检索结果-内蒙古大学图书馆

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Robert A Kaufman Emi Lee Manas Satish Bedmutha David Kirsh Nadir Weibel Cognitive Science University of California San Diego La Jolla California USA University of California San Diego La Jolla California USA UC San Diego La Jolla California USA Cognitive Science University of California San Diego San Diego California USA Computer Science and Engineering & The Design Lab UC San Diego La Jolla California USA

The Robustness of Structural Features in Species Interaction Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Fard, Sanaz Hasanzadeh Dolson, Emily Department of Computer Science and Engineering Michigan State University United States Program in Ecology Evolution and Behavior Michigan State University United States

Species interaction networks are a powerful tool for describing ecological communities;they typically contain nodes representing species, and edges representing interactions between those species. For the purposes of drawing abstract inferences about groups of similar networks, ecologists often use graph topology metrics to summarize structural features. However, gathering the data that underlies these networks is challenging, which can lead to some interactions being missed. Thus, it is important to understand how much different structural metrics are affected by missing data. To address this question, we analyzed a database of 148 real-world bipartite networks representing four different types of species interactions (pollination, host-parasite, plant-ant, and seed-dispersal). For each network, we measured six different topological properties: number of connected components, variance in node betweenness, variance in node PageRank, largest Eigenvalue, the number of non-zero Eigenvalues, and community detection as determined by four different algorithms. We then tested how these properties change as additional edges – representing data that may have been missed – are added to the networks. We found substantial variation in how robust different properties were to the missing data. For example, the Clauset-Newman-Moore and Louvain community detection algorithms showed much more gradual change as edges were added than the label propagation and Girvan-Newman algorithms did, suggesting that the former are more robust. Robustness also varied for some metrics based on interaction type. These results provide a foundation for selecting network properties to use when analyzing messy ecological network data. © 2025, CC BY.

关键词： Anthropogenic

Momentum-Based Distributed Economic Dispatch of Smart Grids in Time-Varying Directed Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Network science and engineering 2025年

作者： Zhang, Keke Lu, Qingguo Zhou, Qixing Li, Huaqing Xia, Dawen Huang, Tingwen Chongqing University College of Computer Science China Southwest University College of Electronic and Information Engineering China Kaili University College of Microelectronics and Artificial Intelligence College of Big Data Engineering China Texas A&M University at Qatar Science Program Doha23874 Qatar

In this paper, we investigate the economic dispatch problem of smart grids in time-varying directed networks. The EDP essentially revolves around optimizing the distribution of generation power amongst multiple generators, with the aim of fulfilling load demands at the lowest possible total generation cost, while strictly conforming to the constraints imposed by the local generation capacity. For a faster resolution of the EDP, we propose an efficient distributed accelerated economic dispatch algorithm that incorporates a unified momentum acceleration strategy into the push-pull deviation tracking approach. The involved acceleration strategy under specific momentum parameters includes two well-known acceleration strategies, i.e., the heavy-ball and Nesterov acceleration strategies, which is more flexible and provides additional improvements in convergence. We present rigorously theoretical proof of linear convergence to the optimal dispatch with explicit bounds for step size and momentum parameters. Finally, to verify the effectiveness of our algorithm and the correctness of the theoretical analysis, we conduct simulations of diverse EDP studies in smart grids. © 2013 IEEE.

关键词： Smart power grids

Emotion Recognition by Learning the Manifold of Fused Multiscale Information of EEG Signals

学校读者我要写书评

暂无评论

IEEE Transactions on Affective Computing 2025年

作者： Li, Cunbo Zhang, Shuhan Mu, Yufeng Yang, Lei Peng, Yueheng Li, Fali Zhang, Yangsong Liang, Zhen Cao, Zehong Wan, Feng Yao, Dezhong Li, Peiyang Xu, Peng University of Electronic Science and Technology of China Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu610054 China University of Macau Centre for Cognitive and Brain Sciences Institute of Collaborative Innovation China Southwest University of Science and Technology School of Computer Science and Technology Mianyang621010 China Shenzhen University School of Biomedical Engineering Medical School Shenzhen518060 China Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging Shenzhen518060 China University of South Australia STEM Mawson Lakes Campus AdelaideSA5095 Australia School of Computer Science University of Technology Sydney Australia University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology Centre for Cognitive and Brain Sciences Institute of Collaborative Innovation China Chongqing University of Posts and Telecommunications School of Bioinfomatics Chongqing400065 China

