep learning has started to outperform its rivals over the last five years, due to its capability to automatically find the features in the data, and classify them. In this study, deep learning is used to detect a buried target collected by a ground penetrating radar (GPR). The GPR data is generated by the GprMax simulation program, and a deep learning model of two convolution and two pooling layers...
Traffic incident detection (TID) is an important part of any modern traffic control because it offers an opportunity to maximise road system performance. For the complexity and the nonlinear characteristics of traffic incidents, this paper proposes a novel fuzzy deep learning based TID method which considers the spatial and temporal correlations of traffic flow inherently. Parameters of the deep network...
Despite the overwhelming success of deep learning in various speech processing tasks, the problem of separating simultaneous speakers in a mixture remains challenging. Two major difficulties in such systems are the arbitrary source permutation and unknown number of sources in the mixture. We propose a novel deep learning framework for single channel speech separation by creating attractor points in...
Deep learning is a model of machine learning loosely based on our brain. Artificial neural network has been around since the 1950s, but recent advances in hardware like graphical processing units (GPU), software like cuDNN, TensorFlow, Torch, Caffe, Theano, Deeplearning4j, etc. and new training methods have made training artificial neural networks fast and easy. In this paper, we are comparing some...
Risk refers to a set of events that lead to loss but risk from the tax perspective refers to the taxpayers' behaviors that may lead to negligence from the public property by the taxpayers due to tax evasion. Such actions cause unusual volatilities in the amounts envisaged in the government budgeting. The fiscal and financial transactions outside the scope of the precautionary bound and failure to...
In this paper, we propose a set of algorithms to design signal timing plans via deep reinforcement learning. The core idea of this approach is to set up a deep neural network (DNN) to learn the Q-function of reinforcement learning from the sampled traffic state/control inputs and the corresponding traffic system performance output. Based on the obtained DNN, we can find the appropriate signal timing...
This paper introduces techniques for Deep Learning in conjunction with spiked random neural networks that closely resemble the stochastic behaviour of biological neurons in mammalian brains. The paper introduces clusters of such random neural networks and obtains the characteristics of their collective behaviour. Combining this model with previous work on extreme learning machines, we develop multilayer...
This work addresses short-term traffic flow prediction by proposing a big-data-based framework. The proposed framework uses data fusion to deal with heterogeneous data generated from various sources. The data are categorized into two types: streams of data and event-based data. In this work, Deep Belief Networks (DBNs) are used to independently predict traffic flow using streams of data, i.e., historical...
Quantitative trading strategies are designed to look for relationships between data about an underlying security and its future price and then to generate alpha on a trading desk. Recent years have witnessed the increasing attention from both academic and corporate sectors on enhancing quantitative trading by machine learning techniques due to their excellent predictive powers, with a few successful...
In the past, many software reliability models have been proposed by several researchers. Several model selection criteria such as Akaike's information criterion, mean square errors, predicted relative error and so on, are used for the selection of optimal software reliability models. These assessment criteria can be useful for the software managers to assess the past trend of fault data. However,...
Outdoor mapping and localization based on appearance is especially challenging since usually separate processes of mapping and localization are required at different times of day. The problem is harder in the outdoors where continuous change in sun angle can drastically affect the appearance of a scene. In this work, we propose a method for instantaneous visual direction determination for the autonomous...
Network Functions Virtualisation (NFV) continues to gain attention as a paradigm shift in the way telecommunications services are deployed and managed. By separating Network Functions (NFs) from traditional middleboxes, NFV is expected to lead to reduced CAPEX and OPEX, and to more agile services. However, one of the main challenges to achieving these objectives is on how physical resources can be...
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.