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.
Analog computational circuits have been demonstrated to provide substantial improvements in power and speed relative to digital circuits, especially for applications requiring extreme parallelism but only modest precision. Deep machine learning is one such area and stands to benefit greatly from analog and mixed-signal implementations. However, even at modest precisions, offsets and non-linearity...
Prediction of Land use and cover change using remotely sensed imagery has attracted huge attention. From several decades, multiple researchers have investigated different approaches. The complex nature of the land use change process, due to human-nature interactions and the singularities of satellite images, demands a well-studied approach. Yet, a synthesis document is needed to provide a synthetic...
Efficient energy conservation policies must be implemented in order to reduce residential electricity consumption. The emergence of smart electricity meters has paved way to use electricity efficiently compared to that of digital meters. These meters have been deployed in many countries since 2000s. Utility companies are using such meters to provide accurate energy consumption data to their consumers...
Limitations of the existing methods and models for uneven energy consumption forecast are defined. The energy consumption planning method based on informational technologies, the probability theory, the game theory, hour energy prices and volumes relations is offered. All possible variants of prices and volumes relations are identified. Two utility functions for positive and negative correction of...
This study aims to present time series-based forecasting for Malaysian crude palm oil prices using neural network algorithms. Daily prices of soy bean oil and currency exchange rates are tested as input features, in addition to crude palm oil prices. Efforts are focused on finding the optimal network structures for the modelling of crude palm oil price forecasting. Neural network structures with an...
Since the introduction of artificial neural networks (ANN) the numerous investigations of concrete systems had been proposed. But further development of the theory and applications of networks follows to the investigations of new examples of dependent of time systems with anticipatory property. New special class of anticipatory systems had been introduced by D, Dubois — namely the system with strong...
Deep brain stimulation (DBS) is an established therapy for a variety of neurological disorders, including Parkinson's disease, essential tremor, and dystonia. Recent DBS research has pursued methods for closed-loop control to provide more effective management of symptoms, side effects, and device power consumption. Most closed-loop DBS (CLDBS) studies to date use simple threshold-based controllers...
This paper considers the modelling of scalar fields exhibiting non-stationary noise in the context of Gaussian Process (GP) regression. We show how a Heteroscedastic GP produces more accurate predictions of the variance of a process of this type compared to the standard Homoscedastic model. We present a parametric model for the noise process and derive analytical solutions to the Log Marginal Likelihood...
The purpose of this article is to present the methodology of creation of multi-aspect models of system objects that can be used at all stages of the life-cycle. Multi-aspect modeling are based at a technology of engineering of knowledge, the cybernetic approach and the methodology of object-oriented programming. The article presents the results of research in the field of multi-aspect modeling, the...
In data-driven modelling in dynamic networks, it is commonly assumed that all measured node variables in the network are noise-disturbed and that the network (vector) noise process is full rank. However when the scale of the network increases, this full rank assumption may not be considered as realistic, as noises on different node signals can be strongly correlated. In this paper it is analyzed how...
In this paper, we take the average impact value method as the evaluation of neural network variable correlation indicators, analysis the data provided by Professor P. Cortez and A. Morais from University of Minho (Portugal) using the MIVBP algorithm to filtrate 13 characterization factors to get 7 characterization parameters affect forest fires, construct the simulation model of the prediction of...
The paper described the structure comparison of Bayesian Belief Network models for individual behavior rate estimate based on data about the last episodes of that behavior. We compared two types of network structures: expert-based and data-based. For model learning and evaluation we used data from social network VKontakte about episodes of publishing posts. The sample size was 3803 users with 785066...
Regression trees are extended to be learnt from data with epistemic uncertainty. Modelling uncertainty with belief functions, the attribute selection strategy based on error interval is discussed and a complete tree construction procedure is proposed. As a general approach, error intervals weighted by mass functions are calculated for making the best splitting choice. Including classical regression...
The study presented in this paper aims to explore students' characteristics and to determine student groups based on their previous education and socio-demographic characteristics. Descriptive data mining method, cluster analysis, is applied in the analysis process. Data used in the research is collected among first, second and third year IT students. Research results indicate profile of successful...
dynamic cloud workloads necessitate forecasting methodologies for accurate resource provisioning affecting both cloud providers and clients. This paper focuses on forecasting in the cloud in order to understand its underlying workload dynamics. It analyzes recent workload traces and discovers characteristics that are not adequately captured by traditional linear & nonlinear models employed for...
A battery test that predicts the electrical performance with high accuracy is vital for circuit design. The purpose is to control its runtime and insure safety in battery-based electrical system such as Electric Vehicles (EVs). The nonlinear behavior of batteries depends on many internal and external factors such as temperature, chemistry, load current profile, age, etc. Modeling the behaviors of...
Aroma analysis follows a well-established procedure which provides a list of odorants that contribute to a given food aroma. However, such a procedure does not allow establishing the actual sensory profile of the food because the perceptual influence of mixed odorants is poorly considered. To improve the aroma analysis efficiency, we explored an innovative strategy which combines classical aroma analysis...
Hospital re-admission refers to special medical events that a patient previously discharged from the hospital is readmitted within a short period of time (say 30 days). A re-admission not only downgrades the quality of living of the patient, it also adds significant financial burdens to the health care systems. To date, many systems exist to use computational approaches to predict the likelihood of...
Years of research in software engineering have given us novel ways to reason about, test, and predict the behavior of complex software systems that contain hundreds of thousands of lines of code. Many of these techniques have been inspired by nature such as genetic algorithms, swarm intelligence, and ant colony optimization. In this paper we reverse the direction and present BioSIMP, a process that...
For the past decades, stock prediction has been a popular topic in financial applications. Many approaches including machine learning based and statistical models have been employed to forecast price changes in stock market. Considering the power of Restricted Bolztmann Machine (RBM) for feature extraction, we propose to incorporate RBM and several classifiers to predict short-term stock market trend...
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.