检索结果-内蒙古大学图书馆

A Tree-Guided CNN for Image Super-Resolution

IEEE Transactions on Consumer Electronics 2025年

作者： Tian, Chunwei Song, Mingjian Fan, Xiaopeng Zheng, Xiangtao Zhang, Bob Zhang, David Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Northwestern Polytechnical University School of Software Xi’an710129 China Fuzhou University College of Physics and Information Engineering Fuzhou350108 China University of Macau Pattern Analysis and Machine Intelligence Group Department of Computer and Information Science Macau999078 China School of Science and Engineering Guangdong Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Deep convolutional neural networks can extract more accurate structural information via deep architectures to obtain good performance in image super-resolution. However, it is not easy to find effect of important layers in a single network architecture to decrease performance of super-resolution. In this paper, we design a tree-guided CNN for image super-resolution (TSRNet). It uses a tree architecture to guide a deep network to enhance effect of key nodes to amplify the relation of hierarchical information for improving the ability of recovering images. To prevent insufficiency of the obtained structural information, cosine transform techniques in the TSRNet are used to extract cross-domain information to improve the performance of image super-resolution. Adaptive Nesterov momentum optimizer (Adan) is applied to optimize parameters to boost effectiveness of training a super-resolution model. Extended experiments can verify superiority of the proposed TSRNet for restoring high-quality images. © 1975-2011 IEEE.

关键词： Cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Detection of stress for visually impaired people using EEG signals based on time-frequency domain analysis 19

Detection of stress for visually impaired people using EEG s...

引用

19th International Conference on Machine Learning and Cybernetics, ICMLC 2020

作者： Sultana, Samia Rahman, Md Anisur Zavid Parvez, Mohammad BRAC University Software Engineering and HCI Research Group Department of Computer Science and Engineering Bangladesh Charles Sturt University School of Computing and Mathematics Australia

ISBN: (纸本)9780738124261

Stress refers to body's physical, emotional and psychological reaction to any environmental change needing adjustment with major impact on human psychology. Stress is specially difficult to manage for visually impaired people (VIP) as they can become easily stressed in unknown situations. Electroencephalogram (EEG) signals can be used to detect stress as it basically represents the ongoing electrical signal changes in human brain. Literature shows that the stress detection techniques are mostly based on either time or frequency domain analysis. However, using either time or frequency domain analysis may not be sufficient to provide appropriate outcome for stress detection. Hence, in this paper a method is proposed using empirical mode decomposition (EMD) and short-term Fourier transform (STFT) are used to extract features considering spatio-temporal information from EEG signals. In the EMD, the signal is first decomposed into intrinsic mode functions (IMFs) representing a finite number of signals while maintaining the time domain and STFT is used to convert time domain to time-frequency domain. Support vector machine (SVM) is applied to classify the stress of VIP in unfamiliar indoor environments. The performance of the proposed method is compared with a state-of-the-art technique for stress detection. The experimental results demonstrate the superiority of the proposed technique over the existing technique. © 2020 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

An advanced deep neural network for fundus image analysis and enhancing diabetic retinopathy detection

引用

Healthcare Analytics 2024年 5卷 100303-100303页

作者： Mehedi Shamrat, F M Javed Shakil, Rashiduzzaman Sharmin Hoque ovy, Nazmul Akter, Bonna Ahmed, Md Zunayed Ahmed, Kawsar Bui, Francis M. Moni, Mohammad Ali Department of Computer System and Technology University of Malaya Kuala Lumpur 50603 Malaysia Department of Computer Science and Engineering Daffodil International University Dhaka 1216 Bangladesh Department of Software Engineering Daffodil International University Dhaka 1216 Bangladesh Department of Computer Science and Engineering European University of Bangladesh Dhaka 1216 Bangladesh Department of Electrical and Computer Engineering University of Saskatchewan 57 Campus Drive Saskatoon S7N 5A9 SK Canada Group of Biophotomatiχ Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Santosh Tangail 1902 Bangladesh Health Informatics Research Lab Department of Computer Science and Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St Lucia 4072 QLD Australia

