检索结果-内蒙古大学图书馆

Hybrid descriptor definition for content based image classification using fusion of handcrafted features to convolutional neural network features

引用

International Journal of Information technology (Singapore) 2021年第4期13卷 1365-1374页

作者： Das, Rik Kumari, Khusbu De, Sourav Manjhi, P.K. Thepade, Sudeep Department of Post Graduate Program in Information Technology Xavier Institute of Social Service Ranchi Jharkhand India Department of Computer Applications Yogoda Satsanga Mahavidyalaya Ranchi Jharkhand India Department of Computer Science & Engineering Cooch Behar Government Engineering College Cooch Behar India Department of Mathematics Vinoba Bhave University Hazaribag Jharkhand India Department of Computer Engineering Pimpri Chinchwad College of Engineering Pune India

The efficacy of content-based image classification is dependent on the richness of the feature vectors extracted from the image data. Traditional feature extraction techniques highlight single low level image characteristics like shape, size, texture, color etc. for feature generation. The process often fails to extract meaningful descriptors since considering a single image characteristic will ignore other rich properties of image contents. Mass adoption of Convolutional Neural Network (CNN) has significantly improved classification performances for content-based image data. Recent literature has documented high level of precision for image classification by carrying out transfer learning with open source pre trained Convolutional Neural Network (CNN). However, the concept of transfer learning experiences major setback in case of limited training data due to overfitting of training instances during finetuning. This work has identified this challenge and has attempted to capture probability distribution of input images to a pre trained Convolution Neural Network by utilizing it as a fixed weight feature extractor. The proposed approach has addressed the overfitting problem by removing the finetuning step involved in transfer learning. Further investigation on robust descriptor definition is carried out by concatenating the pre-trained CNN features to handcrafted features. The hybrid architecture has encouraging outcomes that have outclassed the classification accuracies of state-of-the-art handcrafted techniques. © 2021, Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Augmented feature learning Feature fusion Handcrafted features Image classification Pre trained Convolutional Neural Network (CNN) Representation learning

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Reinforcement Learning in Assembly Path Planning based on 3D Point Clouds

An Implementation of Reinforcement Learning in Assembly Path...

引用

2018 International Automatic Control Conference, CACS 2018

作者： Chang, Wen-Chung Andini, Dianthika Puteri Pham, Van-Toan Department of Electrical Engineering National Taipei University of Technology Taipei106 Taiwan International Graduate Program in Electrical Engineering and Computer Science National Taipei University of Technology Taipei106 Taiwan

ISBN: (纸本)9781538662786

3D point clouds consisting of a lot of informatively geometric data have been playing critical roles in many applications such as 3D segmentation, polyline annotation for lane tracking, and especially in manufacturing industry. In particular, this paper proposes to apply Reinforcement Learning (RL) to resolve an automated assembly task based on 3D point cloud data. To address this task, the proposed structure is separated into 2 stages including registration stage and assembly path planning stage. Firstly, in the registration stage, one of the objects is matched to an assembled model to determine the transformation between two 3D point clouds by using RANdom Sample Consensus (RANSAC) and Iterative Closet Point (ICP). Secondly, we employ Q-learning method to train a model to make optimal decisions in assemble path planning task. The entire optimized assembly path planning task has been successfully accomplished for typical objects. Finally, the performance of the approach developed in this paper has been validated by experiments. © 2018 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Simultaneous localization and mapping of a mobile robot with surveillance and flying cameras

Simultaneous localization and mapping of a mobile robot with...

