检索结果-内蒙古大学图书馆

2022 International Conference on Electrical and Computing Technologies and Applications, ICECTA 2022

作者： Zou, Zhao Mubin, Omar Alnajjar, Fady Al Mahmud, Abdullah Khan, Aila Lwin, Michael Western Sydney University School of Computer Data Mathematical Sciences Sydney Australia United Arab Emirates University Artificial Intelligence and Robotics Computer Science and Software Engineering Al Ain United Arab Emirates Swineburne University of Technology School of Design Melbourne Australia Western Sydney University School of Business Sydney Australia

ISBN: (数字)9781665456005

ISBN: (纸本)9781665456005

Older people's healthcare is becoming a prevalent social topic in recent year since the post-war boom babies are entering their retirement ages. The size of the aged population suffering from cognitive decline is increasing since mild cognitive impairment issues are common aging problems. Therefore, the demand for an effective method of reducing the progress of cognitive decline is rising. This paper is a research design including the reasons for conducting this proposed research, the research approaches design and the hypothesis. Generally, the proposed study aims at creating a conceptual framework for implementing interactive robot-assisted cognitive rehabilitation training. The study will focus on the auditory modalities (voice pitch and speech style) of the humanoid robots. The research result is expected to provide an empirical reference for cognitive rehabilitation for older adults using humanoid robots. © 2022 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-GRU model for Session-based Recommender Systems

A Hybrid CNN-GRU model for Session-based Recommender Systems

引用

International Conference on computer and Communications (ICCC)

作者： Abebe Tamrat Tegene Qiao Liu Yanglei Gan Elias Jimale Melak Ayenew Habte Leka School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Center of Excellence of AI and Robotics Addis Ababa Science and Technology University Addis Ababa Ethiopia School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

In many e-commerce recommendation systems, user profiles are mostly not available. In such cases, the recommendation task considers user behaviors like click sessions or browsing history. Traditional recommender methods often rely on users’ past interactions for recommending user interests, which is difficult to apply to session-based recommender systems. However, these methods perform very poorly on this task. Recently, deep learning techniques such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs) showed outstanding performance in session-based recommendation problems. In this paper, we propose a hybrid CNN and gated recurrent unit (GRU) model that exploits the advantages of both CNN and GRU in modeling the rigid order requirement for interactions inside sessions and modeling the sequential long-term dependencies in session data, respectively. Our proposed hybrid model has two architectures: the first part consists of the CNN layers that take input from Item ID to learn local features and relationships in sessions, and the second part is a GRU layer that takes the output from the CNN layer to learn the long-term dependencies in that session. This hybrid technique enables the architecture for modeling prominent features in the session to provide accurate recommendations. Extensive experiments over a real-world dataset demonstrate that the proposed hybrid model performs well and outperforms those GRU and CNN-based models in the state-of-the-art recommendation task on both metrics used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Coordinated Scheduling of Electric Vehicles and Battery Energy Storage Systems

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Shang, Xiao-Ju Mishra, Yateendra Yang, Yin Liu, Jin-Long Yu, Zu-Guo Tian, Yu-Chu School of Mathematics and Computational Science Xiangtan University Hunan411105 China National Center for Applied Mathematics in Hunan Xiangtan University Hunan411105 China School of Electrical Engineering and Robotics Queensland University of Technology GPO Box 2434 BrisbaneQLD4001 Australia School of Computer Science Queensland University of Technology GPO Box 2434 BrisbaneQLD4001 Australia