Diabetic retinopathy (DR) involves retina damage due to diabetes, often leading to blindness. It is diagnosed via color fundus injections, but the manual analysis is cumbersome and error-prone. While computer vision techniques can predict DR stages, they are computationally intensive and struggle with complex data extraction. In this research, our prime objective was to automate the process of DR classification into its various stages using convolutional neural network (CNN) models. We employed the performance of fifteen pre-trained models with our novel proposed diabetic retinopathy network (DRNet13) model. We aimed to discern the most efficient model for accurate diabetic retinopathy (DR) staging based on fundus images from five DR classes. We preprocessed the image using a median filter for noise reduction and Gamma correction for image enhancement. We expanded our dataset from 3662 to 7500 images to create a more generalized training model through various augmentation techniques. We also evaluated multiple evaluation metrics, including accuracy, precision, F1-score, Sensitivity, Specificity, Area under the curve (AUC), Mean Squared Error (MSE), False Positive Rate (FPR), False Negative Rate (FNR), in addition to confusion matrices for an in-depth comparison of the performance of these models. Feature maps were employed to illuminate decision making areas in the DRNet13 model, which achieved a 97 % accuracy rate for DR detection, surpassing other CNN architectures in speed and efficiency. Despite a few misclassifications, the model's capability to identify critical features demonstrates its potential as an impactful diagnostic tool for timely and accurate identification of diabetic retinopathy. © 2024 The Authors

关键词： Classification Convolutional neural network Diabetic retinopathy network Diagnostic analytics Feature map

来源：评论

学校读者我要写书评

暂无评论

3D Generative Models: A Survey

arXiv

引用

arXiv 2022年

作者： Shi, Zifan Peng, Sida Xu, Yinghao Geiger, Andreas Liao, Yiyi Shen, Yujun Department of Computer Science and Engineering the Hong Kong University of Science and Technology Hong Kong School of Software Technology Zhejiang University China Department of Information Engineering the Chinese University of Hong Kong Hong Kong Autonomous Vision Group University of Tubingen Tubingen AI Center Germany College of Information Science & Electronic Engineering Zhejiang University China Ant Group China

Generative models aim to learn the distribution of observed data by generating new instances. With the advent of neural networks, deep generative models, including variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models (DMs), have progressed remarkably in synthesizing 2D images. Recently, researchers started to shift focus from 2D to 3D space, considering that 3D data is more closely aligned with our physical world and holds immense practical potential. However, unlike 2D images, which possess an inherent and efficient representation (i.e., a pixel grid), representing 3D data poses significantly greater challenges. Ideally, a robust 3D representation should be capable of accurately modeling complex shapes and appearances while being highly efficient in handling high-resolution data with high processing speeds and low memory requirements. Regrettably, existing 3D representations, such as point clouds, meshes, and neural fields, often fail to satisfy all of these requirements simultaneously. In this survey, we thoroughly review the ongoing developments of 3D generative models, including methods that employ 2D and 3D supervision. Our analysis centers on generative models, with a particular focus on the representations utilized in this context. We believe our survey will help the community to track the field’s evolution and to spark innovative ideas to propel progress towards solving this challenging task. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Mechanical Vibrations on a Deployable Nanosatellite Antenna: SAR Performance Analysis

Mechanical Vibrations on a Deployable Nanosatellite Antenna:...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Andrew C. M. Austin Timothy Pelham Simone Mencarelli Annalisa Tresoldi Mohammed Dabboor Guglielmo Aglietti Michael J. Neve Communication Systems and Networks Group University of Bristol Bristol UK Department of Electrical Computer and Software Engineering University of Auckland Auckland New Zealand Te Pūnaha Ātea—Auckland Space Institute University of Auckland Auckland New Zealand Science and Technology Branch Environment and Climate Change Canada Dorval QC Canada

