We propose a 3D nonparametric, entropy-based, coupled, multishape approach for the segmentation of subcortical brain structures in magnetic resonance images (MRI). Our method uses PCA to capture structures variability...
详细信息
ISBN:
(纸本)9781424406715;1424406714
We propose a 3D nonparametric, entropy-based, coupled, multishape approach for the segmentation of subcortical brain structures in magnetic resonance images (MRI). Our method uses PCA to capture structures variability. Because of complex relationships of pose and shape of the coupled structures, we only use their shape and size relation. To this end, we apply separate registrations of the structures. For each structure, we consider a similarity transform using seven parameters. In addition, to generate most accurate results, we estimate probability density functions (pdf) iteratively. The proposed method minimizes an entropy-based energy function using quasi-Newton algorithm. To improve the results, we use analytical derivatives. Sample results are given for the segmentation of putamen, thalamus and caudate illustrating the impact of coupling on the accuracy of the results.
Standard IP multicast makes no provision for authenticating or authorizing the participant hosts, nor for ensuring confidentiality of the data stream. An architecture for achieving these goals is proposed, based on th...
详细信息
Standard IP multicast makes no provision for authenticating or authorizing the participant hosts, nor for ensuring confidentiality of the data stream. An architecture for achieving these goals is proposed, based on the use of an extended version of the Host Identity Protocol. The applicability of the model is demonstrated for peer-to-peer multicasting and for non-shared media access networks. A formal validation of a two-layer peer-to-peer network based on this architecture has been completed.
This report summarizes the proceedings of a workshop discussion session presentation and visualization of aspects relating to duplicated, copied, or cloned code. The main outcomes of the working session were: (a) a re...
详细信息
Model-based approaches have proven fruitful in the design and implementation of intelligent systems that provide automated diagnostic functions. A wide variety of models are used in these approaches to represent the p...
详细信息
ISBN:
(纸本)1563478935
Model-based approaches have proven fruitful in the design and implementation of intelligent systems that provide automated diagnostic functions. A wide variety of models are used in these approaches to represent the particular domain knowledge, including analytic state-based models, input-output transfer function models, fault propagation models, and qualitative and quantitative physics-based models. Diagnostic applications are built around three main steps: observation, comparison, and diagnosis. If the modeling begins in the early stages of system development, engineering models such as fault propagation models can be used for testability analysis to aid definition and evaluation of instrumentation suites for observation of system behavior. Analytical models can be used in the design of monitoring algorithms that process observations to provide information for the second step in the process, comparison of expected behavior of the system to actual measured behavior. In the final diagnostic step, reasoning about the results of the comparison can be performed in a variety of ways, such as dependency matrices, graph propagation, constraint propagation, and state estimation. Realistic empirical evaluation and comparison of these approaches is often hampered by a lack of standard data sets and suitable testbeds. In this paper we describe the Advanced Diagnostics and Prognostics Testbed (ADAPT) at NASA Ames Research center. The purpose of the testbed is to measure, evaluate, and mature diagnostic and prognostic health management technologies. This paper describes the testbed's hardware, software architecture, and concept of operations. A simulation testbed that accompanies ADAPT, and some of the diagnostic and decision support approaches being investigated are also discussed.
Cellular network faults prediction models using mobile intelligent agent are presented in this paper. Cellular networks are uncertain and dynamic in their behaviours and therefore we use different artificial intellige...
详细信息
Cellular network faults prediction models using mobile intelligent agent are presented in this paper. Cellular networks are uncertain and dynamic in their behaviours and therefore we use different artificial intelligent techniques to develop platform independent, autonomous, reasoning and robust agents that can report on any unforeseen anomaly within the cellular network service provider. The specific design and implementation is done using Java Agent DE-velopment Framework (JADE). The partial results obtained from the experiments conducted are presented and discussed in this paper.
The scheduling of vehicle movement activities is an important component in highspeed railway transit operations planning process. This paper presents a mathematical programming approach to vehicle routing for the Penn...
详细信息
The scheduling of vehicle movement activities is an important component in highspeed railway transit operations planning process. This paper presents a mathematical programming approach to vehicle routing for the Pennsylvania Transrapid Maglev Train System. A mathematical model of the routing procedure is first derived. Based on this model, the vehicle routing problem is formulated into a constrained optimization problem, in which the train miles travelled are maximized subject to various operational and safety requirements. This large scale non-linear optimization problem is then solved by a genetic algorithm.
Sensor networks are becoming increasingly pervasive. Existing methods of aggregation in sensor networks offer mostly standard mathematical operators over homogeneous data types. In this paper, we instead focus on supp...
详细信息
Acquired software products from suppliers are being increasing tremendously because of insufficiency of resources and capable employees. To manage and monitor the product acquisition process effectively according to a...
详细信息
Acquired software products from suppliers are being increasing tremendously because of insufficiency of resources and capable employees. To manage and monitor the product acquisition process effectively according to a signed contract with a supplier, an organization has to define the standard of workflow, deliverable products in each step and staff roles and responsibilities, etc. Thus, there is a need to incorporate these diversified processes into a single process model that could helps to reach the software product acquisition goal. CMMI defines supplier agreement management process area (SAM) that relates to product acquisition but it does not describe how the organization should do to achieve its expectation. This research presents a business workflow process model for SAM process area of CMMI: capability level 2. It consists of three layers: contextual layer, elaboration layer, and definition layer. A software tool called supplier agreement management tool (SAMT) is also developed to help integrate the details of our approach and can be used for the proposed process model.
In this paper, a low-power architecture (ByZFAD Stands for Bypass Zero, Feed A Directly) for shift-and-add multipliers is proposed. The architecture considerably lowers the switching activity of conventional multiplie...
详细信息
ISBN:
(纸本)1595934790
In this paper, a low-power architecture (ByZFAD Stands for Bypass Zero, Feed A Directly) for shift-and-add multipliers is proposed. The architecture considerably lowers the switching activity of conventional multipliers. The modifications include the removal of the shift of B register, direct feeding of A to the adder, bypassing the adder whenever possible, using a ring counter instead of the binary counter, and removal of the partial product shift. To show the efficiency of the architecture, we have compared the switching activity of the proposed architecture with that of the conventional architecture for a radix-2 shift-and-add multiplier. The results for a 32-bit multiplier show that, the proposed architecture lowers the total switching activity up to 76% when compared to the traditional architecture. Copyright 2006 ACM.
暂无评论