检索结果-内蒙古大学图书馆

1st IEEE International Symposium on Consumer Technology, ISCT 2024

作者： Rinartha, Komang Ku, Lun-Wei Social Networks and Human Centered Computing Program Taiwan International Graduate Program Institute of Information Science 128 Academia Road Sec. 2. Nangang Taipei115 Taiwan Institute of Information Science Academia Sinica Taipei Taiwan

ISBN: (纸本)9798350365191

Speech emotion recognition (SER) is a Machine Learning (ML) topic that is now receiving a lot of research attention. This can be attributed to its growing capacity, improvements in algorithms, and utilization in practical situations. Furthermore, speech contains not just auditory information but also lexical information. Both speech-based emotion recognition and text-based emotion recognition, called bimodal emotion recognition, can be highly beneficial for human interaction. Take an example, maintaining the communication between elder parents who are left behind after their children leave for education, employment, and family dynamics who can be greatly affected, both physically and emotionally, by feelings of loneliness and social isolation. Bimodal emotion recognition employs both text-based and audio-based methods to identify emotions. Each algorithm was trained separately and then combined using a late fusion technique. RoBERTa text-based emotion recognition can be combined with CNN audio-based emotion recognition by using late fusion to create a bimodal emotion recognition that can obtain more than 50% of accuracy by combining text and audio in a similar proportion or relying on text more than audio. By adjusting the proportion of text or audio emotion recognition, we can get better result of recognition and it can be customized by the user's preference. We elaborate on creating bimodal emotion recognition, conversational interface, a framework for emotion monitoring system, and give the example of a combined algorithm to perform emotion recognition. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Convergence analysis of a Schrödinger problem with moving boundary

引用

Mathematics and Computers in Simulation 2025年 238卷 45-64页

作者： Alfaro Vigo, Daniel G. Gomes, Daniele C.R. do Carmo, Bruno A. Rincon, Mauro A. Institute of Computing Federal University of Rio de Janeiro Caixa Postal 68.530 RJ Rio de JaneiroCEP 21941-590 Brazil Graduate Program in Informatics Federal University of Rio de Janeiro Caixa Postal 68.530 RJ Rio de JaneiroCEP 21941-590 Brazil

In this article, we present the mathematical analysis of the convergence of the linearized Crank–Nicolson Galerkin method for a nonlinear Schrödinger problem related to a domain with a moving boundary. The convergence analysis of the numerical method is carried out for both semidiscrete and fully discrete problems. We establish an optimal error estimate in the L2-norm with order O(τ2+hs),2≤s≤r, where h is the finite element mesh size, τ is the time step, and r−1 represents the degree of the finite element polynomial basis. Numerical simulations are provided to confirm the consistency between theoretical and numerical results, validating the method and the order of convergence for different degrees p≥1 of the Lagrange polynomials and also for Hermite polynomials (degree p=3), which form the basis of the approximate solution. © 2025 International Association for Mathematics and Computers in Simulation (IMACS)

关键词： Convergence of numerical methods

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Commercial Opportunities Qualification Using the BANT Methodology under the Fuzzy Set Theory Framework. 28th

A Novel Approach for Commercial Opportunities Qualification ...

引用

28th International Conference on Knowledge Based and Intelligent information and Engineering Systems, KES 2024

作者： Leite, Marcus Vinicius Abe, Jair Minoro Hoffmann Souza, Marcos Leandro Graduate Program in Production Engineering-Paulista University-UNIP Rua Dr. Bacelar 1212 São Paulo-SP04026002 Brazil Graduate Program in Applied Computing-Vale do Rio dos Sinos University-UNISINOS Av. Unisinos 950 - São LeopoldoRS-93022-000 Brazil

