检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition

作者： Tianchen Gu Jiaqi Wang Zhaori Bi Changhao Yan Fan Yang Yajie Qin Tao Cui Xuan Zeng State Key Laboratory of Integrated Chips and Systems School of Microelectronics Fudan University Shanghai China State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences & University of Chinese Academy of Sciences Beijing China State Key Laboratory of Integrated Chips and Systems School of Information Science and Technology Fudan University Shanghai China

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

We propose a novel scalable Bayesian optimization method with truncated subspace sampling (tSS-BO) to tackle high-dimensional optimization challenges for large-scale analog circuit sizing. To address the high-dimensional challenges, we propose subspace sampling subject to a truncated Gaussian distribution. This approach limits the effective sampling dimensionality down to a constant upper bound, independent of the original dimensionality, leading to a significant reduction in complexity associated with the curse of dimensionality. The distribution covariance is iteratively updated using a truncated flow, where approximate gradients and center steps are integrated with decaying prior subspace features. We introduce gradient sketching and local Gaussian process (GP) models to approximate gradients without additional simulations to mitigate systematic errors. To enhance efficiency and ensure compatibility with constraints, we utilize local GP models for the selection of promising candidates, avoiding the cost of acquisition function optimization. The proposed tSS-BO method exhibits clear advantages over state-of-the-art methods in experimental comparisons. In synthetic benchmark functions, the tSS-BO method achieves up to $4.93\times$ evaluation speedups and a remarkable over $30\times$ algorithm complexity reduction compared to the Bayesian baseline. In real-world analog circuits, our method achieves up to $2\times$ speedups in simulation number and runtime.

关键词： Adaptation models Upper bound Runtime Systematics Optimization methods Gaussian processes Analog circuits

来源：评论

学校读者我要写书评

暂无评论

An End-to-End S-AF-RCNN based Framework for Just-in-Time Defect Prediction

An End-to-End S-AF-RCNN based Framework for Just-in-Time Def...

引用

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： R.J.T. Nirmalraj Pon Ramalingam V. Sreetharan P.M.D. Ali Khan N Divya Muruganantham Ponnusamy School of Management Hindustan Institute of Technology and Science (Deemed to be University) Chennai Department of Computer Science and Engineering St Martin’s Engineering College Secunderabad Telangana India School of Computing Mohan Babu University Tirupati India Department of Civil Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Indian Institute of Information Technology Kalyani West Bengal India

The problem of defect prediction is very important, especially at the change-level. Change-level defect prediction, also known as just-in-time defect prediction, has the potential to not only guarantee software quality during the development process but also force the developers to find and correct errors as soon as possible. Deep learning is a current hot issue in the literature on machine learning. It has not yet been determined whether deep learning can be utilized to enhance the fault prediction performance. Preprocessing in the suggested method makes use of independence analysis and redundancy analysis. It uses the SMOTE algorithm to choose features. The proposed model is trained with S-AF-RCNN. When compared to more conventional approaches like RCNN and Fast- RCNN, the proposed method performs admirably.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Image Analysis-Based Automated Method using Deep Learning for Grain Counting

An Image Analysis-Based Automated Method using Deep Learning...

引用

International Conference on Industrial and information Systems, ICIIS

作者： Ramesh Ajikaran Ashen Iranga Hewarathna Vigneshwaran Palanisamy Charles Joseph Selvarajah Thuseethan Dept. of Computing and Infromation Systems Sabaragamuwa University of Sri Lanka Dept. of Software Engineering Sabaragamuwa University of Sri Lanka Dept. of Computer Science FAU Germany School of Information Technology Deakin University Australia