引用

2018 SICE International Symposium on Control Systems, SICE ISCS 2018

作者： Chang, Wen-Chung Wu, Chia-Hung Huang, Yang-Cheng Andini, Dianthika Puteri Department of Electrical Engineering National Taipei University of Technology Taipei106 Taiwan International Graduate Program in Electrical Engineering and Computer Science National Taipei University of Technology Taipei106 Taiwan

ISBN: (纸本)9784907764586

Localization and exploration of robotic systems has been a highly active research area in recent years. In order to explore unknown environments with better precision, a robotic system employing surveillance and flying cameras is proposed in this paper. Specifically, a mobile robot equipped with an onboard monocular camera performs visual simultaneous localization and mapping with extended Kalman filtering (EKF-VSLAM) and moves from indoor to outdoor environments. To correct the estimation errors of the system during the task, a least squares-based correction approach is proposed. The proposed robotic system employs surveillance cameras in indoor environment and a flying camera in outdoor environment to correct estimation error from the onboard monocular camera. The proposed correction approach, integrated with the conventional EKF-VSLAM, has been validated by experiments demonstrating better precision. © 2018 The Society of Instrument and Control Engineers - SICE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Diversity-Optimized Group Extraction in Social Networks

引用

IEEE Transactions on Computational Social Systems 2024年第1期11卷 756-769页

作者： Hsu, Bay-Yuan Chen, Yi-Ling Ho, Ya-Chi Chang, Po-Yuan Chang, Chih-Chieh Shia, Ben-Chang Shen, Chih-Ya National Tsing Hua University Department of Industrial Engineering and Engineering Management Hsinchu30013 Taiwan National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei10607 Taiwan Hsinchu31040 Taiwan Fu Jen Catholic University Department of Business Administration New Taipei City24205 Taiwan National Taiwan University of Science and Technology Management Undergraduate Program Taipei10607 Taiwan National Tsing Hua University Department of Computer Science Hsinchu30013 Taiwan

In this article, we propose to study a novel research problem to boost group performance, that is, social-aware diversity-optimized group extraction (SDGE), which takes into consideration the two important factors: 1) group diversity and 2) social tightness. We prove the NP-hardness of SDGE and propose an effective algorithm, named group shrinking for diversity maximization (GSDM) with a performance guarantee, that is, GSDM is a three-approximation algorithm to the SDGE problem studied in this article. We further propose three effective pruning strategies that are able to boost the efficiency of GSDM but do not deteriorate its performance. We conduct extensive experiments on multiple large-scale real datasets to evaluate the performance of GSDM. The experimental results show that our proposed GSDM outperforms the other baseline approaches significantly, in terms of solution quality and efficiency. Moreover, the experimental results also confirm that our proposed pruning strategies indeed boost the efficiency of the algorithm. © 2014 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Development of Educational Game for Indonesian History Lesson Focusing on Indonesia Pre-Literacy Relics 'Prehistoria' for Grade X High School Student

Development of Educational Game for Indonesian History Lesso...

引用

2020 International Conference on computer engineering, Network, and Intelligent Multimedia, CENIM 2020

作者： Nugroho, Supeno Mardi Susiki Rahman, Muhammad Daffa Abiyyu Hariadi, Mochamad Arief, Muhammad Faculty of Intelligent Electrical and Informatics Technology Sepuluh Nopember Institute of Technology Computer Engineering Department Surabaya Indonesia Tokyo University of Technology Media Science Program Graduate School of Bionics Computer and Media Sciences Tokyo Japan

ISBN: (纸本)9781728182834

The development of game technology has opened up new possibilities in learning methods through educational games. However, in Indonesia, the application of this concept is lacking. One lesson that can benefit from educational games is Indonesian History in class X, with a focus on history in the pre-literacy period. This study aims to create a puzzle-Adventure type of digital game that can help educate students about the pre-literacy period, developed with Unity, and uses WebGL as a target device while referring to Indonesia's revised 2013 national curriculum. The result of this research is the creation of a digital game that can be played on average of 254.36 seconds, with potential for educational use. A survey result shows that many of the ancient objects and some of the ages are well-recognized. However, the survey also shows many of the gameplay aspects, such as UI, gameplay features, and adventure elements, need improvements. © 2020 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

