检索结果-内蒙古大学图书馆

Asilomar Conference on Signals, Systems & computers

作者： Aleksandar Armacki Himkant Sharma Dragana Bajović Dušan Jakovetić Mrityunjoy Chakraborty Soummya Kar Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA USA Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur Kharagpur India Department of Power Electronics and Computer Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia Department of Mathematics and Informatics Faculty of Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

We study the effects of center initialization on the performance of a family of distributed gradient-based clustering algorithms introduced in [1], that work over connected networks of users. In the considered scenario, each user contains a local dataset and communicates only with its immediate neighbours, with the aim of finding a global clustering of the joint data. We perform extensive numerical experiments, evaluating the effects of center initialization on the performance of our family of methods, demonstrating that our methods are more resilient to the effects of initialization, compared to centralized gradient clustering [2]. Next, inspired by the $K$ -means++ initialization [3], we propose a novel distributed center initialization scheme, which is shown to improve the performance of our methods, compared to the baseline random initialization.

关键词： computers Clustering methods Clustering algorithms Convergence

来源：评论

学校读者我要写书评

暂无评论

Time-dependent alternative route planning 20

Time-dependent alternative route planning

引用

20th Symposium on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems, ATMOS 2020

作者： Kontogiannis, Spyros Paraskevopoulos, Andreas Zaroliagis, Christos D. Department of Computer Science and Engineering University of Ioannina Greece Computer Technology Institute and Press "Diophantus" Patras Greece Department of Computer Engineering and Informatics University of Patras Greece Department of Computer Engineering and Informatics University of Patras Greece Computer Technology Institute and Press "Diophantus" Patras Greece

ISBN: (纸本)9783959771702

We present a new method for computing a set of alternative origin-to-destination routes in road networks with an underlying time-dependent metric. The resulting set is aggregated in the form of a time-dependent alternative graph and is characterized by minimum route overlap, small stretch factor, small size and low complexity. To our knowledge, this is the first work that deals with the time-dependent setting in the framework of alternative routes. Based on preprocessed minimum travel-time information between a small set of nodes and all other nodes in the graph, our algorithm carries out a collection phase for candidate alternative routes, followed by a pruning phase that cautiously discards uninteresting or low-quality routes from the candidate set. Our experimental evaluation on real time-dependent road networks demonstrates that the new algorithm performs much better (by one or two orders of magnitude) than existing baseline approaches. In particular, the entire alternative graph can be computed in less than 0.384sec for the road network of Germany, and in less than 1.24sec for that of Europe. Our approach provides also "quick-and-dirty" results of decent quality, in about 1/300 of the above mentioned query times for continental-size instances. © Spyros Kontogiannis, Andreas Paraskevopoulos, and Christos D. Zaroliagis

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Classifying Simulated Gait Impairments using Privacy-preserving Explainable Artificial Intelligence and Mobile Phone Videos

arXiv

引用

arXiv 2024年

作者： Reddy, Lauhitya Anand, Ketan Kaushik, Shoibolina Rodrigo, Corey McKay, J. Lucas Kesar, Trisha M. Kwon, Hyeokhyen Department of Biomedical Engineering Emory University Georgia Institute of Technology AtlantaGA United States Department of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States Department of Computer Science Emory University AtlantaGA United States Department of Rehabilitation Medicine Emory University AtlantaGA United States Department of Neurology Emory University AtlantaGA United States Department of Biomedical Informatics Emory University AtlantaGA United States

Accurate diagnosis of gait impairments is often hindered by subjective or costly assessment methods, with current solutions requiring either expensive multi-camera equipment or relying on subjective clinical observation. There is a critical need for accessible, objective tools that can aid in gait assessment while preserving patient privacy. In this work, we present a mobile phone-based, privacy-preserving artificial intelligence (AI) system for classifying gait impairments and introduce a novel dataset of 743 videos capturing seven distinct gait patterns. The dataset consists of frontal and sagittal views of trained subjects simulating normal gait and six types of pathological gait (circumduction, Trendelenburg, antalgic, crouch, Parkinsonian, and vaulting), recorded using standard mobile phone cameras. Our system achieved 86.5% accuracy using combined frontal and sagittal views, with sagittal views generally outperforming frontal views except for specific gait patterns like Circumduction. Model feature importance analysis revealed that frequency-domain features and entropy measures were critical for classifcation performance, specifically lower limb keypoints proved most important for classification, aligning with clinical understanding of gait assessment. These findings demonstrate that mobile phone-based systems can effectively classify diverse gait patterns while preserving privacy through on-device processing. The high accuracy achieved using simulated gait data suggests their potential for rapid prototyping of gait analysis systems, though clinical validation with patient data remains necessary. This work represents a significant step toward accessible, objective gait assessment tools for clinical, community, and tele-rehabilitation settings. © 2024, CC BY-NC-SA.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Enhancing Graph Representation Learning with Localized Topological Features

