检索结果-内蒙古大学图书馆

Compact Model Build Upon Dynamic Weighting Artificial Neural Network Approach for Complementary Field Effect Transistors

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 246-253页

作者： Butola, Rajat Li, Yiming Kola, Sekhar Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation The Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program The Institute of Communications Engineering the Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

In this work, a dynamic weighting-artificial neural network (DW-ANN) methodology is presented for quick and automated compact model (CM) generation. It takes advantage of both TCAD simulations for high accuracy and SPICE simulations for cost-effectiveness. This methodology is developed for gate-all-around (GAA) silicon (Si) nanosheet (NS) complementary field effect transistor (CFET), a potential candidate for future CMOS technology due to its innate properties. The critical process variation (PV) sources that severely degrade the CFET performance are estimated using DW-ANN. It reduces the computation cost and predicts the effects of PV sources with less than 1% error. Furthermore, a compact DW-ANN-based Verilog-A model has been developed that captures the dc as well as transient behavior accurately for circuit-level analysis. CFET-based circuits such as inverter, 6T-static random access memory (SRAM), and ring oscillator (RO) are characterized and implemented using DW-ANN-based CM. The overall average error of the model is reported as less than 2%. Therefore, the proposed device and circuit modeling approach provides a feasible solution for the rapid compact modeling of new emerging devices with good convergence and high accuracy. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

DiffMat:Latent diffusion models for image-guided material generation

引用

Visual Informatics 2024年第1期8卷 6-14页

作者： Liang Yuan Dingkun Yan Suguru Saito Issei Fujishiro Graduate School of Science and Technology Keio UniversityKanagawaJapan School of Computing Tokyo Institute of TechnologyTokyoJapan Department of Information and Computer Science Keio UniversityKanagawaJapan

Creating realistic materials is essential in the construction of immersive virtual *** existing techniques for material capture and conditional generation rely on flash-lit photos,they often produce artifacts when the illumination mismatches the training *** this study,we introduce DiffMat,a novel diffusion model that integrates the CLIP image encoder and a multi-layer,crossattention denoising backbone to generate latent materials from images under various *** a pre-trained StyleGAN-based material generator,our method converts these latent materials into high-resolution SVBRDF textures,a process that enables a seamless fit into the standard physically based rendering pipeline,reducing the requirements for vast computational resources and expansive *** surpasses existing generative methods in terms of material quality and variety,and shows adaptability to a broader spectrum of lighting conditions in reference images.

关键词： SVBRDF Diffusion model Generative model Appearance modeling

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

引用

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Regular languages that can be approximated by testing subword occurrences

Computer Software

引用

computer Software 2023年第2期40卷 49-60页

作者： Sin'ya, Ryoma Yamaguchi, Yutaro Nakamura, Yoshiki Mathematical Science Course Akita University Japan Graduate School of Information Science and Technology Osaka University Japan Department of Computer Science School of Computing Tokyo Institute of Technology Japan

A language L is said to be regular-measurable if there exists an infinite sequence of pairs of regular languages that "converges" to L. Instead of regular languages, this paper examines measuring power of several fragments of regular languages: piecewise testable (PT) and alphabet testable (AT) languages. In particular, we showed that, while AT-measurability for regular languages is co-NP complete, PT-measurability is decidable in linear time. © 2023 Japan Society for Software science and Technology. All rights reserved.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Focus Your Attention: Multiple Instance Learning with Attention Modification for Whole Slide Pathological Image Classification

