检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Ray, Amartya Gayen, Soumyajit Kaplun, Dmitrii Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9783031781032

Skin cancer poses a serious global health challenge, where timely and precise diagnosis is essential to improve patient outcomes. Recently, neural networks have proven to be highly effective tools for automated skin cancer classification, significantly advancing the field of dermatology. This paper introduces a novel approach to generate edge maps from dermoscopic images using a holistically nested edge detector model. These edge maps enhance the detection of shape and symmetry irregularities, which are key indicators of malignancy, and improve the focus on relevant regions of interest. We then propose an edge-guided dual-branch neural network, called EDB-Net, for the classification task. Branch 1 handles edge maps, while Branch 2 processes original dermoscopic images. To highlight significant regions and focus on specific lesion areas, we incorporate a novel channel-spatial synergistic attention block within Branch 2. Additionally, we introduce a unique strategy to modulate the generated attention maps using edge features extracted from the edge maps in Branch 1, creating edge-guided features that refine the overall feature representation. In the final stage, both edge-guided and attention-aided features are combined, producing more distinct and contextually relevant outputs, thereby significantly enhancing classification performance. Our model achieves accuracies of 0.927 and 0.848 on the challenging HAM10000 and ISIC 2016 datasets, respectively, without employing any data augmentation. The source code of the proposed model is available at: https://***/Cmatermedicalimageanalysis/EDB_Net. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Virtual Synchronous Generator Droop control for Renewable Energy Sources

Virtual Synchronous Generator Droop Control for Renewable En...

引用

2024 IEEE Global Energy Conference, GEC 2024

作者： Cakmak, Fevzi Aykat, Sukru Kazanbaş, Mehmet Cemil Akgul, Sabahattin Department of Electricity and Energy Mardin Atuklu University Mardin Turkey Department of Computer Engineering Mardin Atuklu University Mardin Turkey Department of Control and Automation Engineering Yildiz Technical University Istanbul Turkey Department of Handicrafts Mardin Atuklu University Mardin Turkey

ISBN: (纸本)9798331532611

The connection of large-scale RES (renewable energy source) to the grid and the increase in the efficiency of energy production also causes different power quality problems. It has become mandatory for these inverter-based systems to participate in load frequency control. For this purpose, the design and simulation of a virtual synchronous generator (VSG), which enables RES to operate like synchronous generators, has been carried out in Matlab/Simulink environment. It is observed that the VSG keeps the load frequency stable according to different load conditions. ©2024 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

The supplemental definition of dynamic behavior of partially observable object for phasily limited control task 11

The supplemental definition of dynamic behavior of partially...

引用

11th IEEE International Conference on Intelligent Systems, IS 2022

作者： Ivashchuk, Viacheslav National University of Food Technologies Dacitcs Department of Automation and Computer-Integrated Technologies of Control Systems Kyiv Ukraine

ISBN: (纸本)9781665456562

each dynamically active object, regardless of its own nature, has limited energy, which limits its ability to change state coordinates. The research has scientific importance for non-stationary objects, which do not allow to estimate the state coordinates directly by measuring system, and the prediction of behavior of these coordinates is complicated by interparametric relationships in the object. The solution is possible by combining the dynamic game on minmax estimates and by the next descending by quadratic criterion, which does not disturb the limitations, which are adequate to real capabilities of the object. The rough of control system are explained by providing only the necessary descending conditions as a formal approximation of a confidence space terms of a complex of space sets, which give the lower and the upper approximation of the original behavior of space of object's variables. © 2022 IEEE.

关键词： minmax phasily limited Riccati Savage risk

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 231-239页

作者： Yahui Liu Bin Tian Yisheng Lv Lingxi Li Fei-Yue Wang the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190 IEEE the Transportation and Autonomous Systems Institute(TASI)and the Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University Indianapolis(IUPUI)Indianapolis 46202 USA

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://***/yahuiliu99/PointC onT.

