检索结果-内蒙古大学图书馆

Offsets Reconstruction Method for Clock Skew Measurement Over High-Jitter Communication

SN computer science 2025年第5期6卷 1-14页

作者： Sastra, Nyoman Putra Saputra, Komang Oka Teng, Wei-Chung Study Program of Electrical Engineering Faculty of Engineering Udayana University Jalan Raya Kampus Bukit Jimbaran Bali Badung 80361 Indonesia Department of Computer Science and Information Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Rd Taipei 106 China

Measuring clock skew of devices over a network fully relies on the offsets, the differences between sending and receiving times. Offsets that shape a thick line are the most ideal one as their slope is directly the clock skew sought. When some outliers separate from the thick line due to higher delay jitter, current advanced approaches use the lower bound or the majority of offsets to derive accurate clock skew. However, outliers in offsets that shape parallel dotted lines, reduce the availability of offsets in the lower region, and scatter widely the offsets from their majority zone. These conditions drive the current skew estimation approaches to lose their accuracy. This paper then developed a new method, which reconstructs back the outliers into their origin positions, in order to provide ideal offsets for clock skew measurement. The experimental evaluations have demonstrated that the clock skew accuracy of dotted-lines offsets tampered by outliers was improved from 2.1 to 0.9 ppm by the proposed reconstruction method. For a broader purpose, the reconstruction method has been adjusted to be implemented also on non-dotted-lines offsets. The robustness of the proposed method for this case has also been exhibited by the very ideal reconstructed offsets that shape like a thick line. © The Author(s) 2025.

关键词： Clock skew Delay jitter Dotted lines Hough transform

来源：评论

学校读者我要写书评

暂无评论

On the Impact of Knowledge Distillation for Model Interpretability 40

On the Impact of Knowledge Distillation for Model Interpreta...

引用

40th International Conference on Machine Learning, ICML 2023

作者： Han, Hyeongrok Siwon, Kim Choi, Hyun-Soo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of ZIOVISION Inc. Chuncheon Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields. The code is available at https://***/Rok07/KD_***. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Neurocognitive assessment under various human-robot teaming environments 46

Neurocognitive assessment under various human-robot teaming ...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Packy, Anna L. Jayahankar, Jayesh Teymourlouei, Arya Stone, Joshua Oh, Hyuk Katz, Garrett E. Reggia, James A. Gentili, Rodolphe J. University of Maryland Neuroscience and Cognitive Science Program College Park United States University of Maryland Department of Computer Science College Park United States University of Maryland Department of Electrical & Computer Engineering College Park United States University of Maryland Department of Kinesiology College Park United States Syracuse University Department of Electrical Engineering & Computer Science Syracuse United States

ISBN: (纸本)9798350371499

Human-robot teaming has become increasingly important with the advent of intelligent machines. Prior efforts suggest that performance, mental workload, and trust are critical elements of human-robot dynamics that can be altered by the robot's behavior. Most prior human-robot teaming studies used behavioral analyses, but a limited number used neural markers, without the use of physical robots and complex tasks. Here we combine behavioral and EEG cortical dynamics to examine cognitive-motor processes when individuals complete a complex task under various team environments with a robot. The results revealed that altering the robot quality affected both behavioral and EEG dynamics. Task completion with an experienced robot led to greater team performance and human trust along with lower mental workload compared to an inexperienced teammate or when individuals performed alone. EEG changes suggest that different attentional processes were engaged when humans worked with the robot and performed alone, and that visual processing was more prominent when teaming with an inexperienced teammate. This work can inform human cognitive-motor processes and the design of robotic controllers in human-robot teams. © 2024 IEEE.

