检索结果-内蒙古大学图书馆

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing

作者： K. Taga K. Kameyama K. Toraichi Doctoral Program in Risk Engineering Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki Japan Tsukuba Advanced Research Alliance University of Tsukuba Tsukuba Ibaraki Japan

In this paper, we looked into two issues in pattern recognition using neural networks trained by back propagation (BP), namely inefficient learning and insufficient generalization. We observed that these phenomena are partly caused by the way the hidden layer units responds to the inputs. In order to solve the issues, we introduced regularization of the hidden layer unit response which amounts to suppressing the correlation among the response of the hidden layer units, and pruning the unit with the method unit fusion. The results of using the proposed technique were compared with the case of conventional technique in pattern recognition problems. From the results of the experiments, the rate of correct recognition increased when using regularization in the hidden layer unit response is performed, and it turned out that the required number of training epochs also decreases.

关键词： Neural networks Feature extraction systems engineering and theory Pattern recognition Computer vision Statistics

来源：评论

学校读者我要写书评

暂无评论

Layered neural network training with model switching and hidden layer feature regularization

Layered neural network training with model switching and hid...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： K. Kameyama K. Taga Tsukuha Advanced Research Alliance University of Tsukuba Tsukuba Ibaraki Japan Doctoral Program in Risk Engineering Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki Japan

This work introduces a scheme of layered neural network training, which incorporates a dynamical model alteration during training, and regularization of the features extracted in the hidden layer units. So far, use of Model Switching (MS), which is a simultaneous search scheme for an optimal model and parameter, proved to improve training efficiency and generalization ability as a side effect. In MS, the operation to switch the network to a different model involve orthogonalization of the features extracted in the hidden layer. Assuming that the orthogonalization contributes to the observed merits, joint use of MS and orthogonalization of the hidden layer feature by introducing a regularization term in the training, is introduced. The network trained by the proposed training scheme is applied to a pattern recognition problem, and some improvement in training efficiency and generalization ability were observed.

关键词： Neural networks Pattern recognition Feature extraction Switches Supervised learning systems engineering and theory Data mining Probability density function Size measurement

来源：评论

学校读者我要写书评

暂无评论

Modeling intracranial fluid flows and volumes during traumatic brain injury to better understand pressure dynamics

Modeling intracranial fluid flows and volumes during traumat...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： W. Wakeland J. McNames M. Aboy D. Hollemon B. Goldstein Systems Science Ph.D. Program Portland State University Portland OR USA Biomedical Signal Processing Laboratory Electrical and Computer Engineering Portland State University Portland OR USA Complex Systems Laboratory Division of Pediatric Critical Care Oregon Health and Sciences University Portland OR USA

We describe a computer model of intracranial pressure (ICP) dynamics that evaluates clinical treatment options for elevated ICP during traumatic brain injury (TBI). The model uses fluid volumes as primary state variables and explicitly models fluid flows as well as the resistance, compliance, and pressure associated with each intra- and extracranial compartment (arteries and arterioles, capillary bed, veins, venous sinus, ventricles, and brain parenchyma). The model evaluates clinical events and therapies such as intraand extra-parenchymal hemorrhage, cerebral edema, cerebrospinal fluid drainage, mannitol administration, head elevation, and mild hyperventilation. The model is able to replicate observed clinical behavior in many cases, including elevated ICP associated with severe cerebral edema following subdural, epidural, or intraparenchymal hematoma. The model also mimics cerebrovascular regulatory mechanisms that are activated during TBI.

关键词： Brain modeling Brain injuries Fluid dynamics Blood Logic Laboratories Fluid flow Medical treatment Signal processing Cranial pressure

来源：评论

学校读者我要写书评

暂无评论

Study on the vision-based indoor navigation of an Alife robot

Study on the vision-based indoor navigation of an Alife robo...

引用

Annual Conference of Industrial Electronics Society

作者： Jiwu Wang H. Kimura M. Sugisaka Department of Electrical and Electronics Engineering Oita University Oita Japan The Institute of Physical and Chemical Research (RIKEN) Bio-Mimetric Control Research Center Nagoya Japan Complex Systems Department of Complexity Science and Engineering The University of Tokyo Tokyo Japan

It is a prerequisite for a mobile robot to realize steady and reliable navigation. But its reliability is often weakened by an unavoidable slip and some incorrigible drift errors of sensors, especially after a long distance navigation. Although perceptual landmarks were solutions to such problems, it is easy to miss landmarks at some specific spots when the robot moves at different speeds, especially at higher speeds. And if the landmarks were put in any intervals, or if the illumination conditions were not good, it is more difficult to find them. In order to detect and extract the artificial landmarks robustly under different illuminating conditions, some low level but robust image processing technique was implemented. The moving speed was controlled with the visual servoing control method. When the robot suddenly can not find some specific landmarks at some specific spots because of the higher speed or rapid turn of the road, it will search for the landmarks based on its intelligence, the inertia of the previous motion, and find the landmark in the shortest time. These methods were verified by the reliable vision-based indoor navigation of an Alife mobile robot.

