The capability to dynamically retrieve detailed multimedia which may come from knowledge bases as well as sensor information in response to specific user queries offers the potential to create decision support systems...
详细信息
This paper presents a modified PSO algorithm for solving constrained multi-objective optimization problems. Based on the constraint dominance concept, the proposed approach defines two sets of selection rules for dete...
详细信息
This paper presents a modified PSO algorithm for solving constrained multi-objective optimization problems. Based on the constraint dominance concept, the proposed approach defines two sets of selection rules for determining the cognitive and social components of the PSO algorithm. The simulation results to the four constrained multi-objective optimization problems demonstrate the proposed approach is able to find Pareto-optimal solutions effectively.
Extracting required patterns from huge amount of mixed data is an area of interest to the researchers. Various promising and already established algorithms are currently using in the name of data Clustering. Clusterin...
详细信息
Extracting required patterns from huge amount of mixed data is an area of interest to the researchers. Various promising and already established algorithms are currently using in the name of data Clustering. Clustering is used for partitioning the data into number of data sets or group. In this paper, we review four popular clustering algorithms from data mining perspective.
Hypertension,among diabetes,obesity and others,is one of the common human diseases that is genetically expressed as complex traits to which genetic,environmental,and demographic factors contribute *** the underlying g...
详细信息
Hypertension,among diabetes,obesity and others,is one of the common human diseases that is genetically expressed as complex traits to which genetic,environmental,and demographic factors contribute *** the underlying genes and examining their interactions, a crucial step in understanding the molecular pathogenesis of complex diseases,is both a statistical and a computational challenge,stressing the need for novel strategies to move this process *** this paper we propose a new method to study the association of multiple gene interactions for complex *** method is carried out by two ***,we sequentially select additionally associated SNP loci combinations by minimizing the p-value of a test based on an information measure,measure of information ***,this approach is called MID ***,the significance of the selected associated loci combinations is assessed by an x *** MID method is model-free and nonparametric,it is easy to compute and *** capability of the MID method is confirmed by applying it to investigate the multiple gene interactions on risk of hypertension in northern Han Chinese,where thirty-three SNP loci with three-genotype in eleven candidate genes are *** results are consistent with those of Gu et al(2006).Additionally,we get some other new *** indicates that our idea is indeed feasible and useful in practice.
Most of the online courses nowadays are offered mainly in asynchronous mode, enabling students with the freedom of time and distance. Nonetheless, the drop-out rate for online courses is high. With online synchronous ...
详细信息
Most of the online courses nowadays are offered mainly in asynchronous mode, enabling students with the freedom of time and distance. Nonetheless, the drop-out rate for online courses is high. With online synchronous instruction students have both freedom of distance and punctuality of regular progress and the drop-out rate is found to be greatly reduced. However, there is a lack of online synchronous teaching pedagogies in the literature for teachers. This study aims to identify major issues that need to be considered in online synchronous instruction environments using observations of real online synchronous instruction in a physical setup. This paper then recommends some pedagogical guidelines for effective online synchronous teaching.
data analysis processes in scientific applications can be expressed as coarse-grain workflows of complex data processing operations with data flow dependencies between them. Performance optimization of these workflows...
详细信息
ISBN:
(纸本)9781605585871
data analysis processes in scientific applications can be expressed as coarse-grain workflows of complex data processing operations with data flow dependencies between them. Performance optimization of these workflows can be viewed as a search for a set of optimal values in a multi-dimensional parameter space. While some performance parameters such as grouping of workflow components and their mapping to machines do not affect the accuracy of the output, others may dictate trading the output quality of individual components (and of the whole workflow) for performance. This paper describes an integrated framework which is capable of supporting performance optimizations along multiple dimensions of the parameter space. Using two real-world applications in the spatial data analysis domain, we present an experimental evaluation of the proposed framework. Copyright 2009 ACM.
In this paper we present a new visualization paradigm to represent and assist the understanding of a correlative multi-level graph, a group of interconnected networks. Such a graph is formed via term association minin...
详细信息
In this paper we present a new visualization paradigm to represent and assist the understanding of a correlative multi-level graph, a group of interconnected networks. Such a graph is formed via term association mining, and the visualization paradigm consists of three components: terrain surface visualization units, terrain surface arrangement, and terrain surface correlation. We apply this paradigm to visualize and explore a pair of correlative core cancer terms network and core gene terms network. The results show that our visualization paradigm design is consistent with the derived associations, and is effective in preserving major features as the landmarks in the terrain surfaces.
Video retrieval and indexing research aims to efficiently and effectively manage very large video databases, e.g., CCTV records, which is a key component in video-based object and event analysis. In this paper, for th...
详细信息
Video retrieval and indexing research aims to efficiently and effectively manage very large video databases, e.g., CCTV records, which is a key component in video-based object and event analysis. In this paper, for the purpose of video retrieval, we propose a novel method to represent video data by developing an optical flow tensor (OFT) and incorporating hidden Markov models (HMMs). As video is content-sensitive and normally carries rich motion information of objects, optical flow field is first employed to estimate such motion. Then, a shot HMMs tree is built to model video clips in different levels in a database. Experimental results demonstrate that the newly developed method inherits advantages of both optical flow and HMMs in video representation. With the newly developed video representation, in video retrieval and indexing tasks, no need to exhaustively compare a query video shot with all video shot records in the database. Moreover, the novel representation method works well when linear discriminant analysis (LDA) is utilized to reduce the feature dimensionality and further speed up the retrieval procedure.
In this work we describe a system for the monitoring and management of patients with neurodegenerative diseases, focusing on Parkinson's Disease and Amyotrophic Lateral Sclerosis. The system exploits a single wear...
详细信息
In this work we describe a system for the monitoring and management of patients with neurodegenerative diseases, focusing on Parkinson's Disease and Amyotrophic Lateral Sclerosis. The system exploits a single wearable sensors' setting to detect and quantify all patient symptoms. An easy to use touchscreen interface allows patients and caregivers to provide additional useful information and assist patients to perform standard predefined tests which otherwise are performed in the clinician's office. The system exploits patient information to suggest appropriate treatment changes based on accumulated medical knowledge. In this paper the architecture of the system, as well as, its innovative features are presented.
In the current work, a system for the monitoring, assessment and management of patients with chronic movement disorders such as Parkinson's disease (PD) is presented. The so called PERFORM system consists of the p...
详细信息
In the current work, a system for the monitoring, assessment and management of patients with chronic movement disorders such as Parkinson's disease (PD) is presented. The so called PERFORM system consists of the patient and the healthcare center subsystem. PERFORM monitors patient's motion status in daily activities, using a set of light wearable sensors. Based on the analysis of the acquired signals, PERFORM assesses PD symptoms and their severity, integrates patient's demographic, clinical and history data and proposes treatment plans based on advanced data mining algorithms. In this work we present two main modules of PERFORM system, the tremor assessment module and the data miner module.
暂无评论