检索结果-内蒙古大学图书馆

Information Technology (ACIT)

作者： Mouhamed Laid Abimouloud Khaled Bensid Mohamed Elleuch Oussama Aiadi Monji Kherallah National Engineering School of Sfax University of Sfax Sfax Tunisia Advanced Technologies for Environment and Smart Cities (ATES Unit) University of Sfax Sfax Tunisia Laboratory of Electrical Engineering LAGE University of KASDI Merbah Ouargla Ouargla Algeria National School of Computer Science (ENSI) University of Manouba Manouba Tunisia Artifcial Intelligence and Information Technology Laboratory (LINATI) University of KASDI Merbah Ouargla Ouargla Algeria Faculty of Sciences University of Sfax Sfax Tunisia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Kidney tumors are commonly diagnosed through computed tomography (CT) imaging, making accurate classification into normal or Cyst categories essential for effective treatment planning. In this study, we propose kidney tumor classification using knowledge distillation between a Token vision transformer (teacher model) and a Vision transformer (student model). The teacher model employs a token-based learning mechanism to capture spatially important regions of the CT images, which are then distilled into the student model to enhance its performance while maintaining computational efficiency. Our method processes CT radiography images by partitioning them into non-overlapping patches that are fed into transformer encoder layers. The teacher model, equipped with a Token Learner module, extracts salient tokens, while the student model is trained using both true labels and softened teacher predictions through temperature-scaled softmax. This knowledge distillation framework is tested on a binary classification task to distinguish normal from cyst kidney tumors. The results indicate that the student model achieves comparable accuracy to the teacher model, despite having fewer parameters and faster inference times. Specifically, the student model achieves a peak accuracy of 95.96% and a recall of 95.56% at α =0.1 and temperature T =9. These findings show that knowledge distillation allows the student model to perform efficiently, delivering high classification accuracy with reduced computational resources. This approach presents a viable solution for real-time medical image classification in resource-constrained settings and demonstrates potential applicability to other medical imaging tasks.

关键词： Radiography computer vision Accuracy Computational modeling Computed tomography Predictive models Transformers Computational efficiency Kidney Tumors

来源：评论

学校读者我要写书评

暂无评论

Unsupervised detection of small hyperreflective features in ultrahigh resolution optical coherence tomography

arXiv

引用

arXiv 2023年

作者： Reimann, Marcel Won, Jungeun Takahashi, Hiroyuki Yaghy, Antonio Hwang, Yunchan Ploner, Stefan Lin, Junhong Girgis, Jessica Lam, Kenneth Chen, Siyu Waheed, Nadia K. Maier, Andreas Fujimoto, James G. Department of Electrical Engineering and Computer Science Research Laboratory of Electronics Massachusetts Institute of Technology United States Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Germany New England Eye Center Tufts Medical Center United States

Recent advances in optical coherence tomography such as the development of high speed ultrahigh resolution scanners and corresponding signal processing techniques may reveal new potential biomarkers in retinal diseases. Newly visible features are, for example, small hyperreflective specks in age-related macular degeneration. Identifying these new markers is crucial to investigate potential association with disease progression and treatment outcomes. Therefore, it is necessary to reliably detect these features in 3D volumetric scans. Because manual labeling of entire volumes is infeasible a need for automatic detection arises. Labeled datasets are often not publicly available and there are usually large variations in scan protocols and scanner types. Thus, this work focuses on an unsupervised approach that is based on local peak-detection and random walker segmentation to detect small features on each B-scan of the volume. © 2023, CC BY-NC-SA.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

ECG abnormality detection Based on Multi-domain combination features and LSTM

ECG abnormality detection Based on Multi-domain combination ...

