检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Xu, Xinyi Wang, Shuaiqi Foo, Chuan-Sheng Low, Bryan Kian Hsiang Fanti, Giulia Department of Computer Science National University of Singapore Singapore Department of Electrical and Computer Engineering Carnegie Mellon University United States Institute for Infocomm Research Agency for Science Technology and Research Singapore

data valuation is a class of techniques for quantitatively assessing the value of data for applications like pricing in data marketplaces. Existing data valuation methods define a value for a discrete dataset. However, in many use cases, users are interested in not only the value of the dataset, but that of the distribution from which the dataset was sampled. For example, consider a buyer trying to evaluate whether to purchase data from different vendors. The buyer may observe (and compare) only a small preview sample from each vendor, to decide which vendor's data distribution is most useful to the buyer and purchase. The core question is how should we compare the values of data distributions from their samples? Under a Huber characterization of the data heterogeneity across vendors, we propose a maximum mean discrepancy (MMD)-based valuation method which enables theoretically principled and actionable policies for comparing data distributions from samples. We empirically demonstrate that our method is sample-efficient and effective in identifying valuable data distributions against several existing baselines, on multiple real-world datasets (e.g., network intrusion detection, credit card fraud detection) and downstream applications (classification, regression). © 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

Evaluation of Adaptive Synthetic Resampling Technique for Imbalanced Breast Cancer Identification

引用

Procedia computer science 2024年 235卷 1000-1007页

作者： Tsehay Admassu Assegie Ayodeji Olalekan Salau Kanimozhi Sampath Rajkumar Govindarajan Sangeetha Murugan B. Lakshmi Department of Computer Science College of Engineering and Technology Injibara University Injibara Ethiopia Department of Electrical/Electronics and Computer Engineering Afe Babalola University Ado-Ekiti Nigeria Department of Computer Science & Engineering (Cyber Security) Madanapalle Institute of Technology and Science Madanapalle Andhra Pradesh India Department of Computer Science & Engineering (Data Science) Madanapalle Institute of Technology and Science Madanapalle Andhra Pradesh India Department of Computer Science & Engineering Madanapalle Institute of Technology and Science Madanapalle Andhra Pradesh India Department of Computer Science & Technology Madanapalle Institute of Technology and Science Madanapalle Andhra Pradesh India

As one of the most common types of cancer among women, breast cancer is a serious health concern worldwide. Early detection is crucial for successful treatment and improved survival rates. However, detecting breast cancer is challenging due to imbalanced classification, where the minority class (cancerous) is ominously smaller than the majority class (non-cancerous). In this paper, we explore the use of logistic regression (LR) and the adaptive synthetic resampling (ADASYN) technique to address imbalanced classification in breast cancer detection. To that end, we collected the Wisconsin Breast Cancer dataset, which contains 569 instances. The dataset is imbalanced, with 212 malignant (cancerous) cases and 357 benign (non-cancerous) cases. Then, we trained support vector machine, LR, K-nearest neighbor, gradient, and adaptive boosting on the imbalanced dataset. Finally, we trained these algorithms on resampled data with the ADASYN oversampling and we evaluated their performance using cross-validation score with 5-folds. The results of the experiment showed that using ADASYN with LR significantly improved the performance the LR model. The LR model achieves 99.46% accuracy on breast cancer diagnosis. Moreover, the confusion matrix shows that among the 188 samples, the model misclassified one cancerous instance. Thus, we concluded that the proposed model is effective for breast cancer diagnosis.

关键词： Breast cancer detection imbalanced classification machine learning Adaptive synthetic oversampling

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Semantic Segmentation Approaches for Polyp and Lesion Detection in Medical Imaging 2

Benchmarking Semantic Segmentation Approaches for Polyp and ...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Pandiyaraju, V. Sunil, Meghana Shravya, V. Venkatraman, Shravan Kannan, A. Vellore Institute of Technology School of Computer Science and Engineering Chennai India Anna University Department of Information Science and Technology Chennai India

