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 attack the problem of building classifiers for public faces from web images collected through querying a name. The search results are very noisy even after face detection, with several irrelevant faces corresponding to other people. Moreover, the photographs are taken in the wild with large variety in poses and expressions. We propose a novel method, Face Association through Model Evolution (FAME),...
Four models are used to estimate the hourly solar radiation on 15 pieces of different tilted photovoltaic (PV) modules in Wuhan, China based on power and solar radiation data during a whole year. The optimum tilt angle (OTA) in Wuhan for yearly and semi-yearly adjustment was determined. Then it was determined that the best mode is the tilt angle of PV module adjusted every half a year. In semi-yearly...
In this article, the thermal expansion effect is considered as the main cause of the gradual shift in the forcedisplacement relationship, which describes the operation of Pneumatic Artificial Muscles (PAMs). A modified static force modeling approach is proposed, based on fundamental PAM modeling techniques, while incorporating the geometrical properties that are being affected by the thermal build-up...
The article describes a research on recognizing emotional states on the basis of keystroke dynamics. An overview of various studies and applications of emotion recognition based on data coming from keyboard is presented. Then, the idea of an experiment is presented, i.e. the way of collecting and labeling training data, extracting features and finally training classifiers. Different classification...
In this paper we investigate thermal network models with different model orders applied to various Dutch low-energy house types with high and low interior thermal mass and containing floor heating. Parameter estimations are performed by using data from TRNSYS simulations. The paper discusses results in relation to model order and the order which yields a sufficient level of accuracy is determined...
Electronic health record (EHR) systems are used in healthcare industry to observe the progress of patients. With fast growth of the data, EHR data analysis has become a big data problem. Most EHRs are sparse and multi-dimensional datasets and mining them is a challenging task due to a number of reasons. In this paper, we have used a nursing EHR system to build predictive models to determine what factors...
The actual field survey data from the Rice Department of Thailand's Ministry of Agriculture over a large area wastes a huge amount of resources. To solve this problem, this paper proposes a new approach to estimate rice phenology using SAR images derived from the RADARSAT-2 data. In this work, we divided the rice phenology into five stages, consisting of seedling, tillering, reproductive, ripening,...
The chances of winning highly valued Information Technology (IT) service contracts are influenced by various factors. Identifying key factors driving the competition and the early prediction of the outcome (either winning or losing such sales opportunities) can have significant business benefits. Given the complexity of IT services, range of potential attributes, and scarcity of comparable data sets,...
Dynamic Traffic Assignment (DTA) has become a main component of modern traffic control centres. To calibrate a DTA model the observations from the field are required. There has been increasing number of sensors and technologies which can provide these data. In this paper we briefly describe these sensors and elaborate on the various traffic data types that are used in dynamic demand calibration. The...
Nowadays, more and more service consumers pay great attention to QoS (Quality of Service) when they find and select appropriate Web services. For most of the approaches to QoS-aware Web service recommendation, the list of Web services recommended to target users is generally obtained based on rating-oriented predictions, aiming at predicting the potential ratings that a target user may assign to the...
Different people may have a different learning styles and it is important to provide the most suitable content and course materials for learning. However, determining the learning style may be difficult due to limited information about the learner and lack of a learner profile. The learner has to complete a questionnaire form based on educational theory in order to determine the learning style. Moreover,...
Service functionality can be provided by more than one service consumer. In order to choose the service which creates the most benefit before its consumption, a selection based on previous measurable experiences by other consumers is beneficial. In this paper, we present the results of our analysis of two machine learning approaches to predict the best service within this selection problem. The first...
PHM (Prognostic and Health Management) is a new concept, which is to ensure the normal operation of the complicated system, to achieve its functionality and reliability better. In this situation, the remaining useful life (RUL) prediction has aroused more and more concerns. Although the life prediction methods are many, there are not a set of systemic of evaluation parameters to evaluate the accuracy...
Pattern classification or clustering plays important role in a wide variety of applications in different areas like psychology and other social sciences, biology and medical sciences, pattern recognition and data mining. A lot of algorithms for supervised or unsupervised classification have been developed so far in order to achieve high classification accuracy with lower computational cost. However,...
Modern computer systems generate massive amounts of data in real-time. We have come to the age of big data, where the amount of information exceeds the perceptive abilities of any human being. Frequently the massive data collections arrive over time, in the form of a data stream. Not only the volume and velocity of data poses a challenge for machine learning systems, but also its variability. Such...
Within-Sample Choice Distribution and Sample size are important considerations in the estimation of logit model, but their effects on the estimation accuracy have not been systematically studied. Therefore, the objective of this paper is to provide an empirical examination to the above issues through a set of simulated choice datasets. In this paper, the utility function coefficients and alternative...
Partial discharge (PD) is a phenomenon of electric discharge typically caused by the damaged or aged insulation of high voltage equipment in power grids, such as transformers, switch gears, and cable terminals. In the context of Prognostic and Health Management (PHM), detection and monitoring of PD are important to ensure the reliability of electrical assets and to avoid catastrophic failures. Machine...
This paper describes the performance of a commercial AlphaMOS 4000 Electronic Nose coupled with Discriminant Factorial Analysis (DFA) as statistical tool used in discriminating the differences between pure and mixture agarwood oils by their volatile properties. The proposed techniques in this paper for testing and evaluating the capability of E-Nose for classifying and testing two different groups...
This paper provides the first evidence, using listed Japanese companies, that information in accruals has become more helpful as an early warning indicator of Financial Statement Fraud when they are appropriately preprocessed.
Several well-known simple behavioral models for solid state power amplifier (SSPA) devices are reviewed and compared. This paper proposes an improvement to White et al's model and discusses their use of the Rapp model for AM/AM and AM/PM device modeling. Furthermore an improvement to Honkanen & Haggman's phase shift addition to Rapp's model is given thus allowing phase shifts greater than zero...
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.