引用

International Conference on computer engineering and Applications (ICCEA)

作者： Qingshan Liu Cuiyun Gao Yang Zhao Songqun Huang Yuqing Zhang Zhonghai Lu Power Quality Analysis and Load Detection Technology Laboratory Anhui Jianzhu University Hefei China Department of Cardiovasology Changhai Hospital Second Military Medical University Shanghai China KTH Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm Sweden

Most scholars use fixed-length sample to ECG abnormalities based on MIT-BIH dataset, which lead to information loss. To address this problem, this paper proposes a method for ECG abnormality detection based on TSH-L method. The TSH-L method include:(1) Use the 3R ECG sample selection method to select ECG samples.(2) Extract multi-domain combination features including time-domain features, frequency domain features and time-frequency domain features.(3) LSTM is used for classification, and the algorithm is trained and tested based on the MIT-BIH dataset, obtain relatively optimal features as spliced normalized fusion features including kurtosis, skewness and RR interval time domain features, STFT-based sub-band spectrum features, and harmonic ratio features. Experiments show that: TSH-L method proposed in the paper has a high accuracy of 97.74% for the detection of ECG abnormalities of MIT-BIH dataset. The method 3R-TSH-L proposed in this paper is expected to be widely used in family-oriented healthcare.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ferroelectric domain nucleation and switching pathways in hafnium oxide.

arXiv

引用

arXiv 2023年

作者： Sebastian Calderon, V. Jaszewski, Samantha T. Kelley, Kyle P. Ihlefeld, Jon F. Dickey, Elizabeth Department of Materials Science and Engineering Carnegie Mellon University PittsburghPA15213 United States Department of Materials Science and Engineering University of Virginia CharlottesvilleVA22904 United States Center for Nanophase Materials Sciences Oak Ridge National Laboratory Oak RidgeTN37831 United States Charles L. Brown Department of Electrical and Computer Engineering CharlottesvilleVA22904 United States

Nanoscale ferroelectrics that can be integrated into microelectronic fabrication processes are highly desirable for low-power computing and non-volatile memory devices. However, scalable novel ferroelectric materials, such as hafnium oxide (HfO2), remain in a state of development, and a clear understanding of the effects of relevant compositional and processing parameters to control their ferroelectric properties and the actual polarization switching mechanisms are still under investigation. One key fundamental knowledge gap is the polarization switching pathway in ferroelectric hafnia. To further our fundamental understanding of domain nucleation and switching, we have studied polarization switching pathways in HfO2-x thin films in real-time at the atomic scale using transmission electron microscopy. We employed differential phase contrast imaging that allows for the acquisition of both hafnium and oxygen atomic column signals and facilitates the observation of relative movement of atomic columns between both sublattices. Our results demonstrate that the switching pathway involves a transient tetragonal-like local structure, as oxygen ions shift in locations and remain within their parent hafnium polyhedra. © 2023, CC BY.

关键词： Hafnium oxides

来源：评论

学校读者我要写书评

暂无评论

Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling Under Data Governance

SSRN

引用

SSRN 2023年

作者： Qin, Zhaoming Dong, Nanqing Liu, Di Cao, Junwei Automatic Control Laboratory EPFL Lausanne1015 Switzerland Department of Computer Science University of Oxford OxfordOX1 3QD United Kingdom Department of Electrical Engineering Tsinghua University Beijing100084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

As a data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving cooperative residential load scheduling problems. In a simplified scenario, centralized training, the most common paradigm for MARL, precludes large-scale deployment of MARL in communication-constrained cloud-edge environments. As a remedy, distributed training shows unparalleled advantages in real-life application scenarios compared with its centralized counterpart. However, distributed training still faces the challenge of system scalability, e.g., the high communication burden during coordinating individual agents, and needs to comply with data governance in terms of privacy. In this work, we propose a novel MARL solution to address these two practical issues. The proposed solution is based on actor-critic methods, where the global critic is a learned function of individual critics computed solely based on local observations of residences. In this way, the private data of residences is preserved completely and the communication cost is reduced significantly. The simulation experiments demonstrate that the proposed framework can achieve comparable performance to the state-of-the-art actor-critic framework without data governance and communication constraints. © 2023, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A transfer learning based model for brain tumor detection using magnetic resonance imaging