Recent research has consistently indicated that the fusion of electroencephalography (EEG) features from multiple modalities can integrate cognitive state expressions across diverse dimensions, resulting in a substantial increase in emotion recognition accuracy. However, redundant information within the fused multimodal features could lead to the curse of dimensionality and overfitting of the learning model. In this work, we propose a multiscale EEG feature fusion and representation strategy for EEG emotion recognition named manifold of multiscale information fusion (MMIF), in which the optimal manifold of the multiscale fusion of local and global brain activation patterns can be automatically learned to realize an efficient representation of emotional EEG signals. To evaluate the performance, in this work, both off- and online EEG emotion recognition experiments were conducted, and the experimental results consistently verified the effectiveness and feasibility of the MMIF applied in real-time emotion decoding systems. Furthermore, the analytical experiments confirmed the discriminative capabilities and cognitive interpretability of the MMIF. In summary, the proposed MMIF model may provide an efficient avenue for exploring representations and enhancing the discrimination of multimodal fusion features, which may also provide a promising solution for designing online affective braincomputer interaction systems. © 2010-2012 IEEE.

关键词： Information fusion

LESA: Learnable LLM Layer Scaling-Up

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Yifei Cao, Zouying Ma, Xinbei Yao, Yao Qin, Libo Chen, Zhi Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China School of Computer Science and Engineering Central South University China ByteDance China

Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. However, existing depth scaling-up methods rely on empirical heuristic rules for layer duplication, which result in poorer initialization and slower convergence during continual pre-training. We propose LESA, a novel learnable method for depth scaling-up. By concatenating parameters from each layer and applying Singular Value Decomposition, we uncover latent patterns between layers, suggesting that inter-layer parameters can be learned. LESA uses a neural network to predict the parameters inserted between adjacent layers, enabling better initialization and faster training. Experiments show that LESA outperforms existing baselines, achieving superior performance with less than half the computational cost during continual pre-training. Extensive analyses demonstrate its effectiveness across different model sizes and tasks.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Multilayer neural networks

MCT-Net: a multi-branch hybrid CNN-transformer model for medical image segmentation

学校读者我要写书评

暂无评论

Pattern Analysis and Applications 2025年第2期28卷 1-21页

作者： Shen, Longfeng Diao, Liangjin Peng, Rui Chen, Jiacong Lu, Zhengtian Ge, Fangzhen Anhui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior (ICACB) College of Computer Science and Technology Huaibei Normal University Huaibei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui Big-Data Research Center on University Management Huaibei Normal University Huaibei China

In recent years, neural networks have demonstrated substantial progress in medical image segmentation. However, accurately segmenting objects in medical images is often restricted by edge blurring, which complicates the delineation of structures of interest. The purpose of this study is to develop a multi-branch hybrid CNN-transformer model to address the issue of edge blurring in medical image segmentation. This approach enables more precise edge detection and segmentation. Integrating hybrid CNN and transformer decoders facilitates detailed recovery while preserving global structures, thus minimizing errors in regions with blurred edges. Additionally, we incorporate a hybrid attention mechanism at the model’s bottleneck to enhance feature transfer between the encoder and decoder. The model was trained using the ACDC, Synapse, and polyp datasets, with a focus on improving segmentation accuracy in regions with blurry edges. Experimental results reveal that the proposed model surpasses existing state-of-the-art methods on the ACDC, Synapse, and polyp datasets, demonstrating its superior performance and effectiveness. These results suggest that the proposed model offers a significant improvement in handling edge blurring, with potential applications in enhancing medical image analysis and diagnostics.

关键词：

Using Machine Learning and Neural Networks to Analyze and Predict Chaos in Multi-Pendulum and Chaotic Systems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ramachandruni, Vasista Reddy Nara, Sai Hruday Lalu, Geo Yang, Sabrina Kumar, Mohit Ramesh Jain, Aarjav Mehta, Pratham Koo, Hankyu Damonte, Jason Akl, Marx Department of Computer Science and Engineering Aspiring Scholars Directed Research Program 46249 Warm Springs Blvd. FremontCA94539 United States

A chaotic system is a highly volatile system characterized by its sensitive dependence on initial conditions and outside factors. Chaotic systems are prevalent throughout the world today: in weather patterns, disease outbreaks, and even financial markets. Chaotic systems are seen in every field of science and humanities, so being able to predict these systems is greatly beneficial to society. In this study, we evaluate 10 different machine learning models and neural networks [1] based on Root Mean Squared Error (RMSE) and R^2 values for their ability to predict one of these systems, the multi-pendulum. We begin by generating synthetic data representing the angles of the pendulum over time using the Runge Kutta Method for solving 4th Order Differential Equations (ODE-RK4) [2]. At first, we used the single-step sliding window approach, predicting the 50st step after training for steps 0-49 and so forth. However, to more accurately cover chaotic motion and behavior in these systems, we transitioned to a time-step based approach. Here, we trained the model/network on many initial angles and tested it on a completely new set of initial angles, or "in-between" to capture chaotic motion to its fullest extent. We also evaluated the stability of the system using Lyapunov exponents. We concluded that for a double pendulum, the best model was the Long Short Term Memory Network (LSTM)[3] for the sliding window and time step approaches in both friction and frictionless scenarios. For triple pendulum, the Vanilla Recurrent Neural Network (VRNN)[4] was the best for the sliding window and Gated Recurrent Network (GRU) [5] was the best for the time step approach, but for friction, LSTM was the best. © 2025, CC BY.