The mechanical vibrations of a high-strain glass-fibre composite deployable X-band synthetic aperture radar (SAR) antenna structure are investigated using a finite element method. The antenna is approximately $\mathrm{2}\ \mathrm{m}\times \mathrm{0}.\mathrm{3}\ \mathrm{m}$ , and exhibits natural frequencies at 2.8 Hz and 7.6 Hz. The radiation patterns for a reflectarray formed from the structure are calculated using a ray-tracing approach for the nominal and mechanically deformed cases. The mechanically deformed antenna pattern is defocused, and a SAR system model shows this reduces the signal-to-noise ratio of a point scattering target by approximately 6 dB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Active EV Battery Cell Voltage Balancing Systems: Current Issues and Prospective Solutions

A Comprehensive Review of Active EV Battery Cell Voltage Bal...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Chandan Chetri Alvin Huynh Sheldon S. Williamson Department of Electrical Computer and Software Engineering Smart Transportation Electrification and Energy Research (STEER) Group Advanced Storage Systems and Electric Transportation (ASSET) Laboratory Faculty of Engineering and Applied Science Ontario Tech University Oshawa Canada

The performance of a battery pack is greatly affected by an imbalance between the cells. Cell balancing is a very important criterion for Battery Management System (BMS) to operate properly. This paper presents the various cell balancing topologies which have been presented by various researchers in the past years. A novel topology has also been discussed, which improves the overall efficiency of the components being used. Various comparison parameters such as Control, Speed, Efficiency, Power Effects, Manufacturability, Size, and Cost have been considered.

关键词： Industrial electronics Electric potential Costs Equalizers Battery management systems Transformers Power electronics

来源：评论

学校读者我要写书评

暂无评论

Power Management of Supercapacitors using Auxiliary Bank Switching for Hybrid Energy Storage Systems 12

Power Management of Supercapacitors using Auxiliary Bank Swi...

引用

12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020

作者： Dasari, Yashwanth Ronanki, Deepak Williamson, Sheldon S. Group Faculty of Engineering and Applied Science Department of Electrical Computer and Software Engineering OshawaONL1G 0C5 Canada

ISBN: (纸本)9781728158266

The hybridization of battery and supercapacitors (SCs) forms a highly effective energy storage system (ESS) for the electrified transportation that offers both energy and power at the same time as per the load requirements. However, the SC bank in hybrid ESS (HESS) deficits in delivering power for a longer duration to serve a higher number of transients. To reduce the burden on batteries and the overall system cost, a new auxiliary bank switching strategy for SCs with enhanced power delivery duration is introduced in this paper. A simple power management control is proposed to effectively switch the SCs from parallel to series combinations while serving the dynamic load demands. The key performance of the proposed circuit is holistically evaluated using PLECS simulations and a scaled-down laboratory prototype in terms of maximum power delivery time and SC cell energy utilization. The impact on passive components of the bi-directional converter with proposed architecture in terms of current stress is analyzed in detail. Finally, the suitability of the proposed architecture in HESS for an electric vehicle (EV) is verified on an OPAL-RT real-time simulator under a standard new European driving cycle. © 2020 IEEE.

关键词： Power management

来源：评论

学校读者我要写书评

暂无评论

Keywords-driven web APIs group recommendation for automatic app service creation process

Keywords-driven web APIs group recommendation for automatic ...

引用

作者： Gong, Wenwen Lv, Chao Duan, Yucong Liu, Zengguang Khosravi, Mohammad R. Qi, Lianyong Dou, Wanchun College of Information and Electrical Engineering China Agricultural University Beijing China China Telecom Smart Home Competence Center Nanjing China E-Surfing Smart Home Technology Co. Ltd Nanjing China School of Computer Science and Cyberspace Security Hainan University Haikou China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Department of Computer Engineering Persian Gulf University Bushehr Iran Telecommunications Group Department of Electrical and Electronic Engineering Shiraz University of Technology Shiraz Iran School of Information Science and Engineering Qufu Normal University Rizhao China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