arXiv

引用

arXiv 2025年

作者： Z., Yan Q., Zhao Z., Ye T., Ma L., Gao Z., Tang Y., Wang C., Chen Wangxuan Institute of Computer Technology Peking University China Computer Science and Engineering Department University of California San Diego United States Department of Biomedical Informatics Stony Brook University United States Halıcıoğlu Data Science Institute University of California San Diego United States Weill Cornell Medicine Cornell University United States

Representation learning on graphs is a fundamental problem that can be crucial in various tasks. Graph neural networks, the dominant approach for graph representation learning, are limited in their representation power. Therefore, it can be beneficial to explicitly extract and incorporate high-order topological and geometric information into these models. In this paper, we propose a principled approach to extract the rich connectivity information of graphs based on the theory of persistent homology. Our method utilizes the topological features to enhance the representation learning of graph neural networks and achieve state-of-the-art performance on various node classification and link prediction benchmarks. We also explore the option of end-to-end learning of the topological features, i.e., treating topological computation as a differentiable operator during learning. Our theoretical analysis and empirical study provide insights and potential guidelines for employing topological features in graph learning tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

New Paradigms in Manifold Learning for Knowledge Discovery and Inverse Design of Photonic Nanostructures 19

New Paradigms in Manifold Learning for Knowledge Discovery a...

引用

Quantum Sensing and Nano Electronics and Photonics XIX 2023

作者： Zandehshahvar, Mohammadreza Javani, Mohammad Hadigheh Kiarashi, Yashar Zhu, Muliang Brown, Tyler Bao, Daqian Marzban, Mahmoodreza Pourabolghasem, Reza Adibi, Ali School of Electrical and Computer Engineering Georgia Institute of Technology 778 Atlantic Dr NW GA30332 United States Clark Atlanta University 223 James P Brawley Dr SW AtlantaGA30314 United States Department of Biomedical Informatics Emory School of Medicine 100 Woodruff Circle AtlantaGA30322 United States

ISBN: (纸本)9781510659650

This talk is focused on using the intelligent aspects of machine learning (ML) for both the understanding of the subtle properties of nanophotonic devices and their inverse design to achieve a desired response. It will be shown that by reducing the dimensionality of the problem using manifold learning techniques and simplifying the resulting networks using pruning, the computation complexity of the underlying artificial intelligence (AI) algorithms will be considerably reduced. Furthermore, by optimally defining the loss function (or the metric) for AI algorithms, priceless information about the properties of photonic nanostructures can be uncovered while facilitating the better visualization of the input-output relationship in these nanostructures. In addition, the resulting manifold-learning algorithms can be optimally trained to facilitate the inverse design of such nanostructures while minimizing the structural complexity. This talk will provide the foundation for both knowledge discovery and design in photonic nanostructures using manifold learning and metric learning and their application to the highly desired metaphotonic structures as an example platform. © 2023 SPIE.

关键词： Nanostructures

来源：评论

学校读者我要写书评

暂无评论

Promoting Accurate Image Reconstruction via Synthetic Noise for Unsupervised Screw Anomaly Detection and Location

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Chen, Jian Wen Ju Lin, Wan Li, Kuan Ming Mrozek, Dariusz Hung, Che Lun National Tsing Hua University Department of Computer Science Hsinchu300044 Taiwan National Kaohsiung University of Science and Technology Department of Mold and Die Kaohsiung80778 Taiwan National Taiwan University Department of Mechanical Engineering Taipei106319 Taiwan Silesian University of Technology Department of Applied Informatics Gliwice44-100 Poland National Yang Ming Chiao Tung University Institute of Biomedical Informatics Taipei11221 Taiwan