Demand generation is crucial for organizations, supplying sales teams with well-qualified commercial opportunities. Despite the wide variety of existing opportunity qualification methodologies, the subjective nature of experts' final evaluation remains an obstacle to efficiency and productivity in the business process. This research investigated how Fuzzy Set Theory and Fuzzy Logic could be applied to the BANT methodology for qualifying commercial opportunities, aiming to replace these deliberative evaluations by experts to increase the sales cycle performance. A fuzzy inference system was developed to emulate the assessments of the experts. The analysis of the ratings obtained after processing a sample of commercial opportunities from 2022 and 2023 confirmed the system's effectiveness in aligning with expert perceptions. While the study indicated room for refinements in the model, the findings underscore the potential to streamline the qualification of opportunities and improve sales cycle performance. © 2024 The Authors.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

Video Quality Enhancement Using Multi-Domain Spatio-Temporal Deformable Fusion

Video Quality Enhancement Using Multi-Domain Spatio-Temporal...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Gilberto Kreisler Garibaldi da Silveira Júnior Bruno Zatt Daniel Palomino Guilherme Correa Video Technology Research Group - ViTech Graduate Program in Computing - UFPel Pelotas Brazil

ISBN: (数字)9798331522124

ISBN: (纸本)9798331522131

Lossy video compression introduces visual artifacts that degrade video quality, where deep neural networks (DNNs) are effective in enhancement. However, conventional DNN-based methods often focus on a single video compression standard, limiting their deployment in multiple cases. To overcome this issue, this study introduces a multi-domain video quality enhancement architecture based on the Spatio-Temporal Deformable Fusion (STDF) technique. This method enables the model to enhance videos compressed with multiple codecs, maintaining reliable performance across standards. After trained, the proposed architecture was tested with videos compressed by the High Efficiency Video Coding (HEVC) encoder, the Versatile Video Coding (VVC) encoder, the VP9 codec and the AOMedia Video 1 (AV1) codec. Results show an average Peak Signal-to-Noise Ratio (PSNR) improvement between 0.228 dB and 0.787 dB.

关键词： Training Visualization Codecs PSNR Artificial neural networks Video compression Quality assessment Video recording Standards High efficiency video coding

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

Developer-Centric Task Allocation: An Intelligent Approach for Enhanced Software Productivity 15

Developer-Centric Task Allocation: An Intelligent Approach f...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Fensterseifer Filho, Evandro L. R. Assuncao, Joaquim V. C. Fontoura, Lisandra M. Federal University of Santa Maria - Ufsm Graduate Program in Computer Science RS Santa Maria Brazil Federal University of Santa Maria - Ufsm Applied Computing Department RS Santa Maria Brazil

ISBN: (纸本)9798350368833

Software projects are affected by technical knowledge as well as the personality of the team. Such factors can reduce or increase the software quality and development speed. For successful task allocation, it is essential to consider the skills and profile of each developer, thus maximizing their productivity. In projects with large teams, task allocation can be challenging, and the help of tools can facilitate its execution. In this work, we propose an intelligent approach for allocating software development tasks suitable to the profile of developers. From the literature, we define the appropriate skills and technical profiles for a development team, and the assessment is based on the developer completing a questionnaire. We developed a recommendation system to suggest tasks to be allocated to developers, employing text processing techniques. For validation, 495 tasks were used from an actual project developing simulator software for military training. The recommended allocations were evaluated by the project developers and used to improve the system. Validations showed that the developed approach makes consistent and coherent task recommendations to developers according to the developer profile, as participants agree with the recommendation for 76% of tasks. © 2024 IEEE.

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

Applying the Diamond Model of Intrusion Analysis: Brazil's Operation 'Car Wash' Cyberattack

Applying the Diamond Model of Intrusion Analysis: Brazil's O...

引用

2022 International Symposium on Networks, Computers and Communications, ISNCC 2022

作者： Ximenes, Pablo Mello, Patricia School of Cybersecurity and Privacy College of Computing Atlanta United States Computer Science Graduate Program Fortaleza Brazil

ISBN: (数字)9781665485449

ISBN: (纸本)9781665485449

This paper uses the Diamond Model of intrusion analysis to discuss the intricacies and unfoldings of the cyberattack that enabled Operation 'Car Wash' leak (nicknamed 'VazaJato'), one of the most significant leaks in Brazil's political history. Our discussion tries to understand the cyberattack that took place in a threat intelligence perspective and, as a result, it draws conclusions and presents an assessment and some recommendations with regards to cybersecurity policy. © 2022 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Coding Efficiency-Aware Hardware Design for VVC Affine Motion Estimation Reconstructor