引用

AIP Conference Proceedings 2025年第1期3224卷

作者： Saurabh Srivastava Tasneem Ahmed Rajeev Kumar Amit Saxena Department of Computer Science & Engineering Moradabad Institute of Technology Moradabad India Advanced Computing and Research Laboratory Dept. of Computer Application Integral University Lucknow India

Rapid and uncontrolled proliferation of cells is the cause of brain tumors. If treatment is not carried out early, death can occur. A major challenge in detecting a brain tumor is that it originates from variations in size, shape, and location. Since tumor cells are diverse, it might be difficult for radiologists to classify brain tumors, which are malignant diseases. The overall survival of patients, treatment planning, and risk factor identification depend on robust and accurate tumor classification and prediction. In the medical field, deep learning (DL) and machine learning (ML) are often employed to diagnose illnesses. Various tools have been developed that are used to diagnose different diseases such as heart disease, lung cancer, and many more. In this study, a DL-based transfer learning technique has been used to build a model that can easily identify whether a patient is suffering from a brain tumor or not. Brain tumors have been categorized into four types of categories based on the characteristics of the tumor. Patients who are suffering from the first and second categories of tumors can be saved by treatments that include surgery, radiation therapy, and chemotherapy. The third and fourth categories of tumors are more dangerous because these categories of tumors spread very fast, so if it is diagnosed early stage then the patient can be saved or increase the patient’s life span. Glioma, Meningioma, and Pituitary are a dangerous form of tumors, and the survival rate of patients who are suffering from these is very low. The developed system can predict that a patient is suffering from a brain tumor or not using MRI, and also predict the type of tumor such as Glioma, Meningioma, and Pituitary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PFS3F: Probabilistic Fusion of Superpixel-wise and Semantic-aware Structural Features for Hyperspectral Image Classification

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhang, Ying Duan, Puhong Liang, Lianhui Kang, Xudong Li, Jun Plaza, Antonio Hunan University of Technology College of Railway Transportation Zhuzhou412007 China Hunan University School of Robotics Changsha410082 China Guangxi University School of Electrical Engineering Nanning530004 China China University of Geosciences Hubei Key Laboratory of Intelligent Geo-Information Processing the School of Computer Science Wuhan430078 China Hyperspectral Computing Laboratory Department of Technology of Computers and Communications Escuela Politecnica University of Extremadura CaceresE-10071 Spain

Processing high-dimensional data cubes and developing high-performance classifiers are core objectives in the field of hyperspectral image classification (HSIC). Superpixel-based methods are widely used in HSIC due to their efficacy in reducing redundant information and enhancing local features. However, imprecise segmentation, especially in complex structures and textures of hyperspectral images (HSIs), may lead to inconsistencies in the regions extracted by superpixels and the boundaries between different ground objects. Such inconsistencies significantly degrade the classification performance of HSIs. Alternatively, when parameter settings are inaccurate, edge-aware feature extraction methods often introduce sharpening artifacts at the image boundaries, resulting in a decrease in classification accuracy. To effectively address these challenges, we propose a novel probabilistic fusion method for HSIC. This method consists of the following stages. First, spatial information is extracted by a multiscale superpixel segmentation method and then probabilistically optimized by the extended random walk (ERW) method. Next, semantic-aware structural features (S2Fs) are extracted along with edge information of different objects. Lastly, a probabilistic framework is proposed to fuse the class probabilities of superpixel-based spatial information and semantic-aware structural features. Experimental results on three real datasets show state-of-the-art classification performance, even with limited training sets. ©1991-2012 IEEE.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

L-SPEX: LOCALIZED TARGET SPEAKER EXTRACTION

arXiv

引用

arXiv 2022年

作者： Ge, Meng Xu, Chenglin Wang, Longbiao Chng, Eng Siong Dang, Jianwu Li, Haizhou College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Kuaishou Technology Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Japan Advanced Institute of Science and Technology Ishikawa Japan The Chinese University of Hong Kong Shenzhen China

