检索结果-内蒙古大学图书馆

CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Shi, Yukai Shi, Cidan Weng, Zhipeng Tian, Yin Xian, Xiaoyu Lin, Liang Guangdong University of Technology School of Information Engineering Guangzhou510006 China Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei230601 China CRRC Academy Co. Ltd Beijing China Sun Yat-sen University School of Computer Science Guangzhou510006 China

Infrared and visible image fusion (IVIF) is increasingly applied in critical fields such as video surveillance and autonomous driving systems. Significant progress has been made in deep learning-based fusion methods. However, these models frequently encounter out-of-distribution (OOD) scenes in real-world applications, which severely impact their performance and reliability. Therefore, addressing the challenge of OOD data is crucial for the safe deployment of these models in open-world environments. Unlike existing research, our focus is on the challenges posed by OOD data in real-world applications and on enhancing the robustness and generalization of models. In this paper, we propose an infrared-visible fusion framework based on Multi-View Augmentation. For external data augmentation, Top-k Selective Vision Alignment is employed to mitigate distribution shifts between datasets by performing RGB-wise transformations on visible images. This strategy effectively introduces augmented samples, enhancing the adaptability of the model to complex real-world scenarios. Additionally, for internal data augmentation, self-supervised learning is established using Weak-Aggressive Augmentation. This enables the model to learn more robust and general feature representations during the fusion process, thereby improving robustness and generalization. Extensive experiments demonstrate that the proposed method exhibits superior performance and robustness across various conditions and environments. Our approach significantly enhances the reliability and stability of IVIF tasks in practical applications. © 1991-2012 IEEE.

关键词： Image fusion

Brain Region Knowledge Based Dual-Stream Transformer for EEG Emotion Recognition

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2025年

作者： Lin, Yichuan Xu, Geng-Xin Liang, Haotian Wang, Yishan Wan, Feng Li, Ye Southern University of Science and Technology Shenzhen518055 China Research Center for Biomedical Information Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Hangzhou Institute of Advanced Technology Chinese Academy of Sciences China Department of Electrical and Computer Engineering The Faculty of Science and Technology The Centre for Cognitive and Brain Sciences The Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation University of Macau China

In consumer electronics, affective computing allows devices to recognize and respond to the emotional states of individuals, thereby enhancing personalization and satisfaction. Electroencephalogram (EEG)-based emotion recognition methods have garnered attention for their capability to provide real-time, objective insights into emotional and cognitive states. Existing research mainly focuses on extracting temporal and spectral features from EEG signals for emotion recognition. However, electrode shifts may occur across different experiments during data acquisition, resulting in models with limited robustness and constrained classification performance. To address this challenge, this paper introduces a Brain Region Knowledge based Dual-Stream network (BRKDSnet) for emotion recognition. It employs a dual-stream architecture to effectively fuse the temporal, spectral, and spatial features of EEG signals. By incorporating prior brain region partition knowledge, it efficiently aggregates channel features into distinct brain region features. Such a brain region based partition mitigates noise issues caused by electrode shifts during user wearing in consumer electronic applications, and leading to learn more robust feature representations. The experiments conducted on the widely used emotion recognition datasets SEED and SEED-IV shows that BRKDSnet achieves state-of-the-art results, with accuracies of 97.81% (improved by 0.64%-3.57% compared to existing works) and 90.76% (improved by 3.13%-11.39%) respectively. Finally, through analysis of the visualization results, it is found that EEG channels located in the temporal lobe contributed the most to emotion recognition classification, which also provides the potential for future applications in wearable devices. © 2025 IEEE.

关键词： Electroencephalography

2D Polynomial Regression Modeling for Predictive Analysis of Glucose Concentration in NP-Model Fractal Microwave Sensor Using Frequency and Transmission Coefficient Disparities

学校读者我要写书评

暂无评论

2D Polynomial Regression Modeling for Predictive Analysis of...

International Electrical engineering Congress (iEECON)

作者： Nutyada Nantapanich Pisit Mahatthanajatuphat Norakamon Wongsin Wilaiporn Lee Department of Electronics and Telecommunication Engineering Faculty of Engineering Rajamangala University of Technology Thanyaburi Pathum Thani Thailand Regular Program in Mathematics-Science Yothinburana School Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

The article introduces a two-dimensional polynomial regression model for the predictive analysis of glucose concentration in a fractal microwave sensor NP model, utilizing frequency and transmission coefficient differences to examine their correlation with glucose concentration levels. The sensor employed in this investigation is fabricated on an economical FR-4 substrate to minimize costs. The sensor structure is developed with the fractal structure reduction method established by the NP model to operate at a frequency of roughly 2.97 GHz. The CST Studio software is utilized to analyze the findings from the simulation of the suggested sensor structure. Furthermore, the proposed sensor is integrated into a test apparatus comprising a sensor platform and a liquid tube constructed from PPA material. The liquid under examination is a glucose and water mixture at varying concentrations. It was analyzed using a VNA instrument to evaluate its frequency response and the magnitude of the alteration in the transmission coefficient. The values are utilized to create a two-dimensional polynomial regression model. The experiments demonstrated that the proposed sensor model possesses an Adjusted R² value of 0.99499 and an average error of approximately 3.57% for glucose concentration analysis throughout the range of 5% to 30%, with sensitivities of 0.00879 dB/% for insertion loss and 0.092 MHz/% for frequency variation, facilitating accurate glucose concentration prediction analysis.

