检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Soubki, Adil Murzaku, John Zeng, Peter Rambow, Owen Department of Computer Science Department of Linguistics Institute for Advanced Computational Science Stony Brook University United States

Automatically recognizing a human’s complete cognitive state from text is a difficult task;from text, a model has to recognize a combination of concepts including belief, emotion, common ground, sentiment, and intention. Humans do not only track and update cognitive state from the meaning of words and sentences, but also from paralinguistic cues such as prosody. The NLP community has broadly focused on text-only approaches to cognitive state tasks, but audio can provide vital missing information. We posit that text-to-speech (TTS) models learn to track aspects of cognitive state in order to produce naturalistic audio, and that the signal audio models implicitly identify is orthogonal to the information that language models exploit. We present Synthetic Audio Data fine-tuning (SAD), a framework where we show that seven tasks related to cognitive state modeling benefit from multimodal training on both text and zero-shot synthetic audio data from an off-the-shelf TTS system. We show an improvement over the text-only modality when adding synthetic audio data to text-only corpora. Furthermore, on tasks and corpora that do contain gold audio, we show our SAD framework achieves competitive performance using text and synthetic audio compared to text and gold audio. Copyright © 2025, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Microwave-induced cooling in double quantum dots: Achieving millikelvin temperatures to reduce thermal noise around spin qubits

引用

Physical Review B 2025年第1期111卷 014305-014305页

作者： Daryoosh Vashaee Jahanfar Abouie Department of Materials Science and Engineering and Department of Electrical and Computer Engineering North Carolina State University Raleigh North Carolina 27606 USA Department of Physics Institute for Advanced Studies in Basic Sciences Zanjan 45137-66731 Iran

Spin qubits in gate-defined quantum dots are emerging as a leading technology due to their scalability and long coherence times. However, maintaining these qubits at ultralow temperatures typically requires complex cryogenic systems. This paper proposes a gate-defined double quantum dot (DQD) cooling system, where the DQDs act as refrigerants to reduce the local phonon environment around computational qubits. The cooling process occurs in two distinct stages: the first step involves microwave-induced state depopulation combined with fast cyclic detuning to transfer the DQD's population to the ground state, effectively lowering the DQD's temperature. In the second step, the cooled DQD interacts with and absorbs phonons resonant with the DQD spin energy, thereby filtering out these phonons that contribute to spin-lattice relaxation in the surrounding environment. This study focuses on the first step, presenting detailed calculations and numerical results that demonstrate the feasibility of achieving local DQD temperatures below 10mK at a bath temperature of 1K. The sensitivity of the cooling performance to detuning energy, magnetic field strength, spin-orbit couplings, and diabatic return time is analyzed, while the phonon filtering in the second step will require further investigation.

关键词： Semiconductor quantum dots

来源：评论

学校读者我要写书评

暂无评论

Dynamic Programming Algorithms for Fast and Accurate Cell Lineage Tree Reconstruction from CRISPR-Based Lineage Tracing Data

Dynamic Programming Algorithms for Fast and Accurate Cell ...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Dai, Junyan Molloy, Erin K. Department of Computer Science University of Maryland College Park20742 United States University of Maryland Institute for Advanced Computer Studies University of Maryland College Park20742 United States

ISBN: (纸本)9783031902512

CRISPR-based lineage tracing has emerged as a promising approach for studying cell transformations during development and disease progression. However, the high ratio of cells to mutations, coupled with missing data from silencing or dropout, challenges tree reconstruction, even with the leading method Startle, which is based on Star Homoplasy Parsimony (SHP). Here, we present Star-CDP, the first dynamic programming algorithm that solves the SHP problem within a constrained search space Σ defined by subsets of cells from which a solution cell lineage tree must draw its clades. When Σ is the power set, Star-CDP is an exact exponential algorithm with time complexity O(nm|Σ|2), where n and m denote the number of cells and sites, respectively. We show how to build clade constraints that are polynomially-sized and effective in practice. We also develop algorithms to efficiently count, sample, and build consensus trees from all solutions to the clade-constrained SHP problem, motivated by the challenges in producing consistent phylogenetic signal across the tree with current lineage tracing technologies. In simulations, Star-CDP’s strict consensus typically achieves the best f1-score for the majority of model conditions studied, except when the proportion of missing data from silencing versus dropout reached 100%. Lastly, we analyzed lineage tracing data from a mouse model of lung adenocarcinoma, finding that Star-CDP produced plausible trees, often lowering the number of migration and reseeding events needed to explain metastases compared to Startle. Star-CDP is available on Github: https://***/molloy-lab/Star-CDP. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Multimodal Learning in Image Processing