In the process of quality analysis of grains, number counting is one of the key steps for agricultural production. Traditional manual grain counting methods are time-consuming and subject to human error, and automated methods have the potential to improve accuracy and save time. In this study, we aimed to develop an image analysis-based method to automatically quantify the number of grains in a quicker manner. The 576 grain images were collected manually, and labelImg tagging tool used to annotate to generate a text file with their respective positions by drawing bounding boxes manually. The datasets consist were separated into three groups: training, validation, and test. For object detection, the YOLOv5, YOLOv4, and YOLOv3 algorithms represent cutting-edge deep learning frameworks. They replace the tedious and error-prone manual counting process by precisely identifying and counting grains in images obtained from agricultural fields. This technique helps to increase grain counting's precision and effectiveness. We believe this method will be extremely beneficial in guiding the development of high throughput systems for counting the number of grains in other crops as it performs well with a wide range of backgrounds, picture sizes, grain sizes, as well as various quantities of grain crowding. When compared to the other two approaches, YOLOv4 performed well in terms of accuracy, speed, and robustness (97.65%), demonstrating that the suggested strategy is competitive with other cutting-edge deep networkst.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discovering latent class labels for multi-label learning 29

Discovering latent class labels for multi-label learning

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Huang, Jun Xu, Linchuan Wang, Jing Feng, Lei Yamanishi, Kenji Graduate School of Information Science and Technology University of Tokyo Japan School of Computer Science and Technology Anhui University of Technology China School of Computing and Mathematical Sciences University of Greenwich United Kingdom School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9780999241165

Existing multi-label learning (MLL) approaches mainly assume all the labels are observed and construct classification models with a fixed set of target labels (known labels). However, in some real applications, multiple latent labels may exist outside this set and hidden in the data, especially for large-scale data sets. Discovering and exploring the latent labels hidden in the data may not only find interesting knowledge but also help us to build a more robust learning model. In this paper, a novel approach named DLCL (i.e., Discovering Latent Class Labels for MLL) is proposed which can not only discover the latent labels in the training data but also predict new instances with the latent and known labels simultaneously. Extensive experiments show a competitive performance of DLCL against other state-of-the-art MLL approaches. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. 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

Big data analytics and machine learning techniques to manage the smart grid

Big data analytics and machine learning techniques to manage...

引用

International Conference on Computer Communication and Informatics (ICCCI)

作者： M. Elavarasi Ramakrishna Kolikipogu Mahesh Kotha M. V. B. T. Santhi school of computing sciences Vels University Pallavaram Chennai India Information Technology Chaitanya Bharathi Institute of Technology (A) Hyderabad India Department of CSE (AI&ML) CMR Technical Campus Hyderabad India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India

Big data is a crucial part of the Energy Internet. Integrating renewables and smart grids is vital and exciting. Any power plant must collect and evaluate data to make educated choices. This study examines big data analytics in renewable energy based power plants. This paradigm implements big data analytics for renewable energy utilities and smart grids. The authors describe a five-step machine-learning approach to predict smart grid dependability. Using 64,000 occurrences and 12 attributes from an intelligent grid data system, we expected the system’s stability using three machine-learning algorithms. The penalized linear regression model achieves 95% accuracy using 70% of the training data. The random forest model is 84% accurate vs 77% for the decision tree. CNN and gradient-boosted decision tree models obtained 86% classification accuracy. This study’s small dataset prevents extensive data analyses. Cloud computing and real-time event analysis are well-suited for a data analytics infrastructure. Future research should include data from additional countries and renewable energy sources.

关键词： Renewable energy sources Computational modeling Training data Big Data Stability analysis Real-time systems Smart grids

来源：评论

学校读者我要写书评

暂无评论

Customer Churn Prediction in the Telecom Sector with Machine Learning and Adaptive k-Means Cluster using Imbalance Data

Customer Churn Prediction in the Telecom Sector with Machine...

引用

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

作者： N L Aravinda R Archana Reddy Bala Dhandayuthapani V Jithendra P R Nayak Ahmad Husseen Electronics and Communication Engineering Department Mallareddy Engineering College for Women (Autonomous) Hyderabad Telangana India School of Computer Science and Engineering SR University Warangal Telangana India Department of IT College of Computing and Information Sciences University of Technology and Applied Sciences Shinas branch Oman Department of CSE Srinivas Institute of Technology Valachil Mangalore India The Islamic university Najaf Iraq