关键词： Navigation Robot vision systems Robot sensing systems Mobile robots Robustness Intelligent robots Lighting Image processing Visual servoing Roads

来源：评论

学校读者我要写书评

暂无评论

A summating, exponentially-decaying CMOS synapse for spiking neural systems 03

A summating, exponentially-decaying CMOS synapse for spiking...

引用

Proceedings of the 17th International Conference on Neural Information Processing systems

作者： Rock Z. Shi Timothy Horiuchi Electrical and Computer Engineering Department University of Maryland College Park MD and Institute for Systems Research University of Maryland College Park MD Electrical and Computer Engineering Department University of Maryland College Park MD and Institute for Systems Research University of Maryland College Park MD and Neuroscience and Cognitive Science Program University of Maryland College Park MD

Synapses are a critical element of biologically-realistic, spike-based neural computation, serving the role of communication, computation, and modification. Many different circuit implementations of synapse function exist with different computational goals in mind. In this paper we describe a new CMOS synapse design that separately controls quiescent leak current, synaptic gain, and time-constant of decay. This circuit implements part of a commonly-used kinetic model of synaptic conductance. We show a theoretical analysis and experimental data for prototypes fabricated in a commercially-available 1.5µm CMOS process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulating the cladistic evolution of manufacturing

引用

Innovation 2003年第2-3期5卷 144-156页

作者： James S Baldwin[a] Peter M Allen[b] Belinda Winder[c] Keith Ridgway[d] [a] Advanced Manufacturing Research Centre with Boeing Department of Mechanical Engineering University of Sheffield Sheffield UK[b] Head of Complex Systems Management Centre School of Management Cranfield University Bedford UK[c] Head of Industrial Psychology Research Group Department of Mechanical Engineering University of Sheffield Sheffield UK[d] Director of the Advanced Manufacturing Research Centre with BoeingDepartment of Mechanical Engineering University of Sheffield Sheffield UK

SummarySummaryA common belief within manufacturing is ‘the only constant is change’. Manufacturing cladistics was first developed in the early 1990s not only as a means of classibling manufacturing organisations but also, and perhaps more importantly, as a tool to both help deal with change, and use as a guide for organisational re-engineering. However, this approach has one major limitation — it is only a description of the past; the future is not represented. Uncertainty in decision-making and unknown barriers are thought to be major inhibitors behind the introduction of important innovations in technical, organisational and social domains. This paper reports on the results of a study that interprets two complimentary, but currently unrelated, areas of research, manufacturing cladistics and evolutionary systems methodology. This new framework would enable the exploration of evolutionary processes involved in the interactions of technologies and practices, facilitating decision-making as well as the exploration of new organisational structures.

关键词： manufacturing cladistics evolutionary systems modelling management’ decision making organisational transformations

来源：评论

学校读者我要写书评

暂无评论

A method on tracking common boundaries of color regions in function approximation-based image coding

A method on tracking common boundaries of color regions in f...

引用

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing

作者： T. Sugiyama P.W.H. Kwan K. Toraichi K. Katagishi Doctoral Program Graduate School of Systems and Information Engineering University of Tsukuba Japan Core Research for Evolutional Science & Technology Program Japan Science and Technology Corporation Japan Institute of Information Sciences and Electronics University of Tsukuba Japan

A boundary tracking method crucial to function approximation-based image coding is proposed that solves the problems caused by duplicate tracking the common boundaries of color regions when methods conventionally applied to bilevel raster images are inappropriately used. Experimental evaluation is performed to verify its effectiveness.

关键词： Function approximation Image coding Colored noise Color Image reconstruction systems engineering and theory Electronic mail Performance evaluation Spline Internet

来源：评论

学校读者我要写书评

暂无评论

A new method on assigning function types to line segments for function approximation-based image coding

A new method on assigning function types to line segments fo...

