检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： Jiarui Xing Nian Wu Kenneth C. Bilchick Frederick H. Epstein Miaomiao Zhang Department of Electrical and Computer Engineering University of Virginia USA School of Medicine University of Virginia Health System USA Department of Biomedical Engineering University of Virginia Health System USA Department of Computer Science University of Virginia USA

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Class imbalance in the medical image dataset is almost inherent due to the limited availability of clinical data for certain diseases and patient populations. Under-represented classes in the training set affect the classification task because the classifier tends to learn more from the majority classes, which are more common in the dataset and ignore data from the minority classes. To mitigate this issue, we propose a method to learn using two different convolutional neural network-based experts; such experts try to learn boundaries within the head classes, between the head and tail classes, and within the tail classes. During expert training, we integrate the MixUp regularization method to augment imbalanced data, employing distinct data sampling strategies for more effective mixing compared to random selection in traditional MixUp. During the inference phase, we combine the logits of the different experts based on their expertise in the corresponding classes. This way, we can improve the accuracy of the head and tail classes. Experiments using highly imbalanced and long-tailed datasets demonstrate the effectiveness of the suggested framework.

关键词： Training Accuracy Head Three-dimensional displays Tail Data models Task analysis

来源：评论

学校读者我要写书评

暂无评论

Advancing Hardware Implementation of Hyperdimensional Computing for Edge Intelligence

Advancing Hardware Implementation of Hyperdimensional Comput...

引用

IEEE International Conference on Artificial Intelligence Circuits and systems (AICAS)

作者： Eman Hassan Meriem Bettayeb Baker Mohammad Electrical Engineering and Computer Science Department System on Chip Lab Khalifa University of Science and Technology Abu Dhabi United Arab Emirates

ISBN: (数字)9798350383638

ISBN: (纸本)9798350383645

Hyperdimensional Computing (HDC) is a promising paradigm known for its energy efficiency and simplicity. Human brain functions inspire HDC, which operates in high-dimensional spaces with low-precision data, making it suitable for efficient machine-learning applications. This paper analyzes the State-of-the-Art (SOTA) significance and challenges of implementing HDC on diverse hardware platforms, including Application Specific Integrated Circuits (ASIC), Central Processing Units (CPU), and Field-Programmable Gate Arrays (FPGA), and explores its potential in In-Memory Computing (IMC). Also, the significance of hardware-accelerated Associative Memory (AM) in HDC systems is discussed, emphasizing its role in optimizing overall performance and efficiency.

关键词： Application specific integrated circuits Associative memory Circuits and systems Machine learning In-memory computing Hardware Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning Methods for Process Optimization in Electronic Packaging Processes 24

Application of Machine Learning Methods for Process Optimiza...

引用

24th European Microelectronics and Packaging Conference, EMPC 2023

作者： Niegisch, Corinna Haag, Sabine T. Braun, Tanja Hulck, Ole Schneider-Ramelow, Martin Robert Bosch GmbH Corporate Sector Research and Advance Engineering Renningen Germany Fraunhofer IZM Departement System Integration and Interconnection Technologies Berlin Germany Technical University Berlin Faculty IV Electrical Engineering and Computer Science Berlin Germany

ISBN: (纸本)9780956808691

Epoxy resins are commonly used as encapsulation materials in electronic packaging processes. Fluctuations in the materials lead to both changes in processability and to varying quality. Ideally, these variations should be identified, and measures taken as quickly as possible to reduce scrap parts and thus costs. A promising optimization approach for encapsulation processes are machine learning models, which have already shown good results in quality predictions, especially for injection molding. Subsequent quality measurements are avoided with good quality prediction models. With this type of models, not only predictions can be made, but also optimal parameter combinations can be found. In this paper, models for predicting quality criteria warpage and residual enthalpy of the epoxy molding compound were set up, trained and validated. Time series of in-situ sensors were used, from which relevant features were extracted and which, together with machine parameters, provide a dataset for prediction. The most promising prediction models are random forest regression and gradient boosting regression. They predict warpage with an accuracy of 90 % to 91 % and the residual enthalpy with an accuracy of 95 %. Subsequently, optimization models of the machine parameters were set up. All relevant target variables were considered in a cost function, through the minimization of which an optimal parameter set was found. The gradient boosted tree and Bayesian optimization were determined to be the most promising models, as they lead to the lowest values of the respective cost function. © 2023 IMAPS-Europe.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Multimodal Diffusion Bridge with Attention-Based SAR Fusion for Satellite Image Cloud Removal

arXiv

引用

arXiv 2025年

作者： Hu, Yuyang Lohit, Suhas Kamilov, Ulugbek S. Marks, Tim K. Department of Electrical & System Engineering Washington University St. Louis United States Departments of Computer Science & Engineering and Electrical & System Engineering Washington University St. Louis United States United States

