检索结果-内蒙古大学图书馆

IEEE Conference on computer Vision and Pattern Recognition Workshops

作者： Sadaf Afshar Albert Ali Salah Computational Science and Engineering Program Boğaziçi University Istanbul Turkey Department of Computer Engineering Boğaziçi University Istanbul Turkey

Improved dense trajectory features have been successfully used in video-based action recognition problems, but their application to face processing is more challenging. In this paper, we propose a novel system that deals with the problem of emotion recognition in real-world videos, using improved dense trajectory, LGBP-TOP, and geometric features. In the proposed system, we detect the face and facial landmarks from each frame of a video using a combination of two recent approaches, and register faces by means of Procrustes analysis. The improved dense trajectory and geometric features are encoded using Fisher vectors and classification is achieved by extreme learning machines. We evaluate our method on the extended Cohn-Kanade (CK+) and EmotiW2015 Challenge databases. We obtain state-of-the-art results in both databases.

关键词： Videos Trajectory Feature extraction Mouth Face recognition Support vector machines Cameras

来源：评论

学校读者我要写书评

暂无评论

Layered ensemble model for short-term traffic flow forecasting with outlier detection

Layered ensemble model for short-term traffic flow forecasti...

引用

IEEE International Forum on Research and Technologies for Society and Industry Leveraging a better tomorrow (RTSI)

作者： Amr Abdullatif Stefano Rovetta Francesco Masulli Department of Computer Science Robotics and Systems Engineering University of Genova Genova Italy College of Science and Technology Temple University Sbarro Institute for Cancer Research and Molecular Medicine Philadelphia PA USA

ISBN: (纸本)9781509011322

Real time traffic flow forecasting is a necessary requirement for traffic management in order to be able to evaluate the effects of different available strategies or policies. This paper focuses on short-term traffic flow forecasting by taking into consideration both spatial (road links) and temporal (lag or past traffic flow values) information. We propose a Layered Ensemble Model (LEM) which combines Artificial Neural Networks and Graded Possibilistic Clustering obtaining an accurate forecast of the traffic flow rates with outlier detection. Experimentation has been carried out on two different data sets. The former was obtained from real UK motorway and the later was obtained from simulated traffic flow on a street network in Genoa (Italy). The proposed LEM model for short-term traffic forecasting provides promising results and given the ability for outlier detection, accuracy, robustness of the proposed approach, it can be fruitful integrated in traffic flow management systems.

关键词： Forecasting Predictive models Neural networks Roads Computational modeling Data models Industries

来源：评论

学校读者我要写书评

暂无评论

Shot noise detection in hBN-based tunnel junctions

arXiv

引用

arXiv 2017年

作者： Zhou, Panpan Hardy, Will J. Watanabe, Kenji Taniguchi, Takashi Natelson, Douglas Department of Physics and Astronomy Rice University 6100 Main Street HoustonTX77005 United States Applied Physics Program Smalley-Curl Institute Rice University 6100 Main Street HoustonTX77005 United States National Institute for Materials Science 1-1 Namiki Tsukuba Ibaraki305-0044 Japan Department of Electrical and Computer Engineering Rice University 6100 Main Street HoustonTX77005 United States Department of Materials Science and Nanoengineering Rice University 6100 Main Street HoustonTX77005 United States

High quality Au/hBN/Au tunnel devices are fabricated using transferred atomically thin hexagonal boron nitride as the tunneling barrier. All tunnel junctions show tunneling resistance on the order of several kΩ/µm2. Ohmic I-V curves at small bias with no signs of resonances indicate the sparsity of defects. Tunneling current shot noise is measured in these devices, and the excess shot noise shows consistency with theoretical expectations. These results show that atomically thin hBN is an excellent tunnel barrier, especially for the study of shot noise properties, and this can enable the study of tunneling density of states and shot noise spectroscopy in more complex systems. Copyright © 2017, The Authors. All rights reserved.

关键词： Shot noise

来源：评论

学校读者我要写书评

暂无评论

Supporting student attainment and management of competencies in a trans-disciplinary degree program 123

Supporting student attainment and management of competencies...

引用

123rd ASEE Annual Conference and Exposition

作者： Van Epps, Amy S. Ashby, Iryna Gray, Colin M. Exter, Marisa Purdue University Department of Library Science and Engineering Librarian West Lafayette United States Purdue University Learning Design and Technology Program West Lafayette United States Purdue University Department of Computer Graphics Technology West Lafayette United States Department of Learning Design and Technology College of Education Purdue University West Lafayette United States

