检索结果-内蒙古大学图书馆

13th international conference on Computing and Information technology, IC2IT 2017

作者： thongkam, Puripat Leesutthipornchai, Pakorn Department of Computer Science Faculty of Science and Technology Thammasat University Pathum Thani Thailand

ISBN: (纸本)9783319606620

Feature selection is a pre-processing for choosing relevant features and ignores features that tend to have no predictive information. Feature selection is applied to improve the accuracy of classification process. High relevant features have a tendency to get high classification performance. this paper proposed the ensemble of multiple feature ranking techniques by considering ranker priority for feature selection. Five individual feature ranking algorithms (information gain, gain ratio, symmetrical uncertainty, reliefF and oneR) are investigated and considered together as ensemble, based on ranking priority. the lung cancer, lymphoma, breast cancer, ovarian cancer and leukemia datasets were gathered from Kent Ridge bio-medical data and Machine Learning data repository. the datasets are applied to ensemble features selection algorithm. the obtained results are compared to results from individual feature ranking algorithms and the existing ensemble algorithm. the selected features are applied to classification algorithms. Area under the curve (AUC), precision and recall values from six classification algorithms are used to evaluate the obtained features. the experimental results show that the selected features from proposed ensemble features selection algorithm are greater than those of individual feature ranking techniques and the existing ensemble features selection algorithm. © Springer international Publishing AG 2018.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

An enhanced deep convolutional encoder-decoder network for road segmentation on aerial imagery 13th

An enhanced deep convolutional encoder-decoder network for r...

引用

13th international conference on Computing and Information technology, IC2IT 2017

作者： Panboonyuen, Teerapong Vateekul, Peerapon Jitkajornwanich, Kulsawasd Lawawirojwong, Siam Department of Computer Engineering Faculty of Engineering Chulalongkorn University Bangkok Thailand Department of Computer Science Faculty of Science King Mongkut’s Institute of Technology Ladkrabang Bangkok Thailand Bangkok Thailand

ISBN: (纸本)9783319606620

Object classification from images is among the many practical examples where deep learning algorithms have successfully been applied. In this paper, we present an improved deep convolutional encoder-decoder network (DCED) for segmenting road objects from aerial images. Several aspects of the proposed method are enhanced, incl. incorporation of ELU (exponential linear unit)—as opposed to ReLU (rectified linear unit) that typically outperforms ELU in most object classification cases;amplification of datasets by adding incrementally-rotated images with eight different angles in the training corpus (this eliminates the limitation that the number of training aerial images is usually limited), thus the number of training datasets is increased by eight times;and lastly, adoption of landscape metrics to further improve the overall quality of results by removing false road objects. the most recent DCED approach for object segmentation, namely SegNet, is used as one of the benchmarks in evaluating our method. the experiments were conducted on a well-known aerial imagery, Massachusetts roads dataset (Mass. Roads), which is publicly available. the results showed that our method outperforms all of the baselines in terms of precision, recall, and F1 scores. © Springer international Publishing AG 2018.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

New Modified Current Starved Ring Voltage Controlled Oscillator and Frequency to Voltage Rectifier for Noise Suppression from 1-6 GHz in 180 nm technology 7

New Modified Current Starved Ring Voltage Controlled Oscilla...

引用

7th international conference on advances in Computing and Communications (ICACC)

作者： Suhas, D. Bharadwaj, Sippee Tezpur Univ Dept Elect & Commun Engn Tezpur 784001 Assam India Kaziranga Univ Sch Engn & Technol Jorhat 785006 Assam India

this paper proposes a new and simple combined effort of a NMOS sink current starved ring voltage controlled oscillator (NS-CSRVCO) fed-back with a manual frequency to voltage rectifier (FVR) for noise suppression in mixed signal applications. the VCO and FVR operate from 1-6 GHz, with the VCO providing a tuning range of 176.4% with excellent linearity in oscillation frequencies from 0.3444 GHz - 5.679 GHz with a center frequency of 3.024 GHz, within a control voltage (VDD) of 0.6 V to 2.5 V. the properties of both the VCO and FVR makes it suitable for Military, Satellite applications in the microwave range. (c) 2017 the Authors. Published by Elsevier B.V.

