检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Lin, Jingru Ge, Meng Wang, Wupeng Li, Haizhou Feng, Mengling Department of Electrical and Computer and Engineering National University of Singapore Singapore119077 Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore117549 Singapore Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China

Self-supervised pre-trained speech models were shown effective for various downstream speech processing tasks. Since they are mainly pre-trained to map input speech to pseudo-labels, the resulting representations are only effective for the type of pre-train data used, either clean or mixture speech. With the idea of selective auditory attention, we propose a novel pre-training solution called Selective-HuBERT, or SHuBERT, which learns the selective extraction of target speech representations from either clean or mixture speech. Specifically, SHuBERT is trained to predict pseudo labels of a target speaker, conditioned on an enrolled speech from the target speaker. By doing so, SHuBERT is expected to selectively attend to the target speaker in a complex acoustic environment, thus benefiting various downstream tasks. We further introduce a dual-path training strategy and use the cross-correlation constraint between the two branches to encourage the model to generate noise-invariant representation. Experiments on SUPERB benchmark and LibriMix dataset demonstrate the universality and noise-robustness of SHuBERT. Furthermore, we find that our high-quality representation can be easily integrated with conventional supervised learning methods to achieve significant performance, even under extremely low-resource labeled data. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Bounds on the ground state energy of quantum p-spin Hamiltonians

arXiv

引用

arXiv 2024年

作者： Anschuetz, Eric R. Gamarnik, David Kiani, Bobak T. Institute for Quantum Information and Matter Caltech Walter Burke Institute for Theoretical Physics Caltech MIT Center for Theoretical Physics MIT United States Operations Research Center Statistics and Data Science Center Sloan School of Management MIT United States John A. Paulson School of Engineering and Applied Sciences Department of Electrical Engineering and Computer Science MIT Harvard United States

We consider the problem of estimating the ground state energy of quantum p-local spin glass random Hamiltonians, the quantum analogues of widely studied classical spin glass models. Our main result shows that the maximum energy achievable by product states has a well-defined limit (for even p) as n → ∞ and is Eproduct∗ = √2 log p in the limit of large p. This value is interpreted as the maximal energy of a much simpler so-called Random Energy Model, widely studied in the setting of classical spin glasses. The proof of the limit existing follows from an extension of Fekete’s Lemma after we demonstrate near super-additivity of the (normalized) quenched free energy. The proof of the value follows from a second moment method on the number of states achieving a given energy when restricting to an ǫ-net of product states. Furthermore, we relate the maximal energy achieved over all states to a p-dependent constant γ (p), which is defined by the degree of violation of a certain asymptotic independence ansatz over graph matchings. We show that the maximal energy achieved by all states E∗ (p) in the limit of large n is at most pγ (p)Eproduct∗ . We also prove using Lindeberg’s interpolation method that the limiting E∗ (p) is robust with respect to the choice of the randomness and, for instance, also applies to the case of sparse random Hamiltonians. This robustness in the randomness extends to a wide range of random Hamiltonian models including SYK and random quantum max-cut. Copyright © 2024, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Monarch Butterfly Optimization based Multi-Convolution Neural Network for Lung Cancer Classification

Monarch Butterfly Optimization based Multi-Convolution Neura...

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： Uma Maheswari S Myasar Mundher adnan Lathakumari K R Pradeep V Hirald Dwaraka Praveena Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science The Islamic university Najaf Iraq Dept of ECE Nitte Meenakshi Institute of Technology Bengaluru India Department of Information Science and Engineering Alva's Institute of Engineering and Technology Mangalore India Department of ECE School of Engineering Mohan Babu University Erstwhile Sree Vidya nikethan Engineering College Andhra Pradesh India

