检索结果-内蒙古大学图书馆

19th Sound and Music Computing Conference, SMC 2022

作者： Kaliakatsos-Papakostas, Maximos Bastas, Grigoris Makris, Dimos Herremans, Dorrien Katsouros, Vassilis Maragos, Petros Institute for Language and Speech Processing Athena R.C. Athens Greece School of Electrical and Computer Engineering NTUA Athens Greece Department of Computer Science and Design Pillar SUTD Singapore

ISBN: (纸本)9782958412609

Guitar tablature transcription consists in deducing the string and the fret number on which each note should be played to reproduce the actual musical part. This assignment should lead to playable string-fret combinations throughout the entire track and, in general, preserve parsimonious motion between successive combinations. Throughout the history of guitar playing, specific chord fingerings have been developed across different musical styles that facilitate common idiomatic voicing combinations and motion between them. This paper presents a method for assigning guitar tablature notation to a given MIDI-based musical part (possibly consisting of multiple polyphonic tracks), i.e. no information about guitar-idiomatic expressional characteristics is involved (e.g. bending etc.) The current strategy is based on machine learning and requires a basic assumption about how much fingers can stretch on a fretboard;only standard 6-string guitar tuning is examined. The proposed method also examines the transcription of music pieces that was not meant to be played or could not possibly be played by a guitar (e.g. potentially a symphonic orchestra part), employing a rudimentary method for augmenting musical information and training/testing the system with artificial data. The results present interesting aspects about what the system can achieve when trained on the initial and augmented dataset, showing that the training with augmented data improves the performance even in simple, e.g. monophonic, cases. Results also indicate weaknesses and lead to useful conclusions about possible improvements. Copyright: © 2022 First author et al.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data

引用

ACM Transactions on Intelligent Systems and Technology 2024年第6期15卷 1-28页

作者： Liu, Ji Jia, Juncheng Zhang, Hong Yun, Yuhui Wang, Leye Zhou, Yang Dai, Huaiyu Dou, Dejing Hithink RoyalFlush Information Network Co. Ltd. Hangzhou China School of Computer Science and Technology Soochow University Suzhou China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China Baidu Research Beijing China Key Lab of High Confidence Software Technologies Ministry of Education and Software Institute Peking University Beijing China Department of Computer Science and Software Engineering Auburn University AuburnAL United States Department of Electrical and Computer Engineering North Carolina State University RaleighNC United States Bedi Cloud and School of Computer Science Fudan University Beijing China

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this article, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent tradeoff between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller). © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

ReguloGPT: Harnessing GPT for End-to-End Knowledge Graph Construction of Molecular Regulatory Pathways

ReguloGPT: Harnessing GPT for End-to-End Knowledge Graph Con...

引用

2024 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2024

作者： Wu, Xidong Jo, Sumin Zeng, Yiming Das, Arun Zhang, Ting-He Patel, Parth Wei, Yuanjing Li, Lei Gao, Shou-Jiang Zhang, Jianqiu Pratt, Dexter Chiu, Yu-Chiao Huang, Yufei University of Pittsburgh Electrical and Computer Engineering PittsburghPA United States University of Pittsburgh Medical Center Hillman Cancer Center PittsburghPA United States University of Pittsburgh School of Medicine Department of Medicine PittsburghPA United States The University of Texas at San Antonio Electrical and Computer Engineering San AntonioTX United States Language Technologies Institute Carnegie Mellon University PittsburghPA United States University of California San Diego Department of Medicine La Jolla CA United States University of Pittsburgh School of Medicine Department of Microbiology and Molecular Genetics PittsburghPA United States

