检索结果-内蒙古大学图书馆

Annual Conference on Information Sciences and Systems (CISS)

作者： Ian DeTore John Samsundar Cleon Davis Electrical and Computer Engineering Program Johns Hopkins University Baltimore MD USA Electrical and Computer Engineering Program Johns Hopkins University Laurel MD USA

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

This study introduces two novel hybrid machine-learning architectures for multilabel anomaly detection in electrocardiograms (EKGs): a 1D modified ResNet combined with a transformer encoder and an equivalent 2D ResNet-Transformer hybrid. This work is among the first to utilize two separate CNN-transformer architectures tailored specifically for temporal and spatial features in multilabel EKG data. Our models address the challenges of imbalanced data and multilabel classification by leveraging the PTB-XL dataset, containing over 21,000 annotated samples across five diagnostic superclasses, namely myocardial infarction, conduction disturbances, hypertrophy, ST-T wave changes, and normal EKGs. We applied advanced data augmentation techniques to mitigate class imbalance, including the Multilabel Synthetic Minority Over-Sampling Technique (ML-SMOTE). Additionally, we employed digital signal processing to denoise the EKG signals and convert time-series data into time-frequency representations for 2D modeling. Experimental results demonstrate the effectiveness of our approach, with the 1D model achieving an area under the curve (AUC) of 91.5% and the 2D model achieving an AUC of 87.2%. These findings demonstrate the potential of specialized architectures for comprehensive multilabel EKG anomaly detection.

关键词： Time-frequency analysis Multi label classification Machine learning Electrocardiography Myocardium Brain modeling Transformers Data models Electromyography Anomaly detection

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

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection 38

Textual Training for the Hassle-Free Removal of Unwanted Vis...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lee, Saehyung Mok, Jisoo Park, Sangha Shin, Yongho Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm Korea YH Seoul 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

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT. © 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

Sample-efficient adversarial imitation learning

引用

The Journal of Machine Learning Research 2024年第1期25卷 1545-1576页

作者： Dahuin Jung Hyungyu Lee Sungroh Yoon Electrical and Computer Engineering Seoul National University Seoul Republic of Korea Electrical and Computer Engineering Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Republic of Korea

Imitation learning, in which learning is performed by demonstration, has been studied and advanced for sequential decision-making tasks in which a reward function is not predefined. However, imitation learning methods still require numerous expert demonstration samples to successfully imitate an expert's behavior. To improve sample efficiency, we utilize self-supervised representation learning, which can generate vast training signals from the given data. In this study, we propose a self-supervised representation-based adversarial imitation learning method to learn state and action representations that are robust to diverse distortions and temporally predictive, on non-image control tasks. In particular, in comparison with existing self-supervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions. We theoretically and empirically observe that making an informative feature manifold with less sample complexity significantly improves the performance of imitation learning. The proposed method shows a 39% relative improvement over existing adversarial imitation learning methods on MuJoCo in a setting limited to 100 expert state-action pairs. Moreover, we conduct comprehensive ablations and additional experiments using demonstrations with varying optimality to provide insights into a range of factors.

关键词： imitation learning adversarial imitation learning self-supervised learning data efficiency

来源：评论

学校读者我要写书评

暂无评论

The use of long short-term memory models to estimate soybean pricing: a regional climate data evaluation from Brazil

引用

IEEE Access 2025年 13卷 101869-101884页

作者： Oliva, Jefferson Tales Martelli, Otavio Pigozzo Barbosa, Marco Antonio De Castro Molin, Viviane Dal Casanova, Dalcimar Teixeira, Marcelo Federal University of Technology-Paraná Graduate Program in Electrical and Computer Engineering Pato Branco Brazil Federal University of Technology-Paraná Department of Academic Informatics Pato Branco Brazil Federal University of Technology-Paraná Graduate Program in Production and Systems Engineering Pato Branco Brazil

This work uses machine learning methods to analyze the influence of the Brazilian climate on international soybean price variability. For this purpose, climatic data, historical series of the extended national consumer price index, dollar price historical series, soybean harvest historical series, and international soybean price historical series are collected from different data sources. The data is then preprocessed and grouped by state. Afterward, data from the five most productive Brazilian states, Mato Grosso (MT), Mato Grosso do Sul (MS), Goiás (GO), Paraná (PR), and Rio Grande do Sul (RS), which together correspond to 74.9% of total production, are chosen. Then, predictive models were built using the long short-term memory (LSTM) method, which is applied to each state dataset considering two different settings: with and without climatic data. Thus, two models were built for each Brazilian state, totaling ten predictors. These models are evaluated using 10-fold sequential split cross-validation, whose predictive results are used for performance comparison through statistical hypothesis testing. In the experimental evaluation, when trained with climatic data, the PR model achieved the lowest average values of root mean squared error (RMSE) and mean absolute error (MAE), which are 20.90 and 16.72, respectively. Regarding predictors trained without climate data, the RS and PR obtained the lowest averaged values of RMSE (20.84) and MAE (16.81), respectively. After performing statistical hypothesis tests, no significant differences were found between the models, stating, with certainty 95%, that the Brazilian climatic data did not influence soybean prices in our study. © 2013 IEEE.