ISBN: (纸本)9798331534950

In medical imaging, semantic segmentation is essential because it can precisely locate and isolate regions of interest, such lesions or tumours, from intricate anatomical systems. Deep learning (DL) has led to a substantial evolution in segmentation approaches, which have improved medical diagnostics' accuracy and efficiency. The performance of six cutting-edge models is assessed in this paper: LinkNet, U-Net with ResNet50, LinkNet with ResNet50, FPN Net, Simple U-Net, and SegNet-Transformer across four segmentation tasks - polyp detection, lung lesion segmentation from Computed Tomography (CT) scans, breast lesion detection from ultrasound images, and Segmenting brain tumours with magnetic resonance imaging (MRI). With results like 0.9618 for brain tumour segmentation and 0.9483 for lung lesion segmentation, SegNet-Transformer consistently obtained the highest Dice Coefficient across all tests, demonstrating superior ability in capturing intricate boundaries. Other models, such as U-Net with ResNet50, performed competitively with Dice scores of 0.9375 for lung lesion segmentation and 0.9472 for brain tumors but required slightly more memory and longer training times. This study underscores that model performance varies across different tasks, revealing specific strengths and weaknesses. Ultimately, while SegNet-Transformer demonstrates robustness, the choice of model should be informed by the unique requirements of each segmentation task, balancing accuracy, efficiency, and computational demands. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A geometric-approach based Combinatorial Transformative Scalogram analysis for multiclass identification of pathologies in a voice signal

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Khumukcham, Ranita Nongmeikapam, Kishorjit Department of Electronics and Communication Engineering Indian Institute of Information Technology Mantripukhri Manipur Imphal795002 India Department of Computer Science and Engineering Indian Institute of Information Technology Mantripukhri Manipur Imphal795002 India

Many researchers have preferred non-invasive techniques for recognizing the exact type of physiological abnormality in the vocal tract by training machine learning algorithms with feature descriptors extracted from the voice signal. However, until now, most techniques have been limited to classifying whether a voice is normal or abnormal. It is crucial that the trained Artificial Intelligence (AI) be able to identify the exact pathology associated with voice for implementation in a realistic environment. Another issue is the need to suppress the ambient noise that could be mixed up with the spectra of the voice. Current work proposes a robust, less time-consuming and non-invasive technique for the identification of pathology associated with a laryngeal voice signal. More specifically, a two-stage signal filtering approach that encompasses a score-based geometric approach and a glottal inverse filtering method is applied to the input voice signal. The aim here is to estimate the noise spectra, to regenerate a clean signal and finally to deliver a completely fundamental glottal flow-derived signal. For the next stage, clean glottal derivative signals are used in the formation of a novel fused-scalogram which is currently referred to as the "Combinatorial Transformative Scalogram (CTS)." The CTS is a time-frequency domain plot which is a combination of two time-frequency scalograms. There is a thorough investigation of the performance of the two individual scalograms as well as that of the CTS *** classification metrics are used to investigate performance, which are: sensitivity, mean accuracy, error, precision, false positive rate, specificity, Cohen’s kappa, Matthews Correlation Coefficient, and F1 score. Implementation of the VOice ICar fEDerico II (VOICED) standard database provided the highest mean accuracy of 94.12% with a sensitivity of 93.85% and a specificity of 97.96% against other existing techniques. The current method performed well despite the d

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation 40

MergeSFL: Split Federated Learning with Feature Merging and ...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Liao, Yunming Xu, Yang Xu, Hongli Wang, Lun Yao, Zhiwei Qiao, Chunming University of Science and Technology of China School of Computer Science and Technology China Suzhou Institute for Advanced Research University of Science and Technology of China China University at Buffalo Department of Computer Science and Engineering The State University of New York United States

ISBN: (纸本)9798350317152

Recently, federated learning (FL) has emerged as a popular technique for edge AI to mine valuable knowledge in edge computing (EC) systems. To boost the performance of AI applications, large-scale models have received increasing attention due to their excellent generalized abilities. However, training and transmitting large-scale models will incur significant computing and communication burden on the resource-constrained workers, and the exchange of entire models may violate model privacy. To relax the burden of workers and protect model privacy, split federated learning (SFL) has been released by integrating both data and model parallelism. Despite resource limitations, SFL also faces two other critical challenges in EC systems, i.e., statistical heterogeneity and system heterogeneity. In order to address these challenges, we propose a novel SFL framework, termed MergeSFL, by incorporating feature merging and batch size regulation in SFL. Concretely, feature merging aims to merge the features from workers into a mixed feature sequence, which is approximately equivalent to the features derived from IID data and is employed to promote model accuracy. While batch size regulation aims to assign diverse and suitable batch sizes for heterogeneous workers to improve training efficiency. Moreover, MergeSFL explores to jointly optimize these two strategies upon their coupled relationship to better enhance the performance of SFL. Extensive experiments are conducted on a physical platform with 80 NVIDIA Jetson edge devices, and the experimental results show that MergeSFL can improve the final model accuracy by 5.82% to 26.22%, with a speedup by about 1.39× to 4.14×, compared to the baselines. © 2024 IEEE.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Solar Image Synthesis with Generative Adversarial Networks 23