关键词： Runge Kutta methods

Development of Charge Integrator Circuits with a Microcontroller for Cylindrical Capacitive Sensors in Paddy Moisture Balance Detectors

学校读者我要写书评

暂无评论

Development of Charge Integrator Circuits with a Microcontro...

International Electrical engineering Congress (iEECON)

作者： Sudarat Tokampang Nattapong Apirattanon Noppadon Sisuk Anucha Kaewpoonsuk Deparment of Physics Faculty of Science Naresuan University Phitsanulok Thailand Program of Computer Engineering Faculty of Industrial Technology Phibunsongkhram Rajabhat University Phitsanulok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

This article presents a method for indirectly measuring the moisture content of paddy using a cylindrical capacitive sensor combined with Charge Integrator Circuits. The moisture measurement device operates based on the principle of the dielectric constant of paddy, which changes according to the moisture content within them. The system consists of a moisture detection section utilizing a cylindrical capacitor, a signal generator operating at a frequency of 500 Hz with a microcontroller, a signal conditioning circuit converting the signal to voltage, and a processing unit. Testing was conducted with paddy at five different moisture levels, demonstrating the ability to accurately determine the moisture content of the rice. When compared to the commercially available PM-450TH moisture meter, the results showed a linear response across the measurement range, with an R 2 value of 0.9824 and an average error of 2.6%. This technology has the potential for further development and application to other types of seeds in the future.

关键词： Accuracy Moisture measurement Microcontrollers Circuits Measurement uncertainty Moisture Dielectric measurement Capacitive sensors Standards Charge measurement

Convergence of energy-based learning in linear resistive networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huijzer, Anne-Men Chaffey, Thomas Besselink, Bart van Waarde, Henk J. Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Groningen Netherlands CogniGron - Groningen Cognitive Systems and Materials Center Netherlands Control Group Department of Engineering University of Cambridge United Kingdom School of Electrical and Computer Engineering University of Sydney Australia

Energy-based learning algorithms are alternatives to backpropagation and are well-suited to distributed implementations in analog electronic devices. However, a rigorous theory of convergence is lacking. We make a first step in this direction by analysing a particular energy-based learning algorithm, Contrastive Learning, applied to a network of linear adjustable resistors. It is shown that, in this setup, Contrastive Learning is equivalent to projected gradient descent on a convex function, for any step size, giving a guarantee of convergence for the *** Codes 65K10, 68T05, 93B30, 93D99 © 2025, CC BY-SA.

关键词： Contrastive Learning

Overlapped Error Correction Codes in Two-Dimensional Structures

学校读者我要写书评

暂无评论

Overlapped Error Correction Codes in Two-Dimensional Structu...

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Andrew Fritsch Wagner Savaris Adahil Muniz Giovanna Borba Rodrigo Girardi Jarbas Silveira César Marcon Graduate Program in Computer Science (PPGCC) Pontifical Catholic University of Rio Grande do Sul (PUCRS) Brazil Graduate Program in Teleinformatics Engineering (PPGETI) Federal University of Ceará (UFC) Brazil

ISBN: (数字)9798331522124

ISBN: (纸本)9798331522131

The continuous advancement of communication systems necessitates the development of algorithms capable of identifying and correcting errors that may arise during data transmission and storage. This pursuit of reliability is particularly crucial in critical systems and sectors that are challenging to access, such as space exploration, passenger transportation, and financial services. In this context, the Error Correction Code (ECC) is a fundamental tool for providing a certain degree of reliability to these systems. This research proposes a novel technique to enhance the error correction capacity of ECCs by leveraging region overlapping. Specifically, we propose correcting data areas protected by more than one ECC, which allows for the inference of logical correlations between ECCs, thereby augmenting their error detection and correction capability. Our focus is bidimensional codeword structures, commonly known as 2D-ECCs, which entail a hierarchical arrangement of ECCs. We evaluated the ECC proposal, comparing its error correction and detection capabilities. Through this evaluation, we aim to demonstrate the technique's efficacy in bolstering the reliability and resilience of communication systems, particularly in critical domains where precision and accuracy are paramount.

关键词： Fault tolerance Fault tolerant systems Transportation Error correction codes Error correction Space exploration Proposals Integrated circuit reliability Financial services Resilience