In Fall 2014, a large Midwestern land-grant research university piloted a competency-based model as the foundation for an undergraduate transdisciplinary program focusing on connecting engineering and technology with humanities and social sciences. Students enrolled in this program progress through a set of competencies that require them to master cross-disciplinary and cross-functional skills needed to be successful in a 21stcentury workplace. Now in its second year, the competency-based program has undergone significant changes that include a more substantial definition of competencies at each of the three levels of competence (developing, emerging, and proficient), scaffolding needed to support students on their path towards gaining competencies, and significant mentoring by faculty, TAs, and professional advisers to support competency attainment. In this paper, we will share challenges and discoveries made by the faculty throughout the first two years of the novel Competency-Based Education (CBE) experience, including a reflection on how such experiences impacted modifications of the CBE model from Year 1 to Year 2, the ways in which the program supported individual attainment and management of competencies by students, and the value of the mentorship program in supporting student-driven learning paths. We will also share insights into students' perceptions of the benefits, challenges, and frustrations of being part of this pilot program based on interview and survey data provided by the 33 members of the initial cohort. This overview of the ways this program supported students in attaining competencies through coursework, individual mentoring, and scaffolding may be instructive as institutions seek to bring CBE to scale and increase holistic student learning for the 21stcentury. © American Society for engineering Education, 2016.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Retraction: LUC Algorithm in Visual Cryptography (J. Phys.: Conf. Ser. 1114 012090)

引用

Journal of Physics: Conference Series 2018年第1期1114卷

作者： Ratnadewi Christian Dio Alpha G Darmawan Napitupulu Heri Nurdiyanto Nuning Kurniasih Abdurrozaq Hasibuan GS Achmad Daengs Rosida Tiurma Manurung Indrya Mulyaningsih Robbi Rahim Castaka Agus Sugianto Dahlan Abdullah Department of Electrical Engineering Universitas Kristen Maranatha Bandung Indonesia Research Center for Quality System and Testing Technology Indonesian Institute of Sciences Banten Indonesia STMIK Dharma Wacana Indonesia Faculty of Communication Sciences Library and Information Science Program Universitas Padjadjaran Bandung Indonesia Universitas Islam Sumatera Utara Indonesia University of 45 Surabaya Indonesia Graduate Program in Scientific Psychology Universitas Kristen Maranatha Bandung Indonesia Department of Education Institut Agama Islam Negeri Syekh Nurjati Cirebon Indonesia School of Computer and Communication Engineering Universiti Malaysia Perlis Kubang Gajah Malaysia Politeknik TEDC Bandung Indonesia Department of Informatics Universitas Malikussaleh Aceh Utara Indonesia

This paper was retracted by IOP Publishing on 12 December 2018. This paper was published due to a technical error and was not intended to be included in this journal. Retraction published: 8 February 2019

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and preliminary characterization of a soft wearable exoskeleton for upper limb

Design and preliminary characterization of a soft wearable e...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Leonardo Cappello Dinh Khanh Binh Shih-Cheng Yen Lorenzo Masia Department of Robotics Brain and Cognitive Science Istituto Italiano di Tecnologia Genova Italy School of Mechanical & Aerospace Engineering Nanyang Technological University Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore

ISBN: (纸本)9781509032884

Exoskeletons targeting the upper limb have been broadly developed both for rehabilitation and to augment user's physical performance. Generally, they are rigid robotic interfaces characterized by a non negligible mechanical impedance at the end effector and consequently perceived by the upper limbs as an external body. The rigid frame, moreover, adds kinematic constrains to the natural joint kinematics which may result in discomfort and ultimately in pain. The concept of soft wearable exoskeleton (or exosuit) has been developed and tested for the lower limb and the hand to address such issues thanks to their minimal inertial contribution and influence on the natural kinematics. In the current paper the design of an soft robotic interface for the elbow joint is presented, whose aim is to provide assistance torque to the targeted joint to facilitate the execution of the activities of daily living. Differently from the state-of-the-art design solutions, our system is able to drive both flexion and extension of the same joint with a single motor in an agonist-antagonist fashion, making the actuation stage compact and energy efficient. A clutching mechanism is also included in the design in order to save power during static configuration, preventing the motor to hold the joint position for a large amount of time. An exosuit has been designed to transfer the torque of the actuator to the biomechanical joint by means of Bowden cables. Two series elastic elements are employed to overcome the drawbacks of the agonist-antagonist mechanism and to provide additional compliance at the end effector. A preliminary test has been finally performed in order to characterize the actuation.

关键词： Cable shielding Actuators Springs Gears Brushless DC motors

来源：评论

学校读者我要写书评

暂无评论

LUC Algorithm in Visual Cryptography

引用

Journal of Physics: Conference Series 2018年第1期1114卷

Nowadays, messaging technology in digital data form more often used and not less messages that confidentially wanted. Then it should be modified so that can be understood only by the sender and the intended recipients. All of this system can be realization by using cryptography. LUC algorithms are introduced by Smith and Lennon in 1993. LUC algorithm is an algorithm that based on the use of Lucas sequence (specific arithmetic operations derived from Lucas row) that rarely used to enhance the security of the messages. In this research, LUC algorithm is combined with visual cryptography to process the encryption and the description of a colored image. Four different images were used in the trial here. The performance of the system is assessed using Structural similarity (SSIM) which has an assessment similar to human eye. If the image quality is the same as the original image, then the SSIM value is one. Whereas if the quality of decryption image is very different from the original image then the value of SSIM is zero.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Energy Efficient Hybrid Clustering Routing Protocol for Underwater WSNs

An Energy Efficient Hybrid Clustering Routing Protocol for U...

