检索结果-内蒙古大学图书馆

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 528-536页

作者： Chaolu Meng Yunyun Shi Quan Zou Ruijun Liu Colledge of Computer and Information Engineering Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry Inner Mongolia Agricultural University Hohhot China Colledge of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu China School of Software Beihang University Beijing China

The identification of protein sequences depends on the effective selection of an optimized set of features. Traditional algorithms prioritize global feature importance, often overshadowing the significance of local metrics. Addressing this imbalance, we introduce an innovative algorithm that fuses feature ranking with an advanced weight quantization technique. This algorithm unfolds in two pivotal stages: initially, it generates a weighted directed graph based on normal distribution metrics; subsequently, it employs the HodgeRank algorithm to amalgamate these rankings. Specifically, the algorithm evaluates feature score normality by employing z-scores for skewness and kurtosis, resulting in a graph that quantitatively reflects both local and global feature contributions. HodgeRank then translates this graph into a Laplacian matrix, enabling the calculation of a comprehensive scoring function for each feature. We refine the initial rankings by incorporating weights during the integration phase, capturing a holistic view of feature significance. The proposed method, termed HodgeRankWeight, showcases superior performance, achieving accuracy rates of 87.02%, 92.84%, and 74.51% across different datasets. In head-to-head comparisons, HodgeRankWeight outstripped existing models, achieving an overall accuracy of 82.6923% and setting a new benchmark for precision in protein sequence identification. We also offer a complimentary web server for related research.

关键词： Sorting Directed graphs Kurtosis Gaussian distribution Feature extraction Measurement Matrix decomposition Bioinformatics Vectors Quantization (signal)

来源：评论

学校读者我要写书评

暂无评论

SAHSD: Enhancing Hate Speech Detection in LLM-Powered Web Applications via Sentiment Analysis and Few-Shot Learning 34

SAHSD: Enhancing Hate Speech Detection in LLM-Powered Web Ap...

引用

34th ACM Web Conference, WWW 2025

作者： Wang, Yulong Li, Hong Wei, Ni State Key Laboratory of Networking and Switching Technology School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China College of Big Data and Information Engineering Guizhou University Guiyang China School of Communication Science and Engineering Fudan University Shanghai China

ISBN: (纸本)9798400712746

As large language models (LLMs) increasingly power web applications, including social networks, the challenge of moderating hate speech has become a critical concern for the Web. These LLM-powered applications, while offering near-human interaction capabilities, are vulnerable to harmful or biased content due to imperfect training data scraped from the Web. Current hate speech detection methods often struggle with limited annotated data, especially for real-time moderation on these platforms. This paper introduces Sentiment-Aided Hate Speech Detection (SAHSD), a novel approach designed to enhance hate speech detection specifically in LLM-powered web applications. By treating hate speech detection as a few-shot learning task, SAHSD utilizes sentiment analysis to refine pre-trained language models (LM) for improved accuracy in recognizing harmful content. SAHSD first employs publicly available sentiment datasets to train a sentiment analysis model, which is then fine-tuned by merging sentiment prompts with hate speech prompts, enabling efficient and accurate detection even with limited training samples. The effectiveness of SAHSD is demonstrated through experiments on widely used web-sourced datasets like SBIC and HateXplain. SAHSD achieves an exceptional F1-score of 0.99 with only 64 training samples and outperforms advanced techniques such as ToKen, MRP, and HARE, with significant improvements of 33% on SBIC and 95% on HateXplain. SAHSD surpasses GPT-4 in generalization performance across multiple datasets, showing an 8% improvement when trained on equal-sized samples. These results underscore SAHSD’s potential to enhance content moderation in LLM-driven web platforms, contributing to a safer, more inclusive and accountable Web ecosystem. © 2025 Copyright held by the owner/author(s).

关键词： Hate Speech Large Language Model Machine Learning Security

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cross-Dimensional Transformer for long-term wellhead pressure forecasting during hydraulic fracturing

引用

engineering Applications of Artificial Intelligence 2025年 154卷

作者： Zhang, Tao Zhong, Yuan Zhou, Jing Li, Ping Gong, Jie School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation Southwest Petroleum University Chengdu610500 China

