检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Fuchao Cheng, Jianhong Liu, Hui Dong, Yongqiang Jia, Yuheng Hou, Junhui College of Software Engineering Southeast University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Yam Pak Charitable Foundation School of Computing and Information Sciences Saint Francis University Hong Kong Department of Computer Science City University of Hong Kong Hong Kong China

In partial label learning (PLL), every sample is associated with a candidate label set comprising the ground-truth label and several noisy labels. The conventional PLL assumes the noisy labels are randomly generated (instance-independent), while in practical scenarios, the noisy labels are always instance-dependent and are highly related to the sample features, leading to the instance-dependent partial label learning (IDPLL) problem. Instance-dependent noisy label is a double-edged sword. On one side, it may promote model training as the noisy labels can depict the sample to some extent. On the other side, it brings high label ambiguity as the noisy labels are quite undistinguishable from the ground-truth label. To leverage the nuances of IDPLL effectively, for the first time we create class-wise embeddings for each sample, which allow us to explore the relationship of instance-dependent noisy labels, i.e., the class-wise embeddings in the candidate label set should have high similarity, while the class-wise embeddings between the candidate label set and the non-candidate label set should have high dissimilarity. Moreover, to reduce the high label ambiguity, we introduce the concept of class prototypes containing global feature information to disambiguate the candidate label set. Extensive experimental comparisons with twelve methods on six benchmark data sets, including four fine-grained data sets, demonstrate the effectiveness of the proposed method. The code implementation is publicly available at https://***/Yangfc-ML/CEL. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Classification Using VGG-19 Based Faster-RCNN 7th

Plant Disease Classification Using VGG-19 Based Faster-RCNN

引用

Proceedings of the 7th International Conference on Advances in Computing and Data sciences, ICACDS 2023

作者： Nawaz, Marriam Nazir, Tahira Khan, Muhammad Attique Rajinikanth, Venkatesan Kadry, Seifedine Department of Software Engineering University of Engineering and Technology Taxila Taxila47050 Pakistan Faculty of Computing Department of Computer Science Riphah International University Gulberg Green Campus Islamabad Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Department of Applied Data Science Noroff University College Kristiansand4612 Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9783031379390

Early plant disease diagnosis can help farmers avoid spending money on costly crop pesticides and aid them to boost food production. Scientists have put a lot of effort to classify plant diseases, but it is difficult to quickly locate and identify different crop abnormalities due to the high degree of resemblance between the normal and damaged parts of plant leaves. Additionally, the procedure of detecting plant diseases has been made more challenging due to the extensive color, size, shape, and intensity variations in the background and foreground of the plant images. To address the existing difficulties, we have introduced an effective deep learning (DL) based system called Faster-RCNN o recognize and classify various types of plant diseases. The suggested method consists of 3 basic steps. In order to identify the area of interest in investigated samples, we first create annotations for them which are later used for Faster-RCNN training. The Faster-RCNN model employs the VGG-19 network to extract the relevant keypoints from the given images which are later passed to the regressor and classification units to identify and categorize the various crop diseases using the estimated features. We evaluated our method on a widely used standard plant sample repository called the PlantVillage database, and the findings show that our approach is reliable for classifying plant diseases under a variety of image-capturing scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Robust Uplift Modeling with Large-Scale Contexts for Real-time Marketing 25

Robust Uplift Modeling with Large-Scale Contexts for Real-ti...

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1

作者： Zexu Sun Qiyu Han Minqin Zhu Hao Gong Dugang Liu Chen Ma Gaoling School of Artificial Intelligence Renmin University of China Beijing China School of Statistics Renmin University of China Beijing China Department of Computer Science and Technology Zhejiang University Hangzhou China Kuaishou Technology Beijing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9798400712456

