检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zheng, Fang Zhou, Hang Li, Guoliang Ni, Fuchuan Huazhong Agricultural University Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Key Laboratory of Smart Farming Technology for Agricultural Animals Ministry of Agriculture and Rural Affairs College of Informatics Wuhan China Huazhong Agricultural University College of Informatics Wuhan China Hubei Engineering Technology Research Center of Agricultural Big Data Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan China

ISBN: (纸本)9798350386226

While convolutional neural network(CNN) have historically achieved significant success in 3D medical image segmentation, recent advancements in Vision Transformer (ViT) have led to increased popularity of Transformer architectures in this field. Leveraging the global information extraction capabilities of Transformers, we propose a novel parallel structure combining CNN and Transformer for multimodal brain tumor segmentation, named PTCNet. We introduce two key improvements to enhance multimodal segmentation:1) Introducing a novel channel attention module that replaces spatial self-attention in the Transformer to improve cross-modal information extraction.2) Enhancing the reversible feature extraction module based on residual structures to better detect small lesions. We evaluated our method on the BraTS 2023 brain metastasis dataset, achieving an average DSC of 61.42%, which is 1.12% higher than the second place. The innovative structure and improved modules of PTCNet significantly enhance performance in multimodal brain tumor segmentation tasks. Code and models are available at https://***/naiqizh/PTCNet. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Effective 3C Resource Utilization and Fair Allocation Strategy for Multi-Task Federated Learning

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2023年 1卷 153-167页

作者： Zhang, Chaofeng Dong, Mianxiong Ota, Kaoru School of Information and Electronic Engineering Advanced Institute of Industrial Technology Shinagawa Tokyo140-0011 Japan Department of Sciences and Informatics Muroran Institute of Technology Muroran050-0071 Japan

Nowadays, one of the main challenges in expanding AI applications is the effective use of Computation, Communication, and Caching (3C) resources. The complexity of the cloud environment and the diversity of resource usage make it challenging to complete federated learning tasks in a cost-effective, timely, and seamless manner. To address these issues, this paper proposes a comprehensive approach to optimize the overall service efficiency of federated learning in time-varying and 3C-constrained environments. Firstly, a utility function based on convergence efficiency is proposed to reflect the physical benefits of processing AI tasks. Then, a fair allocation strategy consistent with the optimization goal is designed by modeling the task allocation process through virtual queue Lyapunov drift. Next, a Federated Learning Long Short-Term Memory (LSTM) based Queuing Optimization and Allocation Policy Calculation Algorithm (FL-QAPC) is proposed for resource allocation policy calculation using multi-dimensional network state inputs with time series. This algorithm implements predictive control based on historical records. Finally, a feasible experimental test platform is conducted, which is extended to an actual wireless mobile scenario based on 5G. The superiority of the proposed solution is verified through comparison with other benchmarks. © 2023 Institute of Electrical and Electronics Engineers. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

The effect of augmentation and filtration on noisy environment's acoustic signals to detect abnormalities in industrial machines based on artificial neural networks 14

The effect of augmentation and filtration on noisy environme...

引用

14th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2023 and The 6th International Conference on Emerging Data and Industry 4.0, EDI40 2023

作者： Qurthobi, Ahmad Maskeliunas, Rytis Department of Multimedia Engineering Faculty of Informatics Kaunas University of Technology Studentust. 50 Kaunas51368 Lithuania

The use of acoustic methods for failure detection is increasing in recent times. By using the acoustic method, some features related to the condition of the equipment under test can also be extracted. The main objective of this study was to compare the effect of using filters and augmentation on audio signals in the data training process on the accuracy and loss generated during training and testing. The model is developed using an artificial neural network. The MIMII dataset, which can be accessed openly, is being used for training and testing purposes. Based on the four scenarios designed, it can be seen that the movement of changes in accuracy values in tests involving the use of original data and augmented data is faster (close to 100% after the twentieth epoch) than the other methods. This is because the augmentation process in the form of a time shift does not change the signal in the frequency domain. Moreover, the test signal used is a periodic signal. © 2023 Elsevier B.V.. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

NUMERICAL ASPECTS OF THE CO-ROTATING VORTEX PAIR PROBLEM IN AEROACOUSTICS 10

NUMERICAL ASPECTS OF THE CO-ROTATING VORTEX PAIR PROBLEM IN ...