Observational analysis of wellhead pressure variations is crucial for detecting fracturing fluid leakage and assessing wellbore integrity during fracturing operations. Accurately predicting multi-time step pressure changes is essential for enhancing oil and gas extraction efficiency while ensuring wellhead safety. This paper proposes the Enhanced Cross-Dimensional Transformer (ECformer), a time series model that predicts long-term wellhead pressure by capturing time-variable dependencies, the cross-dimensional information, in fracturing operation data. ECformer employs Patch Generation to segment local data regions, enabling the Cross-Dimensional Enhancement Structure to capture latent time-variable relationships. Patch Shuffle and Multi-Scale Fusion further refine temporal extraction and feature-level analysis at the patch scale, thereby enhancing prediction accuracy. Experimental results show that ECformer outperforms the newer Near Time Transformer (NTformer) and Patch Time Series Transformer (PatchTST) in long-term wellhead pressure prediction, reducing the Mean Squared Error (MSE) by 3.5% and 33.4% within 90 s and by 6.6% and 38.5% within 120 s about the average of multiple data sets. ECformer shows higher accuracy in long-step predictions, providing greater potential for future proactive risk prevention. © 2025

关键词： Leak detection

来源：评论

学校读者我要写书评

暂无评论

A segmentation method for oral CBCT image based on Segment Anything Model and semi-supervised teacher-student model

引用

Medical Physics 2025年 2025 May 7页

作者： Gan, Jianhong Kang, Runqing Deng, Xun He, Tongli Yu, Nie Gan, Yuling Wei, Peiyang Chen, Xiangyi Peng, Xiaoli Li, Zhibin College of Software Engineering Chengdu University of Information Technology Chengdu China Sichuan Key Laboratory of Software Automatic Generation and Intelligent Service Chengdu University of Information Technology Chengdu China Key Laboratory of Meteorological Software China Meteorological Administration Chengdu China Dazhou Key Laboratory of Government Data Security Sichuan University of Arts and Science Dazhou China College of Applied Mathematics Chengdu University of Information Technology Chengdu China The Fifth Research Institute of Telecommunications Technology Chengdu China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Xinjiang Technical Institute of Physics &Chemistry Chinese Academy of Sciences Urumqi China College of Instrumentation and Electrical Engineering Jilin University Changchun China

Background: Accurate segmentation of oral cone beam computed tomography (CBCT) images is essential for research and clinical diagnosis. However, irregular and blurred tooth boundaries in CBCT images complicate the labeling of oral tissues, and insufficient labeled samples further limit the generalization ability of segmentation models. The Segment Anything Model (SAM) demonstrates strong generalization and segmentation accuracy across diverse tasks as a vision foundation model. The Teacher-Student (TS) model has proven effective in semi-supervised learning approaches. Purpose: To accurately segment various parts of oral CBCT, such as enamel, pulp, bone, blood vessels, air, etc., an improved segmentation method named SAM-TS is proposed, which combines SAM with the TS model. SAM-TS leverages Low-Rank Adaptation (LoRA) to fine-tune the SAM model on oral CBCT images with fewer parameters. Methods: To efficiently utilize numerous unlabeled images for training models, the LoRA strategy is improved to fine-tune the SAM. The fine-tuned SAM and teacher models collaboratively generate pseudo-labels on unlabeled images, which are filtered and utilized to train the student model. Then, a data augmentation-based Mean Intersection over Union (MIoU) method is proposed to filter out unreliable or spurious pseudo-labels. Finally, the Exponential Moving Average (EMA) method is used to transfer the student model's parameters to the teacher model. After repeating this process, the final optimized student model for segmentation is obtained. The experimental results demonstrate that incorporating unlabeled data into model training through SAM-TS significantly enhances the model's generalization ability and segmentation accuracy. Results: Compared to the baseline algorithm, the proposed method achieves an overall improvement of over 6.48% in MIoU. In the tooth segmentation task, the minimum MIoU and maximum MIoU increased by at least 10% and 27.32%, respectively. In the bone segmentation

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Leapfrog Polymorphic Neural Ordinary Differential Equation

引用

IEEE Signal Processing Letters 2025年 32卷 2139-2143页

作者： Zhang, Xiao Wei, Wei Zhang, Zhen Zhang, Lei Northwestern Polytechnical University School of Software Xi'an710072 China Northwestern Polytechnical University Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Xi'an710072 China Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Xi'an710072 China The University of Adelaide school of computer science AdelaideSA5005 Australia