Electric vehicles (EVs) and battery energy storage systems (BESS) are rapidly gaining adoption worldwide as emerging consumer electronics products, playing an important role in the transition to sustainable energy. While their integration into power grids offers significant benefits when managed appropriately, it also introduces challenges related to grid stability and efficiency, such as increased peak demand and voltage fluctuations. Effective management of these challenges demands coordinated scheduling of EVs and BESS for both charging from the grid and discharging back into it. Various optimization approaches, including mixed-integer nonlinear programming (MINLP), have been proposed to tackle this problem. However, these approaches often involve numerous binary decision variables, which result in increased computational complexity or even make the computation practically infeasible in large-scale scenarios. To address this issue, this paper formulates the coordinated scheduling of EVs and BESS as a nonconvex constrained optimization problem with significantly fewer decision variables. A Modified Jacobi Proximal Alternating Direction Method of Multipliers (M-ProxJADMM) is proposed to efficiently solve the problem, with guaranteed convergence. Case studies are conducted to validate the effectiveness of the M-ProxJADMM algorithm in optimizing the coordinated scheduling of EVs and BESS. © 1975-2011 IEEE.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Detecting and Predicting Knee Osteoarthritis Severity

Deep Learning Approaches for Detecting and Predicting Knee O...

引用

Recent Advances in Information technology for Sustainable Development (ICRAIS), International Conference on

作者： Shilpa Karegoudra Veeresha R K Vamsidhar Yendapalli Department of Computer Science and Engineering NMAM Institute of Technology (NMAMIT) Nitte (Deemed to be University) Udupi India Department of Robotics and Artificial Intelligence NMAM Institute of Technology (NMAMIT) Nitte (Deemed to be University) Udupi India Department of Computer Science and Engineering GITAM School of Technology Bengaluru GITAM University Karnataka India

ISBN: (数字)9798350354461

ISBN: (纸本)9798350354522

Knee osteoarthritis stands as one of the most prevalent musculoskeletal ailments globally. Its initial signs include joint stiffness, discomfort, and limitations in functionality, marking it as a significant joint disorder. Older adults are more likely to have arthritis, and it normally gets worse with age. If there are no early, effective therapies used, it can lead to impairment in older people. Therapy must be started as soon as possible; otherwise, a full knee replacement may be necessary. The very subjective nature of the standard procedures creates a barrier to early illness progression detection. This study involves in-depth exploration and examination of the application of deep learning techniques for knee osteoarthritis detection and severity prediction. In this work EfficientNet-B6 was chosen for its superior performance in balancing accuracy, speed, and resource efficiency. Unlike models such as MobileNet or ResNet, X-ray images are used to train the model to predict the severity of knee osteoarthritis. The model classifies the data with an accuracy of 87%. A website for OA prediction is developed, the user needs to drag and drop an X-ray image in the dialog box given. The predicted output along with the severity will be shown within a few seconds. This website is very easy to use.

关键词： Deep learning Accuracy Medical treatment Predictive models Planning Osteoarthritis Sustainable development Older adults X-ray imaging Standards

来源：评论

学校读者我要写书评

暂无评论

N Observation Photon Counting Imaging With Preprocessing

N Observation Photon Counting Imaging With Preprocessing

引用

International Joint Conference on computer science and Software Engineering (JCSSE)

作者： Gilsu Yeo Hyun-Woo Kim Myungjin Cho Min-Chul Lee Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka City Fukuoka School of ICT Robotics and Mechanical Engineering IITC Hankyoung National University Anseong Kyonggi-do Republic of Korea

ISBN: (数字)9798350381764

ISBN: (纸本)9798350381771

In this paper, we explain our method to enhance the conventional integral imaging method. The photon-counting imaging is used to obtain the image including objects or scene under photon-lacked environments. And the conventional $N$ observation photon counting imaging obtains three-dimensional (3D) image by repeating the estimation to obtain more accurate information of object or scene than conventional photon-counting imaging under almost photon-lacked environments. To enhance the visual quality and information of 3D objects in the conventional $\mathrm{N}$ observation photon counting imaging, the volumetric computational reconstruction (VCR) is utilized as preprocessing and combined $N$ observation photon counting integral imaging in this paper.