The lung cancer generally presented a pulmonary nodule on images of diagnostic and correct estimation in malignant pulmonary nodules is difficult for diagnosis and protecting of lung cancer. However, the existing methods has less classification accuracy because of irrelevant features on classification of lung cancer. In this research, proposed a Monarch Butterfly Optimization based Multi-Convolution Neural Network (MBO based M-CNN) method for lung cancer classification. dataset used for lung cancer classification is LIDC-IDRI dataset and it is pre-processed by Histogram Equalization (HE). Then, the features are extracted by Gray Level Co-occurrence Matrix (GLCM) and extracted features are selected by Monarch Butterfly Optimization (MBO) algorithm. Then, the lung cancer classification is performed by Multi-Convolution Neural Network (M-CNN). The performance of proposed algorithm is tested in terms of accuracy, precision, sensitivity and specificity. Developed technique obtained accuracy 99.71%, precision 95.39%, sensitivity 99.46%, f1-score 97.45% that is better than previous method like Adaptive Boosting Self-Normalized Multiview Convolution Neural Network (AdaBoost-SNMV-CNN).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on multi-interface and multi-channel Routing protocols for Channel Allocation and Path Selection

Research on multi-interface and multi-channel Routing protoc...

引用

Chinese Automation Congress (CAC)

作者： Zhong Hui Peng Wenbo Liaoning Province Big Data Management and Analysisline Laboratory of Urban Construction School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China

Wireless mesh network is a wireless multi hop mesh topology network, which is a very promising wireless network access technology. Multi interface multi-channel wireless mesh network can further release the performance of mesh network and make full use of RF resources. This paper proposes a multi- interface multi-channel routing protocol IAPDCA (Interference Avoidance Path Detection Channel Allocation) which combines path selection and channel allocation. IAPDCA protocol interacts real-time information between MAC layer and routing layer. Each node selects the channel with the lowest channel interference index on the target path, so as to reduce the channel interference and channel conflict of neighbor nodes. In the aspect of path selection, IAPDCA takes the physical interference model as the basis to select a path with the least interference as the target path to establish a route. Through the analysis and improvement of AODV protocol, the multi-interface and multi-channel scheme is added, and the algorithm proposed by IAPDCA protocol is deployed. The simulation results show that IAPDCA can effectively improve the network performance compared with the existing multi-interface multi-channel routing protocols.

关键词： Measurement Simulation Wireless networks Wireless mesh networks Interference Channel allocation Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Understanding the Bad Development Practices of Android Custom Permissions in the Wild

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Zhang, Xiaohan Yu, Zhiyuan Li, Xinghua Zhang, Cen Sun, Cong Zhang, Ning Deng, Robert H. Xidian University State Key Laboratory of Integrated Service Networks School of Cyber Engineering Xi'an710071 China Ministry of Education Engineering Research Center of Big data Security China Washington University in St. Louis Department of Computer Science and Engineering St. LouisMO63130 United States Nanyang Technological University 639798 Singapore Singapore Management University 188065 Singapore

Android system provides application developers with the ability to define custom permissions, which serve to regulate the sharing of resources and functionalities with other applications. However, developers' improper development practices can render the permission mechanism ineffective, facilitating easy exploitation by attackers. This paper presents a comprehensive examination of the problematic practices surrounding custom permissions employed by developers, referred to as Bad Practices of Custom Permissions (BPCP issues). To accomplish this, we conducted an empirical study and identified nine common BPCP issue patterns that can lead to various adverse consequences, such as installation failures, crashes, and even component hijacking. To automatically identify these patterns of bad practices, we devised PERMEAGRE, a static analysis tool. Employing PERMEAGRE, we performed a large-scale analysis of 83,085 applications obtained from seven major app markets, aiming to detect instances of BPCP issues. The results revealed that more than 26% of the analyzed apps contained at least one issue, and a significant number of apps had garnered millions of downloads. Our analysis delved into the underlying causes of these issues. Consequently, this analysis sheds light on the potential threat landscape associated with bad practices in custom permissions, emphasizing the urgent requirement for effective mitigation strategies. © 2004-2012 IEEE.