Solar Image Synthesis with Generative Adversarial Networks

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Jiang, Haodi Wang, Jason T. L. Sam Houston State University Department of Computer Science HuntsvilleTX77341 United States New Jersey Institute of Technology Department of Computer Science NewarkNJ07102 United States

ISBN: (纸本)9798350374889

Solar activities are caused by the evolution of solar magnetic fields. Magnetic field parameters derived from photo-spheric vector magneto grams of solar active regions have been used to analyze and forecast extreme space weather events such as flares and coronal mass ejections. Unfortunately, the most recent Solar Cycle 24 was relatively weak with few large events, though it is the only solar cycle in which time-series vector magnetograms have been available. In this paper, we focus on two NASA instru-ments, namely the Michelson Doppler Imager (MDI) onboard the Solar and Heliospheric Observatory (SOHO) launched in Solar Cycle 23 (1996-2008), and the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory (SDO) launched in Solar Cycle 24 (2008-2019). While SOHOIMDI provides data from the more active Solar Cycle 23, it only offers line-of-sight (LOS) magneto grams without vector magnetograms. We propose Solar Image GAN (SIGAN), a generative adversarial network model designed to synthesize vector magnetic field images for Solar Cycles 23 and 24. SIGAN is trained using Ha images, SDOIHMI LOS, and vector magnetograms. It can generate vector magneto grams for both SDOIHMI and SOHOIMDI using Ha images and LOS magneto grams as input. Extensive experiments demonstrated the good performance of the proposed approach. © 2024 IEEE.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

On Generalization Bounds for Neural Networks with Low Rank Layers 36

On Generalization Bounds for Neural Networks with Low Rank L...

引用

36th International Conference on Algorithmic Learning Theory, ALT 2025

作者： Pinto, Andrea Rangamani, Akshay Poggio, Tomaso Center for Brains Mind and Machines Massachusetts Institute of Technology United States Department of Data Science New Jersey Institute of Technology United States

While previous optimization results have suggested that deep neural networks tend to favour low-rank weight matrices, the implications of this inductive bias on generalization bounds remain underexplored. In this paper, we apply a chain rule for Gaussian complexity (Maurer, 2016a) to analyze how low-rank layers in deep networks can prevent the accumulation of rank and dimensionality factors that typically multiply across layers. This approach yields generalization bounds for rank and spectral norm constrained networks. We compare our results to prior generalization bounds for deep networks, highlighting how deep networks with low-rank layers can achieve better generalization than those with full-rank layers. Additionally, we discuss how this framework provides new perspectives on the generalization capabilities of deep networks exhibiting neural collapse. © 2025 A. Pinto, A. Rangamani & T. Poggio.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Canonically Correlated Autoencoder-Enabled Prediction Model for Customer Churn Prediction

引用

computers, Materials & Continua 2022年第11期73卷 3757-3769页

作者： Olfat M.Mirza GJose Moses R.Rajender E.Laxmi Lydia Seifedine Kadry Cheadchai Me-Ead Orawit Thinnukool Department of Computer Science College of Computers and Information SystemsUmm Al-Qura UniversityMakkahSaudi Arabia Department of Computer Science Engineering Malla Reddy Engineering College500100India Department of Computer Science Engineering Lendi Institute of Engineering&TechnologyDenkada535005India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeNorway Program in Statistics and Information Management Faculty of ScienceMaejo UniversityChiang Mai50290Thailand Department of Modern Management and Information Technology College of Arts Media and TechnologyChiang Mai UniversityChiang Mai50200Thailand