引用

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing

作者： F. Kawazoe K. Toraichi P.W.H. Kwan Donoral Program Graduate School of Systems and lnformation Engineering University of Tsukuba Japan Institute of Information Science and Electronics University of Tsukuba Japan Core Research for Evolutional Science & Technology Program Japan Science and Technology Corporation Japan

This paper proposes a new method to determine the types of function for approximating line segments using an algorithm based on binary search. In the function approximation-based image coding, it is essential that the joint points between different types of line segment be extracted precisely. Through experiments, it is verified that the proposed method extracts straight lines and arcs more precisely than the earlier method.

关键词： Image segmentation Function approximation Image coding Paper technology Flowcharts systems engineering and theory Information science Electronic mail Pixel Target tracking

来源：评论

学校读者我要写书评

暂无评论

Significance of intracranial pressure pulse morphology in pediatric traumatc brain injury

Significance of intracranial pressure pulse morphology in pe...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： M. Aboy J. McNames D. Cuesta-Frau W. Wakeland T. Thong S. Lai B. Goldstein Biomedical Signal Processing Laboratory Electrical and Computer Engineering Portland State University Portland OR USA Computer Vision Group ETS-Alcoi Polytechnic University of Valencia Spain Systems Science Ph.D. Program Portland State University Portland OR USA Biomedical Engineering OGI School of Science and Engineering Oregon Health and Sciences University Portland OR USA Complex Systems Laboratory Department of Pediatrics Oregon Health and Sciences University Portland OR USA

We investigated the relationship between the intracranial pulse pressure (ICP/sub PP/) and the mean intracranial pressure (ICP/sub M/). In adult patients, several research groups have described a linear relationship between ICP/sub PP/ and ICP/sub M/ within the range of cerebral autoregulation. Current monitoring and therapy are mainly based on the mean ICP/sub M/, since it is believed that the ICP/sub M/ contains most of the information provided by the other pulse morphology metrics. In this paper we attempt to answer whether there is further information within the ICP morphology not explained by ICP/sub M/ that might be of prognostic significance. We screened ICP records of 42 patients admitted to the Pediatric Intensive Care Unit at Doernbecher Children's Hospital for segments in which the ICP/sub M/ varied at least 5 mmHg during a 1-hour period. We found 54 segments in 9 different pediatric TBI patients (ages 0.2-17.8 years, mean=9.9 years). ICP/sub PP/ and ICP/sub M/ were calculated for each pulse using an automatic pressure detection algorithm. The coefficient of linear correlation r was > 0.70 in 43/54 segments (p < 0.001), which indicates that there exists a linear relationship between ICP/sub PP/ and ICP/sub M/. However, we found r > 0.90 only in 16/54 segments (p=NS) . This result and visual inspection of ICP/sub PP/ vs. ICP/sub M/ density plots suggest that ICP pulse pressure is not fully explained by the ICP M.

关键词： Cranial pressure Morphology Brain injuries Iterative closest point algorithm Pediatrics Patient monitoring Medical treatment Hospitals Detection algorithms Inspection

来源：评论

学校读者我要写书评

暂无评论

Sorting on Single-Channel Wireless Sensor Networks

引用

International Journal of Foundations of Computer Science 2003年第3期14卷 391-403页

作者： Jacir Luiz Bordim Koji Nakano Hong Shen Adaptive Communications Research Laboratories Advanced Telecommunications Research Institute International 2-2-2 Hikaridai Kyoto 619-0288 Japan School of Artificial Complex Systems Engineering Hirhoshima University Kagamiyama Higashi-Hiroshima 799-8527 Japan School of Information Science Japan Advanced Institute of Science and Technology Asahidai Tatsunokuchi Ishikawa 923-1292 Japan

A Wireless Sensor Network (WSN) is a distributed system consisting of a large number of wireless sensing devices and a base station. Due to their compactness and low-cost, sensor networks can be distributed at a fraction of the cost of conventional wired sensors and actuator systems. The physical world generates an unlimited amount of data that can be observed and monitored. Hence, designing protocols to coordinate WSNs with hundreds, or even thousands, of sensors will face many challenges. In this work we focus on the design of protocols that enable the sensor nodes to coordinate among themselves to achieve a larger task. From this standpoint, we present a sorting protocol for wireless sensor networks. We show that in a WSN consisting of n sensor nodes, where each sensor stores an element and has a fixed transmission range r. sorting can be performed in time slots when . We also reason that future applications of wireless sensor networks are very likely to employ short-range radio communications (i.e., r less than 100 meters). If this is the case, the time complexity of our sorting protocol is optimal.

关键词： Wireless sensor networks sorting bitonic sorting sensing devices

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：