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5791-5804页

作者： Cheng, Hailun Huang, Shenjin Cai, Linghan Xu, Yangfan Wang, Runming Zhang, Yongbing Tsinghua University Institute of Biopharmaceutical and Health Engineering Shenzhen International Graduate School Shenzhen518055 China Harbin Institute of Technology Faculty of Computing Harbin150001 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China

computer-aided pathology diagnosis based on whole slide images, which is often formulated as a weakly supervised multiple instance learning (MIL) paradigm. Current approaches generally employ attention mechanisms to aggregate instance-level features. However, the weakly supervised signal and the imbalanced instance distribution often lead to inaccurate attention localization, compromising the performance and generalization capability of the MIL framework. To address these problems, this paper presents a novel MIL framework called FAMIL that focuses on inaccurate attention and refines them. FAMIL adopts a dual-branch structure and incorporates two innovative online data augmentation strategies: attention-based Mixup (ABMix) and attention-based Masking (ABMask). ABMix emphasizes the significance of positive instances, generalizing Mixup in the MIL scenarios, while ABMask flexibly identifies challenging positive instances to optimize the feature representation. Moreover, these two methods are plug-and-play and can be easily embedded into attention-based MIL methods. Extensive experiments on three public benchmarks demonstrate the superiority of our FAMIL, outperforming current state-of-the-art methods. The test AUC for the binary tumor classification can be up to 92.61% over CAMELYON16. And the AUC over the cancer subtype classification can be up to 93.81% and 98.41% on TCGA-NSCLC and TCGA-RCC datasets, respectively. © 1991-2012 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Utilizing AHP with SVM and Top-K Algorithms for Improved Decision-Making Results

Utilizing AHP with SVM and Top-K Algorithms for Improved Dec...

引用

2024 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2024

作者： De Jesus, Mervin Jommel T. Ballera, Melvin A. Graduate Program Technological Institute of the Philippines Manila Philippines Department of Computer Science Technological Institute of the Philippines Manila Philippines

ISBN: (纸本)9798331521219

Making decisions requires different information, especially when it is crucial. The traditional Analytic Hierarchy Process (AHP) is a great algorithm that will help make these decisions more quickly because it organizes the choices in a hierarchy. However, this algorithm has trouble with big datasets and changing decision settings because they depend on pairwise comparisons and subjective judgments when making decisions. Additionally, fuzzy and stochastic AHP algorithms were developed to improve the traditional ones. However, these algorithms are complex to use on a large scale and require many computers. This study presents a novel algorithm (Top-TC AHP) that integrates Support Vector Machine (SVM) and Top-K algorithms into the traditional AHP to help people make decisions faster and better. It uses SVM to sort data and get the probabilities of the criteria for the alternatives and Top-K to choose the top options. Time complexity, consistency ratio, and throughput were the metrics used to gauge the performance of the novel algorithm. As a result, when comparing Top-TC AHP to other ways, it gets better consistency, makes computing more manageable, and speeds things up. Because of this, it is beneficial for dealing with large amounts of data and situations that change quickly. In addition, the Top-TC AHP algorithm can help people make smart decisions in many areas, such as business and school planning. ©2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Modified Recommender Algorithm based on Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) Methodology with Entropy Weighting Method (EWM) 4

Modified Recommender Algorithm based on Technique for Order ...

引用

4th International Conference of science and Information Technology in Smart Administration, ICSINTESA 2024

作者： Pacaon, Mark Reden S. Ballera, Melvin A. Technological Institute of the Philippines Graduate Program Manila Philippines Technological Institute of the Philippines Department of Computer Science Manila Philippines

ISBN: (纸本)9798350376111

This research exhibits an algorithm adapted from the Technique for Order of Preference by Ideal Solution (TOPSIS) methodology, integrating the Entropy Weighting Method (EWM) for objective and efficient recommendation processes. Decision-making methodologies have indicated gaps of subjective influence affecting performance values on several implementations with additional limitations on the flexibility of handling complex problems that require multiple factors while maintaining an acceptable running time. The study takes this into account and formulates an adaptable and efficient framework that offers objective and data-driven recommendations for diverse situations. Future endeavors include subjecting the framework to real-life scenarios and testing its effectiveness. © 2024 IEEE.

关键词： decision-making entropy weighting method modified algorithm multicriteria TOPSIS

来源：评论

学校读者我要写书评

暂无评论

Decision Support Framework: Integrating Analytic Hierarchy Process with Support Vector Machine and Top-K Algorithms

Decision Support Framework: Integrating Analytic Hierarchy P...

