检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liebel, Grischa Klünder, Jil Hebig, Regina Lazik, Christopher Nunes, Inês Graßl, Isabella Steghöfer, Jan-Philipp Exelmans, Joeri Oertel, Julian Marquardt, Kai Juhnke, Katharina Schneider, Kurt Gren, Lucas Happe, Lucia Herrmann, Marc Wyrich, Marvin Tichy, Matthias Goulão, Miguel Wohlrab, Rebekka Kalantari, Reyhaneh Heinrich, Robert Greiner, Sandra Rukmono, Satrio Adi Chakraborty, Shalini Abrahão, Silvia Amaral, Vasco Department of Computer Science Reykjavik University Menntavegur 1 Reykjavik102 Iceland Software Engineering Group Leibniz University Hannover Welfengarten 1 Hannover30167 Germany Department of Software Engineering University of Rostock Albert-Einstein-Straße Rostock18057 Germany Department of Software Engineering Humboldt-Universität zu Berlin Unter den Linden 6 Berlin10099 Germany Frankfurt Germany Department of Software Engineering II University of Passau Innstraße 33 Passau94032 Germany XITASO GmbH Austraße 35 Augsburg86153 Germany Department of Computer Science University of Antwerp Middelheimlaan 1 Antwerp2020 Belgium Department of Informatics Karlsruhe Institute of Technology Am Fasanengarten 5 Karlsruhe75131 Germany SMT-EMI6 Carl Zeiss SMT GmbH Rudolf-Eber-Straße 2 Oberkochen73447 Germany Department of Computer Science and Engineering Chalmers | University of Gothenburg Gothenburg41127 Sweden Department of Interdisciplinary Didactics Karlsruhe Institute of Technology Engesserstr. 2 Karlsruhe75131 Germany Department of Computer Science Saarland University Saarland Informatics Campus Saarbrücken66123 Germany Institute of Software Engineering and Languages Ulm University James-Franck-Ring Ulm89081 Germany Department of Computer Science NOVA School of Science & Technology Campus de Caparica Caparica2829-516 Portugal Department of Engineering Design and Teaching Innovation University of Ottawa 800 King Edward Avenue OttawaK1N6N5 Canada KASTEL - Institute of Information Security and Dependability Karlsruhe Institute of Technology Am Fasanengarten 5 Karlsruhe75131 Germany Department of Computer Science University of Bern Bern3012 Switzerland Department of Mathematics and Computer Science Eindhoven University of Technology De Zaale Eindhoven5600 MB Netherlands Instituto Universitario Mixto de Tecnología Informática Universitat Politècnica de València Camino de Vera s/n Valencia46022 Spain

Purpose: Software modelling and Model-Driven engineering (MDE) is traditionally studied from a technical perspective. However, one of the core motivations behind the use of software models is inherently human-centred. Models aim to enable practitioners to communicate about software designs, make software understandable, or make software easier to write through domain-specific modelling languages. Several recent studies challenge the idea that these aims can always be reached and indicate that human factors play a role in the success of MDE. However, there is an under-representation of research focusing on human factors in modelling. Methods: During a GI-Dagstuhl seminar, topics related to human factors in modelling were discussed by 26 expert participants from research and industry. Results: In breakout groups, five topics were covered in depth, namely modelling human aspects, factors of modeller experience, diversity and inclusion in MDE, collaboration and MDE, and teaching human-aware MDE. Conclusion: We summarise our insights gained during the discussions on the five topics. We formulate research goals, questions, and propositions that support directing future initiatives towards an MDE community that is aware of and supportive of human factors and values. © 2024, CC BY.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Transformers in medical image analysis

