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.
The paper suggests the methods for learning compact representation of the optimal decision policies in a Markov decision process (MDP) framework for sensor-network based human health monitoring systems. The learning of a small decision policy is key to deploying the model in small sensor nodes with limited memory. The decision process enables distributed sensor nodes to adapt their sampling rates...
Motivation: Machine learning in bioinformatic sheds light on the traditional biography research. Through the prediction of functional genes from amino sequence information, the experimental cost for new gene finding could be reduced. Results: We propose an effective machine-learning approach based on artificial neural networks (ANN), to assess the chance of a protein in rice to be disease resistant...
Soft computing in the area of information security is a promising field for the creation of intelligent solutions. This paper discusses a method for digital watermarking using artificial neural networks to realize secure copyright protection of visual information without any damage. The discussed watermark extraction keys and feature extraction keys identify the secure and unique hidden patterns for...
Prediction of deformation of foundation pit by means of conventional method such as mechanics analysis or numerical method often has a large error because the deformation process of foundation pit is a highly complicated nonlinear evolution process. A novel method based on Gaussian process (GP) machine learning is proposed for solving the problem of deformation prediction of foundation pit. GP is...
Two extensive research areas in Machine Learning are classification and prediction. Many approaches have been focused in the induction of ensemble to increase learning accuracy of individual classifiers. Recently, new approaches, different to those that look for accurate and diverse base classifiers, are emerging. In this paper we present a system made up of two layers: in the first layer, one ensemble...
This paper reviews main forecasting techniques used for power system applications. Available forecasting techniques have been discussed with focus on electricity load and price forecasting as well as wind power prediction. Forecasting problems have been classified based on time frame, application specific area and forecasting techniques. Appropriate examples based on data pertaining to the Victorian...
The deployment of wearable health monitoring systems (WHMS) is expected to address several important healthcare-related issues such as increasing healthcare costs, the rising number of the elderly population and treatment of chronic conditions. However, most of the currently developed WHMS simply serve as ambulatory physiological data loggers and transmitters in order to make the recorded bio-signals...
Support vector machine (SVM) is a novel machine learning method based on statistical learning theory (SLT). SVM is powerful for the problem with small samples, non linear and high dimension. A multi-class SVM classifier is applied to predict the coal and gas outburst in the paper. In this model, the dominant factors are the input vectors and the degree of outburst danger is divided into four types:...
Prosthetic hands of increasing capability and sophistication are being built, but how does the user tell the hand what to do? One method is to use the low-level electrical signals associated with forearm muscle movement, or electrogmyograms (EMGs). This paper describes an experiment in which supervised learning, or classification, was used to build a model that decides which of a set of hand gestures...
The performance and regression precision of weak learners (accuracies should be greater than 0.5) for pattern recognition and forecasting can be upgraded using AdaBoost algorithm. Support vector machine (SVM) is a state-of-the-art learning machines and have been widely used in pattern recognition area since 90's of 20th contrary, however the performance of SVM is not stable and easily influenced due...
Training neural networks has attracted many researchers for a long time. Many training algorithms and their improvements have been proposed. However, up to now, improving performance of training algorithms for neural networks is still a challenge. In this paper, we investigate a new training method for single hidden layer feedforward neural networks (SLFNs) which use `tansig' activation function....
As a powerful machine learning approach for pattern recognition problems, support vector machine is known to have good generalization ability. Based on the index system of enterprise's self-fulfillment capability, a new integrated evaluation model is established by using support vector regression method. The method has advantages of accuracy, convenience, reliability and rapidity. The method is illustrated...
Travel time prediction is a very important problem in intelligent transportation system research. We examine the use of boosting, a machine learning technique in travel time prediction, and combine boosting and neural network models to increase prediction accuracy. In addition, quality of service (QoS) factors such as bandwidth play an important role in travel time prediction, so we also explore the...
Ensemble-classifier is a technique that uses a combination of multiple classifiers to reach a more precise inference result than a single classifier. In this paper, a three-layer hierarchy multi-classifier intrusion detection architecture is proposed to promote the overall detection accuracy. For making every individual classifier is independent from others, each uses a diverse soft computing technique...
Based on the concept of granular computing, this article proposes a novel Boolean conversion (BC) method to reduce data attribute number for the purpose of improving the efficiency of learning in artificial intelligence. Data with large amount of attributes usually cause a system freezes or shuts down. The proposed method combines large amount attributes to smaller number ones by the way of Boolean...
In this work we tested and compared artificial metaplasticity (AMP) results for multilayer perceptrons (MLPs). AMP is a novel artificial neural network (ANN) training algorithm inspired on the biological metaplasticity property of neurons and Shannon's information theory. During training phase, AMP training algorithm gives more relevance to less frequent patterns and subtracts relevance to the frequent...
Neural network tree (NNTree) is a hybrid model for machine learning. Compared with single model fully connected neural networks, NNTrees are more suitable for structural learning, and faster for decision making. To increase the realizability of the NNTrees, we have tried to induce more compact NNTrees through dimensionality reduction. So far, we have used principal component analysis (PCA) and linear...
In this paper, we propose a new self-supervised learning method for competitive learning as well as self-organizing maps. In this model, a network enhances its state by itself, and this enhanced state is to be imitated by another state of the network. We set up an enhanced and a relaxed state, and the relaxed state tries to imitate the enhanced state as much as possible by minimizing the free energy...
This paper investigates the use of machine learning to predict a sensitive gait parameter based on acceleration information from previous gait cycles. We investigate a k-step look-ahead prediction which attempts to predict gait variable values based on acceleration information in the current gait cycle. The variable is the minimum toe clearance which has been demonstrated to be a sensitive falls risk...
There is an increasing trend towards personalization of services and interaction. The use of computational models for learning to predict user emotional preferences is of significant importance towards system personalization. Preference learning is a machine learning research area that aids in the process of exploiting a set of specific features of an individual in an attempt to predict her preferences...
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.