Deep learning has achieved some success in addressing the challenge of cloud removal in optical satellite images, by fusing with synthetic aperture radar (SAR) images. Recently, diffusion models have emerged as powerful tools for cloud removal, delivering higher-quality estimation by sampling from cloud-free distributions, compared to earlier methods. However, diffusion models initiate sampling from pure Gaussian noise, which complicates the sampling trajectory and results in suboptimal performance. Also, current methods fall short in effectively fusing SAR and optical data. To address these limitations, we propose Diffusion Bridges for Cloud Removal, DB-CR, which directly bridges between the cloudy and cloud-free image distributions. In addition, we propose a novel multimodal diffusion bridge architecture with a two-branch backbone for multimodal image restoration, incorporating an efficient backbone and dedicated cross-modality fusion blocks to effectively extract and fuse features from synthetic aperture radar (SAR) and optical images. By formulating cloud removal as a diffusion-bridge problem and leveraging this tailored architecture, DB-CR achieves high-fidelity results while being computationally efficient. We evaluated DB-CR on the SEN12MS-CR cloud-removal dataset, demonstrating that it achieves state-of-the-art results. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Microwave assisted pyrolysis of biomass feedstock fundamentals and the effect of process parameters - A Review 4

Microwave assisted pyrolysis of biomass feedstock fundamenta...

引用

4th International Conference on Emerging Electrical Energy, Electronics and Computing, ICE4CT 2022

作者： Hamzah, Husam Talib Veluru, Sridevi Hasan, Hikmat Mohammed Abed, Hayder Yousif Mahdi, Husam Salah Hamdullah, Noor Abdulqader Tukarambai, M. Poiba, Venkata Rao Srikanth, R. Department of Chemical Engineering College of Engineering Andhra University Visakhapatnam India Department of Electrical Engineering Faculty of Engineering Ferdowsi University of Mashhad Mashhad Iran Department of Electrical Engineering University of Technology Baghdad Iraq Department of Computer Science and System Engineering College of Engineering Andhra University Visakhapatnam India Electrical and Computer Engineering School of Engineering and Architecture Altinbas University Istanbul Turkey Department of Chemical Engineering Anil Neerukonda Institute of Technology and Sciences Sangivalasa India

Globally, biomass usage as a supply of non-depletable resources materials used in the production of energy at their rawest state is an issue. Pyrolysis is a method of thermally treating biomass that as a consequence in the formation of liquid, products, both solid and gaseous. Elevated heating is required to transform the complicated composition of the biomass's underlying structure matrix into usable products. Heating with a microwave oven has the potential to become a competitive option. to more traditional methods of heating. Owing to its ease of operation and rapid heating rate, it has recently been widely employed in pyrolysis. The goals of this research are to found the principles of MW-assisted pyrolysis action and to examine some critical issues characteristics of operation that have an influence on the yield of a product. This procedure appears to be governed by a number of operational factors for instance, microwave power and temperature degree, the addition of microwave absorbers and their concentration, initial relative humidity, primary sweep gas flow rate/time spent in residence. © Published under licence by IOP Publishing Ltd.

关键词： Biomass

来源：评论

学校读者我要写书评

暂无评论

Automatic LPI Radar Waveform Recognition Using Vision Transformer

Automatic LPI Radar Waveform Recognition Using Vision Transf...

引用

2023 IEEE International Radar Conference, RADAR 2023

作者： Kim, Junseob Cho, Sunghwan Hwang, Sunil Choi, Yeongyoon Korea Military Academy Department of Electrical Engineering 01805 Korea Republic of Defense Acquisition Program Administration Maneuver System Coordination and Contract Team 13809 Korea Republic of Gist Department of Electrical Engineering and Computer Science 61005 Korea Republic of

ISBN: (纸本)9781665482783

This paper investigates the classification of low probability of intercept (LPI) radar signals by exploiting the intrinsic advantages of the Vision Transformer (ViT). Due to the characteristics of LPI radar signals, such as intrapulse modulation, wide frequency bands, and low transmission power, these signals are challenging to be detected and classified using traditional analytic methods. This has led to the adoption of various deep learning techniques to overcome these limitations. On the one hand, the ViT, originally developed for natural language processing, has demonstrated outstanding performance in computer vision by replacing the structure of the convolutional neural network (CNN) with the transformer, specifically leveraging self-attention. Therefore, this paper explores a method based on the ViT technique for classifying LPI signal images. The simulation results show that the proposed ViT method outperforms the traditional CNN method by 12.8% at -10dB SNR. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A four-dimensional model for the information storage/output of life