引用

Intelligent Medicine 2023年第1期3卷 59-78页

作者： Kelei He Chen Gan Zhuoyuan Li Islem Rekik Zihao Yin Wen Ji Yang Gao Qian Wang Junfeng Zhang Dinggang Shen Medical School of Nanjing University NanjingJiangsu 210093China National Institute of Healthcare Data Science at Nanjing University NanjingJiangsu 210093China BASIRA Laboratory Faculty of Computer and Informatics EngineeringIstanbul Technical UniversityIstanbulTurkey School of Science and Engineering ComputingUniversity of DundeeUK State Key Laboratory for Novel Software Technology Nanjing UniversityNanjingJiangsu 210093China School of Biomedical Engineering ShanghaiTech UniversityShanghai 201210China Department of Research and Development Shanghai United Imaging Intelligence Co.Ltd.Shanghai 200030China Shanghai Clinical Research and Trial Center Shanghai 201703China

Transformers have dominated the field of natural language processing and have recently made an impact in the area of computer *** the field of medical image analysis,transformers have also been successfully used in to full-stack clinical applications,including image synthesis/reconstruction,registration,segmentation,detection,and *** paper aimed to promote awareness of the applications of transformers in medical image ***,we first provided an overview of the core concepts of the attention mechanism built into transformers and other basic ***,we reviewed various transformer architectures tailored for medical image applications and discuss their *** this review,we investigated key challenges including the use of transformers in different learning paradigms,improving model efficiency,and coupling with other *** hope this review would provide a comprehensive picture of transformers to readers with an interest in medical image analysis.

关键词： Transformer Medical image analysis Deep learning Diagnosis Registration Segmentation Image synthesis Multi-task learning Multi-modal learning Weakly-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Latent Dirichlet Allocation for Topic Discovery and Segmentation in Big Data

Latent Dirichlet Allocation for Topic Discovery and Segmenta...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： A. Clementking S. Rani R. Roseline Purushothaman K E G. Kavitha S. Murugan Mount Carmel College (Autonomous) Bengaluru Karnataka India Department of BCA/IT Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai Tamil Nadu India PG Department of Computer Applications St. Joseph’s College of Arts and Science(Autonomous) Cuddalore Tamil Nadu India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Vinayaka Missions Kirupananda Variyar Engineering College Vinayaka Missions Research Foundation (Deemed to be University) Salem Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

Using Latent Dirichlet Allocation (LDA) for topic identification and segmentation in big data helps identify significant patterns and topics from large text corpora. LDA will be implemented and optimized to rapidly process and analyze large datasets, revealing hidden subjects and enhancing content structure. Creating a strong framework for accurate and scalable subject modeling would improve analysis and decision-making in social media analytics, consumer feedback, and academic research. The LDA technique must be refined to accommodate large data's great dimensionality and complexity while being computationally efficient. An innovative topic identification tool that processes large-scale text data quickly and reliably will reveal theme patterns and improve big data management and use. The Bigdata Corpus results demonstrate the results for Topic Distribution Across Documents in a sample of 5 topics and 5 documents vary from 0.1 to 0.25. The same dataset also has Top Words per Topic. 10 example words for 10 subjects the identical dataset with another instance has values from 0.03-0.15. Document clustering based on topic proportions in a sample of 5 documents clustering 5 topics yields 0.1–0.75.

关键词： Analytical models Accuracy Social networking (online) Computational modeling Scalability Big Data Parallel processing Information and communication technology Resource management Reliability

来源：评论

学校读者我要写书评

暂无评论

Blockchain based electronic educational document management with role-based access control using machine learning model

引用

Scientific Reports 2025年第1期15卷 1-19页

作者： Chinnasamy, P. Subashini, B. Ayyasamy, Ramesh Kumar Kiran, Ajmeera Pandey, Binay Kumar Pandey, Digvijay Lelisho, Mesfin Esayas Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Engineering Srivilliputtur India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur Chennai India Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Perak Kampar Malaysia Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India Department of Information Technology College of Technology Govind Ballabh Pant University of Agriculture and Technology Pantnagar Uttrarakhand India Department of Technical Education (Government of Uttar Pradesh) Uttar Pradesh Kanpur India Department of Statistics College of Natural and Computational Science Mizan-Tepi University Tepi Ethiopia