ISBN: (纸本)9798350351552

Molecular Regulatory Pathways (MRPs) are key to understanding biological functions. Knowledge Graphs (KGs) help organize and analyze MRPs by structuring complex interactions. Current methods for extracting KGs from biomedical literature struggle with hierarchical relationships and context. Large language Models (LLMs) like GPT-4 show promise in addressing these issues but remain underexplored for end-to-end KG construction. We present reguloGPT, a novel GPT-4 based in-context learning prompt designed for the end-to-end extraction of a regulatory graph and context from a sentence that describes regulatory interactions. reguloGPT employs a context-aware relational graph to capture MRPs' hierarchical structure and resolves semantic inconsistencies by embedding context directly within the relational edges. We created a benchmark dataset comprising four hundred annotated PubMed titles on N6 -methyladenosine (m6 A) regulations. Rigorous evaluations of reguloGPT on the benchmark dataset showed marked improvements over existing algorithms and other LLMs. We further developed a novel G-Eval scheme, leveraging GPT-4 for annotation-free performance evaluation that demonstrated agreement with evaluations on the benchmark dataset. Lastly, we constructed m6 A-KG by applying reguloGPT to 1,396 m6 A-related titles and demonstrated its utility in elucidating m6 A's reg-ulatory mechanisms of cancer phenotypes across various cancers. These results underscore reguloGPT's potential for advancing biological knowledge extraction. All reguloGPT works including source code, benchmark datasets, and m6 A-KG are available at https://***/Huang-AI4Medicine-Lab/reguloGPt. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Stray Lion Optimizer based LSTM Model for Detecting the Fake News

Stray Lion Optimizer based LSTM Model for Detecting the Fake...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Vadakkethil Somanathan Pillai, Sanjaikanth E Kumar Pareek, Piyush Kumar Dhiman, Vinod Zanke, Pankaj Hassan, Muntather Muhsin University of North Dakota School of Electrical Engineering and Computer Science Grand Forks United States Nitte Meenakshi Institute of Technology Department of Aiml Bengaluru India Gavs Technologies Na Inc PrincetonNJ United States Sapiens International Corporation The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq

ISBN: (纸本)9798350360660

Because of the damage it can do to people, communities, and countries, the massive spread of misinformation across many internet stages has develop an urgent issue. In order to address this issue, the scientific community is presently making significant efforts. Fighting disinformation at its earliest stages is difficult since current techniques for detecting fake news overstate the impact of public opinion. In order to address this problematic, the paper suggests a new framework for detecting bogus news using optimizer-based Deep Learning. At first, the d-D feature vectors for the textual data are recovered using the TF-IDF weighting algorithm. The LSTM algorithm is then told to use the retrieved characteristics. To process the parameters of LSTM and extract the n-gram from the text, the Stray Lion Swarm Optimization Algorithm (SLSOA) is used. In order to identify false news, these retrieved traits are then combined. We apply established assessment methods to two real-world datasets of false news and assess the outcomes. Also included are comparisons with other meta-heuristic algorithms and more modern approaches to detecting false news. The outcomes clearly demonstrate that the suggested model outperforms current models on different datasets. LSTM-SLOA attained as 0.9865 and LSTM measure as 0.7414 and then RNN as 0.7525 and also CNN as 0.6381 and then DBN attained as 0.8118 congruently. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Traffic Management of Vehicles using Deep Learning Approach in Smart Cities

An Intelligent Traffic Management of Vehicles using Deep Lea...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Botir Elov Adilbek Dauletov Yadala Sucharitha Feruza Khalilova Mukhayyo Latipova Mukhtasarkhon Abdullayeva Computer Linguistics and Digital Technology Alisher Navo'i Tashkent State University of Uzbek Language and Literature Tashkent Uzbekistan Department of Digital Technologies Alfraganus University Tashkent Uzbekistan Department of Computer Science and Engineering VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad India Department of Electrical Power Engineering Fergana Polytechnic Institute Fergana Uzbekistan

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Smart traffic management of automobiles has been one of the utmost sought-after issues in the academic community due to the ever-increasing pace of urbanization and civilization over the last several centuries. Vehicle dissection, traffic density appraisal, and vehicle tracing are the three main components of smart traffic management. This problem becomes more difficult to resolve when there are occlusions, background clutter, and fluctuations in traffic density. In light of this need, we explore a deeper learning approach based on R-CNN s for faster vehicle segmentation in this study. There is adaptive backdrop modeling in the computational framework. It solves problems with lighting and shadows as well. The use of topological active net deformable models allows for segmentation that is more precise. The deformations mentioned can be accomplished with the aid of topological and stretched topological active nets. Minimizing energy allows for mesh deformation. Using a tweaked version of the stretched topological active net improves the segmentation accuracy to 98.3%. The investigational findings show that this framework is better than other methods.

