检索结果-内蒙古大学图书馆

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Fuzzy logic evaluation for student performance analysis in higher education

引用

AIP Conference Proceedings 2025年第1期3280卷

作者： Anand Swaroop Ravindra Bharadwaj Suhani Yadav Abhishek Singh Shiv Prakash Department of Computer Science & Engineering Institute of Engineering & Technology Dr. A.P.J Abdul Kalam Technology University Lucknow Uttar Pradesh INDIA Department of Physics and Computer Science Dayalbagh Educational Institute Agra Uttar Pradesh INDIA Department of Cognitive Science Dayalbagh Educational Institute Agra Uttar Pradesh INDIA Department of Computer Science & Engineering University of Allahabad Prayagraj Uttar Pradesh INDIA

Higher education establishments are presently confronted with a competitive landscape that includes growing employer demand and Industry 4.0 obstacles. Because of this, graduates are expected by industry and society to possess a broad knowledge base, strong critical thinking abilities, and a positive disposition. Higher education establishments must thus make sure that students succeed in this cutthroat climate. To ensure that this, a comprehensive analysis of the pupils’ performance must be conducted, highlighting both their strengths and weaknesses. This essay concentrated on the annual study of student performance utilizing fuzzy logic assessment techniques. Fuzzy logic was created using a subset of student traits performance evaluation using MATLAB software. In this approach, the evaluation qualities of students (knowledge, communication, etc.) served as the weighing criteria for assessing both the academic performance and the development of the students’ personalities. Next, an expert system built based on the Mamdani technique and employing fuzzy logic was evaluated on a sample of actual student marks. The outcomes of the traditional and fuzzy expert systems were subsequently contrasted. Based on the findings, the causes of the pupils’ shortcomings were determined, including whether they lacked academic or in the formation of personality. This finding might help universities choose the right lectures, exercises, and evaluation methods for both to better meet the industry’s need for human resources and to students.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rapid information gain explains cross-linguistic tendencies in numeral ordering 41

Rapid information gain explains cross-linguistic tendencies ...

引用

41st Annual Meeting of the cognitive science Society: Creativity + Cognition + Computation, CogSci 2019

作者： Liu, Emmy Xu, Yang Department of Computer Science Cognitive Science Program University of Toronto Canada

ISBN: (纸本)0991196775

One previously unexplained observation about numeral systems is the shared tendency in numeral expressions: Numerals greater than 20 often have the larger constituent number expressed before the smaller constituent number (e.g., twenty-four as opposed to four-twenty in English), and systems that originally adopt the reverse order of expression (e.g., four- and-twenty in Old English) tend to switch order over time. To explore these phenomena, we propose the view of Rapid Information Gain and contrast it with the established theory of Uniform Information Density. We compare the two theories in their ability to explain the shared tendency in the ordering of numeral expressions around 20. We find that Rapid Information Gain accounts for empirical patterns better than the alternative theory, suggesting that there is an emphasis on information front-loading as opposed to information smoothing in the design of large compound numerals. Our work shows that fine-grained generalizations about numeral systems can be understood in information-theoretic terms and offers an opportunity to characterize the design principles of lexical compounds through the lens of informative communication. © cognitive science Society: Creativity + Cognition + Computation, CogSci *** rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Gender convergence in the expressions of love: A computational analysis of lyrics 42

Gender convergence in the expressions of love: A computation...

引用

42nd Annual Meeting of the cognitive science Society: Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020

作者： El Sanyoura, Lana Xu, Yang Department of Computer Science Cognitive Science Program University of Toronto Canada

Love is a central theme in modern music, but do women and men differ in their expressions of love? Results from empirical studies on gender differences in love attitudes have evolved from showing consistent differences to more similarities over time and witnessed gender convergence in relationship expectations, housework responsibilities, and sexual attitudes. Independently, pop culture studies have shown how music can be used as a contextual artifact whose lyrics can reflect a culture's changing psychological processes and ideologies. We combine these two research areas to explore whether the gender convergence reported in psychological studies is mirrored in love songs. Using a corpus of lyrics and song metadata from 1960 to 2009, we present a computational analysis of the lexical distribution of lyrics across genre, gender and time. We show that love songs between vocalists who are men vs. women have become significantly more similar in their lyrical expressions of love. © 2020 The Author(s)

关键词： Computational methods

来源：评论

学校读者我要写书评

暂无评论

A predictability-distinctiveness trade-off in the historical emergence of word forms 41

A predictability-distinctiveness trade-off in the historical...