关键词： Brazilian Climatic Data Long-Short Term Memory Machine Learning Soybean Time Series

来源：评论

学校读者我要写书评

暂无评论

Boost DC-DC Converter with Non-dissipative Snubber

引用

IEEJ Transactions on electrical and Electronic engineering 2024年第11期19卷 1858-1878页

作者： Yau, Yeu-Torng Department of Ph.D. Program Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung No.57 Sec. 2 Zhongshan Rd. Taiping Dist Taichung41170 Taiwan

To provide a hold-up time function in DC-DC supplies for cell site stations or data centers, using a boost converter with a bulk output capacitor as a front-end converter stage is a simple and highly cost-effective solution. However, conventional boost converters with a hard-switching operation result in low conversion efficiency and increased electromagnetic interference emissions. In this paper, a boost converter with a new non-dissipative snubber is proposed that only requires two additional diodes, an inductor, and a multilayer ceramic capacitor. The main feature of the proposed snubber is that the components are not located on the main power processing path. This means they only require low ratings, improving cost-effectiveness. A prototype converter is analyzed, realized, and applied to a 300 W redundant DC-DC power supply module for a 5G cell base station. © 2024 The Author(s). IEEJ Transactions on electrical and Electronic engineering published by Institute of electrical Engineers of Japan and Wiley Periodicals LLC. © 2024 The Author(s). IEEJ Transactions on electrical and Electronic engineering published by Institute of electrical Engineers of Japan and Wiley Periodicals LLC.

关键词： Boost converter

来源：评论

学校读者我要写书评

暂无评论

High-Precision Robotic Arm for Silicon Wafer Handling and Alignment in Small-Scale Semiconductor Fabrication

High-Precision Robotic Arm for Silicon Wafer Handling and Al...

引用

IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)

作者： Luke Bassett Maria Apostle Federica Aveta Dept. of Electrical and Computer Engineering Program in Computer Engineering Wentworth Institute of Technology Boston MA USA Dept. of Electrical and Computer Engineering Program in Electrical Engineering Wentworth Institute of Technology Boston MA USA

ISBN: (数字)9798331540906

ISBN: (纸本)9798331540913

Semiconductors play a critical role in almost every sector of electronics. In the United States, semiconductor manufacturing is limited, having very few large-scale automation tools compared to those in Taiwan. Instead, these smaller fabs rely heavily on human interaction with wafer handling. This can add significant points of failure such as scratching, particle defects, and stress on the wafer. The goal of this project is to develop a low-cost, automated wafer handling robotic arm with the ability to automatically align the notch of a wafer, effectively removing an entire movement step in the fabrication process. The robotic arm is able to lift a wafer from a wafer cassette and move it freely in the x-y plane while simultaneously rotating the notch to the correct alignment. The robot design is based on a dual-arm SCARA robot and is fully custom designed and manufactured. The main components of the robot include parallel dual-joint arms, a base mount for the arm motors, an end effector with a pulley belt system for wafer rotation, and a wafer notch detection and alignment system using a computer vision algorithm. Future directions for the project include manufacturing the z-axis base for vertical movement and the rotation base for rotational motion, whose preliminary designs have been already completed.

关键词： Fabrication computer vision Pulleys Semiconductor device manufacture Motors Mobile communication Silicon End effectors Robots Stress

来源：评论

学校读者我要写书评

暂无评论

Adversarial Environment Design via Regret-Guided Diffusion Models 38

Adversarial Environment Design via Regret-Guided Diffusion M...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chung, Hojun Lee, Junseo Kim, Minsoo Kim, Dohyeong Oh, Songhwai Interdisciplinary Program in Artificial Intelligence ASRI Seoul National University Korea Republic of Department of Electrical and Computer Engineering ASRI Seoul National University Korea Republic of

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD. © 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

Metasurfaces for next-generation wireless communication systems

引用

National Science Review 2023年第8期10卷 17-19页

作者： Younes Ra'di Nikita Nefedkin Petar Popovski Andrea Alù Department of Electrical Engineering and Computer Science Syracuse University Photonics Initiative Advanced Science Research Center City University of New York Department of Electronic Systems Aalborg University Physics Program Graduate Center City University of New York

The pace of development in the world of 5G communication systems has proven to be much more demanding than previous generations, with 5G-Advanced seemingly around the corner [1]. Extensive research is already underway to structure the next generation of wireless systems(i.e. 6G), which may potentially enable an unprecedented level of human–machine interaction [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Majorization theoretical approach to entanglement enhancement via local filtration

引用

Physical Review A 2024年第4期110卷 042430页

作者： Zacharie Van Herstraeten Nicolas J. Cerf Saikat Guha Christos N. Gagatsos Wyant College of Optical Sciences The Centre for Quantum Information and Communication École Polytechnique de Bruxelles CP 165 Department of Electrical and Computer Engineering Department of Electrical and Computer Engineering The Program in Applied Mathematics The

From the perspective of majorization theory, we study how to enhance the entanglement of a two-mode squeezed vacuum (TMSV) state by using local filtration operations. We present several schemes achieving entanglement enhancement with photon addition and subtraction, and then consider filtration as a general probabilistic procedure consisting in acting with local (nonunitary) operators on each mode. From this, we identify a sufficient set of two conditions for these filtration operators to successfully enhance the entanglement of a TMSV state, namely, the operators must be Fock orthogonal (i.e., preserving the orthogonality of Fock states) and Fock amplifying (i.e., giving larger amplitudes to larger Fock states). Our results notably prove that ideal photon addition, subtraction, and any concatenation thereof always enhance the entanglement of a TMSV state in the sense of majorization theory. We further investigate the case of realistic photon addition (subtraction) and are able to upper bound the distance between a realistic photon-added (-subtracted) TMSV state and a nearby state that is provably more entangled than the TMSV, thus extending entanglement enhancement to practical schemes via the use of a notion of approximate majorization. Finally, we consider the state resulting from k-photon addition (on each of the two modes) on a TMSV state. We prove analytically that the state corresponding to k=1 majorizes any state corresponding to 2≤k≤8 and we conjecture the validity of the statement for all k≥9.

关键词： Entanglement production Measures of continuous variables entanglement Quantum correlations, foundations & formalism Quantum entanglement

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：