The emergence of digital technology has led to a significant increase in the importance of educational credential storage, exchange, and verification for organisations, enterprises, and universities. academic record forgery, record misuse, credential data tampering, time-consuming verification procedures, ownership and control difficulties, and other problems plague the education sector. Machine learning (ML) and blockchain, two of the most disruptive methods, have replaced traditional techniques in the education sector with highly technological and efficient ways. Our study aims to propose a novel electronic educational document management technique using a blockchain-based fuzzy feed-forward convolutional temporal neural network that detects malicious users. Here, the training is carried out based on NLP analysis in document word weight indexing. This document management access control is based on role-based access with simulated remora swarm optimisation. In order to identify malicious users, this suggested system logs access requests on the blockchain and authenticated users. The findings demonstrate that this suggested architecture performs as intended in every case. The experimental analysis is based on a malicious user detection dataset regarding Prediction accuracy, Mean average precision, F-measure, Latency, QoS, Contract execution time, and Throughput. Based on dataset feature analysis, the proposed B-FCTNN_SRSO achieved a prediction accuracy of 98%, a mean average precision (MAP) of 95%, and an F1 score of 97%, with a latency of 96%. Additionally, based on blockchain security analysis, the B-FCTNN_SRSO attained a QoS of 97%, a precision of 94%, and a throughput of 96%. © The Author(s) 2025.

关键词： Blockchain Electronic educational document management Remora swarm optimization Role-based access Temporal neural network

来源：评论

学校读者我要写书评

暂无评论

Uncovering distinct public transport user profiles and the factors influencing the users’ intentions

引用

Journal of Urban Mobility 2025年 7卷

作者： Kriswardhana, Willy Ismael, Karzan Duleba, Szabolcs Esztergár-Kiss, Domokos Department of Transport Technology and Economics Faculty of Transportation Engineering and Vehicle Engineering Budapest University of Technology and Economics Műegyetem rkp. 3. Budapest H-1111 Hungary Department of Civil Engineering Faculty of Engineering Universitas Jember Jember 68121 Indonesia Department of City Planning Engineering Technical College of Engineering Sulaimani Polytechnic University Sulaimani 46001 Iraq Institute of Mathematics and Informatics University of Nyíregyháza Nyíregyháza Hungary HUN-REN Institute For Computer Science And Control (SZTAKI) Hungary

Given the escalating environmental challenges, it is clear that the approach to the usage of public transport (PT) must be reconsidered. Loyal PT users help attract other travelers through positive recommendations, this drives interest in exploring the relationships between service quality, satisfaction, and loyalty. Although these relationships in the PT context have been studied, there have been limited efforts to explore the variability of their effects. Therefore, this research explores how service quality, satisfaction, involvement, and prior knowledge influence the behavioral intentions to use PT across various traveler groups. The hypotheses are tested by using multi-group analysis in the structural equation modeling framework, and three user profiles are revealed by applying the latent class cluster analysis. The results indicate that involvement strongly influences the behavioral intentions, while satisfaction impacts the intentions solely when involvement acts as a moderator. Class-specific results indicate that younger females living outside the city center put greater emphasis on service quality improvements for their satisfaction and involvement in PT services compared to males and older individuals residing in the city center. Low-income students living in the city center are more likely to use PT if they feel confident how to use the service. The results are relevant for PT operators and related stakeholders in maintaining travelers’ loyalty. © 2025 The Author(s)

关键词： Heterogeneity Intention Involvement Public transport Satisfaction Service quality

来源：评论

学校读者我要写书评

暂无评论

Sim2Real Grasp Pose Estimation for Adaptive Robotic Applications

arXiv

引用

arXiv 2022年

作者： Horváth, Dániel Bocsi, Kristóf Erdős, Gábor Istenes, Zoltán Centre of Excellence in Production Informatics and Control Institute for Computer Science and Control Eötvös Loránd Research Network Budapest Hungary CoLocation Center for Academic and Industrial Cooperation Eötvös Loránd University Budapest Hungary Department of Manufacturing Science and Engineering Budapest University of Technology and Economics Budapest Hungary

