检索结果-内蒙古大学图书馆

SINGER SEPARATION FOR KARAOKE CONTENT GENERATION

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lin, Hsuan-Yu Chen, Xuanjun Jang, Jyh-Shing Roger Graduate Institute of Networking and Multimedia Taiwan Graduate Institute of Communication Engineering Taiwan Dept. of Computer Science and Information Engineering National Taiwan University Taipei Taiwan

Due to the rapid development of deep learning, we can now successfully separate singing voice from mono audio music. However, this separation can only extract human voices from other musical instruments, which is undesirable for karaoke content generation applications that only require the separation of lead singers. For this karaoke application, we need to separate the music containing male and female duets into two vocals, or extract a single lead vocal from the music containing vocal harmony. For this reason, we propose in this article to use a singer separation system, which generates karaoke content for one or two separated lead singers. In particular, we introduced three models for the singer separation task and designed an automatic model selection scheme to distinguish how many lead singers are in the song. We also collected a large enough data set, MIR-SingerSeparation 1, which has been publicly released to advance the frontier of this research. Our singer separation is most suitable for sentimental ballads and can be directly applied to karaoke content generation. As far as we know, this is the first singer-separation work for real-world karaoke applications. © 2021, CC BY.

关键词： Source separation

FAD-SAR: A Novel Fishing Activity Detection System via Synthetic Aperture Radar Images Based on Deep Learning Method

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bai, Yanbing Li, Siao Ju, Rui-Yang Yang, Zihao Yu, Jinze Chiang, Jen-Shiun Center for Applied Statistics School of Statistics Renmin University of China Beijing100872 China Graduate Institute of Networking and Multimedia National Taiwan University Taipei City106335 Taiwan Department of Mechanical Systems Engineering Tokyo University of Agriculture and Technology Tokyo183-8538 Japan Department of Electrical and Computer Engineering Tamkang University New Taipei City251301 Taiwan

Illegal, unreported, and unregulated (IUU) fishing activities seriously affect various aspects of human life. However, traditional methods for detecting and monitoring IUU fishing activities at sea have limitations. Although synthetic aperture radar (SAR) can complement existing vessel detection systems, extracting useful information from SAR images using traditional methods remains a challenge, especially in IUU fishing. This paper proposes a deep learning based fishing activity detection system, which is implemented on the xView3 dataset using six classical object detection models: SSD, RetinaNet, FSAF, FCOS, Faster R-CNN, and Cascade R-CNN. In addition, this work employs different enhancement techniques to improve the performance of the Faster R-CNN model. The experimental results demonstrate that training the Faster R-CNN model using the Online Hard Example Mining (OHEM) strategy increases the Avg-F1 value from 0.212 to 0.216. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

A Hybrid Approach for Binary Classification of Imbalanced Data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tsai, Hsin-Han Yang, Ta-Wei Wong, Wai-Man Chou, Cheng-Fu Department of Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei10617 Taiwan Information Technology Office National Taiwan University Hospital Taipei100225 Taiwan

Binary classification with an imbalanced dataset is challenging. Models tend to consider all samples as belonging to the majority class. Although existing solutions such as sampling methods, cost-sensitive methods, and ensemble learning methods improve the poor accuracy of the minority class, these methods are limited by overfitting problems or cost parameters that are difficult to decide. We propose HADR, a hybrid approach with dimension reduction that consists of data block construction, dimentionality reduction, and ensemble learning with deep neural network classifiers. We evaluate the performance on eight imbalanced public datasets in terms of recall, G-mean, and AUC. The results show that our model outperforms state-of-the-art methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning systems

Lower Bounds for the Minimum Spanning Tree Cycle Intersection Problem

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Dubinsky, Manuel Chao, Kun-Mao Massri, César Taubin, Gabriel Ingeniería en Informática Departamento de Tecnología y Administración Universidad Nacional de Avellaneda Argentina Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan Departamento de Matemática Universidad de CAECE CABA Argentina School of Engineering Brown University ProvidenceRI United States

Minimum spanning trees are important tools in the analysis and design of networks. Many practical applications require their computation, ranging from biology and linguistics to economy and telecommunications. The set of cycles of a network has a vector space structure. Given a spanning tree, the set of non-tree edges defines cycles that determine a basis. The intersection of two such cycles is the number of edges they have in common and the intersection number -denoted $\cap(G)$-, is the number of non-empty pairwise intersections of the cycles of the basis. The Minimum Spanning Tree Cycle Intersection problem consists in finding a spanning tree such that the intersection number is minimum. This problem is relevant in order to integrate discrete differential forms. In this paper, we present two lower bounds of the intersection number of an arbitrary connected graph $G=(V,E)$. In the first part, we prove the following statement:[[EQUATION]]where $n = |V|$ and $\nu$ is the \emph{cyclomatic number} of $G$. In the second part, based on some experimental results and a new observation, we conjecture the following improved tight lower bound:[[EQUATION]]where $2 \nu = q (n-1) + r$ is the integer division of $2 \nu$ and $n-1$. This is the first result in a general context, that is for an arbitrary connected graph. © 2024, The Authors. All rights reserved.