关键词： Measurement Visualization Three-dimensional displays Accuracy Imaging Lakes Video recording

来源：评论

学校读者我要写书评

暂无评论

DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation

arXiv

引用

arXiv 2024年

作者： Xu, Guoping Wu, Xiaming Liao, Wentao Wu, Xinglong Huang, Qing Li, Chang Hubei Key Laboratory of Intelligent Robotics School of Computer Science and Engineering Wuhan Institute of Technology Hubei Wuhan430205 China Department of Biomedical Engineering Hefei University of Technology Anhui Hefei230009 China

Objective: Accurately segmenting lesions in ultrasound images remains a challenging task due to the inherent ambiguity in distinguishing boundaries between lesions and adjacent tissues. Although deep learning has made significant progress in accurate ultrasound image segmentation, there is still a lack of attention to the quality of boundary segmentation and its relationship with the body. As a result, the current accuracy of ultrasound image segmentation still has room for improvement in enhancing the precision of lesion delineation. We aim to improve the overall segmentation accuracy and the quality of boundary segmentation by exploring the relationship between the body and the boundary in ultrasound images. Methods: We introduce a dual-branch structure based on a deep neural network that allows the model to learn the relationship between the body and boundary parts under supervision, leading to an improvement in overall segmentation accuracy and boundary segmentation quality. Additionally, we propose a novel feature fusion module aimed at facilitating the integration and interaction of body and boundary information. Based on the dual-branch structure and feature fusion strategy, we have designed UBBS-Net for ultrasound image segmentation. Results: The proposed approach is evaluated on three challenging public ultrasound image datasets. Our experimental results demonstrate the superiority of the proposed method compared to existing state-of-the-art methods. Specifically, we achieve a Dice Similarity Coefficient of 81.05±10.44% for breast cancer segmentation, 76.41±5.52% for brachial plexus nerves segmentation, and 87.75±4.18% for infantile hemangioma segmentation on BUSI, UNS and UHES datasets, respectively. Conclusions: We propose UBBS-Net, a novel network for ultrasound image segmentation that combines body and boundary information with a proposed feature fusion module. Our method outperforms existing approaches on three challenging public datasets, demonstratin

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

A Quality Diversity Study in EvoDevo Processes for Engineering Design

A Quality Diversity Study in EvoDevo Processes for Engineeri...

引用

Congress on Evolutionary Computation

作者： Edgar Buchanan Simon Hickinbotham Rahul Dubey Imelda Friel Andrew Colligan Mark Price Andy M. Tyrrell Intelligent Systems & Robotics Research Group School of Physics Engineering and Technology University of York UK Computer Science Missouri State University USA School of Mechanical & Aerospace Engineering Queen's University Belfast

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

For a long time engineering design has relied on human engineers manually crafting and refining designs using their expertise and experience. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are employed to investigate a broader design space that may go beyond what human engineers have considered. Previous literature has demonstrated the use of quality and diversity (QD) algorithms in evolutionary approaches to drive the process to better quality solutions. This paper provides a study to understand the effects of using QD algorithms in EvoDevo processes for engineering design. This paper also analyses the impact of using different behavioural characterisations (BC) in the performance of the quality of the solutions found. The results demonstrate that quality and diversity algorithms can find better solutions than other EAs for engineering design problems. It was also found that the characterisation of the BC is important to get the best results.

关键词： Measurement Dimensionality reduction Refining Evolutionary computation Calibration

来源：评论

学校读者我要写书评

暂无评论

PU-SDF: Arbitrary-Scale Uniformly Upsampling Point Clouds via Signed Distance Functions

PU-SDF: Arbitrary-Scale Uniformly Upsampling Point Clouds vi...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Shaohui Pan Yong Xu Ruotao Xu School of Computer Science and Engineering South China University of Technology Guangzhou China Peng Cheng Laboratory ShenZhen China Communication and Computer Network Laboratory of Guangdong Guangzhou China Institute of Super Robotics South China University of Technology Guangzhou China