关键词： Deep learning Integrated circuits Deformable models Fluctuations Smart cities Deformation Communication systems Computational modeling Lighting Traffic control

来源：评论

学校读者我要写书评

暂无评论

Decoding the future: exploring and comparing ABE standards for cloud, IoT, blockchain security applications

引用

Multimedia Tools and Applications 2025年第13期84卷 12299-12327页

作者： Singamaneni, Kranthi Kumar Yadav, Kusum Aledaily, Arwa N. Viriyasitavat, Wattana Dhiman, Gaurav Kaur, Amandeep Department of Computer Engineering and Technology Chaitanya Bharathi Institute of Technology T.S Gandipet Hyderabad500075 India College of Computer Science and Engineering University of Ha’il Hail Saudi Arabia Business Information Technology Division Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University Bangkok Thailand School of Sciences and Emerging Technologies Jagat Guru Nanak Dev Punjab State Open University Patiala India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Chitkara Centre for Research and Development Chitkara University Himachal Pradesh 173212 India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Division of Research and Development Lovely Professional University Phagwara India Centre of Research Impact and Outcome Chitkara University Punjab Rajpura140417 India MEU Research Unit Middle East University Amman Jordan

Data security poses a significant challenge in cloud computing, the Internet of Things (IoT), and blockchain applications. Attribute-Based Encryption (ABE) has emerged as a promising cryptographic solution for secure data sharing and access management in these contexts. This research article focuses on enhancing security in cloud, IoT, and blockchain applications through a comprehensive examination and comparison of various ABE standards. The study begins with an in-depth literature review on ABE requirements, offering insights into the evolving landscape, challenges, and trends. This review serves as the foundation for the research, which aims to compare ABE standards based on cryptographic techniques, encryption/decryption processes, and access control rules, considering criteria like flexibility, efficiency, scalability, and security. Statistical analyses complement the comparative study, generating empirical data on ABE standard performance. Key metrics, including key size, storage overhead, encryption/decryption time, and computational complexity, are considered to identify trends and draw meaningful conclusions. The research also explores use cases for different ABE models within blockchain, IoT, and cloud computing applications, pinpointing scenarios where specific ABE models excel. The study contributes to advancing access control and secure data-sharing technologies in specified domains, aiding researchers, practitioners, and developers in selecting the most appropriate encryption method. By systematically outlining advantages and disadvantages of various Cipher Text ABE standards, the research facilitates informed decision-making. Additionally, practical use cases ensure alignment between ABE models and the distinctive traits and requirements of each domain, expanding the toolset for enhancing data security in blockchain, IoT, and cloud computing applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springe

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Telehealth Data Security and Privacy Solutions for Sensitive Health Records using Cloud Computing and Isolation Forest Algorithm 2

Telehealth Data Security and Privacy Solutions for Sensitive...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Prathik, A. Banu, S. Parveen Sagar, B.S. Prakash, A. John Felix Thamizhamuthu, R. Velmurugan, S. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha College of Liberal Arts and Sciences Department of Commerce Tamil Nadu Chennai India Reva University Department of Electrical and Electronics Engineering Karnataka Bengaluru India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Campus-Chengalpattu Tamil Nadu Chennai India T.J.S. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350368413

Protecting the confidentiality of patient's personal health information as it is sent and kept in the cloud is of the utmost importance due to the increasing number of telehealth services. This research provides a new healthcare data security approach using cloud computing and the Isolation Forest method. To identify important challenges and provide a novel technique, a thorough literature study on telehealth security, privacy issues, and cloud-based solutions. It uses the Isolation Forest method for anomaly detection in combination with encryption and access restriction systems to identify intrusion attempts. It uses simulated telehealth data in trials to test the system's work. Findings show substantial gains in privacy and data security with computational burden. Healthcare practitioners and legislators will find results useful in their pursuit of solutions to the problem of securing patients' private health information throughout the rise of telemedicine. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation

arXiv

引用

arXiv 2023年

作者： Fu, Yu-Kuan Tseng, Liang-Hsuan Shi, Jiatong Li, Chen-An Hsu, Tsu-Yuan Watanabe, Shinji Lee, Hung-Yi College of Electrical Engineering and Computer Science National Taiwan University Taiwan Language Technologies Institute Carnegie Mellon University United States