Neural Ordinary Differential Equations (NODEs) revolutionize the way we view residual networks as solvers for initial value problems (IVPs), with layer depth serving as the time step. In this study, we propose a more efficient extension of NODEs called Leap-Frog Polymorphic Neural ODEs (LF-NODEs). LF-NODEs introduce the leap-frog updating scheme, breaking free from the specific structure of time-evolving mixtures of multiple dynamical systems. In each time step (corresponding to each residual network layer), LF-NODEs integrate the features of multiple dynamical systems (residual network layers) by employing time-variant weights from different dynamical systems. Our LF-NODEs not only overcome the limitations in the representation power of individual residual networks but also provide a more flexible and effective structure for residual networks based on multiple dynamical systems. The efficiency of the leap-frog updating scheme is theoretically derived and demonstrated. Furthermore, we expand the model by incorporating a multi-scale approach (LF-MSNODEs) to achieve even more accurate model representations. Empirical results showcase the improvements provided by our proposed methods in 2D concentric spheres task, irregularly sampled time series prediction, and classification tasks. Additionally, the results provide empirical evidence that the learned feature space enhances system efficiency with fewer parameters and function evaluations compared to the baseline methods. © 1994-2012 IEEE.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multi-Scale Receptive Fields and Foreground Focus Mechanism

arXiv

引用

arXiv 2025年

作者： Lei, Yujie Sun, Wenjie Jia, Sen Li, Qingquan Zhang, Jie College of Information and Electrical Engineering China Agricultural University Beijing100083 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Key Laboratory of Spatial Smart Sensing and Services Shenzhen University Shenzhen518060 China Key Laboratory of Agricultural Machinery Monitoring and Big Data Applications Ministry of Agriculture and Rural Affairs Beijing100083 China

Challenges in remote sensing object detection (RSOD), such as high inter-class similarity, imbalanced foreground-background distribution, and the small size of objects in remote sensing images significantly hinder detection accuracy. Moreover, the trade-off between model accuracy and computational complexity poses additional constraints on the application of RSOD algorithms. To address these issues, this study proposes an efficient and lightweight RSOD algorithm integrating multi-scale receptive fields and foreground focus mechanism, named RFWNet. Specifically, we proposed a lightweight backbone network Receptive Field Adaptive Selection Network (RFASNet), leveraging the rich context information of remote sensing images to enhance class separability. Additionally, we developed a Foreground Background Separation Module (FBSM) consisting of a background redundant information filtering module and a foreground information enhancement module to emphasize critical regions within images while filtering redundant background information. Finally, we designed a loss function, the Weighted CIoU-Wasserstein (WCW) loss, which weights the IoU-based loss by using the Normalized Wasserstein Distance to mitigate model sensitivity to small object position deviations. Experimental evaluations on the DOTA V1.0 and NWPU VHR-10 datasets demonstrate that RFWNet achieves advanced performance with 6.0M parameters and can achieves 52 FPS. © 2025, CC BY.

关键词： Information filtering

来源：评论

学校读者我要写书评

暂无评论

GIRP: Energy-Efficient QoS-Oriented Microservice Resource Provisioning via Multi-Objective Multi-Task Reinforcement Learning

引用

IEEE Transactions on Mobile Computing 2025年

作者： Yuan, Honggang Wang, Ting Fu, Min Shi, Yuanming East China Normal University MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore ShanghaiTech University School of Information Science and Technology Shanghai201210 China

Microservice architecture has revolutionized web service development by facilitating loosely coupled and independently developable components distributed as containers or virtual machines. While existing studies emphasize end-to-end latency, this paper investigates energy-efficient quality-of-service (QoS)-oriented microservice provisioning, focusing on both QoS satisfaction and power consumption (PC) conservation. We propose the Green and Intelligent Resource Provision (GIRP) architecture, integrating a data-driven energy-latency-aware resource allocation and scheduling manager to balance latency and PC. To reconcile the trade-offs involved, a dual-objective optimization problem is formulated to minimize latency and energy use by selecting proper servers, allocating CPU cores, and determining service replicas. To address challenges with discrete variables, dual objectives, and implicit mappings, we leverage a model-free deep deterministic policy gradient-based reinforcement learning algorithm. Specifically, we develop a multi-task agent via the Multi-gate Mixture-of-Experts model to simultaneously make two separate actions regarding CPU core numbers and service replica numbers, followed by a single-task agent to determine service scheduling. Extensive experiments on the DeathStarBenchmark testbed validate GIRP's effectiveness, demonstrating approximately 52% resource savings and a 43% reduction in PC compared to leading methods like Sinan, Firm, and heuristic-based algorithms. These results highlight GIRP's capability to optimize microservice orchestration by balancing end-to-end latency and power efficiency. © 2025 IEEE. All rights reserved.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Covert Communication in Underlay Cognitive Radio Networks with Energy Harvesting