引用

computers, Materials & Continua 2025年第2期82卷 3615-3618页

作者： Zhixin Chen Gautam Srivastava Shuai Liu School of Educational Science Hunan Normal UniversityChangsha410081China Institute of Interdisciplinary Studies Hunan Normal UniversityChangsha410081China Department of Math and Computer Science Brandon UniversityBrandonMB R7A 6A9Canada Research Centre for Interneural Computing China Medical UniversityTaichung406040Taiwan Institute of Engineering and Technology Chitkara UniversityChandigarh140401India

1 Introduction onMultimodal Learning in Image Processing IP(Image processing),as a classical research domain in computer application technology,has been researched for *** is one of the most important research directions in computer vision,which is the basis for many current hotspots such as intelligent transportation/education/industry,*** image processing is the strongest link for AI(artificial intelligence)applying to real world application,it has been a challenging research field with the development of AI,from DNN(deep convolutional network),Attention/LSTM(long-short term memory),to Transformer/Diffusion/Mamba based GAI(generated AI)models,e.g.,GPT and Sora[1].Today,the description ability of single-model feature limits the performance of image *** comprehensive description of the image is required to match the computational performance of current large scale models.

关键词： Image computer LSTM

来源：评论

学校读者我要写书评

暂无评论

Portfolio selection based on market states acquired via price and non-price data

引用

Discover Data 2025年第1期3卷 1-21页

作者： Chung, Andy Tanaka-Ishii, Kumiko Yairi, Takehisa Department of Advanced Interdisciplinary Studies Graduate School of Engineering The University of Tokyo Tokyo Japan Department of Computer Science and Engineering School of Fundamental Science and Engineering Waseda University Tokyo Japan

Financial markets exhibit quasi-stationary patterns, known as market states, which previous studies have identified through the correlation structure of asset returns using clustering techniques. In this paper, we propose a novel approach to the portfolio selection problem by leveraging market states through an unsupervised method that extends beyond conventional correlation analysis. We introduce market distance metrics for both price and non-price data to estimate market states. Our proposed model allocates assets based on portfolio choices optimized within specified market states. In addition to using asset return correlations, we experiment with two non-price data sources: (1) a text-based market distance metric derived from Federal Open Market Committee (FOMC) policy statements, and (2) the correlation of multivariate time series search volumes from Google Trends. Using a multi-asset portfolio encompassing major U.S. asset classes, we trained our model from 2016 to 2019 and evaluated its out-of-sample performance from 2020 to 2023. Our findings demonstrate the superiority of our ensemble solution, incorporating multiple market distance metrics with price and non-price data, over established baselines with statistically significant results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer

High-Fidelity Document Stain Removal via A Large-Scale Real-...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Li, Mingxian Sun, Hao Lei, Yingtie Zhang, Xiaofeng Dong, Yihang Zhou, Yilin Li, Zimeng Chen, Xuhang School of Computer Science and Engineering Huizhou University China The Ohio State University Department of Computer Science and Engineering United States School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China School of Electronic and Communication Engineering Shenzhen Polytechnic University China