关键词： Content-based Transformer deep learning feature aggregator local attention point cloud classification

来源：评论

学校读者我要写书评

暂无评论

Cubature Kalman Fusion Filtering Under Amplify-and-Forward Relays With Randomly Varying Channel Parameters

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 356-368页

作者： Jiaxing Li Zidong Wang Jun Hu Hongli Dong Hongjian Liu the Department of Applied Mathematics Harbin University of Science and Technology IEEE the Department of Computer Science Brunel University London the School of Automation Harbin University of Science and Technology the Artificial Intelligence Energy Research Institute Northeast Petroleum University the Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum University the National Key Laboratory of Continental Shale Oil of China Northeast Petroleum University the Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment Ministry of Education Anhui Polytechnic University the School of Mathematics and Physics Anhui Polytechnic University

In this paper, the problem of cubature Kalman fusion filtering(CKFF) is addressed for multi-sensor systems under amplify-and-forward(AaF) relays. For the purpose of facilitating data transmission, AaF relays are utilized to regulate signal communication between sensors and filters. Here, the randomly varying channel parameters are represented by a set of stochastic variables whose occurring probabilities are permitted to exhibit bounded uncertainty. Employing the spherical-radial cubature principle, a local filter under AaF relays is initially constructed. This construction ensures and minimizes an upper bound of the filtering error covariance by designing an appropriate filter gain. Subsequently, the local filters are fused through the application of the covariance intersection fusion rule. Furthermore, the uniform boundedness of the filtering error covariance's upper bound is investigated through establishing certain sufficient conditions. The effectiveness of the proposed CKFF scheme is ultimately validated via a simulation experiment concentrating on a three-phase induction machine.

关键词： Amplify-and-forward (AaF) relays covariance intersection fusion cubature Kalman filtering multi-sensor systems uniform boundedness

来源：评论

学校读者我要写书评

暂无评论

BFuse-Net: Bonferroni Mean Operator-Aided Fusion of Neural Networks for Medical Image Classification 5th

BFuse-Net: Bonferroni Mean Operator-Aided Fusion of Neural ...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Ghosh, Triyas Chakraborty, Soham Kaplun, Dmitrii Gulvanskii, Vyacheslav Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata700032 India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9789819638628

In this paper, we have proposed a novel model, called Bonferroni Mean Operator-aided Fusion of Neural Networks (BFuse-Net). Here, we have taken advantage of the capabilities of four deep learning models as the base learners and then applied a customized attention method to prioritize different fine-grained features by passing their outputs via four parallel pipelines. Next, we have employed a novel aggregation method, a modified Bonferroni Mean operator, to merge the decision scores acquired from every pipeline, prioritizing their individual contributions above their interactions with others in the decision scores. Three medical image datasets— LC25000 (colon cancer), Oral Squamous Cell Carcinoma, and Malaria Cell Images have been used for experimentation. The model yields state-of-the-art outcomes for the three datasets. The source codes and additional results can be found at GitHub repository. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

On non-von Neumann flexible neuromorphic vision sensors

引用

npj Flexible Electronics 2024年第1期8卷 638-663页

作者： Hao Wang Bin Sun Shuzhi Sam Ge Jie Su Ming Liang Jin Institute for Future Shandong Key Laboratory of Industrial Control TechnologySchool of AutomationQingdao UniversityQingdao 266071China College of Electronic and Information Engineering Qingdao UniversityQingdao 266071China Department of Electrical and Computer Engineering and Institute for Functional Intelligent MaterialsNational University of SingaporeSingapore 117583Singapore

The structure andmechanismof thehuman visual system contain rich treasures,and surprising effects can be achieved by simulating the human visual *** this article,starting from the human visual system,we compare and discuss the discrepancies between the human visual system and traditional machine vision *** the wide variety and large volume of visual information,the use of nonvon Neumann structured,flexible neuromorphic vision sensors can effectively compensate for the limitations of traditional machine vision systems based on the von Neumann ***,this article addresses the emulation of retinal functionality and provides an overview of the principles and circuit implementation methods of non-von Neumann computing ***,in terms of mimicking the retinal surface structure,this article introduces the fabrication approach for flexible sensor ***,this article analyzes the challenges currently faced by non-von Neumann flexible neuromorphic vision sensors and offers a perspective on their future development.

关键词： Neumann system starting

来源：评论

学校读者我要写书评

暂无评论

Pervasive Indoor User Identification Leveraging Mobile Single Station Localization

引用

IEEE Internet of Things Journal 2025年第11期12卷 15224-15237页

作者： Nie, Wendi Liu, Zexing Wang, Xiaoyang Duan, Yaoxin Lam, Kam-Yiu Liu, Kai Ng, Joseph K. Y. Xue, Chun Jason Gui, Guan Ministry of Education Key Laboratory of Industrial Internet of Things and Networked Control China Chongqing University of Posts and Telecommunications School of Automation/School of Industrial Internet Chongqing40065 China Institute of Industrial Internet Chongqing401120 China City University of Hong Kong Computer Science Department Hong Kong Chongqing University College of Computer Science Chongqing400030 China Hong Kong Baptist University Computer Science Department Hong Kong Mohamed Bin Zayed University of Artificial Intelligence Department of Computer Science Abu Dhabi United Arab Emirates Nanjing University of Posts and Telecommunications College of Telecommunications and Information Engineering Nanjing210003 China