关键词： Analytical models Adaptation models Correlation Liquids Predictive models Microwave sensors Polynomials Fractals Glucose Predictive analytics

How Deep is Love in LLMs’ Hearts? Exploring Semantic Size in Human-like Cognition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yao, Yao Yang, Yifei Ma, Xinbei Yang, Dongjie Zhang, Zhuosheng Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan University Wuhan430072 China

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival human capabilities in various domains, we are presented with a unique testbed to investigate human cognition through a new lens. Among the many facets of cognition, one particularly crucial aspect is the concept of semantic size—the perceived magnitude of both abstract and concrete words or concepts. This study seeks to investigate whether LLMs exhibit similar tendencies in understanding semantic size, thereby providing insights into the underlying mechanisms of human cognition. We begin by exploring metaphorical reasoning, comparing how LLMs and humans associate abstract words with concrete objects of varying sizes. Next, we examine LLMs’ internal representations to evaluate their alignment with human cognitive processes. Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding, suggesting that real-world, multi-modal experiences are similarly vital for human cognitive development. Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario. The results show that multi-modal LLMs are more emotionally engaged in decision-making, but this also introduces potential biases, such as the risk of manipulation through clickbait headlines. Ultimately, this study offers a novel perspective on how LLMs interpret and internalize language, from the smallest concrete objects to the most profound abstract concepts like ‘love’. The insights gained not only improve our understanding of LLMs but also provide new avenues for exploring the cognitive abilities that define human intelligence. Our code and dataset is publicly available at https://***/Zoeyyao27/LLM-Semantic-Size-Understanding. © 2025, CC BY.

关键词： Semantics

Air-Ground Integrated Online Federated Learning Under Unreliable Communication

学校读者我要写书评

暂无评论

IEEE Transactions on cognitive Communications and Networking 2025年

作者： Jing, Yuqian Qu, Yuben Wu, Tao Dong, Chao Guo, Song Wu, Qihui Ministry of Industry and Information Technology Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing211106 China Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong National University of Defense Technology Anhui Hefei230009 China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong999077 Hong Kong

In recent years, unmanned aerial vehicles (UAVs) equipped with intelligent computing modules for machine learning (ML) have garnered attention. Federated learning (FL), as an emerging distributed learning paradigm, aligns seamlessly with this scenario. UAVs train local models while a terrestrial base station (BS) aggregates the global model, forming an air-ground integrated federated learning (AGIFL) system. However, under air-ground integrated networks with unreliable wireless links, the online retraining of ML models with new samples is promising but challenging in AGIFL. To this end, we study how to enhance the performance of air-ground integrated online FL (AGIOFL) considering packet transmission error. Specifically, we formulate a joint optimization problem for sample selection and client scheduling, aiming to minimize the loss function that maximizes the performance of AGIOFL. To solve the aforementioned problem without explicit expression, we first derive a closed-form expression for the expected convergence rate of the FL algorithm to quantify the impact of AGIOFL and unreliable wireless transmission. Based on this relationship, we reformulate the optimization problem into a mixed-integer nonlinear programming problem. Subsequently, we develop an alternating iterative optimization algorithm (OFL-PE) combining branch-and-bound with the Dinkelbach algorithm to solve this problem. Simulations indicate that OFL-PE converges within 10 iterations only, with a maximum error of less than 7% compared to the exhaustive brute force approach. In addition, we construct a proof-of-concept system based on widely used UAV embedded computers, and experimental results show that OFL-PE demonstrates superior accuracy, convergence, and robustness compared to three existing FL algorithms. © 2015 IEEE.

关键词： Federated learning

Effective Dimension Aware Fractional-Order Stochastic Gradient Descent for Convex Optimization Problems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Partohaghighi, Mohammad Marcia, Roummel Chen, YangQuan Electrical Engineering and Computer Science graduate program University of California Merced United States Department of Applied Mathematics University of California Merced MercedCA United States Lab Department of Mechanical Engineering School of Engineering University of California MercedCA95343 United States

Fractional-order stochastic gradient descent (FOSGD) leverages a fractional exponent to capture long-memory effects in optimization, yet its practical impact is often constrained by the difficulty of tuning and stabilizing this exponent. In this work, we introduce 2SED Fractional-Order Stochastic Gradient Descent (2SEDFOSGD), a novel method that synergistically combines the Two-Scale Effective Dimension (2SED) algorithm with FOSGD to automatically calibrate the fractional exponent in a data-driven manner. By continuously gauging model sensitivity and effective dimensionality, 2SED dynamically adjusts the exponent to curb erratic oscillations and enhance convergence rates. Theoretically, we demonstrate how this dimension-aware adaptation retains the benefits of fractional memory while averting the sluggish or unstable behaviors frequently observed in naive fractional SGD. Empirical evaluations across multiple benchmarks confirm that our 2SED-driven fractional exponent approach not only converges faster but also achieves more robust final performance, suggesting broad applicability for fractional-order methodologies in large-scale machine learning and related domains. © 2025, CC BY.