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Point cloud upsampling is a crucial technique for improving the performance of 3D data understanding, enabling the creation of dense and uniform point clouds from raw and sparse input data. However, most existing methods exhibit limitations in dealing with different scaling factors, either requiring multiple networks or producing unevenly distributed points. To tackle this issue, this paper proposes a deep learning method called PU-SDF, which consists of a local-feature-based signed distance function network (LSDF-network) and a 3D-grid query points generation module (GPGM). The proposed LSDF-network can perform point cloud upsampling at arbitrary rates and can be easily adapted to handle unseen datasets. Additionally, we propose the GPGM that generates uniform and unlimited query points in sparse voxel space with arbitrary resolution. Extensive qualitative and quantitative evaluations demonstrate the superior performance of the PU-SDF method, achieving state-of-the-art point cloud upsampling performance.

关键词： Point cloud compression Training Deep learning Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

DeepExtract: Neural Networks Based Image Keypoints Extraction for Indirect SLAM Algorithms

DeepExtract: Neural Networks Based Image Keypoints Extractio...

引用

IEEE International Conference on Artificial Intelligence in Engineering and technology (IICAIET)

作者： Maurya Gurram Prakash Kumar Uttam Shantipal S. Ohol School of Computer Science and Engineering Vellore Institute of Technology Amaravathi Andhra Pradesh Robotics and Artificial Intelligence RnDE (Engrs) DRDO Pune Maharashtra School of Mechanical Engineering COEP Technological University Pune Maharashtra

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Indirect SLAM (Simultaneous Localization and Mapping) algorithms primarily rely upon image features to estimate poses and to perform loop closure. Traditional image key point extraction algorithms fail to detect features in the image in some cases due to various reasons like low exposure, lack of contours and hardware constraints. To tackle this issue, we propose a U-Net neural network based image keypoint extraction algorithm that works on low cost camera hardware. We utilize an unconventional approach by applying image segmentation techniques to extract Shi- Tomashi features for training the neural network. It is an attempt to building innovative approaches for Deep learning-based visual odometry problem. The primary focus of this work is to establish a new research direction for deep learning based keypoint extraction tailored for real-time SLAM on low-cost and low-power devices. We aim to lay the foundations for further investigation into segmentation-based key-point modeling and its impact on critical SLAM components like feature tracking, mapping, and loop closure detection.

关键词： Training Image segmentation Tracking loops Solid modeling Electric potential Simultaneous localization and mapping Neural networks Feature extraction Cameras Hardware

来源：评论

学校读者我要写书评

暂无评论

Active Generalized Category Discovery

Active Generalized Category Discovery

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Shijie Ma Fei Zhu Zhun Zhong Xu-Yao Zhang Cheng-Lin Liu MAIS Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS China School of Computer Science and Information Engineering Hefei University of Technology China School of Computer Science University of Nottingham Nottingham UK

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes. Given that knowledge learned from old classes is not fully transferable to new classes, and that novel categories are fully unlabeled, GCD inherently faces intractable problems, including imbalanced classification performance and inconsistent confidence between old and new classes, especially in the low-labeling regime. Hence, some annotations of new classes are deemed necessary. However, labeling new classes is extremely costly. To address this issue, we take the spirit of active learning and propose a new setting called Active Generalized Category Discovery (AGCD). The goal is to improve the performance of GCD by actively selecting a limited amount of valuable samples for labeling from the oracle. To solve this problem, we devise an adaptive sampling strategy, which jointly considers novelty, informativeness and diversity to adaptively select novel samples with proper uncertainty. However, owing to the varied orderings of label indices caused by the clustering of novel classes, the queried labels are not directly applicable to subsequent training. To overcome this issue, we further propose a stable label mapping algorithm that transforms ground truth labels to the label space of the classifier, thereby ensuring consistent training across different active selection stages. Our method achieves state-of-the-art performance on both generic and fine-grained datasets. Our code is available at https://***/mashijie1028/ActiveGCD

关键词： Training computer vision Uncertainty Computational modeling Clustering algorithms Transforms Pattern recognition

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：