Presently,customer retention is essential for reducing customer churn in telecommunication *** churn prediction(CCP)is important to predict the possibility of customer retention in the quality of *** risks of customer churn also get essential,the rise of machine learning(ML)models can be employed to investigate the characteristics of customer ***,deep learning(DL)models help in prediction of the customer behavior based characteristic *** the DL models necessitate hyperparameter modelling and effort,the process is difficult for research communities and business *** this view,this study designs an optimal deep canonically correlated autoencoder based prediction(ODCCAEP)model for competitive customer dependent application *** addition,the O-DCCAEP method purposes for determining the churning nature of the *** O-DCCAEP technique encompasses preprocessing,classification,and hyperparameter ***,the DCCAE model is employed to classify the churners or ***,the hyperparameter optimization of the DCCAE technique occurs utilizing the deer hunting optimization algorithm(DHOA).The experimental evaluation of the O-DCCAEP technique is carried out against an own dataset and the outcomes highlighted the betterment of the presented O-DCCAEP approach on existing approaches.

关键词： Churn prediction customer retention deep learning machine learning archimedes optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

USERS AUTHENTICATION ISSUES AND CHALLENGES IN ELECTRONIC COMMERCE APPLICATIONS

USERS AUTHENTICATION ISSUES AND CHALLENGES IN ELECTRONIC COM...

引用

2023 International Conference on Green Energy, Computing and Intelligent Technology, GEn-CITy 2023

作者： Kansro, Nadeem Ahmed Jamali, Mujeeb-Ur-Rehman Department of Computer Science Sindh University Campus Larkana Pakistan Institute of Mathematics and Computer Science University of Sindh Jamshoro Pakistan

ISBN: (纸本)9781839539596

Modern business models that use the cloud are electronic commerce and mobile commerce. A brand-new innovation called cloud computing makes use of the Internet to process and store data from a network of remote machines that are spread out all over the world. Security is a crucial element of every online transaction and it is a key problem with the cloud. Users may lose faith in electronic commerce if its security is compromised. Authentication is the process of validating a user's identification in electronic commerce systems. Personal information about a user shouldn't be accessible to or susceptible to interception by unauthorized parties while it's being transferred. It is a crucial step in the security of systems, as it ensures that only authorized users are able to access sensitive information or perform certain actions. The specific authentication method used will depend on the security requirements of the system, the level of trust required for access, and the level of user inconvenience that is acceptable. Strong authentication is essential for protecting sensitive information and ensuring the integrity of transactions in electronic commerce applications. By verifying the identity of users, authentication helps to prevent unauthorized access and protect against identity theft and fraud. The primary objective of this study is to develop a system for user authentication. Too much security can make it difficult for users to access their accounts, while too little security can make the accounts vulnerable to attack. The proposed system using the PKI based approach underwhich user's authentication is checked and verified by using the Digital Certificate. The empirical results shown that ECC is superior to RSA for generation of Digital Certificate. © The Institution of Engineering & Technology 2023.

关键词： Mobile commerce

来源：评论

学校读者我要写书评

暂无评论

Hybrid Design for Privacy Preserved Image Representation in a Cloud Environment 12th

Hybrid Design for Privacy Preserved Image Representation in ...

引用

12th International Conference on Recent Trends in Computing, ICRTC 2024

作者： Vijay, K. Sorna Shanthi, D. Jaeyalakshmi, M. Vignesh, P. Yuvaraja, M. Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India

ISBN: (纸本)9789819789450

The digital era has made seamless sharing and keeping of media such as images on cloud platforms an integral part of our lives. Still, there is a big issue about user privacy and data security in these repositories. We have thus created a very strong system that is able to do image encryption and decryption so as to protect the privacy of users while at the same time making their pictures accessible. Our system uses hybrid encryption where we try to prevent even cloud service providers from accessing the original files hence ensuring that only the owner who has been authenticated through password based authentication can decrypt or access them. In this way, it allows maintaining high privacy standards without sacrificing user convenience. It starts with preparing photos for encryption so that they are kept safe during transmission and storage. When needed by a user, images are decrypted by our system and become available only to authorized users. Consequently, users can comfortably leave their private photo albums on cloud storage systems knowing too well that their friends cannot access them thereby increasing trust in using cloud services for storing sensitive information. The aim of this work is to increase user privacy and data security in cloud repositories through employing this encryption technique. The users are guaranteed that their private details are not exposed to others enabling them to use cloud storage efficiently without interfering with their privacy at all. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cloud platforms

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：