引用

41st Annual Meeting of the cognitive science Society: Creativity + Cognition + Computation, CogSci 2019

作者： Xu, Aotao Ramiro, Christian Xu, Yang Computer Science Program University of Waterloo Canada Cognitive Science Program University of California Berkeley United States Department of Computer Science Cognitive Science Program University of Toronto Canada

ISBN: (纸本)0991196775

It has been proposed that language evolves under the joint constraints of communicative expressivity and cognitive ease. We explore this idea in the historical emergence of word forms. We hypothesize that new word forms that enter the lexicon should reflect a trade-off between predictability and distinctiveness. An emergent word form can be highly predictable if it efficiently reuses elements from the existing word forms, resulting in low cognitive load. An emergent word form should also be sufficiently distinctive from the existing lexicon, facilitating communicative expressivity. We test our hypothesis by examining the properties of 34,478 emergent word forms over the past 200 years of Modern English. We show how word forms at future time t + 1 are bounded statistically between n-gram generated word forms (highly predictable) and slang words that are outside the standard lexicon (highly distinctive) at time t. Our work supports the view of cognitive economy in lexical emergence. © cognitive science Society: Creativity + Cognition + Computation, CogSci *** rights reserved.

关键词： cognitive economy language evolution lexical emergence lexicon word form

来源：评论

学校读者我要写书评

暂无评论

Investigation of Noise at a Microelectrode during a Faradaic Reaction

ACS Electrochemistry

引用

ACS Electrochemistry 2025年第4期1卷 552-559页

作者： Kaden Wheeler Joseph Gott Brian Roehrich Julia Chung Kajal Kajal Jaroslaw Syzdek Joao Hespanha Lior Sepunaru Department of Chemistry and Biochemistry University of California at Santa Barbara Santa Barbara California 93106 United States Interdepartmental Program in Biomolecular Science and Engineering University of California at Santa Barbara Santa Barbara California 93106 United States Bio-Logic USA LLC 9050 Executive Park Dr. Ste. 110C Knoxville Tennessee 37923 United States Electrical and Computer Engineering Department University of California at Santa Barbara Santa Barbara California 93106 United States

Measurement of small currents is often impeded by a suboptimal signal-to-noise ratio, largely due to background noise. This background noise significantly constrains the range of catalysts accessible for interrogation via micro- and nanoscale electrochemistry. In response, this work reveals how background noise scales in the presence of induced Faradaic reactions. We measured noise under a series of electrochemical conditions and discovered that the induced noise from a Faradaic reaction scales directly with current. Complementary electrochemical impedance spectroscopy measurements demonstrated that diffusional resistance dictates the noise of Faradaic reactions, independent of the electrochemical mechanism. The noise source is thermal in origin and propagates in a predictable trend, which is inversely proportional to the equivalent diffusional resistance of the analyte. The universality of the observed phenomenon allows for better deconvolution of measured charge from background noise, thus assisting in achieving higher resolution and measurement precision, which is a key in micro- and nanoscale electrochemical measurements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gumbel-Softmax Flow Matching with Straight-Through Guidance for Controllable Biological Sequence Generation

arXiv

引用

arXiv 2025年

作者： Tang, Sophia Zhang, Yinuo Tong, Alexander Chatterjee, Pranam Department of Biomedical Engineering Duke University United States Management and Technology Program University of Pennsylvania United States Center of Computational Biology Duke-NUS Medical School Singapore Mila Quebec AI Institute Canada Université de Montréal Canada Department of Computer Science Duke University United States Department of Biostatistics and Bioinformatics Duke University United States

Flow matching in the continuous simplex has emerged as a promising strategy for DNA sequence design, but struggles to scale to higher simplex dimensions required for peptide and protein generation. We introduce Gumbel-Softmax Flow and Score Matching, a generative framework on the simplex based on a novel Gumbel-Softmax interpolant with a time-dependent temperature. Using this interpolant, we introduce Gumbel-Softmax Flow Matching by deriving a parameterized velocity field that transports from smooth categorical distributions to distributions concentrated at a single vertex of the simplex. We alternatively present Gumbel-Softmax Score Matching which learns to regress the gradient of the probability density. Our framework enables high-quality, diverse generation and scales efficiently to higher-dimensional simplices. To enable training-free guidance, we propose Straight-Through Guided Flows (STGFlow), a classifier-based guidance method that leverages straight-through estimators to steer the unconditional velocity field toward optimal vertices of the simplex. STGFlow enables efficient inference-time guidance using classifiers pre-trained on clean sequences, and can be used with any discrete flow method. Together, these components form a robust framework for controllable de novo sequence generation. We demonstrate state-of-the-art performance in conditional DNA promoter design, sequence-only protein generation, and target-binding peptide design for rare disease treatment. © 2025, CC BY-NC-ND.