关键词： Man machine systems

来源：评论

学校读者我要写书评

暂无评论

Seafloor Imaging Maps by Incorporating Side Scan Sonar Technology on Hybrid Autonomous Underwater Glider 6

Seafloor Imaging Maps by Incorporating Side Scan Sonar Techn...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Atmaja, Ardian Budi Kusuma Hidayat, Egi Muhammad Idris Riyanto Trilaksono, Bambang Siregar, Simon Habibullah, Natsir School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Institut Teknologi Bandung Telkom University Doctoral Program of Electrical Engineering Department Computer Engineering Faculty of Applied Science Indonesia

ISBN: (纸本)9798350358346

This research aims to construct a two-dimensional image to represent an underwater geometry map with a Side Scan Sonar (SSS) mounted on a Hybrid Autonomous Underwater Glider (HAUG). Building the underwater map has two stages of the process. The first stage is preprocessing which includes Time-varying gains (TVG), slant range correction, and ground range correction. The second is HAUG navigation, the movement of HAUG orientation to the angle and distance of SSS readings and plotting the geometry of the grid map. With these two stages, a two-dimensional grid map will be formed. Meanwhile, the 3D plot utilizes slant range and ground range correction to obtain the surface height of the bottom of the pool. From the experiments conducted to conduct mapping in the pool, two-dimensional and three-dimensional visual forms of the pool floor and pool walls were produced. The results of the estimated measurement of the width of the pool obtained 14.05 meters and the height of the pool 3.199 meters with an SSS beam angle of 58 degrees. © 2023 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

3D Geometric Shape Assembly via Efficient Point Cloud Matching 41

3D Geometric Shape Assembly via Efficient Point Cloud Matchi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lee, Nahyuk Min, Juhong Lee, Junha Kim, Seungwook Lee, Kanghee Park, Jaesik Cho, Minsu Department of Computer Science and Engineering POSTECH Pohang Korea Republic of Graduate School of Artificial Intelligence POSTECH Pohang Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and compute. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://***/pmtr. Copyright 2024 by the author(s)

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

ENTROPY IS NOT ENOUGH FOR TEST-TIME ADAPTATION: FROM THE PERSPECTIVE OF DISENTANGLED FACTORS 12

ENTROPY IS NOT ENOUGH FOR TEST-TIME ADAPTATION: FROM THE PER...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Lee, Jonghyun Jung, Dahuin Lee, Saehyung Park, Junsung Shin, Juhyeon Hwang, Uiwon Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of AIIS ASRI INMC ISRC Seoul National University Korea Republic of

Test-time adaptation (TTA) fine-tunes pre-trained deep neural networks for unseen test data. The primary challenge of TTA is limited access to the entire test dataset during online updates, causing error accumulation. To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error. Through experimental studies, however, we observed the unreliability of entropy as a confidence metric for TTA under biased scenarios and theoretically revealed that it stems from the neglect of the influence of latent disentangled factors of data on predictions. Building upon these findings, we introduce a novel TTA method named Destroy Your Object (DeYO), which leverages a newly proposed confidence metric named Pseudo-Label Probability Difference (PLPD). PLPD quantifies the influence of the shape of an object on prediction by measuring the difference between predictions before and after applying an object-destructive transformation. DeYO consists of sample selection and sample weighting, which employ entropy and PLPD concurrently. For robust adaptation, DeYO prioritizes samples that dominantly incorporate shape information when making predictions. Our extensive experiments demonstrate the consistent superiority of DeYO over baseline methods across various scenarios, including biased and wild. Project page is publicly available at https://***/DeYO/. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Optimal first-order algorithms as a function of inequalities

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 2557-2625页

作者： Chanwoo Park Ernest K. Ryu Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Massachusetts Department of Mathematical Sciences Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea

In this work, we present a novel algorithm design methodology that finds the optimal algorithm as a function of inequalities. Specifically, we restrict convergence analyses of algorithms to use a prespecified subset of inequalities, rather than utilizing all true inequalities, and find the optimal algorithm subject to this restriction. This methodology allows us to design algorithms with certain desired characteristics. As concrete demonstrations of this methodology, we find new state-of-the-art accelerated first-order gradient methods using randomized coordinate updates and backtracking line searches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spectral Learning of Shared Dynamics Between Generalized-Linear Processes 38