Improving user engagement and platform revenue is crucial for online marketing platforms. Uplift modeling is proposed to solve this problem, which applies different treatments (e.g., discounts, bonus) to satisfy corresponding users. Despite progress in this field, limitations persist. Firstly, most of them focus on scenarios where only user features exist. However, in real-world scenarios, there are rich contexts available in the online platform (e.g., short videos, news), and the uplift model needs to infer an incentive for each user on the specific item, which is called real-time marketing. Thus, only considering the user features will lead to biased prediction of the responses, which may cause the cumulative error for uplift prediction. Moreover, due to the large-scale contexts, directly concatenating the context features with the user features will cause a severe distribution shift in the treatment and control groups. Secondly, capturing the interaction relationship between the user features and context features can better predict the user response. To solve the above limitations, we propose a novel model-agnostic Robust Uplift Modeling with Large-Scale Contexts (UMLC) framework for Real-time Marketing. Our UMLC includes two customized modules. 1) A response-guided context grouping module for extracting context features information and condensing value space through clusters. 2) A feature interaction module for obtaining better uplift prediction. Specifically, this module contains two parts: a user-context interaction component for better modeling the response; a treatment-feature interaction component for discovering the treatment assignment sensitive feature of each instance to better predict the uplift. Moreover, we conduct extensive experiments on a synthetic dataset and a real-world product dataset to verify the effectiveness and compatibility of our UMLC.

关键词： large-scale contexts

来源：评论

学校读者我要写书评

暂无评论

A Novel Attention-based Explainable Deep Learning Framework Towards Medical Image Classification

A Novel Attention-based Explainable Deep Learning Framework ...

引用

Innovative Approaches in Smart Technologies (ISAS), International Symposium on

作者： Gladys W. Muoka Ding Yi Chiagoziem Chima Ukwuoma Moindi Duke Martin Ahmet Arif Aydin Mugahed A. Al-Antari School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China Department of Computer Science Unicaf University Lilongwe Lilongwe Malawi Department of Computer Engineering Faculty of Engineering İnönü University Turkey Department of Artificial Intelligence College of Software & Convergence Technology Daeyang AI Center Sejong University Seoul Korea

Deep learning applications for medical image classification have shown remarkable promise, particularly incorporating attention-based neural networks. This is particularly relevant in medical imaging, where the integration of Artificial Intelligence assists with various imaging tasks, including classification, segmentation, and detection. Deep learning is revolutionizing medical research and playing a significant role in advancing personalized clinical treatment. However, the lack of interpretability in these models presents a significant obstacle to their adoption in clinical practice. Therefore, there is a growing need for a comprehensive understanding of artificial intelligence systems and their internal mechanisms, capabilities, and limitations, which is the focus of the field of explainable AI. This study proposes a novel attention-based explainable deep learning framework for medical image classification tasks, including Covid-19, breast cancer (BreakHis), lung cancer (LC2500), and Retinal optical coherence tomography (OCT). The proposed framework recorded overall accuracies of 98% (Covid-19 Radiography), 95% (BreakHis), 99.8% (LC2500), and 95%(OCT). For visual analysis of the outcomes, we employ and use the LIME, SHAP, and ELI-5 to analyze the achieved results. The study’s primary goal is to bridge the gap between the high performance achieved by attention-based models and the necessity for transparency and interpretability in medical image diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Reconstruction Improvement of Variable Coded Aperture Using Deep Learning Method for Gamma and Lensless Imaging applications

Image Reconstruction Improvement of Variable Coded Aperture ...

引用

Conference on Lasers and Electro-Optics Europe (CLEO EUROPE)

作者： Ariel Schwarz Amir Shemer Eliezer Danan Noa E. Cohen Yossef Danan Department of Electrical and Electronics Engineering Azrieli College of Engineering Jerusalem Israel Faculty of Engineering Bar-Ilan University Ramat-Gan Israel School of Software Engineering and Computer Science Azrieli College of Engineering Jerusalem Israel

ISBN: (纸本)9798350345995

In gamma ray imaging for nuclear medicine, coded aperture is used to improve sensitivity. one of the main reconstructing methods is inverse filtering (deconvolution), where the recorded image is cross-correlated with periodic inverse filter of coded array. The reconstruction is free of coding noise for arbitrary array. However, amplification of quantum noise affect the reconstructed image. Although it is improved by Wiener filtering, the major problem is small terms in the spectral distribution of coded masks. Statistically and experimentally pinhole arrays have at least one term which is zero, resulting unacceptably noisy reconstruction. In our previous research we presented new approach of variable coded aperture (VCA) design for far and near field imaging applications [1–4]. The imaging system is based on time multiplexing method using variable multi pinhole array. The unique variable design enables to overcome the spatial frequencies cutoff and small terms in the Fourier transform exists in static multi pinhole array. The overall pinholes positions are designed to avoid spatial frequencies loss. However, traces of duplications can still be detected in reconstruction using Wiener filtering. Furthermore, since coded aperture blocks most of the photons that enter the detector, the dynamic range of the image is limited, thus leading to low contrast image and inadequate colors gamut.