关键词： Vector spaces

Weak Devices Matter: Model Heterogeneity in Resource-Constrained Federated Learning

学校读者我要写书评

暂无评论

Weak Devices Matter: Model Heterogeneity in Resource-Constra...

IEEE International Conference on Communications (ICC)

作者： Tzu–Hsuan Peng Cheng-Wei Huang Ai-Chun Pang Te-Chuan Chiu Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan R.O.C Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan R.O.C High Performance and Scientific Computing Center National Taiwan University Taipei Taiwan R.O.C Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan R.O.C Department of Computer Science National Tsing Hua University Hsinchu Taiwan R.O.C

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Federated Learning (FL) is a promising framework for enabling edge intelligence while preserving privacy and enhancing communication efficiency. In real-world scenarios, limited and heterogeneous hardware resources among users threaten the overall training efficiency in FL. To address this issue, several model heterogeneity frameworks have emerged in recent years. However, existing studies primarily focus on mitigating idle times on powerful devices, overlooking the fact that strong devices may not always have a positive impact and can potentially become a burden instead. Furthermore, as the resource gap among clients widens or the number of weak devices increases, the model may be hindered by the influence of strong devices. Directly applying existing model heterogeneity frameworks leads to model performance degradation due to the neglect of contributions from weak devices. To make a performance breakthrough, we proposed a novel FL framework called Progressive Width Mixing (PWM), which extracts diverse features and balances the contribution of strong and weak devices and mitigates straggler effects under scenarios with various device distributions. To our best knowledge, we are the first model heterogeneity work that considered straggler effects from the weak devices' point of view. The experiments show that PWM maintains stability over different datasets and outperforms all baselines across various device distributions and non-IID scenarios. PWM makes a leap forward and surpasses all baselines by 7%, and mitigates the negative impact from the strong devices.

关键词： Performance evaluation Training Privacy Philosophical considerations Federated learning Pulse width modulation System recovery

YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chien, Chun-Tse Ju, Rui-Yang Chou, Kuang-Yi Xieerke, Enkaer Chiang, Jen-Shiun Department of Electrical and Computer Engineering Tamkang University New Taipei City251301 Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei City106335 Taiwan School of Nursing National Taipei University of Nursing and Health Sciences Taipei City112303 Taiwan College of Energy and Mechanical Engineering Shanghai University of Electric Power Shanghai201306 China

Wrist trauma and even fractures occur frequently in daily life, particularly among children who account for a significant proportion of fracture cases. Before performing surgery, surgeons often request patients to undergo X-ray imaging first and prepare for it based on the analysis of the radiologist. With the development of neural networks, You Only Look Once (YOLO) series models have been widely used in fracture detection as computer-assisted diagnosis (CAD). In 2023, Ultralytics presented the latest version of the YOLO models, which has been employed for detecting fractures across various parts of the body. Attention mechanism is one of the hottest methods to improve the model performance. This research work proposes YOLOv8-AM, which incorporates the attention mechanism into the original YOLOv8 architecture. Specifically, we respectively employ four attention modules, Convolutional Block Attention Module (CBAM), Global Attention Mechanism (GAM), Efficient Channel Attention (ECA), and Shuffle Attention (SA), to design the improved models and train them on GRAZPEDWRI-DX dataset. Experimental results demonstrate that the mean Average Precision at IoU 50 (mAP 50) of the YOLOv8-AM model based on ResBlock + CBAM (ResCBAM) increased from 63.6% to 65.8%, which achieves the state-of-the-art (SOTA) performance. Conversely, YOLOv8-AM model incorporating GAM obtains the mAP 50 value of 64.2%, which is not a satisfactory enhancement. Therefore, we combine ResBlock and GAM, introducing ResGAM to design another new YOLOv8-AM model, whose mAP 50 value is increased to 65.0%. The implementation code for this study is available on GitHub at https://***/RuiyangJu/Fracture_Detection_Improved_YOLOv8. Copyright © 2024, The Authors. All rights reserved.

关键词： Medical image processing

Evaluation of the Montenegrin Academic Digital Innovation Hub 27

学校读者我要写书评

暂无评论

Evaluation of the Montenegrin Academic Digital Innovation Hu...