ISBN: (纸本)9798331510831

Document images are often degraded by various stains, significantly impacting their readability and hindering downstream applications such as document digitization and analysis. The absence of a comprehensive stained document dataset has limited the effectiveness of existing document enhancement methods in removing stains while preserving fine-grained details. To address this challenge, we construct StainDoc, the first large-scale, high-resolution (2145 x 2245) dataset specifically designed for document stain removal. StainDoc comprises over 5,000 pairs of stained and clean document images across multiple scenes. This dataset encompasses a diverse range of stain types, severities, and document backgrounds, facilitating robust training and evaluation of document stain removal algorithms. Furthermore, we propose StainRestorer, a Transformer-based document stain removal approach. StainRestorer employs a memory-augmented Transformer architecture that captures hierarchical stain representations at part, instance, and semantic levels via the DocMemory module. The Stain Removal Transformer (SRTransformer) leverages these feature representations through a dual attention mechanism: an enhanced spatial attention with an expanded receptive field, and a channel attention captures channel-wise feature importance. This combination enables precise stain removal while preserving document content integrity. Extensive experiments demonstrate StainRestorer's superior performance over state-of-the-art methods on the Stain-Doc dataset and its variants *** and ***, establishing a new benchmark for document stain removal. Our work highlights the potential of memory-augmented Transformers for this task and contributes a valuable dataset to advance future research. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-modal consistent loss diffusion model for Sentinel-3 single image super resolution

引用

Neural Computing and Applications 2025年第10期37卷 7121-7143页

作者： Ibañez, Damian Fernandez-Beltran, Ruben Pla, Filiberto Yokoya, Naoto Xia, Junshi Institute of New Imaging Technologies University Jaume I Castellon de la Plana12071 Spain Department of Computer Science and Systems University of Murcia Murcia30100 Spain Graduate School of Frontier Sciences The University of Tokyo Chiba277-8561 Japan Center for Advanced Intelligence Project RIKEN Tokyo Japan

In the context of Earth observation, the trade-off between spatial, spectral, and temporal resolution often limits the versatility of remote sensing images in many important applications. In response, this paper introduces a novel deep learning diffusion model, specifically tailored to improve the spatial resolution of the optical products acquired by the Sentinel-3 (S3) satellite. Our framework employs a diffusion probabilistic model, benefiting from the higher spatial resolution of the Sentinel-2 satellite during training via a new multi-modal loss formulation. This ensures consistency with the original S3 images while enhancing the spatial details. Two distinct conditional low-resolution encoders were experimented with, providing insights into their respective contributions to the diffusion process. The efficacy of the proposed model is demonstrated through extensive ablation studies and comparisons with state-of-the-art methods, using both synthetic and real S3 products. The findings indicate that our model successfully improves spatial resolution while maintaining the integrity of the spectral information, contributing to the field of remote sensing single-image super-resolution. © The Author(s) 2025.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

A Music Recommender System to Identify the Emotional State of a Person Using Machine Learning Algorithms

A Music Recommender System to Identify the Emotional State o...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Muruganantham A C. Malarvizhi Divya Vahini. S D. Saranya A. Uthiramoorthy Department of Computer Science (PG) Kristu Jayanti College Bengaluru Karnataka India Department of Computer Science PSG Institute of Advanced Studies Coimbatore India Department of Computer Applications Dr.Mahalingam College of Engineering and Technology Pollachi Tamil Nadu India Department of Information Technology Sri Eshwar College of Engineering Coimbatore Department of Computer Science Rathinam College of Arts and Science

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

In today's digital world, customized recommendation algorithms can improve user experiences in many different areas. Within the sphere of intelligent human-technology interaction, this paper specifically examines a music recommender system driven by machine learning algorithms. It figures out what mood users are in and can provide an appropriate response in real time. The system being propounded in this essay uses advanced technology in facial expression recognition. With the help of a webcam, it aims to accurately detect user emotions, including joy, sadness, and anger. Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN) and Support Vector Machines (SVM) have been employed to effectively classify people's mood and recommend an appropriate song. Our extensive tests and examinations show that CNN, RNN, and SVM models are all very good at guessing users' moods--with high precision, recall, F1-score, and accuracy percentages. Furthermore, in-depth analyses like confusion matrixes illuminate how well each model serves as an emotion recognizer. This study's findings are representative of future prospects in affective computing around the globe with major implications for intelligent recommendation systems to which it's important that the models are sensitive. In conclusion, the suggested Music Recommender System is something new for taking a more personal view: We can be as deeply entertained as the web allows us to be--make tailored entertainment paths in the digital era.

