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 introduces a novel model-guided method for liver segmentation in CT and PET-CT images. Using a model liver volume as a template and a liver shape annotated in one of the patient slices, it automatically segments the whole liver volume in the patient dataset. The method is based on non-deformable registration of the model volume to the patient data and combination of components pre-segmented...
The highway toll road system in many countries is incapable of providing the detailed route information of users, and drivers may choose alternative paths rather than the shortest path in the hope of saving the travel cost. Existing ambiguous path identification research is heavily dependent on vehicle detection sensors, and traffic assignment models using simulations. In this paper, we present a...
Trying to PM2.s as the independent variable to establish the “beam-diffuse radiation separated” model, factor analysis showed that, PM2.5 and diffuse ratio have positive correlation. Based on the clearness index Kt and sunshine hours n/N as variables, the polynomial model and the BP neural network algorithm model containing PM2.5 as the independent variable is proposed, the polynomial model is fitted...
Accurate knowledge of the solar resource is required for solar energy generation projects, including preferably data for both the direct normal (DNI) and diffuse horizontal (DHI) components of irradiance, but in many solar datasets, only a single global horizontal (GHI) may be available. This paper undertakes the evaluation of three models-Reindl∗, BRL and DISC — which estimate DNI and DHI in such...
The features of non-payment problem of global economy, including mutual debts have been indicated in the matrix form in the paper. Afterwards this problem has been converted into linear programming setting and solved by the Simplex method. Note that, LP enables us to find the market value of the existing debts in the market. The calculated equilibrium prices of mutual debts mean that potentially there...
The article addresses the problem of identifying subtle causal relations between sets of data defining a control system. The key pros and cons of using a fuzzy method are later examined. It explains the primary aspects of the fuzzy model for revealing implicit causality within a control system based on a combination of a fuzzy set approach and data mining techniques. The tool for carrying out evaluation...
In this research, we provide a solution to the problem of handling the recent flooding in South Bandung, West Java, Indonesia. We offer the solution in determining the locations of the rescue posts. The analysis uses a spatial data clustering algorithm known as CLARANS Algorithm and the spatial similarity is measured using Polygon Dissimilarity Function (PDF). Results showed that clustering of two...
This paper studies a sensitivity analysis of the software project risk assessment model based on data envelopment analysis. Some sufficient conditions and necessary conditions are provided which can hold the efficiency of decision making units, when positive index data and reverse index data of decision making units are changed simultaneously. Finally, a numerical example is presented to give an illustration...
According to the wind speed prediction appeared in data acquisition difficulties, so as to the poor forecast accuracy, this paper proposed the history data of near BP-ANN wind short-term forecast model, with emphasis on BP model of input layer and hidden layer parameters are estimated. In the certain scope, enumerated input layer and hidden layer parameters, and use a large number of data simulation,...
Inverted index is an important data structure used in Information Retrieval operation, which enable all retrieval engines to easily facilitate full-text search. In this paper, Map Reduce algorithm is used for the construction of inverted index, so as to enable it to work in a parallelized manner and also make the data structure to support large scale document corpora. Here, we have considered crime...
Melt index is considered one of the most important variables in determining chemical product quality and thus reliable prediction of melt index (MI) is essential in practical propylene polymerization processes. In this paper, a fuzzy support vector regression (FSVR) based model for propylene polymerization process is developed to predict the MI of polypropylene from other easily measured process variables...
The paper researches math model about equipment failure rate, in order to forecast exactly equipment failure rate and advance equipment integrity rate and mission success rate and reserve rationality maintenance material. The paper establishes the gray-linear regression combined model and conceives math formula between equipment failure rate and use time. At the same time, the gray-linear regression...
In recent years, Lamb wave has shown great potential in structural integrity assessment and life prediction due to the capability of traveling at large distances in structures with little energy loss. However, most of existing researches of Lamb wave based damage detection mainly focus on specific target systems. Physical models which correlate the crack size and damage sensitive features may vary...
Aiming at fault detection rate (FDR) and fault isolation rate (FIR), testability demonstration technology is relatively mature. As an extension of testability technology, PHM (Prognostics and Health Management) provides a more sophisticated form to quantify and predict equipment health state and remaining useful life (RUL). Therefore, many researches attach importance to the prognostic validation...
In the whole life cycle of equipment, multi-source testability demonstration test data (TDTD) which may be acquired at different stages, in different environment and at different levels (system, subsystem or replaceable unit), can be used for testability integrated evaluation. However, the above multi-source data cannot be used for testability integrated evaluation directly for they share many distinctions...
In this paper, we designed a formal language, called Trane, for describing prediction problems over relational datasets, implemented a system that allows data scientists to specify problems in that language. We show that this language is able to describe several prediction problems and even the ones on KAGGLE-a data science competition website. We express 29 different KAGGLE problems in this language...
Julia is a new language for writing data analysis programs that are easy to implement and run at high performance. Similarly, the Dynamic Distributed Dimensional Data Model (D4M) aims to clarify data analysis operations while retaining strong performance. D4M accomplishes these goals through a composable, unified data model on associative arrays. In this work, we present an implementation of D4M in...
There arises the need in many wireless network applications to infer and track different models of interest. Some nodes in the network are informed, where they observe the different models and send information to the uninformed ones. Each uninformed node responds to one informed node and joins its group. In this work, we suggest an adaptive and distributed clustering and partitioning approach that...
Convolutional neural networks show their advantage in human attribute analysis (e.g. age, gender and ethnicity). However, they experience issues (e.g. robustness and responsiveness) when deployed in an intelligent video system. We propose one compact CNN model and apply it in our video system motivated by the full consideration of performance and usability. With the proposed web image mining and labelling...
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.