引用

Nano Research 2023年第2期16卷 2630-2634页

作者： Bo Song Lei Jiang Key Laboratory of Optical Technology and Instrument for Medicine Ministry of EducationShanghai Key Lab of Modern Optical SystemSchool of Optical-Electrical Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Key Laboratory of Bio-inspired Materials and Interfacial Science Technical Institute of Physics and ChemistryChinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China

A large amount of progress has achieved in neuroscience,however,there is still a lack of reasonable model for the storage/output(S/O)of life *** cyclical motion of cardio-and pulmonary-myocyte is a typical process of the life information S/O,while the opening and closing sites of Ca^(2+)ion channels during the motion can form a genetically programmed time-dependent three-dimensional(3D)*** phenomena indicate a strong correlation of the information S/O model of these myocytes with the time-sequence 3D ***,based on the time-dependent Ca^(2+)fluorescence imaging during the motion of cardio-and pulmonary-myocyte,here we suggest a four-dimensional(4D)code of information S/O model in cell and nervous *** from the fact of pulmonary myocyte motion able to be controlled by brain,it is deduced that the 4D code in brain has a role of controlling muscles through a pathway of the central nervous system,peripheral nervous system,neuromuscular junction,and muscle *** addition,we also suggested the 4D code of non-innate skill that can be programmed by the learning/training of a long time(~3 years),such as walking,writing,painting,sports,speech,singing,and ***,this 4D S/O model is reasonable for the ultralow energy consumption of life information transmission.

关键词： four-dimensional(4D)storage/output model life information cell nervous system

来源：评论

学校读者我要写书评

暂无评论

Customer Segmentation in the Retail Sector: A Data Analytics Approach 14

Customer Segmentation in the Retail Sector: A Data Analytics...

引用

14th International Conference on Intelligent Human-Machine systems and Cybernetics, IHMSC 2022

作者： Sahinbas, Kevser Catak, Ferhat Ozgur Istanbul Medipol University Department of Managament Information System Istanbul Turkey University of Stavanger Department of Electrical Engineering and Computer Science Rogaland Norway

ISBN: (数字)9781665461696

ISBN: (纸本)9781665461696

Data analytics techniques are widely used in customer segmentation, which groups objects according to the similarity difference on each object and provides a high level of homogeneity in the same cluster or a high level of heterogeneity between each group. In this study, the behavior of customers in the retail sector was analyzed using customer segmentation data mining methods such as OPTICS, BIRCH, Agglomerative Clustuering, K-Means and DBSCAN algithms. The aim of the study is to investigate different data analytics algorithms using a private textile and retail company that has an agreement with e-commerce sites and marketplaces. OPTICS, BIRCH, Agglomerative Clustuering, K-Means have shown almost same clustering results, DBSCAN has outperformed with 0.206086 Silhouette value. The purpose of this paper is to provide a proof of concept of how e-commerce data analytics can be used in customer segmentation. © 2022 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Large Model Collaborative Optimization Enhanced by Mobile Consumer Electronics Constructed Federated ML

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Bu, Chao Li, Jianlong Wang, Jinsong Tianjin University of Technology Key Laboratory of Computer Vision and System of Ministry of Education School of Computer Science and Engineering Tianjin300384 China Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology School of Computer Science and Engineering Tianjin300384 China

With the rapid development of internet of everything, current Mobile Consumer Electronics (MCEs) can support complex computing due to their specialized data-handling capacity. Thus, federated Machine Learning (ML) and edge computing are integrated to leverage such capacity of MCEs to enhance large model training. This paper studies motivations of all participants that take part in large model collaborative optimization from a global perspective, and proposes the positive promotion pattern that collaborates MCEs, Edge Computing Servers (ECSs), and the centralized computing center to support large model collaborative optimization by introducing the idea of computing economic. We firstly propose the novel three-layered framework for large model collaboratively optimizing based on MCEs constructed federated ML. Secondly, we introduce the economic factor into the large model optimization by devising algorithms to assess consumptions of all participants and dynamically adjust incentive benefits according to the qualities of trained models. Finally, we design the scheme to encourage more MCEs to train local models by adaptively adjusting the ECS pricing strategy with the ECS future economic benefit trend considered. Experimental results validate that our proposed approach is able to optimize the global accuracy and improve the economic benefit more efficiently than the state of the art. © 1975-2011 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

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：