Adaptive robotics plays an essential role in achieving truly co-creative cyber physical systems. In robotic manipulation tasks, one of the biggest challenges is to estimate the pose of given workpieces. Even though the recent deep-learning-based models show promising results, they require an immense dataset for training. In this paper, two vision-based, multi-object grasp pose estimation models (MOGPE), the MOGPE Real-Time and the MOGPE High-Precision are proposed. Furthermore, a sim2real method based on domain randomization to diminish the reality gap and overcome the data shortage. Our methods yielded an 80% and a 96.67% success rate in a real-world robotic pick-and-place experiment, with the MOGPE Real-Time and the MOGPE High-Precision model respectively. Our framework provides an industrial tool for fast data generation and model training and requires minimal domain-specific data. © 2022, CC BY-NC-ND.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Laser written optical Physical Unclonable Functions: a route to commercialization.

Laser written optical Physical Unclonable Functions: a route...

引用

International Conference on Transparent Optical Networks

作者： Dimitris Alexandropoulos Christos Tselios Simone Mazzucato Panagiotis Rizomiliotis Konstantinos Moustakas Thomas Kamalakis Research Centre ATHENA Industrial Systems Institute Patras Greece Department of Materials Science University of Patras Patras Greece SISMA S.p.A. via dell’Industria 1 - 36013 Piovene Rocchette VI Italy Department of Informatics and Telematics Harokopio University of Athens Athens Greece Department of Electrical and Computer Engineering University of Patras Patras Greece

ISBN: (数字)9798350377323

ISBN: (纸本)9798350377330

This paper presents a fabrication approach towards commercialization of optical Physical Unclonable Functions (PUFs) for anti-counterfeiting. We address the limitations of existing complex and expensive implementations by demonstrating strong, intrinsic optical PUFs using computer-Generated Holograms (CGHs) fabricated with industrial-friendly lasers. This novel method offers exceptional security with very low probability of cloning through a low-cost, production-line friendly set-up and a robust signature encoding scheme that utilizes nonlinear dimensionality reduction techniques, to differentiate legitimate variations from counterfeiting attempts. This research paves the way for widespread adoption of PUF technology for real-world applications.

关键词： Integrated optics Laser theory Optical device fabrication Supply chains Cloning Physical unclonable function Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Disentangling Prosody Representations with Unsupervised Speech Reconstruction

arXiv

引用

arXiv 2022年

作者： Qu, Leyuan Li, Taihao Weber, Cornelius Pekarek-Rosin, Theresa Ren, Fuji Wermter, Stefan The Institute of Artificial Intelligence Zhejiang Lab Hangzhou China The Department of Informatics University of Hamburg Hamburg Germany The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity in Automatic Speech Recognition (ASR) and speaker verification tasks respectively. However, it is still an open challenging research question to extract prosodic information because of the intrinsic association of different attributes, such as timbre and rhythm, and because of the need for supervised training schemes to achieve robust large-scale and speaker-independent ASR. The aim of this paper is to address the disentanglement of emotional prosody from speech based on unsupervised reconstruction. Specifically, we identify, design, implement and integrate three crucial components in our proposed speech reconstruction model Prosody2Vec: (1) a unit encoder that transforms speech signals into discrete units for semantic content, (2) a pretrained speaker verification model to generate speaker identity embeddings, and (3) a trainable prosody encoder to learn prosody representations. We first pretrain the Prosody2Vec representations on unlabelled emotional speech corpora, then fine-tune the model on specific datasets to perform Speech Emotion Recognition (SER) and Emotional Voice Conversion (EVC) tasks. Both objective (weighted and unweighted accuracies) and subjective (mean opinion score) evaluations on the EVC task suggest that Prosody2Vec effectively captures general prosodic features that can be smoothly transferred to other emotional speech. In addition, our SER experiments on the IEMOCAP dataset reveal that the prosody features learned by Prosody2Vec are complementary and beneficial for the performance of widely used speech pretraining models and surpass the state-of-the-art methods when combining Prosody2Vec with HuBERT representations. Some audio samples can be found on our demo website1 Copyright © 2022, The Authors. All righ