Spectral Learning of Shared Dynamics Between Generalized-Lin...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Oganesian, Lucine L. Sani, Omid G. Shanechi, Maryam M. Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA United States Ming Hsieh Department of Electrical and Computer Engineering Thomas Lord Department of Computer Science Alfred E. Mann Department of Biomedical Engineering Neuroscience Graduate Program University of Southern California Los AngelesCA United States

Generalized-linear dynamical models (GLDMs) remain a widely-used framework within neuroscience for modeling time-series data, such as neural spiking activity or categorical decision outcomes. Whereas the standard usage of GLDMs is to model a single data source, certain applications require jointly modeling two generalized-linear time-series sources while also dissociating their shared and private dynamics. Most existing GLDM variants and their associated learning algorithms do not support this capability. Here we address this challenge by developing a multi-step analytical subspace identification algorithm for learning a GLDM that explicitly models shared vs. private dynamics within two generalized-linear time-series. In simulations, we demonstrate our algorithm's ability to dissociate and model the dynamics within two time-series sources while being agnostic to their respective observation distributions. In neural data, we consider two specific applications of our algorithm for modeling discrete population spiking activity with respect to a secondary time-series. In both synthetic and real data, GLDMs learned with our algorithm more accurately decoded one time-series from the other using lower-dimensional latent states, as compared to models identified using existing GLDM learning algorithms. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Neurological Diagnostics: Integrating 6G Technology with Deep Learning for Enhanced Detection of Multiple Sclerosis and Myelitis

Revolutionizing Neurological Diagnostics: Integrating 6G Tec...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Noureldeen, Rana M. Elshshtawy, Rahma A. Elgohary, Omnia A. Wahba, Fatma Alzahraa A. Attia, Marco K. Abo Elazm, Zeinab B. Khattap, Mohamed G. Galal Eldeen Mohamed Ali Hassan, Hend Mostafa, Mariam Ibrahim, Nayra Ramadan, Reem Refaat, Yomna Khaled, Mennatallah Maher, Ali Abd Elaziz, Mohamed Gamal Abdellatif Ibrahim, Ahmed Faculty of Applied Health Sciences Galala University Suez435611 Egypt Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Air Defense College Department of Electronics and Electrical Communications Engineering Alexandria Egypt

ISBN: (纸本)9798350351408

This paper proposes an alternative detection frame-work for multiple sclerosis (MS) and idiopathic acute transverse myelitis (ATM) within the 6G-enabled Internet of Medical Things (IoMT) environment. The developed framework relies on the implementation of a deep learning technique known as Dense Convolutional Networks (DenseNets) in the 6G-enabled IoMT to enhance prediction performance. To validate the performance of DenseNets, we compared it with other deep learning techniques, including Convolutional Neural Networks (CNN) and MobileNet, using real-world datasets. The experimental results show the high performance of DenseNets in predicting MS and ATM compared to other methods, achieving an accuracy of nearly 90 %. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Objective Sleep Quality Measurement based on Fuzzy Logic and Wearable Device 8

Objective Sleep Quality Measurement based on Fuzzy Logic and...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Wijaya, Jason A. Andersen, Pauw D. Surantha, Nico Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Department of Electrical Electronic and Communication Engineering Tokyo City University Japan

Sleep is the natural state of relaxation for human being. Sleep quality is an essential yet frequently neglected aspect of sleep in general. Sleep quality is essential because it allows the body to restore itself and prepare for the next day. The standard method for evaluating sleep quality was subjective evaluation. Actigraphy devices, which can measure the sleep cycle, are now widely available. This study developed a method using Fuzzy Logic and an actigraphy device to measure and classify sleep quality. The fuzzy logic method was developed in several stages, which are determining the sleep quality measurement parameters, constructing the fuzzy set for each input variable, and developing the fuzzy rules. To evaluate the proposed fuzzy model, five individuals were invited to participate in the experiment and required to complete the PSQI subjective sleep questionnaire. The evaluation result shows that our proposed Fuzzy model achieves lower error compared to the existing method. © 2023 The Authors. Published by Elsevier B.V.

关键词： actigraphy artificial intelligences fuzzy logic sleep sleep quality

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：