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.
Due to the large amounts of Multimedia data on the Internet, Multimedia mining has become a very active area of research. Multimedia mining is a form of data mining. Data mining uses algorithms to segment data to identify useful patterns and to make predictions. Despite the successes in many areas, data mining remains a challenging task. In the past, multimedia mining was one of the fields where the...
We consider long-haul sensor networks where sensors are remotely deployed over a large geographical area to perform certain tasks, such as tracking and/or monitoring of one or more dynamic targets. A remote fusion center fuses the information provided by these sensors to improve the accuracy of the final estimates of certain target characteristics. In this work, we pursue artificial neural network...
In the paper a method of synthesis of a neural controller which goal is to reduce effects of coupling of the nonlinear multi-input multi-output (MIMO) plant inputs and outputs is presented. The designed neural controller contains a set of neural nets that determine values of parameters of linear decoupling controllers calculated for the adopted nonlinear plant model at its operating points. A known...
Neurocomputing have been adapted in time series forecasting arena, but the presence of outliers that usually occur in data time series may be harmful to the data network training. This is because the ability to automatically find out any patterns without prior assumptions and loss of generality. In theory, the most common training algorithm for Backpropagation algorithms leans on reducing ordinary...
Although deep learning has achieved outstanding performances on several difficult machine learning applications, there are multiple issues that make its application on new problems difficult: speed of training, local minima, and manual selection of hyper-parameters. To overcome these problems, this paper proposes a new evolutionary method, EvoAE, to train auto encoders for deep learning networks....
The recently introduced Dynamic Cortex Memory (DCM) is an extension of the Long Short Term Memory (LSTM) providing a systematic inter-gate connection infrastructure. In this paper the behavior of DCM networks is studied in more detail and their potential in the field of gradient-based sequence learning is investigated. Hereby, DCM networks are analyzed regarding particular key features of neural signal...
This paper presents the use of a training algorithm based on a Lyapunov function approach applied to a stator current controller based on a state variable description of the induction machine plus a reference model. The results obtained with the proposed controller are compared with a previously reported method based on a Nonlinear Auto-Regressive Moving Average with eXogenous inputs (NARMAX) description...
Age classification is a useful tool for creating an automatic system that can identify or verify and classify a person into an age group. In this paper a unique approach for classifying different aged people based on their forearm electromyography (EMG) signal, which has different characteristics from teenager to old is proposed. The Electromyography signal generates from the movement of brachioradialis...
Scattered objects in a digital image have shape and different positions. It also allows some differences in translation, rotation, and scaling. Backpropagation neural network is one of machine learning algorithms that can recognize patterns and identify an object image based on the training provided. Implementation of neural network on image that has a variety of translation, scaling and rotation...
The Java Sea is one of the busiest ship traffic both of domestic and international shipping and potential marine accident is quite high. It is about 43.6% of marine accidents is caused by natural factor. There are two point in this research. Point 1 at latitude 5° 55′29.03″ S longitude 110°51′42.88″ E and point 2 at latitude 4°39′41.99″ S longitude 109°10′7.15″ E. Design predictor of significant wave...
The estimation of unknown function from a number of data inputs has number of various applications like in Engineering, Artificial intelligence, Statistics, Artificial Neural Networks, Genetic algorithms etc. Many papers have described the individual methods. But very less is known about the comparative performance of various methods. In this paper we give the comparative performance of the neural...
The present paper describes an algorithmic technique to speed up weight convergence in neural networks on-line training. Standard pattern backpropagation is modified to train the neural network over a time window of samples and not one sample only, so that a faster weight convergence may be achieved. The use of such training technique is explained in an adaptive control task and problems related to...
Learning for feedforward neural networks can be regarded as a nonlinear parameter estimation problem with the objective of finding the optimal weights that provide the best fitting of a given training set. The extended Kalman filter is well-suited to accomplishing this task, as it is a recursive state estimation method for nonlinear systems. Such a training can be performed also in batch mode. In...
This paper compares the classification performance and training times of feed-forward neural networks with one hidden layer trained with the two network weight optimisation methods. The first weight optimisation method used the extreme learning machine (ELM) algorithm. The second weight optimisation method used the back-propagation (BP) algorithm. Using identical network topologies the two weight...
Breast cancer is one of the leading causes of cancer deaths among women in developed countries including India. Mammography is currently the most effective method for detection of breast cancer. Early diagnosis of the breast cancer allows treatment which could lead to high survival rate. This paper presents breast cancer detection in digital mammography using Image Processing Techniques by Artificial...
In this paper, the Rprop algorithm is compared with Backpropagation in the on-line learning of inverse dynamics using Kawato's feedback error learning structure. Since Rprop is a batch learning algorithm a window of NM samples is used. The samples are selected to avoid unnecessary adaptation of weights. Three nonlinear plants are used as a testbed, for each plant three trajectories are considered...
In 2010, Global Status Report on NCD World Health Organization (WHO) reported that 60 percent of deaths in the world caused by the non-communicable diseases, and one of the non-communicable diseases that consumed a lot of attention was diabetes mellitus. Diabetes is a serious threat to the health development, because diabetes is a disease that caused most other diseases (complications), such as blindness,...
This paper presents the application of FATHOM, a computerised non-verbal comprehension detection system, to distinguish participant comprehension levels in an interactive tutorial. FATHOM detects high and low levels of human comprehension by concurrently tracking multiple non-verbal behaviours using artificial neural networks. Presently, human comprehension is predominantly monitored from written...
Applying weight regularisation to gradient-descent based neural network training methods such as backpropagation was shown to improve the generalisation performance of a neural network. However, the existing applications of weight regularisation to particle swarm optimisation are very limited, despite being promising. This paper proposes adding a regularisation penalty term to the objective function...
This paper focuses on the study of modified constructive training algorithm for Multi Layer Perceptron “MLP” which is applied to face recognition applications. In general, constructive learning begins with a minimal structure, and increases the network by adding hidden neurons until a satisfactory solution is found. The contribution of this paper is to increment the output neurons simultaneously with...
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.