关键词： NS-CSRVCO FVR linearity wide tuning range ultra-low power low die area low ac ripples noise suppression

来源：评论

学校读者我要写书评

暂无评论

Development of early vocal screening service model of Parkinson’s disease 7th

引用

7th international conference on Kansei Engineering and Emotion Research, KEER 2018

作者： Lo, Hsin-Chang Yang, Chia-Yen Chia, Tsorng-Lin Tang, Shih-Tsang Yen, Chieh-Tsung Department of Product Design Ming Chuan University Taipei Taiwan Department of Biomedical Engineering Ming Chuan University Taipei Taiwan Department of Computer and Communication Engineering Ming Chuan University Taipei Taiwan Department of Neurology Dalin Tzu Chi Hospital Chiayi County Taiwan

ISBN: (纸本)9789811086113

Parkinson’s disease (PD) is a progressive and incurable neurodegenerative disease. If PD can be diagnosed and treated as early as possible, not only can it effectively delay the degeneration of the brain, but also further maintain the follow-up quality of patients’ life. this study focuses on developing an early vocal screening service of PD to detecting the stage of PD and helps healthy people to do an early screening of the possibility of developing PD. there are four patients with PD and three neurology physicians that were interviewed. In addition, a questionnaire survey of the healthy people on the acceptance of early screening services. For patients, they have to spend a long time to confirm the diagnosis during the observation period of suspected PD. the existing diagnosis is very dependent on the physician’s expertise and clinical experience, especially the initial diagnosis. thus, it delays the golden period of delaying correction, and early administration and treatment. Healthy people with the condition of PD likely possess little knowledge about it. But, they were willing to try the service of early screening to see whether they are suffering from suspected PD symptoms in a few minutes. According to the results, an early vocal screening service model is developed. the possibility of contracting PD can be detected as early as possible by subtle changes in speech as shown in the voice recording of 3 to 5 minutes left by healthy people, such as trembling, breathing pause, and other factors that are not easily identified by voice detection analysis. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Preface

Advances in Intelligent Systems and Computing

引用

advances in Intelligent Systems and Computing 2019年 817卷 v-vi页

作者： Bansal, Jagdish Chand Das, Kedar Nath Nagar, Atulya Deep, Kusum Ojha, Akshay Kumar Department of Mathematics South Asian University New Delhi India Department of Mathematics Indian Institute of Technology Roorkee RoorkeeUttarakhand India Department of Mathematics National Institute of Technology Silchar SilcharAssam India School of Basic Sciences Indian Institute of Technology Bhubaneswar BhubaneswarOdisha India Department of Mathematics and Computer Science Faculty of Science Liverpool Hope University Liverpool United Kingdom

来源：评论

学校读者我要写书评

暂无评论

Data driven prediction of dengue incidence in thailand 13th

Data driven prediction of dengue incidence in Thailand

引用

13th international conference on Computing and Information technology, IC2IT 2017

作者： Sumanasinghe, Nirosha Mikler, Armin R. Muthukudage, Jayantha Tiwari, Chetan Quiroz, Reynaldo Department of Computer Science College of Engineering University of North Texas DentonTX United States Department of Statistics and Computer Science University of Peradeniya Peradeniya Sri Lanka Department of Geography and the Environment University of North Texas DentonTX United States

ISBN: (纸本)9783319606620

Communicable diseases such as dengue pose a significant threat on public health across the world. Modeling an accurate and efficient prediction of dengue disease will improve public health response planning to outbreaks. However, despite the fact that many researches has focused on dengue prediction, it has been lacking geographical variation of dengue fever taken into account. Dengue is a mosquito-borne virus that annually infects over 400 million people worldwide. the infection pattern is different from region to region. We developed a model for predicting dengue fever for four provinces of thailand with geographical variation taken into account. these predictions show slightly varying outcomes across provinces. Support Vector Regression (SVR) was used as the modeling tool. Additionally, we introduced a novel method of assessing regression model in terms of accuracies over Mean Square Error (MSE) which does not capture the behavior of data pattern spatially. this novel method resulted in 71% accuracy of prediction for Kamphaeng Phet province. the proposed model of prediction facilitates administrative bodies to make informed decisions in the context of public health of thailand. © Springer international Publishing AG 2018.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Golden linear group key agreement protocol 14th

Golden linear group key agreement protocol

引用

14th international conference on Information technology - New Generations, ITNG 2017

作者： Vahidalizadehdizaj, Mohammad Leider, Avery Department of Computer Science Pace University 1 Pace Plaza New YorkNY United States

ISBN: (纸本)9783319549774

Security in group communication has been a significant field of research for decades. Because of the emerging technologies like cloud computing, mobile computing, ad-hoc networks, and wireless sensor networks, researchers are considering high group dynamics in communication security. Group key agreement protocol is for providing enough security for the group communication. Group key agreement protocol is a way to establish a shared cryptographic key between groups of users over public networks. Group key agreement protocol enables more than two users to agree on a shared secret key for their communications. In this paper we want to introduce a new key agreement protocol (GKA) and a new linear group key agreement protocol (GLGKA). these protocols are proper for the emerging dynamic networks. In GLGKA each member of the group can participate in key generation and management process. Our goal is to provide more efficient key generation approach for group members. this protocol can be used in cloud-based data storage sharing, social network services, smart phone applications, interactive chatting, video conferencing, and etc. © Springer international Publishing AG 2018.