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Abstraction engineering

arXiv

引用

arXiv 2024年

作者： Bencomo, Nelly Cabot, Jordi Chechik, Marsha Cheng, Betty H.C. Combemale, Benoit Wąsowski, Andrzej Zschaler, Steffen Durham University Computer Science Durham Durham United Kingdom Luxembourg Institute of Science and Technology University of Luxembourg Esch-sur-Alzette Luxembourg University of Toronto Department of Computer Science TorontoON Canada Michigan State University Department of Computer Science and Engineering 428 S. Shaw Lane 4115 Engineering Building East LansingMI48824 United States University of Rennes IRISA and Inria Campus de Beaulieu Rennes35042 France IT University of Copenhagen Department of Computer Science Rued Langgaards Vej 7 Copenhagen2300 Denmark King’s College London Department of Informatics Bush House 30 Aldwych LondonWC2B 4BG United Kingdom

Modern software-based systems operate under rapidly changing conditions and face ever-increasing uncertainty. In response, systems are increasingly adaptive and reliant on artificial-intelligence methods. In addition to the ubiquity of software with respect to users and application areas (e.g., transportation, smart grids, medicine, etc.), these high-impact software systems necessarily draw from many disciplines for foundational principles, domain expertise, and workflows. Recent progress with lowering the barrier to entry for coding has led to a broader community of developers, who are not necessarily software engineers. As such, the field of software engineering needs to adapt accordingly and offer new methods to systematically develop high-quality software systems by a broad range of experts and non-experts. This paper looks at these new challenges and proposes to address them through the lens of Abstraction. Abstraction is already used across many disciplines involved in software development—from the time-honored classical deductive reasoning and formal modeling to the inductive reasoning employed by modern data science. The software engineering of the future requires Abstraction engineering—a systematic approach to abstraction across the inductive and deductive spaces. We discuss the foundations of Abstraction engineering, identify key challenges, highlight the research questions that help address these challenges, and create a roadmap for future research. © 2024, CC BY.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Oriented User Sentiment Evaluation System on Social Networks using Modified Deep Learning Principles

Artificial Intelligence Oriented User Sentiment Evaluation S...

引用

Mobile Computing and Sustainable informatics (ICMCSI), International Conference on

作者： S. Thangamayan Sandip Nivrutti Jagdale T R.Kalai Lakshmi Jayendra Gopal Thatipudi Penyameen. K Bhola Khan Department of Research and Development Saveetha School of Law Saveetha Institute of Medical and Technical Sciences Chennai Yashwantrao Mohite Institute of Management Karad Bharati Vidyapeeth(Deemed to be University) School Of Management Studies Sathyabama Institute Of Science And Technology Chennai Dept. of Computer Science University of North Texas Velammal College Of Engineering And Technology Madurai Department of Regional Economics MJP Rohilkhand University Bareilly India

Sentiment analysis, a pivotal aspect of natural language processing, is vital for deciphering the emotional nuances embedded in textual data. This project introduces an innovative workflow that amalgamates various techniques to elevate sentiment analysis performance. The workflow encompasses Fuzzy C-means (FCM) clustering for pattern identification, Differential Multi-layer Whale Optimization (DWO) for feature extraction, and a classification phase utilizing diverse deep learning models, including Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). Additionally, Ant Lion Optimization (ALO) ensures system optimization, fostering robustness and adaptability. The proposed system is evaluated against eight distinct deep learning models, each offering unique architectures or configurations. Remarkably, the proposed workflow achieves an impressive accuracy of 96%, underscoring its efficacy in discerning complex sentiments. This high level of accuracy positions the system as a powerful tool for real-world applications where nuanced understanding of human sentiment is paramount. The project contributes to the evolving landscape of sentiment analysis, providing a comprehensive framework for extracting valuable insights from diverse textual datasets.

关键词：

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：