关键词： Deep learning Fourier transforms Image metrics Imaging systems Quantum noise Spatial frequency

来源：评论

学校读者我要写书评

暂无评论

HealthEdge: A Machine Learning-Based Smart Healthcare Framework for Prediction of Type 2 Diabetes in an Integrated IoT, Edge, and Cloud Computing System 14

HealthEdge: A Machine Learning-Based Smart Healthcare Framew...

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： Hennebelle, Alain Materwala, Huned Ismail, Leila Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates Lab School of Computing and Information Systems The University of Melbourne Australia

Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR. © 2023 Elsevier B.V.. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Constrained Intelligent Frequency Control in an AC Microgrid: An Online Reinforcement Learning Based PID Tuning Approach

Constrained Intelligent Frequency Control in an AC Microgrid...

引用

IEEE General Meeting Power& Energy Society

作者： K. Nosrati A. Tepljakov E. Petlenkov V. Skiparev J. Belikov Y. Levron Department of Computer Systems Tallinn University of Technology Tallinn Estonia Department of Software Science Tallinn University of Technology Tallinn Estonia Faculty of Electrical & Computer Engineering Technion—Israel Institute of Technology Haifa Israel

Variable output power in isolated microgrids (MGs) threatens frequency stability and may even degrade power quality. In response, intelligent control methods have been developed and applied to frequency deviation control systems with excellent results. Nevertheless, a potential problem is that the application of such advanced techniques with a large search space is not enough to deal with highly dynamic environment and real-time operations of MGs. In this light, the present study introduces a flexible artificial neural network (ANN)-based frequency deviation control solution in a constrained structure that operates as follows. First, the stable controller parameter space of the PID-based AC microgrid is derived by using the stability boundary locus method. Then, the controller parameters are tuned and updated online by searching for an optimal combination of the coefficients with consideration of output variations sensed by a constrained ANN in the derived reduced parameter space. To accomplish this step, a reinforcement learning technique is applied to train the ANN-based tuners. The performance of the proposed technique has been verified under a given scenario to demonstrate how the reduced parameter space should facilitate the optimization procedure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Signal Attenuation Modeling and Simulation for 5G and Beyond P2P Wireless Communication Networks in FR2 Bands: Comparison within M-Region in Nigeria 2

Signal Attenuation Modeling and Simulation for 5G and Beyond...

引用

2nd International Conference on Multidisciplinary engineering and Applied science, ICMEAS 2023

作者： Alozie, Emmanuel Faruk, Nasir Abdulkarim, Abubakar Usman, Aliyu D. Olayinka Imam-Fulani, Yusuf Garba, Salisu Adewole, Kayode S. Oloyede, Abdulkarim A. Sowande, Olugbenga A. Abdullahi Baba, Bashir Musa, Abdulwaheed Imoize, Agbotiname Lucky Adediran, Yinusa A. Olagunju, Hawau I. Taura, Lawan S. Sule Lamido University Department of Information Technology Kafin Hausa Nigeria Sule Lamido University Directorate of Information and Communication Technology Kafin Hausa Nigeria Ahmadu Bello University Department of Electrical Engineering Kafin Hausa Nigeria Kampala International University Department of Electrical and Telecommunications Engineering Kampala Uganda Ahmadu Bello University Department of Electronics and Telecommunication Engineering Zaria Nigeria University of Ilorin Department of Telecommunication Science Ilorin Nigeria Sule Lamido University Department of Software Engineering Kafin Hausa Nigeria University of Ilorin Department of Computer Science Ilorin Nigeria Sule Lamido University Department of Cyber Security Kafin Hausa Nigeria Kwara State University Department of Electrical and Computer Engineering Malete Nigeria University of Johannesburg Institute for Intelligent Systems Johannesburg South Africa University of Lagos Department of Electrical and Electronics Engineering Lagos Nigeria Ruhr University Institute of Digital Communication Department of Electrical Engineering and Information Technology Bochum Germany University of Ilorin Department of Electrical and Electronics Engineering Ilorin Nigeria Sule Lamido University Department of Physics Kafin Hausa Nigeria