27th International Conference on Information Technology, IT 2023

作者： Lakovic, Luka Kara, Peter A. Ognjanovic, Ivana Bokor, Laszlo Sendelj, Ramo Reich, Christoph Roganovic, Milovan Zoulias, Emmanouil Erakovic, Jevto Radusinovic, Tanja Rakocevic, Nada Simon, Aniko University of Donja Gorica Faculty for Information Systems and Technologies Podgorica81000 Montenegro Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Networked Systems and Services Budapest1111 Hungary Faculty of Science Engineering and Computing Kingston University Wireless Multimedia and Networking Research Group Department of Computer Science School of Computer Science and Mathematics LondonKT1 2EE United Kingdom University of Donja Gorica Humanistic Studies Podgorica81000 Montenegro Furtwangen University Institute of Data Science Cloud Computing and It Security Furtwangen78120 Germany Clinical Centre of Montenegro Clinic for Neurology Podgorica81000 Montenegro National and Kapodistrian University of Athens Faculty of Nursing School of Health Sciences Goudi 11527 Greece Chamber of Economy of Montenegro Podgorica81000 Montenegro Sigma Technology Budapest1093 Hungary

ISBN: (纸本)9798350397512

In the era of global digitalization, digital innovation hubs have become essential, as they function as transforming forces. In this paper, we provide an analysis of the Montenegrin Academic Digital Innovation Hub by applying multi-criteria qualitative evaluation over several criteria: process flow of fully digitized operations of the Hub (with aspects of the innovation life-cycle, ethics, and security), resource management, strategic goals, and feasibility. The paper also proposes a model of comprehensive resource management via the perspective of smart specialization priorities of Montenegro. © 2023 IEEE.

关键词： Life cycle

Assistive Technical Communication of Montenegrin eServices: a Case Study 27

学校读者我要写书评

暂无评论

Assistive Technical Communication of Montenegrin eServices: ...

27th International Conference on Information Technology, IT 2023

作者： Simon, Aniko Lakovic, Luka Kovacevic, Pavle Kara, Peter A. Ognjanovic, Ivana Sendelj, Ramo Reich, Christoph Roganovic, Milovan Mantas, John Bokor, Laszlo Sigma Technology Budapest1093 Hungary University of Donja Gorica Faculty for Information Systems and Technologies Podgorica81000 Montenegro Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Networked Systems and Services Budapest1111 Hungary Kingston University Wireless Multimedia and Networking Research Group Department of Computer Science School of Computer Science and Mathematics Faculty of Science Engineering and Computing LondonKT1 2EE United Kingdom University of Donja Gorica Humanistic Studies Podgorica81000 Montenegro Furtwangen University Institute of Data Science Cloud Computing and It Security Furtwangen78120 Germany Clinical Centre of Montenegro Clinic for Neurology Podgorica81000 Montenegro National and Kapodistrian University of Athens Faculty of Nursing School of Health Sciences Goudi 11527 Greece

ISBN: (纸本)9798350397512

With the advancement of information technology in the recent decades, digital and online services have become essential components of everyday life in Europe. Montenegro is no different in this regard. However, as digital literacy in the country is still in a developing phase in comparison with most countries of the EU, a higher portion of its citizens may rely on assistive technical communication. In this paper, we provide a case study on the assistive technical communication of Montenegrin eServices. The work addresses the sectors of online banking, healthcare services, higher education, national administrative services, and utilities. Our findings highlight the diversity in terms of implemented assistive technical communication, and distinguish usage contexts on the level of adequacy. Yet as the functionalities of Montenegrin eServices are expected to gradually expand in the upcoming years, assistive technical communication must aim to handle the higher extents of service complexity. © 2023 IEEE.

关键词：

RETHINKING THE IMPLEMENTATION TRICKS AND MONOTONICITY CONSTRAINT IN COOPERATIVE MULTI-AGENT REINFORCEMENT LEARNING

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Jian Jiang, Siyang Harding, Seth Austin Liao, Shih-Wei Wu, Haibin Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan Graduate Institute of Electrical Engineering National Taiwan University Taipei Taiwan Department of Computer Science National Taiwan University Taipei Taiwan Graduate Institute of Communication Engineering National Taiwan University Taipei Taiwan

Many complex multi-agent systems such as robot swarms control and autonomous vehicle coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a widely popular MARL algorithm, has been used as a baseline for the benchmark environments, e.g., Starcraft Multi-Agent Challenge (SMAC), Difficulty-Enhanced Predator-Prey (DEPP). Recent variants of QMIX target relaxing the monotonicity constraint of QMIX, allowing for performance improvement in SMAC. In this paper, we investigate the code-level optimizations of these variants and the monotonicity constraint. (1) We find that such improvements of the variants are significantly affected by various code-level optimizations. (2) The experiment results show that QMIX with normalized optimizations outperforms other works in SMAC;(3) beyond the common wisdom from these works, the monotonicity constraint can improve sample efficiency in SMAC and DEPP. We also discuss why monotonicity constraints work well in purely cooperative tasks with a theoretical analysis. We open-source the code at https://***/hijkzzz/pymarl2. Copyright © 2021, The Authors. All rights reserved.

关键词： Multi agent systems