An Optimal Framework for SDN Based on Deep Neural Network

引用

computers, Materials & Continua 2022年第10期73卷 1125-1140页

作者： Abdallah Abdallah Mohamad Khairi Ishak Nor Samsiah Sani Imran Khan Fahad RAlbogamy Hirofumi Amano Samih M.Mostafa Department of Industrial Engineering School of Applied Technical Sciences German Jordanian UniversityAmman35247Jordan School of Electrical and Electronic Engineering Universiti Sains MalaysiaNibong Tebal14300Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and TechnologyThe National University of Malaysia(UKM)Bangi43600SelangorMalaysia Department of Electrical Engineering University of Engineering and TechnologyPeshawar814Pakistan Turabah University College Computer Sciences ProgramTaif UniversityTaif21944Saudi Arabia Research Institute for Information Technology Kyushu UniversityFukuoka819-0395Japan Computer Science-Mathematics Department Faculty of ScienceSouth Valley UniversityQena83523Egypt

Software-defined networking(SDN)is a new paradigm that promises to change by breaking vertical integration,decoupling network control logic from the underlying routers and switches,promoting(logical)network control centralization,and introducing network ***,the controller is similarly vulnerable to a“single point of failure”,an attacker can execute a distributed denial of service(DDoS)attack that invalidates the controller and compromises the network security in *** address the problem of DDoS traffic detection in SDN,a novel detection approach based on information entropy and deep neural network(DNN)is *** approach contains a DNN-based DDoS traffic detection module and an information-based entropy initial inspection *** initial inspection module detects the suspicious network traffic by computing the information entropy value of the data packet’s source and destination Internet Protocol(IP)addresses,and then identifies it using the DDoS detection module based on *** assaults were found when suspected irregular traffic was *** reveal that the algorithm recognizes DDoS activity at a rate of more than 99%,with a much better accuracy *** false alarm rate(FAR)is much lower than that of the information entropy-based detection ***,the proposed framework can shorten the detection time and improve the resource utilization efficiency.

关键词： Deep neural network computer networks data security optimization

来源：评论

学校读者我要写书评

暂无评论

Indoor localization at 5GHz using dynamic machine learning approach (DMLA)

Indoor localization at 5GHz using dynamic machine learning a...

引用

2017 IEEE International Conference on Applied System Innovation, ICASI 2017

作者： Belay, Abebe Yen, Lei Renu, Sakthidasan Lin, Hsin-Piao Jeng, Shiann-Shiun Department of International Graduate Program in Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan Department of Electrical Engineering National Dong Hwa University Taipei Taiwan

ISBN: (纸本)9781509048977

In recent years, Wi-Fi based indoor localization using received signal strength (RSS) gets considerable attention. However, RSS based Wi-Fi localization at 2.4GHz is highly susceptible and unstable. We proposed dynamic machine learning approach (DMLA) at 5GHz to effectively localize Wi-Fi users by means of feed-forward neural network algorithm. The simulation result shows that 90% of tested result has less than 0.4m estimation error, and no result shows greater than 0.47m location estimation errors. © 2017 IEEE.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Revamping robotics education to meet 21st century workforce needs- years 1-2 progress reports

Revamping robotics education to meet 21st century workforce ...

引用

2018 ASEE Conference for Industry and Education Collaboration, CIEC 2018

作者： Sergeyev, Aleksandr Alaraje, Nasser Kuhl, Scott Hooker, Joshua Druschke, Vincent Kinney, Mark Highum, Mark Electrical and Computer Engineering Program School of Technology Computer Science Department Michigan Technological University HoughtonMI49931 United States Bay de Noc Community College

The interdisciplinary nature of robots makes robotics a valuable STEM pedagogical tool. Robots are increasingly used across industry sectors to improve production throughputs while maintaining product quality. The benefits of robotics, however, depend on workers with up-to-date knowledge and skills to maintain and use existing robots, enhance future technologies, and educate users. It is critical that education institutions respond to the demand for robotics specialists by offering courses and professional certification in robotics and automation. This NSF sponsored project introduces a new approach for Industrial Robotics in electrical engineering technology (EET) programs at Michigan Tech and bay de Noc Community College. The curriculum and software developed by this collaboration of two- and four-year institutions match industry needs and provide a replicable model for programs around the US. The project also addresses the need for certified robotic training centers (CRTCs) and provides curriculum and training opportunities for students from other institutions, industry representatives, and displaced workers. In this article, authors report on Year 2 project progress, including the achievements in the developing "RobotRun" robotic simulation software, professional development opportunities for the faculty members from the other institutions, training workshops for K-12 teachers, and robotic one-day camps for high school students. Copyright © 2018, American Society for engineering Education.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