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Fan, Hongbin Yang, Weiwei Pan, Gaofeng Shi, Hui Rong, Chuanzhen Army Engineering University of PLA College of Communications Engineering Nanjing210007 China Xiangnan University College of Computer and Artificial Intelligence Chenzhou423000 China Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software Guilin541004 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China

This paper examines covert communication in underlay cognitive radio networks (CRNs) with energy harvesting (EH), in which considers two scenarios: 1) with perfect channel state information (CSI) of the link from the secondary source (SS) to the primary receiver (PR) at Willie, 2) with statistical CSI of the SS-PR link at Willie. The closed-form expressions for Willie’s detection error probability, the average minimum detection error probability, the transmission outage probability, and the maximum effective covert rate under both cases are derived and analyzed. The maximum effective covert rate is obtained by optimizing the maximum jamming power of the primary transmitter (PT). The numerical results demonstrate that the combined effect of energy conversion efficiency and time allocation ratio of EH, in conjunction with the maximum jamming power of PT, provides a positive effective covert rate in the secondary network. Furthermore, it is evident that the maximum effective covert rate in the secondary network is greater when Willie has access to the perfect CSI of the SS-PR link than that when Willie only has access to the statistical CSI of the SS-PR link. © 2025 IEEE. All rights reserved.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

InsTaG: Learning Personalized 3D Talking Head from Few-Second Video

arXiv

引用

arXiv 2025年

作者： Li, Jiahe Zhang, Jiawei Bai, Xiao Zheng, Jin Zhou, Jun Gu, Lin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University China School of Information and Communication Technology Griffith University Australia RIKEN AIP Japan The University of Tokyo Japan

Despite exhibiting impressive performance in synthesizing lifelike personalized 3D talking heads, prevailing methods based on radiance fields suffer from high demands for training data and time for each new identity. This paper introduces InsTaG, a 3D talking head synthesis framework that allows a fast learning of realistic personalized 3D talking head from few training data. Built upon a lightweight 3DGS person-specific synthesizer with universal motion priors, InsTaG achieves high-quality and fast adaptation while preserving high-level personalization and efficiency. As preparation, we first propose an Identity-Free Pre-training strategy that enables the pre-training of the person-specific model and encourages the collection of universal motion priors from long-video data corpus. To fully exploit the universal motion priors to learn an unseen new identity, we then present a Motion-Aligned Adaptation strategy to adaptively align the target head to the pre-trained field, and constrain a robust dynamic head structure under few training data. Experiments demonstrate our outstanding performance and efficiency under various data scenarios to render high-quality personalized talking heads. Project page: https://***/InsTaG/ . Copyright © 2025, The Authors. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

AD-Det: Boosting Object Detection in UAV Images with Focused Small Objects and Balanced Tail Classes

引用

Remote Sensing 2025年第9期17卷 1556-1556页

作者： Li, Zhenteng Lian, Sheng Pan, Dengfeng Wang, Youlin Liu, Wei College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350002 China Key Laboratory of Intelligent Metro of Universities in Fujian Fuzhou350108 China School of Software and Information Engineering East China Jiaotong University Nanchang330013 China

Object detection in unmanned aerial vehicle (UAV) images poses significant challenges due to complex scale variations and class imbalance among objects. Existing methods often address these challenges separately, overlooking the intricate nature of UAV images and the potential synergy between them. In response, this paper proposes AD-Det, a novel framework employing a coherent coarse-to-fine strategy that seamlessly integrates two pivotal components: adaptive small object enhancement (ASOE) and dynamic class-balanced copy–paste (DCC). ASOE utilizes a high-resolution feature map to identify and cluster regions containing small objects. These regions are subsequently enlarged and processed by a fine-grained detector. On the other hand, DCC conducts object-level resampling by dynamically pasting tail classes around the cluster centers obtained by ASOE, maintaining a dynamic memory bank for each tail class. This approach enables AD-Det to not only extract regions with small objects for precise detection but also dynamically perform reasonable resampling for tail-class objects. Consequently, AD-Det enhances the overall detection performance by addressing the challenges of scale variations and class imbalance in UAV images through a synergistic and adaptive framework. We extensively evaluate our approach on two public datasets, i.e., VisDrone and UAVDT, and demonstrate that AD-Det significantly outperforms existing competitive alternatives. Notably, AD-Det achieves a (Formula presented.) average precision (AP) on the VisDrone dataset, surpassing its counterparts by at least (Formula presented.). © 2025 by the authors.

关键词： Vehicle detection

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：