关键词： Android custom permission empirical study static analysis

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation Use Convolutional Attention Augmentation TransUNet with Skip Connection Enhancement

Medical Image Segmentation Use Convolutional Attention Augme...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Qingzhi Zou Jing Zhao Ming Li Ling Chen Lin Yuan Ronghuan Zhang Yushuai Hu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The primary objective of medical image segmentation is the isolation of pathological tissues and distinct organs from medical images, thereby assisting in medical diagnosis. The methods employed for medical image segmentation encompass convolutional neural networks and transformer-based methods. Although the self-attention mechanism in Transformers improves its capability to capture long-range dependencies, it have limitations in learning local (contextual) relationships between pixels. Some previous research has tried to solve this problem by incorporating convolutional layers into the encoder or decoder of transformers, but sometimes feature inconsistencies arise. To better extract local features from images using convolutional neural networks and to fuse low-resolution and high-resolution features from higher-level and lower features, we propose the Convolutional Attention Augmentation TransUNet (CAA-TransUNet) model. In our model, firstly, we propose a convolutional attention augmentation module that enhances both local and global features by suppressing irrelevant background information. Secondly, we have integrated attention gates into the skip connections to aggregate feature information from various stages of the encoder during the upsampling process. Finally, we employ the technique of aggregating the loss of multi-stage features to expedite convergence speed and enhance performance. The experimental results on three public datasets demonstrate that our proposed model significantly outperforms the baseline methods.

关键词： Image segmentation Pathology Computational modeling Aggregates Logic gates Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

Interpretable Analysis of Oral Mucosal Lesions Using U-Net and Quantum Approaches

Interpretable Analysis of Oral Mucosal Lesions Using U-Net a...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Aparna M Anna Liza Sibi Prachi Kumari Golla Ram Senthil Kumar T. Somasundaram K. Vindhya Savithri Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Dept. of Artificial Intelligence and Data Science School of AI Amrita Vishwa Vidyapeetham Coimbatore India Department of Mathematics Amrita School of Physical Sciences Amrita Vishwa Vidyapeetham Coimbatore India Dept. of Oral & Maxillofacial Pathology and Microbiology Amrita School of Dentistry AIMS Ponekkara PO Kochi India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Oral mucosal lesions are abnormal changes found in the tissue of the mouth. They can be painful and may include abnormal cell growths, as well as rare tongue and hard- palate disorders. They may result from infections, inflamma- tory processes, trauma, autoimmune conditions, or precancerous changes. A recent study found a 59.6% prevalence of oral mucosal lesions among elderly individuals, highlighting a signif- icant association with factors such as age over 65, male gender, tobacco habits, and denture usage. Thus, lesions can significantly impact a patient's quality of life, necessitating accurate diagnosis and timely intervention. In this study, we use a combination of two advanced technologies-U-Net, a deep learning model, and quantum computing-to analyze medical images of oral health. We use a publicly available dataset containing labeled images classified as ‘Lesion’ and ‘Oral Cavity,’ focusing only on lesion detection. Our results show that while the U-Net model achieves 95.02% segmentation accuracy, the quantum approach using QCNN achieves 74.5% accuracy. Although the quantum model does not outperform U-Net in segmentation, it demonstrates potential for future research in quantum-enhanced medical imaging. To measure how well our method works, we use different evaluation techniques, including Dice Coefficient, Intersection over Union (IoU), accuracy, precision, recall, and F1-score. Our results indicate that while quantum computing has shown high accuracy in previous research for classification tasks, its application to segmentation-particularly in oral lesion detection-faces challenges such as lower accuracy, quantum noise, and hardware constraints. This research highlights the potential of integrating AI and quantum approaches for medical diagnosis while acknowledging the need for further improvements in quantum seamcntation models.

关键词： Deep learning Image segmentation Quantum computing Accuracy Computational modeling Hardware Computational efficiency Lesions Artificial intelligence Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Neural Network Sliding-Mode Control with Actor-Critic for a Class of Robot Systems

Fuzzy Neural Network Sliding-Mode Control with Actor-Critic ...

引用

IEEE International Conference on Orange Technologies (ICOT)

作者： Lon-Chen Hung Chun-Cheng Wei Hung-Jen Chen Chih-Fu Yang Wei-Min Cheng Department of Electronic Engineering Lunghwa University of Science and Technology School of Software and Big Data Changzhou College of Information Technology Department of Computer Information and Network Engineering Lunghwa University of Science and Technology

ISBN: (纸本)9781665454209

In this article, a robust fuzzy RBF neural network sliding-mode control with actor-critic for a class of robot systems. Trajectory tracking control of robotic systems has favorable performance for tracking control. The fuzzy RBF neural network sliding-mode and actor-critic method is handled to compensate the uncertainty and disturbance of system. The stability analysis is based on for the proposed adaptive and robust control method. The simulation results show the effectiveness under the uncertainties.