With the ever-increasing popularity of web application programming interfaces (APIs) sharing communities, it is becoming a promising way for software developers to design and create their interesting Apps through composing a set of selected web APIs that can collectively fulfill the App functions expected by the App developer. However, the App developer's web APIs selection decision-makings are often nontrivial due to the massive candidate APIs as well as their diverse functions. Furthermore, it is difficult to guarantee that the selected web APIs are compatible enough. Moreover, traditional web APIs recommendation approaches only return a recommended APIs list, which are often not sufficient to accommodate the App developer's undetermined and fuzzy personalized preferences. Considering the above challenges, a novel keywords-driven web APIs recommendation approach called keywords-driven and compatibility-aware multiple API group recommendation is proposed in this article for green and compatible software, which cannot only satisfy the App developer's functional requirements, but also return a group of web APIs recommended lists. Each returned list includes a set of compatible web APIs. Finally, we design a series of experiments based on a real-world web APIs dataset, that is, PW dataset crawled from ***. experimental reports compared with other competitive approaches in existing literatures indicate the effectiveness and efficiency of our proposal in this work. © 2020 John Wiley & Sons Ltd

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Investigating the effects of gamifying SQL-Tutor 28

Investigating the effects of gamifying SQL-Tutor

引用

28th International Conference on computers in Education, ICCE 2020

作者： Tahir, Faiza Mitrovic, Antonija Sotardi, Valerie Intelligent Computer Tutoring Group Department of Computer Science and Software Engineering University of Canterbury New Zealand School of Educational Studies and Leadership University of Canterbury New Zealand

ISBN: (纸本)9789869721455

The practice of adding game elements to non-gaming educational environments has gained much popularity. Gamification has been found in some studies to increase learner engagement, motivation, and academic performance. However, there is a lack of empirical evidence to prove the effects of gamification in advanced learning technologies like Intelligent Tutoring Systems (ITS). This paper reports the results of an empirical study that included three categories of game elements (goals, assessment and challenges) implemented as badges in the context of SQL-Tutor. The study was conducted in a class under realistic conditions. SQL-Tutor was used voluntarily by 77 undergraduate students enrolled in a second-year database course. Although there were no differences between the experimental and control groups in terms of their interaction with SQL-Tutor and learning outcomes, we found a significant mediating effect of time-on-task on the direct relation between badges and achievement in the gamified condition. We also found evidence that not all students were interested in badges. © ICCE 2020 - 28th International Conference on computers in Education, Proceedings. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Soft, Multi-Layer, Kirigami Inspired Robotic Gripper with a Compact, Compression-Based Actuation System

A Soft, Multi-Layer, Kirigami Inspired Robotic Gripper with ...

引用

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

作者： Joao Buzzatto Junbang Liang Mojtaba Shahmohammadi Saori Matsunaga Rintaro Haraguchi Toshisada Mariyama Bruce A. MacDonald Minas Liarokapis Department of Mechanical and Mechatronics Engineering New Dexterity research group University of Auckland New Zealand Information Technology R&D Center Mitsubishi Electric Corporation Japan Advanced Technology R&D Center Mitsubishi Electric Corporation Japan Department of Electrical Computer and Software Engineering Centre for Automation and Robotic Engineering Science University of Auckland New Zealand

Over the last decade, a plethora of soft robotic devices have been proposed for the execution of complex grasping and dexterous manipulation tasks. Tasks requiring such increased dexterity are typically executed using fully-actuated, rigid end-effectors equipped with sophisticated sensing and controlled with complex control laws. The new class of soft robotic devices offers an alternative to the traditional end-effectors and facilitates the development of robotic grasping and manipulation solutions that are lightweight, safe to interact with, affordable, and easy to use and control. Within the class of soft robotic grippers and hands, promising recent developments were made in ultra-affordable, even disposable mechanisms based on origami and kirigami structures. This paper proposes a new kirigami-inspired robotic gripper geometry employing compression-based actuation. The compression actuation fundamentally differentiates this new design class from previous kirigami grippers, resulting in more compact robotic grippers with superior grasping capabilities. In particular, we investigate how the shapes of the internal cuts of the kirigami geometries can affect the gripper performance in terms of force exertion and grasping capabilities. A series of experiments are conducted to understand better the working principles behind this new type of kirigami grippers and experimentally validate their efficacy in the execution of complex, everyday life tasks. Further demonstrations of the gripper's capabilities include the pick-and-placing of human hair, egg yolk, and even liquids.

关键词：

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：