The United States - Brazil engineering exchange program: Lessons learned

The United States - Brazil engineering exchange program: Les...

引用

118th ASEE Annual Conference and Exposition

作者： Oliveira, Aurenice Menezes Lima Jr., Ivan T. Electrical Engineering Technology Program Michigan Technological University Houghton MI United States Department of Electrical and Computer Engineering North Dakota State University United States

Nowadays, engineering graduates are required to work in an increasingly globalized world, where most large engineering projects currently require multi-national teams of multidisciplinary professionals to work together and, therefore, a better understanding of the global economy, communication skills, cultural awareness, and interpersonal skills are critical to engineers. In this context, universities around the world are increasingly moving to establish international partnerships in their educational and research programs. One of the main purposes of international programs is to provide students value-added technical and cultural experiences. Study abroad programs are recognized as high-impact educational experiences. However, engineering students typically do not have the same variety of offerings of international program as students of other disciplines have, such as humanities or social science students. In this paper, the authors provide an overview of the critical aspects of developing a consortium among two universities in the U.S. and two Brazilian universities with the goal of establishing a self-sustainable student exchange program in undergraduate engineering education, and to increase the participation of U.S. students in international experiences. The activities in this program include the establishment of an agreement betweenthe institutions, the implementation of a course transfer process, and the development of aprocedure for foreign language training and cultural preparation. In addition, we also discuss thekey lessons learned over the first three years of the program. Our program is under the auspices of the U.S. department of Education's Fund for theImprovement of Postsecondary Education (FIPSE) on the U.S. side, and under the auspices ofthe Coordenação de Aperfeiçoamento de Pessoal de Nivel Superior (CAPES) of the BrazilianMinistry of Education, on the Brazilian side. © 2011 American Society for engineering Education.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

3D Facial Reconstruction Applied to Medical Cosmetology 5

3D Facial Reconstruction Applied to Medical Cosmetology

引用

5th IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2023

作者： Hsieh, Sheng-Hsien Lin, Ming-Yi Chen, Ching-Han National Pingtung University of Science and Technology Program of Artificial Intelligence and Mechatronics Pingtung Taiwan Yuan Ze University Department of Computer Science and Engineering Taoyuan Taiwan National Central University Department of Computer Science and Engineering Taoyuan Taiwan

ISBN: (纸本)9798350320978

We present a high-accuracy 3D facial reconstruction system with the following features: real-time 3D facial reconstruction using exposure synchronization multi-camera, feature alignment to quantify facial differences, a software system based on a naked eye 3D display, and medical records for a 3D face database. The proposed system is novel and practical, and the algorithm and the hardware/software architecture improve the current non-quantitative communication status in medical aesthetics. The system achieves preoperative expectations, real-time recording and feedback during surgery, and postoperative tracking analysis, thus making doctor-patient communication more efficient. The facial data database records personal and quantitative beauty data and its changes, providing accurate medical and aesthetic treatment analysis for individuals. In addition, the collected data of different genders, ages, injection sites, and dosages contribute to the development of more accurate medical materials. With artificial intelligence and cloud architecture, we provide reliable data for medical aesthetics customers, helping them understand their medical aesthetic needs. Doctors also provide stable medical care quality to consumers through cloud data, and medical aesthetic consultants do not need to exaggerate medical effects excessively. They can inform customers of specific differences before and after surgery through precise data and provide visual communication and customer expansion to improve consultation conversion rates. © 2023 IEEE.

关键词： Visual communication

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：