关键词： Uncertainty Target tracking Trajectory tracking Simulation Neural networks Manipulators Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Dyformer: A Dynamic Transformer-Based Architecture for Multivariate Time Series Classification

SSRN

引用

SSRN 2023年

作者： Yang, Chao Wang, Xianzhi Yao, Lina Long, Guodong Xu, Guandong School of Computer Science University of Technology Sydney SydneyNSW2007 Australia CSIRO Data61 SydneyNSW2015 Australia School of Computer Science and Engineering University of New South Wales SydneyNSW2052 Australia Australian Artificial Intelligence Institute University of Technology Sydney SydneyNSW2007 Australia

Multivariate time series classification is a critical problem in data mining with broad applications. Transformers have been widely applied to classifying time series;however, they are not designed to effectively exploit the characteristics of time series and bear several limitations, such as lacking the consideration of varied learning strategies for different frequency patterns. We propose a novel dynamic transformer-based architecture called Dyformer for multivariate time series classification. We first propose hierarchical pooling to decompose time series into subsequences covering different frequency components. Then, we implement two types of gates to achieve adaptive learning strategies for different frequency components through a flexible model structure and dynamic information flow. Finally, we employ feature map-wise attention to capture multi-granular temporal patterns and design a joint loss function for the training. Our experiments on 30 benchmark multivariate time series datasets show our model outperforms multiple baselines and state-of-the-art methods. Our model also copes well with limited training samples when pre-trained. © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Scrupulous Liver Cancer Segmentation: An Enhanced U-Net Model with Extended Echo Skip Based ResoReplicate Layer

A Scrupulous Liver Cancer Segmentation: An Enhanced U-Net Mo...

引用

Frontier Technologies and Solutions (ICFTS), International Conference on

作者： Viveka S Prabhuranjith P Madhubala. C K. Hemalatha A. Ramya N.G. Gayathri Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India Department of Artificial Intelligence and Data Science Velalar college of Engineering and Technology Erode Tamilnadu India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Avadi Chennai Tamilnadu India Department of Information Technology Sona College of Technology Tamilnadu India Department of Computer Science and Engineering Indra Ganesan College of Engineering Trichy Tamilnadu India Department of Computer Science and Business Systems K.Ramakrishnan college of Engineering Trichy Tamilnadu India

ISBN: (数字)9798331502768

ISBN: (纸本)9798331502775

Liver segmentation is one of the crucially important components in clinical-decision support system. Improving the tasks of early diagnosis of the critical liver infections and diseases such as jaundice, hepatitis infections and carcinoma can result in effectual outcomes and higher rates of mortality. Infection segmentation from liver is one of the challenging tasks to due to their varying structures, sizes and the location of infections. These are also affected by the low ranges of contrast and to their blurred boundaries. To resolve these pitfalls encountered by the existing approaches, compiled with less accuracy rates, higher model complexity and with higher time for both detection and segmentation. Thus, the proposed method using the U-Net with the Extended Echo Skip based ResoReplicate Layer for segmenting the infectious regions from the livers, using the image dataset from two various sources comprising various CT scan images of livers and images containing hepatic carcinomas of both the gender, 2 anonymous CT-scans and DEPOLL dataset. Thus, the segmentation aids in the appropriate and earlier diagnosis of the infections and for a delivery of precise treatment in aspects of avoiding further complications. These modifications in U-net results in replicating retrieving only the important and the precise features for the detection and are replicated in the following layers for a precise segmentation of infectious areas from liver. The overall segmentation ability of the proposed model will be validated using the probabilistic metrics comprising the Dice Coefficient rates and the Intersection over Union (IOU) score.

关键词： Jaundice Image segmentation Accuracy Liver diseases Computational modeling Computed tomography Rendering (computer graphics) Real-time systems Complexity theory Reliability

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：