ISBN: (纸本)9798350358834

ITU-R categorized Nigeria into four rain regions (i.e., M, N, P, and Q) depending on the atmospheric conditions. Previous works that have conducted rain and attenuation modeling and simulations have assumed similar signal propagation behavior and parameters within locations categorized under the same region. This paper aims to explore these assumptions by conducting an extensive radio propagation simulations of point-to-point microwave links with a clear line-of-sight in order to estimate the total path loss (attenuation), excess path loss, and flat fade margins for each of the locations within the M-regions, i.e., Kano, Sokoto, and Adamawa. Results obtained showed that in all the locations, the loss monotonically increases with distance, with Sokoto having the highest level of signal losses and fading, while, Adamawa has the lowest. The deviation for both total loss, excess loss, and flat fading margin was found to be between 15 dB across the region. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Correction: Agile meets quantum: a novel genetic algorithm model for predicting the success of quantum software development project

引用

Automated software engineering 2024年第1期32卷 1-11页

作者： Khan, Arif Ali Akbar, Muhammad Azeem Lahtinen, Valtteri Paavola, Marko Niazi, Mahmood Alatawi, Mohammed Naif Alotaibi, Shoayee Dlaim M3S Empirical Software Engineering Research Unit University of Oulu Oulu Finland Software Engineering Department Lappeenranta-Lahti University of Technology Lappeenranta Finland Quanscient Oy Tampere Finland VTT Technical Research Ctr of Finland Ltd Oulu Finland Department of Information and Computer Science King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Interdisciplinary Research Centre for Intelligent Secure Systems King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Information Technology Department Faculty of Computers and Information Technology University of Tabuk Tabuk Saudi Arabia Department of Artificial Intelligence and Data Science College of Computer Science and Engineering University of Hail Hail Saudi Arabia

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Photon-Counting CT Denoising with Comprehensive Noise Propagation Model

Self-Supervised Photon-Counting CT Denoising with Comprehens...

引用

IEEE Symposium on Nuclear science (NSS/MIC)

作者： Q. Wu X. Lei M. Su W. Qin X. Yu G. Quan W. Cao W. Wang X. Ji X. Lai Y. Chen School of Computer Science and Engineering Southeast University Nanjing China School of Biomedical Engineering ShanghaiTech University Shanghai China College of Software Engineering Southeast University Nanjing China The CT RPA Department United Imaging Healthcare Shanghai China

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

Photon counting computed tomography (PCCT) is an emerging spectral CT technology with significant potential for revolutionizing clinical CT applications. However, noise amplification during signal decomposition significantly limits the utility of basis material images. While data-driven supervised learning has been successful in reducing noise in conventional CT images, applying this method to PCCT is challenging due to the early phase of clinical studies and difficulty in gathering sufficient clinical data for training. To solve this issue, this paper proposes a projection-domain noise propagation model for noise suppression during material decomposition. Firstly, an analytical model is derived from the decomposition of dual-energy materials to describe in detail the propagation of noise from the detector domain to the projection domain. Such model can accurately describe the variance of each pixel in the basis material images. Secondly, we incorporate this statistical model into self-supervised learning network and define a joint optimization strategy via maximizing the constrained log-likelihood with Gaussian statistics. For self-supervised learning, we suggest to construct pseudo training pairs to learn denoising solely from noisy samples. Extensive analyses on real data demonstrate that the proposed method is promising for improving the virtual monochromatic imaging (VMI) quality of PCCT. Our method uses a small amount of experimental data and could be implemented in a real clinical setting.

关键词： Training Semiconductor device modeling Semiconductor detectors Computed tomography Noise Noise reduction Supervised learning

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：