Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
Deep learning has been proposed for soft sensor modeling in process industries. However, conventional deep neural network (DNN) is a static network and thereby can not embrace evident dynamics in processes. Motivated by nonlinear autoregressive with exogenous input (NARX) model and neural nets based dynamic modeling, a dynamic network called NARX-DNN is put forward by further utilizing historical...
The SFSVC (Super Fast Support Vector Classifier) architecture is implemented to a computational mobile platform and its performances are evaluated against its implementation on a classic machine (personal computer). The aim of this article is to prove that the SFSVC architecture can have good performances on an environment with very limited resources by taking advantages of its compact structure and...
In this paper, we propose to determine whether the viewer's behavior changes or not before, during and after watching a TV program. Are there any behaviors specific to each particular phase of viewing? Here, we propose a flexible and nonintrusive method based on the use of three categories of everyday connected objects (i.e. Smartphone, smartwatch and remote control). Data were collected during participants'...
This paper deals with classification algorithms as one of the basic principles of pattern recognition. We analyze their effect to a feature space and compare the type and the shape of the separating and decision surface, respectively. We proposed a novel classification approach based on Cumulative Fuzzy Membership Function that creates a decision surface in a different way as an MF ARTMAP neural network...
POI recommendation has attracted lots of research attentions recently. There are several key factors that need to be modeled towards effective POI recommendation - POI properties, user preference and sequential momentum of check- ins. The challenge lies in how to synergistically learn multi-source heterogeneous data. Previous work tries to model multi-source information in a flat manner, using either...
We present a neural network model that learns to produce music scores directly from audio signals. Instead of employing commonplace processing steps, such as frequency transform front-ends, harmonicity and scale priors, or temporal pitch smoothing, we show that a neural network can learn such steps on its own when presented with the appropriate training data. We show how such a network can perform...
Most traditional soft sensor modeling requires the labeled training samples that contain both subsidiary and key variables. However, key variables are difficult to be obtained online due to lack of detection information or high measurement cost. In this paper, a novel semi-supervised learning algorithm, called cotraining-style kernel extreme learning machine, is proposed to exploit unlabeled training...
The influence of temperature, irradiance and shielding ratio on the output characteristic curve of photovoltaic cells was studied in this paper. In order to improve the photoelectric conversion efficiency of photovoltaic cells, combining three major factors that affect photovoltaic cells, a maximum power point tracking (MPPT) scheme based on large variation genetic algorithm was proposed. In this...
To solve the problem of low recognition rate which is the existing identification methods of partial discharge faults, a new method was designed with wavelet, singular value and improved particle swarm algorithm to optimize the BP neural network. First, using continuous wavelet and singular value decomposition to get the signal characteristic value; then combined with the significance of inertia weight...
Traditional pairwise learning to rank algorithms pay little attention to top ranked documents in the query list, and do not work well when they are used on a data set with multiple rating grades. In this paper, a novel pairwise learning to rank algorithm is proposed to solve this problem. This algorithm defines a bounded loss function and introduces the preference weights between document pairs into...
This paper evaluates the performance of four artificial intelligence algorithms for building energy consumption prediction. The backward propagation neural network (BPNN), support vector regression (SVR), adaptive network-based fuzzy inference system (ANFIS) and extreme learning machine (ELM) methods are reviewed and their performances for predicting building energy consumption are compared. A selection...
This paper proposes an object detection strategy with a deep reinforcement learning method Double DQN in which, given an image window, a deep reinforcement learning agent is trained to determine which predefined region candidates to focus the attention on. In the Double DQN framework, the first DQN is used to select an action to search the target region and the second is to evaluate the selected action...
We investigate methods for combining multiple selfsupervised tasks—i.e., supervised tasks where data can be collected without manual labeling—in order to train a single visual representation. First, we provide an apples-toapples comparison of four different self-supervised tasks using the very deep ResNet-101 architecture. We then combine tasks to jointly train a network. We also explore lasso regularization...
While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks. A remaining drawback of deep learning approaches is their requirement for an expensive retraining whenever the specific problem, the noise level, noise type, or desired measure of fidelity...
In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks. We propose a novel approach named Second-Order Response Transform (SORT), which appends element-wise product transform to the linear sum of a two-branch network module. A direct advantage of SORT is to facilitate cross-branch response propagation, so that each branch can update its...
The accuracy of object recognition has been greatly improved due to the rapid development of deep learning, but the deep learning generally requires a lot of training data and the training process is very slow and complex. We propose an incremental object recognition system based on deep learning techniques and speech recognition technology with high learning speed and wide applicability. The system...
A power transformer fault diagnosis method based on Improved Particle Swarm Optimization and BP neural network is proposed. The particle swarm algorithm that used to optimize the parameters of the BP neural network is prone to “premature”. By optimizing the inertia weight, in the process of increasing the number of iterations, the inertia weight can be gradually reduced, and the algorithm can avoid...
In view of the emotional polarity classification problem, the deep learning has the disadvantages of incomplete information extraction and low precision, a model combining bi-directional gated recurrent unit with multiple convolution neural network is proposed. The unit is used to extract the history and future information of the sentence, then use the multi-convolution neural network for system training,...
At present, the detection of mixing uniformity in glass furnace batching system is mainly realized by artificial detection. However, this method is time-consuming and laborious, and there are some risks. For the problem of mixing uniformity detection, the nonlinear relation between the actual weight value and the mixing uniformity is established by the BP neural network, which can predict the mixing...
It has been recently shown that neural networks can recover the geometric structure of a face from a single given image. A common denominator of most existing face geometry reconstruction methods is the restriction of the solution space to some low-dimensional subspace. While such a model significantly simplifies the reconstruction problem, it is inherently limited in its expressiveness. As an alternative,...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.