Speaker extraction aims to extract the target speaker’s voice from a multi-talker speech mixture given an auxiliary reference utterance. Recent studies show that speaker extraction benefits from the location or direction of the target speaker. However, these studies assume that the target speaker’s location is known in advance or detected by an extra visual cue, e.g., face image or video. In this paper, we propose an end-to-end localized target speaker extraction on pure speech cues, that is called L-SpEx. Specifically, we design a speaker localizer driven by the target speaker’s embedding to extract the spatial features, including direction-of-arrival (DOA) of the target speaker and beamforming output. Then, the spatial cues and target speaker’s embedding are both used to form a top-down auditory attention to the target speaker. Experiments on the multi-channel reverberant dataset called MCLibri2Mix show that our L-SpEx approach significantly outperforms the baseline system. Copyright © 2022, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data

SynFacePAD 2023: Competition on Face Presentation Attack Det...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Meiling Fang Marco Huber Julian Fierrez Raghavendra Ramachandra Naser Damer Alhasan Alkhaddour Maksim Kasantcev Vasiliy Pryadchenko Ziyuan Yang Huijie Huangfu Yingyu Chen Yi Zhang Yuchen Pan Junjun Jiang Xianming Liu Xianyun Sun Caiyong Wang Xingyu Liu Zhaohua Chang Guangzhe Zhao Juan Tapia Lazaro Gonzalez-Soler Carlos Aravena Daniel Schulz Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Biometrics and Data Pattern Analytics Lab Universidad Autonoma de Madrid Spain Norwegian University of Science and Technology (NTNU) Norway ID R&D Inc New York US School of Cyber Science and Engineering Sichuan University Chengdu China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture China Biometrics and Security Research Group Hochschule Darmstadt Darmstadt Germany I+D Vision Center Santiago Chile

This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition attracted a total of 8 participating teams with valid submissions from academia and industry. The competition aimed to motivate and attract solutions that target detecting face presentation attacks while considering synthetic-based training data motivated by privacy, legal and ethical concerns associated with personal data. To achieve that, the training data used by the participants was limited to synthetic data provided by the organizers. The submitted solutions presented innovations and novel approaches that led to outperforming the considered baseline in the investigated benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?

arXiv

引用

arXiv 2024年

作者： Pu, Yingming Huang, Liping Lin, Tao Chen, Hongyu Zhejiang University Zhejiang Hangzhou310030 China Department of Computer Science and Engineering School of Engineering Wetlake University Zhejiang Hangzhou310030 China Department of Chemistry School of Science Key Laboratory for Quantum Materials of Zhejiang Province Wetlake University Zhejiang Hangzhou310030 China Institute of Natural Sciences Westlake Institute for Advanced Study Hangzhou310024 China Research Center for Industries of the Future Wetlake University Zhejiang Hangzhou310030 China

With the rapid development of artificial intelligence (AI), large language models (LLMs) such as GPT-4 have garnered significant attention in the scientific community, demonstrating great potential in advancing scientific discovery. This progress raises a critical question: are these LLMs well-aligned with real-world physicochemical principles? Current evaluation strategies largely emphasize fact-based knowledge, such as material property prediction or name recognition, but they often lack an understanding of fundamental physicochemical mechanisms that require logical reasoning. To bridge this gap, our study developed a benchmark consisting of 775 multiple-choice questions focusing on the mechanisms of gold nanoparticle synthesis. By reflecting on existing evaluation metrics, we question whether a direct true-or-false assessment merely suggests conjecture. Hence, we propose a novel evaluation metric, the confidence-based score (c-score), which probes the output logits to derive the precise probability for the correct answer. Based on extensive experiments, our results show that in the context of gold nanoparticle synthesis, LLMs understand the underlying physicochemical mechanisms rather than relying on conjecture. This study underscores the potential of LLMs to grasp intrinsic scientific mechanisms and sets the stage for developing more reliable and effective AI tools across various scientific domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Gold nanoparticles

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：