引用

International Workshop on Bio and Intelligent Computing

作者： Mudassir Ejaz Nadeem Javaid Hammad Maqsood Usman Shakeel Zahoor Ali Khan Umar Qasim Department of Computer Science COMSATS Institute of Information Technology Internetworking Program Faculty of Engineering Dalhousie University Cameron Library University of Alberta

ISBN: (纸本)9781509024629

Underwater acoustic communications are a hastily growing field of research and engineering, which once were exclusively for military applications are now extending into commercial fields. Underwater Wireless Sensor Networks (UWSNs) appeal the research community, facing challenges as sensor nodes have energy constraint and radio signals are not suitable for underwater wireless communication. This paper explores an Energy Efficient Hybrid Clustering routing protocol (EEHC) for UWSNs, depicted from Depth-Based Energy-Balanced Hybrid (DB-EBH) routing protocol with integrated clustering technique.

关键词： Acoustic Communication Underwater Wireless Sensor Networks (UWSNs) Energy Efficient Hybrid Clustering (EEHC) Depth-Based Energy-Balanced Hybrid (DB-EBH)

来源：评论

学校读者我要写书评

暂无评论

Texture analysis of tissue aging using global and cluster constrained local coding

Texture analysis of tissue aging using global and cluster co...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yang Song Weidong Cat Fan Zhang Heng Huang David Dagan Feng Yue Wang Mei Chen BMIT Research Group University of Sydney Australia The University of Sydney Sydney NSW AU Department of Computer Science and Engineering University of Texas Arlington USA Bradley Department of Electrical and Computer Engineering Virginia Tech USA Robotics Institute Carnegie Mellon University USA Computer Engineering Department University of Albany State University of New York USA

ISBN: (纸本)9781479923519

Morphological age of various tissues provides important information about aging processes. In this paper, we propose a method for quantifying the tissue age of pharynx terminal bulb in *** from microscopy images. Our method comprises two main components: (i) a multi-modal texture descriptor extracted at two scales; and (ii) an age quantification algorithm with global and cluster-constrained local coding. The performance of our proposed method is evaluated on 970 images of seven age classes in the publicly available IICBU dataset. Our method achieves 21% improvement in classification accuracy when compared to that of the benchmark platform, and our local coding algorithm outperformed the support vector machine model by 10%.

关键词： Encoding Aging Support vector machines Microscopy Image coding Dictionaries Pharynx

来源：评论

学校读者我要写书评

暂无评论

User-adaptive fall detection for patients using wristband

User-adaptive fall detection for patients using wristband

引用

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Young-Hoon Nho Jong Gwan Lim Dae-Eon Kim Dong-Soo Kwon Robotics Program and Human-Robot Interaction research center Korea Advanced Institute of Science and Technology Daejeon Republic of Korea Department of Information Engineering Computer Science and University of Trento Italy KAIST Human-Robot Interaction Research Center Daejeon Republic of Korea Department of Mechanical Engineering Human-Robot Interaction research center Daejeon Republic of Korea

Fall detection systems have been proposed to prevent additional injuries following fall accidents. This paper introduces an easily learnable fall detection system based on the data of an individual patient in a hospital room. The improvement of low performance using a single accelerometer at wrists and the inconvenience of sensor attached to a waist in the conventional approach was concentrated on by integrating heart rate signals to the conventional acceleration approach and changing the sensor location from a waist to wrists. As for the optimal heart rate feature selection, we proposed a four-feature vector combination (root mean square of successive differences, standard deviation of successive differences, normal to normal 50, normal to normal 20) with correlation and mutual information analysis in addition to mean absolute deviation selected as an accelerometer feature. To easily acquire and train the patients' fall data, our system was based on unsupervised learning approaches using Gaussian mixture models for optimal classifiers with the optimal cluster number decided by cluster validation index of square error sum. A 10-fold cross validation was applied for a final performance evaluation where each threshold for separating fall state from non-fall state was automatically decided in several comparison groups, which were created on the basis of fusion timing and used sensors. As a result, despite sensors attached to the wrist, the wearable inconvenience of the conventional is overcome using the feature-level fused approach between heart rates and accelerations with the accuracy up to 98.39 %, which is closest to 99.34 % of the case using a single accelerometer located at the waist.

关键词： Accelerometers Heart rate Wrist Training data Hospitals Robot sensing systems Unsupervised learning

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：