With residuals-based unsupervised models, defects can be detected using only normal samples, boosting both efficiency and practicality in industrial anomaly detection (AD) applications. While these approaches offer benefits, they also present challenges in detecting anomalies in cylindrical objects, such as imprecise image reconstruction and camera blind spots. As a result, this article introduces ScrewNet, an unsupervised AD framework designed specifically for cylindrical objects like screws. To improve the accuracy of reconstruction in the AD network, the synthetic noise module and pair training approach are employed during the training stage. The synthetic noise module, utilizing one of the CycleGAN generators, produces defects that match real-world distributions, thereby enabling the AD network to extract valuable features while preserving image structure. The pair training approach is designed to enable the AD network to achieve accurate reconstruction using similar background input-output pairs. To tackle the inspection blind spots problem, an efficient, cost-effective inspection system using multiple mirrors is developed for the inference stage. This approach enables effective AD across the entire 360° surface of the screw. In experiments, three different types of screw datasets containing both damaged and undamaged screws are provided. Numerous experiments demonstrate the superiority of our approach over several state-of-the-art (SOTA) unsupervised AD networks. For instance, ScrewNet outperforms baselines by 4 dB in average peak signal-to-noise ratio (PSNR) for image reconstruction quality and by 32% in average area under the receiver operating characteristic curve (AUROC) for pixel-level anomaly segmentation. In addition, image-level detection achieves 98.3% accuracy across the three screw datasets. The code is available at https://***/vitowen9580/ScrewNet. © 2025 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Assessment of Driver’s Stress using Multimodal Biosignals and Regularized Deep Kernel Learning

Assessment of Driver’s Stress using Multimodal Biosignals a...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Vishal Singh Roha Nagarajan Ganapathy Nicolai Spicher Sriparna Saha Thomas M. Deserno Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School Brunswick Germany Department of Computer Science Engineering Indian Institute of Technology Patna India Department of Biomedical Engineering Indian Institute of Technology Hyderabad India Institute for Medical Informatics University Medical Center Göttingen Göttingen Germany

In this work, we classify the stress state of car drivers using multimodal physiological signals and regularized deep kernel learning. Using a driving simulator in a controlled environment, we acquire electrocardiography (ECG), electrodermal activity (EDA), photoplethysmography (PPG), and respiration rate (RESP) from N = 10 healthy drivers in experiments of 25min duration with different stress states (5min resting, 10min driving, 10min driving + answering cognitive questions). We manually remove unusable segments and approximately 4h of data remain. Multimodal time and frequency features are extracted and employed to regularized deep kernel machine learning based on a fusion framework. Task-specific representations of different physiological signals are combined using intermediate fusion. Subsequently, the fused multimodal features are fed a support vector machine (SVM) and a random forest (RF) for stress classification. The experimental results show that the proposed approach can discriminate between stress states. The combination of PPG and ECG using RF as classifier yields the highest F1-score of 0.97 in the test set. PPG only and RF yield a maximum F1-score of 0.90. Furthermore, subject-specific cross-validation improves performance. ECG and PPG signals are reliable in classifying the stress state of a car driver. In summary, the proposed framework could be extended to real-time stress state assessment in driving conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-Band Planar Microstrip Monopole Antenna Design Using Multi-Objective Hybrid Optimization Algorithm

Dual-Band Planar Microstrip Monopole Antenna Design Using Mu...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： V. Hosseini F. Shapour P. Pinho Y. Farhang K. Majidzadeh Ch. Ghobadi J. Nourinia S. Barshandeh M. Shokri Zh. Amiri M. Jalilirad K. Kaboutari Department of Computer Engineering and Information Technology Payame Noor University Tehran Iran Computer Engineering Department Urmia Branch Islamic Azad University Urmia Iran Instituto de Telecomunicações Aveiro Portugal Department of Electronics Telecommunications and Informatics University of Aveiro Aveiro Portugal Department of Computer Engineering Khoy Branch Islamic Azad University Khoy Iran Department of Electrical Engineering Urmia University Urmia Iran Department of Computer Science School of Engineering Afagh Higher Education Institute Urmia Iran