关键词： Velocity distribution

来源：评论

学校读者我要写书评

暂无评论

Bootstrapping in miniature language acquisition

引用

cognitive Systems Research 2002年第1期3卷 15-23页

作者： Desai, Rutvik Computer Science Department The Cognitive Science Program Indiana University Bloomington IN 47405 United States

Given the difficulties in learning meanings of words by observing the referent, it has been suggested that children use the syntactic context of the word to predict part of its meaning, a hypothesis known as syntactic bootstrapping. Semantic bootstrapping is the opposite theory that the knowledge of semantics helps in acquiring syntax. While there is evidence that children can apply their knowledge of correlations between syntax and semantics to perform bootstrapping, it is not clear how they come to know about these correlations in the first place. Here, a connectionist network is presented that learns to comprehend a miniature language by associating sentences with the corresponding scenes. In doing so, it learns the syntactic/semantic correlations and exhibits bootstrapping behavior. It is argued that such specialized phenomena can emerge when general mechanisms are applied to a specific task, and it is not always necessary to endow the learner with pre-existing specialized mechanisms. © 2002 Elsevier science B.V. All rights reserved.

关键词： Connectionist modeling Emergence Language acquisition Semantic bootstrapping Syntactic bootstrapping

来源：评论

学校读者我要写书评

暂无评论

Probabilistic genotype-phenotype maps reveal mutational robustness of RNA folding, spin glasses, and quantum circuits

引用

Physical Review Research 2025年第1期7卷 013118-013118页

作者： Anna Sappington Vaibhav Mohanty Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Harvard-MIT Program in Health Sciences and Technology Harvard Medical School Boston Massachusetts 02115 USA and Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Harvard/MIT MD-PhD Program Harvard Medical School Boston Massachusetts 02115 USA and Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Chemistry and Chemical Biology Harvard University Cambridge Massachusetts 02138 USA

Recent studies of genotype-phenotype maps have reported universally enhanced phenotypic robustness to genotype mutations, a feature essential to evolution. Virtually all of these studies make a simplifying assumption that each genotype—represented as a sequence—maps deterministically to a single phenotype, such as a discrete structure. Here we introduce probabilistic genotype-phenotype (PrGP) maps, where each genotype maps to a vector of phenotype probabilities, as a more realistic and universal language for investigating robustness in a variety of physical, biological, and computational systems. We study three model systems to show that PrGP maps offer a generalized framework which can handle uncertainty emerging from various physical sources: (1) thermal fluctuation in RNA folding, (2) external field disorder in the spin-glass ground state search problem, and (3) superposition and entanglement in quantum circuits, which are realized experimentally on IBM quantum computers. In all three cases, we observe a biphasic robustness scaling which is enhanced relative to random expectation for more frequent phenotypes and approaches random expectation for less frequent phenotypes. We derive an analytical theory for the behavior of PrGP robustness, and we demonstrate that the theory is highly predictive of empirical robustness.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Crack Catcher AI — Enabling Smart Fracture Mechanics Approach for Damage Control in Thin Silicon Wafers for 3D Semiconductor Integrated Devices/Packages

Crack Catcher AI — Enabling Smart Fracture Mechanics Approa...

引用

Annual International Symposium on Reliability Physics

作者： Gabriel Preston Greer Gonzolez Andrea S. Karnyoto Fitya S. Mozar Matthew M. Henry Mahmud Isnan Kuncahyo S. Nugroho Henry Candra Muhamad Doris Dianing N. N. Putri Tyas K Sari Bens Pardamean Endang Djuana Derrric Speaks Arief S. Budiman Oregon Renewable Energy Center (OREC) Oregon Institute of Technology (Oregon Tech) Klamath Falls OR USA Dept. of Manufacturing & Mechanical Eng. & Tech. (MMET) Oregon Institute of Technology Klamath Falls OR USA Bioinformatics & Data Science Research Center (BDSRC) Bina Nusantara University Jakarta Indonesia Computer Sci. Dept. BINUS Grad. Program - Master of Computer Sci. Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Center for Artificial Intelligence and Advanced Technology (CAPTIVATE) Universitas TRISAKTI Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Universitas TRISAKTI Jakarta Indonesia Industrial Eng. Dept. BINUS Grad. Program – Master of Industrial Eng. Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331504779

ISBN: (纸本)9798331504786

The importance of silicon cannot be undermined - in photovoltaics (PV) as well as in semiconductor industries. However, silicon is very brittle. Silicon cells/wafers crack easily during manufacturing assembly and/or during device operations. Crack Catcher AI uses novel smart fracture mechanics approach with Artificial Intelligence (AI) methodologies to predict and control crack/damage evolution in thin silicon cells/wafers. This is critical as semiconductor 3D integration technology calls for wafer-to-wafer bonding with utmost alignment accuracy and yield/reliability.

关键词： Semiconductor device measurement Three-dimensional displays Accuracy Semiconductor device reliability Silicon Artificial intelligence Bonding Stress Three-dimensional integrated circuits Stress measurement

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：