IEEE Design and Test

引用

IEEE Design and Test 2025年

作者： Muñoz, Marcello M. Maass, Denis Perleberg, Murilo Agostini, Luciano Corrêa, Guilherme Porto, Marcelo Graduate Program in Computing - PPGC Video Technology Research Group ViTech Federal University of Pelotas - UFPel Pelotas Brazil

One of the most important new tools of the Versatile Video Coding (VVC) standard is the Affine Motion Estimation (AME). The AME contribution to the coding efficiency comes with a high computational cost, especially for real-time high-resolution video encoding, making dedicated hardware for battery-powered devices mandatory. Considering this scenario, this work presents a dedicated hardware design for the Affine Reconstructor of the VVC standard, focusing on high coding efficiency for real-time processing of UHD video. ASIC synthesis results show a circuit area of 179.9k Gates, with a power dissipation of 107.76 mW when targeting the processing of 4K UHD@60fps videos. The proposed design shows the lowest impact in BD-Rate (only 0.54%) in the current literature. © 2013 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Accuracy-Exploration Model for Low-Energy and Gates-Free Approximate Adder Compressors

Accuracy-Exploration Model for Low-Energy and Gates-Free App...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Leonardo Antonietti Morgana da Rosa Eduardo da Costa Rafael Soares Graduate Program on Computing - Federal University of Pelotas (UFPel) Pelotas Brazil Gruduate Program on Electronic Engineering and Computing - Catholic University of Pelotas (UCPel) Pelotas Brazil

ISBN: (数字)9798350377200

ISBN: (纸本)9798350377217

This paper proposes a model for accurately exploring approximate adder compressors (AxAC) utilizing gates-free logic. As case studies, we explore energy-efficient architectures of approximate 3–2 (Ax3-2), 4–2 (Ax4-2), and 5–2 (Ax5-2) adder compressors (AC), focusing exclusively on gates-free in the critical path. This model for the accuracy analysis of AxACs is essential for estimating the optimal arrangements with repetition (AR) of inputs that are the way outputs for these compressors. For instance, the exact 4–2 AC has five inputs (A, B, C, D, and Cin) and three outputs (Cout, Carry, and Sum). Specifically, the Ax3-2 AC generates nine possible architectural-space gates-free AR, the Ax4-2 AC generates 125, and the Ax5-2 AC generates 2, 401 possible output AR. To estimate all output AR, we implemented the accuracy-exploration model in Python. After identifying the best AR, we created a Pareto front addressing the trade-offs between accuracy, energy, and area. The Ax3-2, Ax4-2, and Ax5-2 proposals demonstrate substantial energy and area efficiency improvements while maintaining high accuracy.

关键词： Analytical models Accuracy Focusing Logic gates Compressors Energy efficiency Proposals Integrated circuit modeling Adders Electronic circuits

来源：评论

学校读者我要写书评

暂无评论

A Physical-Based Artificial Neural Networks Compact Modeling Framework for Emerging FETs

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 223-230页

作者： Yang, Ya-Shu Li, Yiming Kola, Sekhar Reddy Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory The Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Institute of Communications Engineering Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan

We report a compact modeling framework based on the Grove-Frohman (GF) model and artificial neural networks (ANNs) for emerging gate-all-around (GAA) MOSFETs. The framework consists of two ANNs;the first ANN constructed with the drain current model not only can capture the main trend of device I - V characteristics but also can predict its variation even when the amount of training data for the ANN is insufficient or outside the range of applied biases. The second one is then designed to improve the model accuracy by further minimizing the errors between the target and the model outputs. We implement the proposed framework to accurately model emerging GAA nanosheet (NS) MOSFETs and complementary FETs (CFETs) without suffering from divergent issues in circuit simulation. In addition, nonphysical behaviors, such as nonzero current at zero bias, do not occur in the modeling framework. Compared to recently reported machine-learning (ML) models, our approach can achieve a similar level of model accuracy with merely 20% amount of the training data. © 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

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：