Most of the speech translation models heavily rely on parallel data, which is hard to collect especially for low-resource languages. To tackle this issue, we propose to build a cascaded speech translation system without leveraging any kind of paired data. We use fully unpaired data to train our unsupervised systems and evaluate our results on CoVoST 2 and CVSS. The results show that our work is comparable with some other early supervised methods in some language pairs. While cascaded systems always suffer from severe error propagation problems, we proposed denoising back-translation (DBT), a novel approach to building robust unsupervised neural machine translation (UNMT). DBT successfully increases the BLEU score by 0.7-0.9 in all three translation directions. Moreover, we simplified the pipeline of our cascaded system to reduce inference latency and conducted a comprehensive analysis of every part of our work. We also demonstrate our unsupervised speech translation results on the established website. Copyright © 2023, The Authors. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

VILMA: A ZERO-SHOT BENCHMARK FOR LINGUISTIC AND TEMPORAL GROUNDING IN VIDEO-language MODELS 12

VILMA: A ZERO-SHOT BENCHMARK FOR LINGUISTIC AND TEMPORAL GRO...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Kesen, Ilker Pedrotti, Andrea Dogan, Mustafa Cafagna, Michele Acikgoz, Emre Can Parcalabescu, Letitia Calixto, Iacer Frank, Anette Gatt, Albert Erdem, Aykut Erdem, Erkut Koç University KUIS AI Center Turkey Koç University Department of Computer Engineering Turkey University of Pisa Department of Computer Science Italy Institute of Information Science and Technologies Italian National Council of Research Italy Hacettepe University Department of Computer Engineering Turkey Aselsan Research Turkey University of Malta Institute of Linguistics and Language Technology Malta Heidelberg University Department of Computational Linguistics Germany Amsterdam UMC University of Amsterdam Department of Medical Informatics Netherlands Amsterdam Public Health Methodology & Mental Health Amsterdam Netherlands Utrecht University Department of Information and Computing Sciences Netherlands

With the ever-increasing popularity of pretrained Video-language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their visio-linguistic capabilities. To address this challenge, we present VILMA), a task-agnostic benchmark that places the assessment of fine-grained capabilities of these models on a firm footing. Task-based evaluations, while valuable, fail to capture the complexities and specific temporal aspects of moving images that VidLMs need to process. Through carefully curated counterfactuals, VILMA offers a controlled evaluation suite that sheds light on the true potential of these models, as well as their performance gaps compared to human-level understanding. VILMA also includes proficiency tests, which assess basic capabilities deemed essential to solving the main counterfactual tests. We show that current VidLMs' grounding abilities are no better than those of vision-language models which use static images. This is especially striking once the performance on proficiency tests is factored in. Our benchmark serves as a catalyst for future research on VidLMs, helping to highlight areas that still need to be explored. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Dependency Induction Through the Lens of Visual Perception 25

Dependency Induction Through the Lens of Visual Perception

引用

25th Conference on Computational Natural language Learning, CoNLL 2021

作者： Su, Ruisi Rijhwani, Shruti Zhu, Hao He, Junxian Wang, Xinyu Bisk, Yonatan Neubig, Graham Electrical and Computer Engineering Carnegie Mellon University United States Language Technologies Institute Carnegie Mellon University United States

ISBN: (纸本)9781955917056

Most previous work on grammar induction focuses on learning phrasal or dependency structure purely from text. However, because the signal provided by text alone is limited, recently introduced visually grounded syntax models make use of multimodal information leading to improved performance in constituency grammar induction. However, as compared to dependency grammars, constituency grammars do not provide a straightforward way to incorporate visual information without enforcing language-specific heuristics. In this paper, we propose an unsupervised grammar induction model that leverages word concreteness and a structural vision-based heuristic to jointly learn constituency-structure and dependency-structure grammars. Our experiments find that concreteness is a strong indicator for learning dependency grammars, improving the direct attachment score (DAS) by over 50% as compared to state-of-the-art models trained on pure text. Next, we propose an extension of our model that leverages both word concreteness and visual semantic role labels in constituency and dependency parsing. Our experiments show that the proposed extension outperforms the current state-of-the-art visually grounded models in constituency parsing even with a smaller grammar size. © 2021 Association for Computational Linguistics.

关键词： Semantics

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：