关键词： Support vector machines Emotion recognition Recurrent neural networks Machine learning algorithms Accuracy Mood Face recognition Computational modeling Convolutional neural networks Recommender systems

来源：评论

学校读者我要写书评

暂无评论

"Cause" is Mechanistic Narrative within Scientific Domains: An Ordinary Language Philosophical Critique of "Causal Machine Learning"

arXiv

引用

arXiv 2025年

作者： Kungurtsev, Vyacheslav Moore, Leonardo Christov Šír, Gustav Krutský, Martin Department of Computer Science Czech Technical University in Prague Czech Republic Institute of Advanced Consciousness Studies Los AngelesCA United States

Causal Learning has emerged as a major theme of research in statistics and machine learning in recent years, promising specific computational techniques to apply to datasets that reveal the true nature of cause and effect in a number of important domains. In this paper we consider the epistemology of recognizing true cause and effect phenomena. We apply the Ordinary Language method of engaging in thought exercises on the customary use of the word "cause", especially in scientific domains, to investigate valid semantics of reasoning about cause and effect. We recognize that the grammars of cause and effect are fundamentally distinct in form across scientific domains, yet they maintain a consistent and central function within every scientific paradigm. This function can best be described as the mechanism underlying fundamental forces of influence as considered prominent in the respective scientific domain. We demarcate 1) physics and engineering as domains wherein mathematical models are sufficient to comprehensively describe causality, 2) biology as introducing challenges of emergence while providing opportunities for showing consistent mechanisms across scale, and 3) the social sciences as introducing grander difficulties for establishing models of low prediction error but providing, through Hermeneutics, the potential for findings that are instrumentally useful, even if not predictively precise. We posit that definitive causal claims regarding a given phenomenon (writ large) can only come through an agglomeration of consistent evidence across multiple domains, such as statistical population-level observations, physiological and biochemical descriptions of underlying dynamics, etc. This presents important scientific and methodological questions as far as harmonizing between language games and emergence across scales. We highlight the role of epistemic hubris in the contemporary crisis of credibility in the sciences, for which causal learning as it is framed today se

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RADAR: Robust DRL-Based Resource Allocation Against Adversarial Attacks in Intelligent O-RAN

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Ergu, Yared Abera Nguyen, Van-Linh Department of Computer Science and Information Engineering Chiayi Taiwan Advanced Institute of Manufacturing with High-tech Innovations CCU Taiwan

The advent of open radio access networks (O-RAN) has introduced intelligent, flexible, and multi-vendor network ecosystems. While O-RAN's open interfaces and artificial intelligence (AI)-driven solutions offer improved performance, energy efficiency, and resource minimization for green networking, they also expose the system to new security vulnerabilities, particularly adversarial attacks. This paper presents a robust defense approach, termed RADAR, designed to secure deep reinforcement learning (DRL)-powered resource allocation mechanisms in O-RAN. RADAR is a multi-faceted defense framework that integrates adversarial input sanitization, proactive adversarial training, and adapted defensive distillation to counter policy infiltration attacks, gradient-based deceptive loss maximization, and signal perturbation injections into the O-CU via the O-DU in O-RAN. This study evaluates the effectiveness of RADAR not only against a novel attack variant - policy infiltration attack (PIA), which manipulates environmental parameters to disrupt allocation decisions, but also against well-known adversarial techniques such as the fast gradient sign method (FGSM) and projected gradient descent (PGD). Experimental results demonstrate that RADAR achieves significant recovery in user data rates across three network slices: 73.33% for eMBB, 64.71% for mMTC and 52.94% for uRLLC, outperforming the existing standalone approach. The findings highlight RADAR's effectiveness in mitigating adversarial attack techniques, underscoring its potential to secure AI-driven core functions in intelligent O-RAN. © 2025 IEEE.

关键词： Energy efficiency

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：