The utilization of Wi-Fi-based technology for pervasive indoor user identification has gained prominence due to its cost-effective nature and compatibility with user devices. Previous works proposed capturing the media access control (MAC) address emitted from a user's device and using Information Elements (IE)-based MAC de-randomization methods to mitigate the impairment caused by random MAC. However, IE types of different Wi-Fi devices are not consistently differentiated, leading to identification errors in IE-based methods. Additionally, typical Wi-Fi fingerprinting approaches require densely pre-deployed Wi-Fi stations, contradicting the principle of pervasive localization. To address these challenges, we propose the mobile single station-based user identification (***) technique, which leverages Wi-Fi mobile single stations for pervasive indoor user identification. *** includes mobile single station localization (MSL) and MAC de-randomization based on users' spatio-temporal location and IE information (***). MSL can be implemented on a standard mobile Wi-Fi station without extensive pre-deployment. *** performs MAC de-randomization using the LIC algorithm to identify users with random MAC addresses. Experimental results demonstrate that *** outperforms previous IE-based user identification methods and multi-station localization techniques. MSL achieves a localization error of 1.15 meters which is better than multi-station with 12 APs of 1.40 meters. *** demonstrates an identification accuracy of 95.24% which is better than AIMAC of 85.48%. © 2014 IEEE.

关键词： Medium access control

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition Using a Multi-modal Deep Neural Network 13th

Hand Gesture Recognition Using a Multi-modal Deep Neural Net...

引用

13th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2024

作者： Fulsunder, Saneet Umar, Saidu Taherkhani, Aboozar Liu, Chang Yang, Shengxiang School of Computer Science and Informatics De Montfort University Leicester United Kingdom Key Laboratory of Networked Control Systems and Digital Factory Department Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China

ISBN: (纸本)9783031579189

As devices around us get more intelligent, new ways of interacting with them are sought to improve user convenience and comfort. While gesture-controlled systems have existed for some time, they either use additional specialized imaging equipment, require unreasonable computing resources, or are simply not accurate enough to be a viable alternative. In this work, a reliable method of recognizing gestures is proposed. The built model correctly classifies hand gestures for keyboard typing based on the activity captured by an ordinary camera. Two models are initially developed for classifying video data and classifying time-series sequences of the skeleton data extracted from a video. The models use different strategies of classification and are built using lightweight architectures. The two models are the baseline models which are integrated to form a single multi-modal model with multiple inputs, i.e., video and time-series inputs, to improve accuracy. The performances of the baseline models are then compared to the multimodal classifier. Since the multimodal classifier is based on the initial models, it naturally inherits the benefits of both baseline architectures and provides a higher testing accuracy of 100% compared to the accuracy of 85% and 75% for the baseline models respectively. © IFIP International Federation for Information Processing 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Gigahertz Optical Digital-to-Analog Multiplier

Gigahertz Optical Digital-to-Analog Multiplier

引用

2023 International Russian automation Conference, RusAutoCon 2023

作者： Kamenskiy, Vladislav Sokolov, Sergey Kurinenko, Marianna Rostov State Transport University «automation and Remote Control in Railway Transport» Department Rostov-on-Don Russia Moscow Technical University of Communications and Informatics Department of Informatics and Computer Engineering Rostov-on-Don Russia

ISBN: (纸本)9798350345551

The article analyzes modern computing devices that perform multiplication operations. The main classes of multipliers built on the basis of both electronic and optical elements are considered. The main disadvantage of these devices, which negatively affects their performance, is the inability to carry out parallel calculations with them. In turn, this disadvantage is due to the fact that multiplication of the multi-bit binary number in general is carried out by calculating the partial products of the bits of the multipliers and their addition with the inevitable implementation of a corresponding, usually very large, number of transfers. The presence of a large number of transfers fundamentally does not allow solving the problem of increasing the speed of calculations. The developed optical binary digital-to-analog multiplier is devoid of this drawback. This optical digital-to-analog multiplier is implemented on the basis of optical splitters, optical couplers and optical banners with a well-developed technology for their manufacture today, which provides a minimum delay time of the optical signal (in the picosecond range). The functional diagram of the proposed optical digital-to-analog multiplier is shown and the principle of its operation is described. The possibility of increasing the speed of this optical digital-to-analog multiplier to the potential for optical information processing circuits is shown. © 2023 IEEE.

关键词： Optical data processing

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：