关键词： Video conferencing

来源：评论

学校读者我要写书评

暂无评论

A new randomized procedure to solve the location routing problem 24th

A new randomized procedure to solve the location routing pro...

引用

24th international conference of the Forum for Interdisciplinary Mathematics, FIM 2015

作者： Quintero-Araujo, Carlos L. Juan, Angel A. Caballero-Villalobos, Juan P. Montoya-Torres, Jairo R. Faulin, Javier IN3 - Department of Computer Science Universitat Oberta de Catalunya Av. Carl Friedrich Gauss 5 Castelldefels08860 Spain International School of Economics and Administrative Sciences Universidad de La Sabana Autopista Norte Km 7 Chía Colombia Industrial Engineering Department Pontificia Universidad Javeriana Carrera 7 No. 40–62 Bogotá Colombia Facultad de Ingenieria Universidad de La Sabana Km 7 autopista norte de Bogotá Chía Colombia Statistics and Operations Research Department Institute of Smart Cities Campus Arrosadia Pamplona31006 Spain

ISBN: (纸本)9783319757919

the Location Routing Problem (LRP) is one of the most important challenging problems in supply chain design since it includes all decision levels in operations management. Due to its complexity, heuristics approaches seem to be the right choice to solve it. In this paper we introduce a simple but powerful approach based on biased randomization techniques to tackle the capacitated version of the LRP. Preliminary tests show that near-optimal or near-BKS can be found in a very short time. © Springer international Publishing AG, part of Springer Nature 2018.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Analysis and prototype sequences of face recognition techniques in real-time picture processing 6th

Analysis and prototype sequences of face recognition techniq...

引用

6th international conference on Frontiers of Intelligent Computing: theory and Applications, FICTA-2017

作者： Kishore, G.D.K. Babureddy, M. Department of Computer Science Krishna University MachilipatnamAndhra Pradesh India

ISBN: (纸本)9789811075650

the present-day implementation and demand of some real-time image processing applications are to be increased in various recent technologies. Some of these techniques are related to biometric applications such as fingerprint identification, face recognition, iris scan implementation, and speech identification;instead of all these techniques, face identification is an emerging concept in biometric applications with video summarization and surveillance, computer interaction with human being, face identification, and image databases in various applications to categorize face classification. In recent days, face identification is a rapid technology, which is a criminal forensic analysis, access control policy and prison dimensionality privacy with recent approaches. So, we have gone through formalized different approaches and techniques with feasible development of various biometric applications. We also discuss different classification and clustering techniques to extract all features of faces for identification in real-time applications. We also give all comprehensiveness with critical analysis in calculation of face detection in general implementation. this survey gives traditional methods to automatic face identification formulation to increase the performance in face identification. We also investigate review of implementation in data mining classification, clustering, and feature extraction methods with parameters which consist of face identification such as facial expression, variation, and facial illumination in biometric application developments. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

computer Simulation of Brocade Based on Modeling Structures 7

Computer Simulation of Brocade Based on Modeling Structures

引用

7th IEEE Annual international conference on CYBER technology in Automation, Control, and Intelligent Systems (CYBER)

作者： Fan, Zhen Zhou, Bowen Zhang, Senlin Liu, Meiqin Zhejiang Univ Coll Elect Engn Hangzhou 310027 Zhejiang Peoples R China

ISBN: (纸本)9781538604908

With the development of textile CAD, great advances have been made on fabric simulation. Most of their methods are based on the simulation of yarn to simulate fabric. However, the effect of their simulation of fabric depends on the complicated and fuzzy characteristic of fabric. From yarn to generate fabric, the fabric loses the reality on wrinkles, lightness, and randomness. According to analyzing the brocade picture, there are few weave structures on the brocade. In this paper, a method has been approved to simulate brocade with weave structure and yarn texture. Firstly, the weave structures on brocade were recognized from the picture of brocade. Secondly, the texture information on the yarn was combined with color and luminance. Finally, based on the weave structures and the texture information, the 2D simulation image of brocade was created. Compared with the true image of brocade, it has same structure with sense of reality on the appearance of the simulated brocade. therefore, the method is useful for the simulation of brocade and contributes to the traditional simulation of fabric with less weave structures.

关键词： brocade weave structure texture mapping luminance model fabric simulation

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：