引用

10th Convention of the European Acoustics Association, EAA 2023

作者： Ulveczki, Mihály Ádám Rucz, Péter Faculty of Electrical Engineering and Informatics Dept. of Networked Systems and Services Budapest University of Technology and Economics Hungary

ISBN: (纸本)9788888942674

The co-rotating vortex pair is a well-known test problem for validating aeroacoustic computational frameworks. Both the flow field and the radiated acoustic far-field can be determined analytically, which allows for the direct comparison of all associated quantities. However, in order to simulate the vortex pair using numerical methods, several approximations must be made. One problem is caused by the singular velocity field at the center of the potential vortex, which must be treated by desingularization that also affects the resulting source terms. Another challenge in finite element formulations is the handling of the unbounded domain, which needs to be artificially truncated. In our paper, the numerical aspects of the vortex pair problem are examined. The effects of the necessary approximations including the desingularization of the vortex-core and discretization to different computational methods are investigated. A method relying on the direct integration of the source terms is compared to different finite element solution strategies. Convergence tests are carried out and discussed for formulations of Lighthill's equation and the perturbed convective wave equation in the frequency domain. © 2023 Ulveczki and Rucz. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization? 38

How Does Black-Box Impact the Learning Guarantee of Stochast...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Jun Chen, Hong Gu, Bin College of Informatics Huazhong Agricultural University China College of Informatics Huazhong Agricultural University China Engineering Research Center of Intelligent Technology for Agriculture China School of Artificial Intelligence Jilin University Mohamed bin Zayed University of Artificial Intelligence China

Stochastic compositional optimization (SCO) problem constitutes a class of optimization problems characterized by the objective function with a compositional form, including the tasks with known derivatives, such as AUC maximization, and the derivative-free tasks exemplified by black-box vertical federated learning (VFL). From the learning theory perspective, the learning guarantees of SCO algorithms with known derivatives have been studied in the literature. However, the potential impacts of the derivative-free setting on the learning guarantees of SCO remains unclear and merits further investigation. This paper aims to reveal the impacts by developing a theoretical analysis for two derivative-free algorithms, black-box SCGD and SCSC. Specifically, we first provide the sharper generalization upper bounds of convex SCGD and SCSC based on a new stability analysis framework more effective than prior work under some milder conditions, which is further developed to the non-convex case using the almost co-coercivity property of smooth function. Then, we derive the learning guarantees of three black-box variants of non-convex SCGD and SCSC with additional optimization analysis. Comparing these results, we theoretically uncover the impacts that a better gradient estimation brings a tighter learning guarantee and a larger proportion of unknown gradients may lead to a stronger dependence on the gradient estimation quality. Finally, our analysis is applied to two SCO algorithms, FOO-based vertical VFL and VFL-CZOFO, to build the first learning guarantees for VFL that align with the findings of SCGD and SCSC. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced Malware Analysis Methods: Behaviour-Based Detection and Reverse engineering 18

Advanced Malware Analysis Methods: Behaviour-Based Detection...

引用

18th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2024

作者： Widiyasono, Nur Selamat, Siti Rahayu Rizal, Randi Fidayan, Abdul Mulyani, Sri Rochani Risnanto, Slamet Siliwangi University Faculty of Engineering Dept. of Informatics Tasikmalaya Indonesia Universiti Teknikal Malaysia Melaka Faculty of Information and Communication Technology Malaysia Universitas Sangga Buana Bandung Indonesia Universitas Sangga Buana Dept. of Informatics Bandung Indonesia

ISBN: (纸本)9798331527686

The tesla malware agent attacked around 4.1% of the networks of various industrial companies. Agent tesla malware can harvest user credentials from various popular applications including Microsoft Edge, Mozilla Firefox, and Google Chrome, becoming a global threat in various sectors and organizations around the world. In addition, the problem is that hackers using the agent tesla malware adopt more sophisticated spear-phishing campaigns and can use more sophisticated social engineering techniques to exploit vulnerabilities. So, with these problems, deeper analysis and implementation of holistic security measures are needed to combat threats, knowing the characteristics and ways to overcome the agent tesla malware in maintaining system and data integrity. This research focuses on overcoming this problem by comparing methods using behavior-based detection (virtual machine), behavior-based detection (sandbox), and reverse engineering to analyze the agent tesla malware. Behavior-based detection is used to observe malware activity when it is running on a computer or virtual machine. Meanwhile, reverse engineering is used to obtain the source code of the malware. The results of the agent tesla malware research analysis obtained using this method are that the malware can steal information from the victim's computer such as the computer username, as well as email and password information contained in the browser. The way the agent tesla malware works is to infect the system, read data on the computer and save the necessary data. Based on the test results in this research, the behavior-based detection (sandbox) method can reveal more actions in the malware with a total of 3877 or 185% more than the reverse engineering method. © 2024 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Structure of Electricity Market in Indonesia and The Challenge of Integrating Large Scale VRE 6

Structure of Electricity Market in Indonesia and The Challen...