引用

2024 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2024

ISBN: (纸本)9798350353464

Effective recommendation systems are essential for supporting decision-making in various fields in this age of abundant information. This paper presents a novel framework for a Modified Recommender Algorithm that combines Top-K and Support Vector Machine (SVM) algorithms with the Analytic Hierarchy Process (AHP). Traditional decision-making frameworks such as AHP are susceptible to subjectivity and inconsistencies, necessitating innovative approaches to improve their reliability and effectiveness. The objective is to improve recommendation systems' efficacy and precision by integrating sophisticated machine-learning techniques with resilient decision-making approaches. The proposed framework establishes the hierarchical structure of decision elements and prioritizes alternatives according to user preferences by utilizing AHP, a potent multi-criteria decision-making tool. Support Vector Machine (SVM) is then used as a text classification model to enrich the feature space for recommendations by classifying textual data into pertinent classes. In addition, the framework applies Top-K Algorithms to select the most pertinent alternatives based on SVM classification output, thereby refining the recommendation results. Top-K Algorithms improve overall recommendation accuracy and relevance by iteratively filtering and ranking alternatives. This research advances the field of data science by providing a thorough framework that combines innovative machine learning techniques with conventional decision-making methodologies to address the challenges of recommendation systems in complex and dynamic environments. ©2024 IEEE.

关键词： Analytic hierarchy process

来源：评论

学校读者我要写书评

暂无评论

Protein Structure Prediction Using Dynamic Speciation Evolutionary Algorithm with Aggregated Problem Information 21

Protein Structure Prediction Using Dynamic Speciation Evolut...

引用

21st IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2024

作者： Parpinelli, Rafael Stubs Wojeicchowski, Nicholas Will, Nilcimar Neitzel State University of Santa Catarina Graduate Program in Applied Computing Joinville Brazil State University of Santa Catarina Computer Science Department Joinville Brazil

ISBN: (纸本)9798350356632

Protein structure prediction in three dimensions represents a fundamental challenge in Structural Bioinformatics. Leveraging problem-specific information such as fragment insertion, secondary structure, and contact maps can significantly enhance the exploration of the search space. In this study, an evolutionary algorithm is introduced, which incorporates such problem information for protein structure prediction. The proposed method employs a dynamic speciation technique alongside fragment insertion to foster population diversity. To ensure a rich variety of fragments, a fragment library is constructed using the Rosetta Quota protocol. Additionally, information from contact maps and secondary structure is integrated into two selection strategies to facilitate a more thorough exploration of the conformational search space. The results of an experimental evaluation involving 9 proteins are presented, demonstrating competitive performance compared to existing literature. Evaluation metrics include RMSD, GDT, and processing time. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Server Cloud Based Security Surveillance Systems: a Design science Research 11

Server Cloud Based Security Surveillance Systems: a Design S...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Nurenie, Alexander Ramadhan, Arief Abdurachman, Edi Trisetyarso, Agung Zarlis, Muhammad Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Telkom University School of Computing Bandung Indonesia

ISBN: (纸本)9798350305968

In this research, the author addresses the prevalent issues faced by users of cloud services, especially those using Peer-to-Peer (P2P) technology, such as connection losses, security concerns, and poor video quality. The study does not delve into the complex problems at the data center level but instead proposes a novel Design science Research approach. This new method, tested with five clients in varied locations, utilizes port forwarding to establish a direct server-client connection, bypassing traditional P2P frameworks. The results show that this approach significantly improves quality over the P2P system. Feedback from clients before and after the experiment indicates a positive response to this new method. This research offers insights into overcoming P2P-related issues in cloud services and contributes to the development of cloud-based server science, presenting a cost-effective, independent alternative to data center-dependent P2P services, with plans for ongoing research in this area. © 2023 IEEE.

关键词： Cost effectiveness

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：