This research uses a new proposed multi-objective optimization algorithm that utilizes an untested combined chaotic map to integrate Customized Mutated PSO (CM-PSO) with a Modified Genetic Algorithm (MGA) to design an antenna with specific electromagnetic characteristics. The hybrid approach achieves preferred outcomes faster than PSO, CM-PSO, GA, and MGA by avoiding being trapped in local minimums. The proposed Metaheuristic Algorithm (MA) functionality has been authenticated successfully using Benchmark Functions (BFs) like rastrigin Function (raF), Ackley Function (AF), Rosenbrock Function (RoF), and Booth Function (BoF). Finally, the validity of the offered approach for electromagnetic applications is demonstrated by optimizing a dual-band planar microstrip monopole antenna with a simple structure, such that its optimized $S_{11}$ be less than -10 dB at two frequency bands encompasses 2.4 to 2.484 and 5.15 to 5.825 GHz for Wireless Local Area Network (WLAN) with IEEE 802.11 standards. The proposed algorithm allows the optimization criteria to be customized. The optimization algorithm developed in MATLAB is used to determine the necessary parameter adjustments in order to achieve expected frequency bands using CM-PSO or an innovative MGA, while high-frequency and electromagnetic simulations are performed using computer Simulation technology (CST) Studio Suite. The dimensions of the proposed antenna's elements are critical input parameters of the algorithm, named decision variables.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Enabling Next Generation Societal Virtual Reality Applications for Virtual Human Teleportation

arXiv

引用

arXiv 2022年

作者： Chakareski, Jacob Khan, Mahmudur Yuksel, Murat Department of Informatics New Jersey Institute of Technology United States Department of Electrical and Computer Engineering York College United States Department of Electrical and Computer Engineering University of Central Florida United States

Virtual reality (VR) is an emerging technology of great societal potential. Some of its most exciting and promising use cases include remote scene content and untethered lifelike navigation. This article first highlights the relevance of such future societal applications and the challenges ahead towards enabling them. It then provides a broad and contextual high-level perspective of several emerging technologies and unconventional techniques and argues that only by their synergistic integration can the fundamental performance bottlenecks of hyper-intensive computation, ultra-high data rate, and ultra-low latency be overcome to enable untethered and lifelike VR-based remote scene immersion. A novel future system concept is introduced that embodies this holistic integration, unified with a rigorous analysis, to capture the fundamental synergies and interplay between communications, computation, and signal scalability that arise in this context, and advance its performance at the same time. Several representative results highlighting these trade-offs and the benefits of the envisioned system are presented at the end. Copyright © 2022, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Dermoscopic Image Classification Using Attention Mechanism and Ensemble Learning Approaches

Dermoscopic Image Classification Using Attention Mechanism a...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Huang, Shanchuan Lei, Hongwei Jin, Liuhan Yang, Jinzhu Jiang, Tao Yao, Yudong Grzegorzek, Marcin Li, Chen Northeastern University Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Liaoning Shenyang China Chengdu University of Traditional Chinese Medicine School of Intelligent Medicine Chengdu China Stevens Institute of Technology Department of Electrical and Computer Engineering United States Institute of Medical Informatics University of Luebeck Luebeck Germany

ISBN: (纸本)9798350324457

Background and purpose: Skin tumours have become one of the most common diseases worldwide. While benign ones are not usually a threat to human health, malignant ones can develop into skin cancer and become life-threatening if left untreated. Early detection of the disease is important for the treatment of patients with skin tumours and dermoscopy is the most effective means of diagnosing skin tumours. However, the complexity of skin tumour cells makes the diagnosis somewhat erroneous for doctors. Therefore, a dermoscopic classification network based on deep learning and computer-aided diagnostic techniques is needed to obtain a high diagnostic accuracy rate for skin tumours. Methods: In this paper, Deep-skin, a model for dermoscopic image classification is proposed, which is based on both attention mechanism and ensemble learning. Considering the characteristics of dermoscopic images, embedding different attention mechanisms on top of Inception-V3 has been suggested to obtain more potential features. We then improve the classification performance by late fusion of the different models. To demonstrate the effectiveness of Deep-skin, experiments and evaluations are performed on the publicly available dataset Skin Cancer: Malignant vs. Benign and compare the performance of Deep-skin with other classification models. Results: The experimental results indicate that Deep-skin performs well on the dataset in comparison to other models, achieving a maximum accuracy of 87.8%.Conclusion: In this paper, the Deep-skin model is proposed for the classification of dermoscopic images and has shown better performance. In the future, we intend to investigate better classification models for automatic diagnosis of skin tumours. Such models can potentially assist physicians and patients in clinical settings. © 2023 IEEE.

关键词： Attention mechanism Ensemble learning Image classification Late fusion Skin Cancer

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：