关键词： Convex optimization

FACE: Few-shot Adapter with Cross-view Fusion for Cross-subject EEG Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Haiqi Chen, C.L. Philip Zhang, Tong Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Pazhou Lab Guangzhou510335 China Engineering Research Center Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China

Cross-subject EEG emotion recognition is challenged by significant inter-subject variability and intricately entangled intra-subject variability. Existing works have primarily addressed these challenges through domain adaptation or generalization strategies. However, they typically require extensive target subject data or demonstrate limited generalization performance to unseen subjects. Recent few-shot learning paradigms attempt to address these limitations but often encounter catastrophic overfitting during subject-specific adaptation with limited samples. This article introduces the few-shot adapter with a cross-view fusion method called FACE for cross-subject EEG emotion recognition, which leverages dynamic multi-view fusion and effective subject-specific adaptation. Specifically, FACE incorporates a cross-view fusion module that dynamically integrates global brain connectivity with localized patterns via subject-specific fusion weights to provide complementary emotional information. Moreover, the few-shot adapter module is proposed to enable rapid adaptation for unseen subjects while reducing overfitting by enhancing adapter structures with meta-learning. Experimental results on three public EEG emotion recognition benchmarks demonstrate FACE’s superior generalization performance over state-of-the-art methods. FACE provides a practical solution for cross-subject scenarios with limited labeled data. Copyright © 2025, The Authors. All rights reserved.

关键词： Emotion Recognition

Can (A)I Change Your Mind?

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Havin, Miriam Kleinman, Timna Wharton Koren, Moran Dover, Yaniv Goldstein, Ariel Department of Cognitive and Brain Sciences The Hebrew University of Jerusalem Israel The Federmann Center for the Study of Rationality The Hebrew University of Jerusalem Israel School of Computer Science and Engineering The Hebrew University of Jerusalem Israel Industrial Engineering and Management Department Ben Gurion Univeristy Israel The Hebrew University Business School Jerusalem Israel

The increasing integration of large language model (LLM) based conversational agents into everyday life raises critical cognitive and social questions about their potential to influence human opinions. Although previous studies have shown that LLM-based agents can generate persuasive content, these typically involve controlled, English-language settings. Addressing this, our preregistered study explored LLM’s persuasive capabilities in more ecological, unconstrained scenarios, examining both static (written paragraphs) and dynamic (conversations via Telegram) interaction types. Conducted entirely in Hebrew with 200 participants, the study assessed the persuasive effects of both LLM and human interlocutors on controversial civil policy topics. Results indicated that participants adopted LLM and human perspectives similarly, with significant opinion changes evident across all conditions, regardless of interlocutor type or interaction mode. Confidence levels increased significantly in most scenarios, except in static LLM interactions. These findings demonstrate LLM-based agents’ robust persuasive capabilities across diverse sources and settings, highlighting their potential impact on shaping public opinions. © 2025, CC BY.

关键词： Chatbots

Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Heyman, Alex Zylberberg, Joel Department of Electrical Engineering and Computer Science York University TorontoON Canada Jules Stein Eye Institute University of California Los AngelesCA United States Learning in Machines and Brains Program CIFAR TorontoON Canada

Contemporary large language models are powerful problem-solving tools, but they exhibit weaknesses in their reasoning abilities which ongoing research seeks to mitigate. We investigate graph coloring as a means of evaluating an LLM’s capacities for systematic step-by-step reasoning and possibility space exploration, as well as effects of semantic problem framing. We test Claude 3.5 Sonnet, Llama 3.1 405B, Gemini 1.5 Pro, GPT-4o, o1-mini, and DeepSeek-R1 on a dataset of k-coloring problems with 2 ≤ k ≤ 4 and vertex count 4 ≤ n ≤ 8, using partial algorithmic solvers to further categorize problems by difficulty. In addition to substantial but varying framing effects, we find that all models except o1-mini and R1 exhibit > 60% error rates on difficult problem types in all frames (> 15% for o1-mini and > 10% for R1), and no model achieves perfect accuracy even in the simple domain of 2-coloring 4-vertex graphs. Our results highlight both the considerable recent progress in LLM systematic reasoning and the limits of its reliability, especially in relation to increasing computational costs. We expect that more complex graph coloring problems, and procedural generation of arbitrary-complexity reasoning problems more broadly, offer further untapped potential for LLM benchmarking. © 2025, CC BY.

关键词：