引用

6th International Conference on Power engineering and Renewable Energy, ICPERE 2024

作者： Isnandar, Suroso Bambang Anggoro Soedjarno, P. Hariyanto, Nanang Tampubolon, Daniel K.F. Jakarta Indonesia Institute of Technology Bandung School of Electrical Engineering and Informatics Bandung Indonesia Risk Management Strategic Policy Division Jakarta Indonesia

ISBN: (纸本)9798331504694

The electricity market in Indonesia is predominantly managed by the state-owned company, Perusahaan Listrik Negara (PLN), which operates as a vertically integrated utility. In recent years, the market has seen increased private sector participation, particularly in electricity generation. This paper provides a comprehensive overview of Indonesia's electricity market, focusing on its structure and the challenges associated with integrating large-scale Variable Renewable Energy (VRE). The integration of VRE presents multifaceted challenges that span technical, economic, regulatory, and social dimensions. Addressing these challenges requires coordinated efforts from all stakeholders, including government agencies, private sector players, and local communities. This paper highlights the significant role of PLN in promoting Rooftop Solar PV (PLTS Atap) and emphasizes the need for substantial investments in technology, infrastructure, and innovative financing schemes to achieve effective VRE integration. By adopting a holistic approach, Indonesia can navigate these challenges and transition towards a more sustainable and resilient energy future. This paper introduces techno-economic risk assessment to identify all risk factors associated with the large VRE integration. Along with the assessment, several risk mitigations will be addressed. This paper also discusses the impacts of energy policies, the structure of different electricity market models, and the strategic plans laid out by the Indonesian government to enhance energy security, access, and environmental sustainability. © 2024 IEEE.

关键词： Power markets

来源：评论

学校读者我要写书评

暂无评论

Optimizing Object Detection Models via Active Learning 11th

Optimizing Object Detection Models via Active Learning

引用

11th Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2023

作者： Costa, Dinis Silva, Catarina Costa, Joana Ribeiro, Bernardete Department of Informatics Engineering CISUC Coimbra Portugal School of Technology and Management Polytechnic Institute of Leiria Leiria Portugal

ISBN: (纸本)9783031366154

Object detection models have made significant progress and achieved state-of-the-art performance, which can now be comparable to human experts in various domains. However, training such models often requires a large amount of labeled data, which can be challenging to obtain. To address this issue, Active Learning (AL) has emerged as a technique to enhance the efficiency of deep learning models by reducing the amount of data and time required to train models to a satisfactory level. In this paper, in the context of smart farming, we propose to study the impact of AL in object detection models trained with a small dataset of labelled images of whitefly-infested tomato leaves. We use YOLOv5 and fit the bounding box with confidence as a score function to select the most active relevant examples. The results show a trade-off between performance and cost suggesting AL outweigh the associated costs when labelled training data is limited. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Fractional Linear Matroid Matching Is in Quasi-NC 32

Fractional Linear Matroid Matching Is in Quasi-NC

引用

32nd Annual European Symposium on Algorithms, ESA 2024

作者： Gurjar, Rohit Oki, Taihei Raj, Roshan Department of Computer Science and Engineering Indian Institute of Technology Bombay Mumbai India Department of Mathematical Informatics Graduate School of Information Science and Technology The University of Tokyo Japan

ISBN: (纸本)9783959773386

The matching and linear matroid intersection problems are solvable in quasi-NC, meaning that there exist deterministic algorithms that run in polylogarithmic time and use quasi-polynomially many parallel processors. However, such a parallel algorithm is unknown for linear matroid matching, which generalizes both of these problems. In this work, we propose a quasi-NC algorithm for fractional linear matroid matching, which is a relaxation of linear matroid matching and commonly generalizes fractional matching and linear matroid intersection. Our algorithm builds upon the connection of fractional matroid matching to non-commutative Edmonds' problem recently revealed by Oki and Soma (2023). As a corollary, we also solve black-box non-commutative Edmonds' problem with rank-two skew-symmetric coefficients. © Rohit Gurjar, Taihei Oki, and Roshan Raj;licensed under Creative Commons License CC-BY 4.0.

关键词： Parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Feedforward control of flat hybrid automata: a behavioral systems theory approach 63

Feedforward control of flat hybrid automata: a behavioral sy...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Zahn, Frederik Kleinert, Tobias Hagenmeyer, Veit Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Karlsruhe Germany Rwth Aachen University Chair of Process Control Engineering Aachen Germany

ISBN: (纸本)9798350316339

Differential flatness has been defined in the literature for continuous time dynamical systems and for discrete time systems. We define flatness of automata from the perspective of behavioral systems theory, and synthesize a flatness definition for hybrid automata. These new definitions allow for feedforward trajectory generation for flat hybrid automata. Additionally, we provide necessary and sufficient conditions of hybrid automaton flatness for different types of continuous state constraints and switching conditions, and how to compute whether a hybrid automaton is flat. We illustrate feedforward trajectory generation based on our findings for a robotic manipulator example. © 2024 IEEE.

关键词： Continuous time systems

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：