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.
Among critically-ill patients, hypotension represents a failure in compensatory mechanisms and may lead to organ hypoperfusion and failure. In this work, we adopt a datadriven approach for phenotype discovery and visualization of patient similarity and cohort structure in the intensive care unit (ICU). We used Hierarchical Dirichlet Process (HDP) as a non-parametric topic modeling technique to automatically...
Modern intensive care units (ICUs) collect large volumes of data in monitoring critically ill patients. Clinicians in the ICUs face the challenge of interpreting large volumes of high-dimensional data to diagnose and treat patients. In this work, we explore the use of Hierarchical Dirichlet Processes (HDP) as a Bayesian nonparametric framework to infer patients' states of health by combining multiple...
In this paper we provide an intelligent and convenient shopping cart, Intelligent Shopping Assistant System (ISAS). With ISAS, customers can concentrate on what he/she has to buy, and do not be bothered where he/she has to buy or it is want to buy. In contrast to conventional shopping cart, two modes of autonomous functions are added to ISAS in order to reduce the labor of customers for pushing goods...
It is well known that the intensive care unit (ICU) is mainly utilized in the medical field. Recently, it has been extended in power industry. For example, the ICU on the transformer can detect the potential defects. Combined with multiple monitoring systems along with the experience of operators, the evolution of the defect can be well determined. Hence, the failure can be effectively prevented....
Visual recognition and pose estimation of 3D industrial objects are challenging due to variations of geometric shapes from perspectives while lacking textures. This paper presents an approach to accurately recognizing industrial objects and estimating their poses based on an adaptive Bayesian framework with optimal feature selection and model-based point cloud matching. First, feature sets that provide...
In this paper, we will investigate a more challenging vehicle matching problem. The problem is formulated as invariant image feature matching among opposite viewpoints of cameras, i.e. complementary object matching. For example, a front vehicle object may be given as a query to retrieve a rear vehicle object of the same vehicle. To solve the complementary object matching, invariant image feature is...
Interpretation of cardiac rhythms is highly dependent on accurate detection of atrial activity. The robustness is an important requirement for clinical usage. This study presents an adaptive QRS detection method for real-time clinical ECG signals. In this method, center differentiation is applied as a whitening filer, and a composite function enhances the high frequency QRS energy. To robustly detect...
This paper presents an approach to the automatic recognition of human emotions from audio-visual bimodal signals using an error weighted semi-coupled hidden Markov model (EWSC-HMM). The proposed approach combines an SC-HMM with a state-based bimodal alignment strategy and a Bayesian classifier weighting scheme to obtain the optimal emotion recognition result based on audio-visual bimodal fusion. The...
In order to solve the problems in multiprocessor environments, such as BEA Tuxedo services, backup and recovery of cache data and so on, a hashing-based multi-machine hot standby architecture and a shared memory-based cache mechanism for static and dynamic data are proposed in the paper. The result shows that the load balancing of service access can be achieved effectively and users can access services...
Considering that the neural network increases rapidly in complexity and is greatly extended in training time due to the gradually increasing input vectors, a fusion algorithm modified by rough set is proposed to preprocess the inputs before neural network. Firstly, the input sample space is reduced to obtain the new decision table according to attribute significance in rough set. Then the reduced...
In order to improve the deficiency and passivity of periodical maintenance for mining equipments, a new mining equipment management mode—4M system is put forward in this paper. It is a quaternity management mode including daily maintenance information management, on-line monitoring, malfunction simulation and predictive maintenance. The overall function and operation process of 4M system is introduced...
BP neural network (back propagation neural network) is a mathematical model for machine learning. It has a strong advantage in terms of prediction of the future events, and taking into account the different applications, its impact factors are different, which makes the model complex and diverse. A general modeling approach is proposed, which creates and stores BP neural network model dynamically,...
Web data mining is the integration of data mining technology and web, how to find useful information in the Web which is the world's largest data of collection is becoming a hot spot of data mining research, this article choosing all the 763 documents' citation as data sample of “web data mining(WDM)”, which was published in Web of Science (SCI-EXPANDED, SSCI, A&HCI) from 1986 to 2009, confirming...
The technology of an intelligent fault diagnosis provides a new way for the reliability and safety of industrial systems, but, it can gradually no longer meet all demand to diagnose faults in complex systems by some existing solitary and static means, because of the equipments and functions complication in a complex industrial system. Considered with the characteristics of a fault diagnosis, a new...
Nowadays, the management style of most distribution networks in rural area is supported by the technology of Computer Management System based on relational database. It doesn't meet the requirement of the increasingly complex situation. GIS technology which develops gradually and is widely used in late years can manage and analysis the spatial information efficaciously. This paper introduces the Software...
Based on geographical and semantic features of remote sensing image, the paper presents a universal remote sensing image data model, and analyzes the logical structure and storage methods of this model. Based on the model, the paper puts forward a remote sensing image retrieval method, and makes analysis of the process of remote sensing image retrieval. At last, on basis of computer and database technology,...
This article analyzes the current Web graphic processing technique, and then it puts forward a new model of object grouping database and technology of rapid graphic refreshment based on the incremental data. Later on it discusses collaborative graphic editing technology to organize GIS data more effectively and improve graphics interaction processing efficiency under network environment.
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.