A crucial aspect of maintaining a customer-oriented business in the telecommunications sector with machine learning (ML) is understanding the reasons and factors that lead to customer churn. However, the dataset is difficult by noise, misclassifications, duplicated data, and imbalanced customer information complicating the process of identifying ways to split the dataset based on events. The under-sampling method address the imbalance data by decreasing the data quantity of majority class, thereby achieving a balanced dataset. This method, utilizing Adaptive k-means clustering, directly determines the reduction based on that data quality in each class. The datasets are combined with class labels to generate a new balanced dataset used for classification in the SVM algorithm, which distinguishes between customer churn and non-churn in the prediction for the telecom sector. The SVM algorithm can perform linear and non-linear classification with a kernel function to control overfitting improve generalization and handle high-dimensional data. The obtained results demonstrate that the proposed method achieves better accuracy of 95.70%, precision of 56.01%, Recall of 55.05%, and F1-score of 96.05% on the telecom churn dataset. These results ensure superior detection and classification performance compared to other existing methods, such as Random Forest (RF), Decision Tree (DT) and K-Nearest Neighbour (KNN).

关键词：

来源：评论

学校读者我要写书评

暂无评论

OpenLS-DGF: An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Ni, Liwei Wang, Rui Liu, Miao Meng, Xingyu Lin, Xiaoze Liu, Junfeng Luo, Guojie Chu, Zhufei Qian, Weikang Yang, Xiaoyan Xie, Biwei Li, Xingquan Li, Huawei Chinese Academy of Sciences State Key Lab of Processors Institute of Computing Technology Beijing100190 China Pengcheng Laboratory Shenzhen518055 China University of Chinese Academy of Sciences Beijing101408 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing100049 China Peking University School of Computer Science Center for Energy-Efficient Computing and Applications Beijing100871 China Ninbo University Faculty of Electrical Engineering and Computer Science Ninbo315211 China Shanghai Jiao Tong University University of Michigan-Shanghai Jiao Tong University Joint Institute MoE Key Laboratory of Artificial Intelligence Shanghai200240 China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou311121 China

This paper introduces OpenLS-DGF, an adaptive logic synthesis dataset generation framework, to enhance machine learning (ML) applications within the logic synthesis process. Previous dataset generation flows were tailored for specific tasks or lacked integrated ML capabilities. While OpenLS-DGF supports various machine learning tasks by encapsulating the three fundamental steps of logic synthesis: Boolean representation, logic optimization, and technology mapping. It preserves the original information in both Verilog and ML-friendly GraphML formats. The Verilog files offer semi-customizable capabilities, enabling researchers to insert additional steps and incrementally refine the generated dataset. Furthermore, OpenLS-DGF includes an adaptive circuit engine that facilitates the final dataset management and downstream tasks. The generated OpenLS-D-v1 dataset comprises 46 combinational designs from established benchmarks, totaling over 966,000 Boolean circuits. OpenLS-D-v1 supports integrating new data features, making it more versatile for new tasks. This paper demonstrates the versatility of OpenLS-D-v1 through four distinct downstream tasks: circuit classification, circuit ranking, quality of results (QoR) prediction, and probability prediction. Each task is chosen to represent essential steps of logic synthesis, and the experimental results show the generated dataset from OpenLSDGF achieves prominent diversity and applicability. The source code and datasets are available at https://***/Logic-Factory/ACE/blob/master/OpenLS-DGF. © 1982-2012 IEEE.

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

Federated Meta-Learning for Few-Shot Fault Diagnosis with Representation Encoding

arXiv

引用

arXiv 2023年

作者： Cui, Jixuan Li, Jun Mei, Zhen Wei, Kang Wei, Sha Ding, Ming Chen, Wen Guo, Song The School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing The Hong Kong Polytechnic University 999077 Hong Kong The Research Institute of Information and Industrialization Integration China Academy of Information and Communications Technology Beijing100191 China Data61 CSIRO SydneyNSW2015 Australia The Department of Electronics Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Engineering Hong Kong University of Science and Technology 999077 Hong Kong

Deep learning-based fault diagnosis (FD) approaches require a large amount of training data, which are difficult to obtain since they are located across different entities. Federated learning (FL) enables multiple clients to collaboratively train a shared model with data privacy guaranteed. However, the domain discrepancy and data scarcity problems among clients deteriorate the performance of the global FL model. To tackle these issues, we propose a novel framework called representation encoding-based federated meta-learning (REFML) for few-shot FD. First, a novel training strategy based on representation encoding and meta-learning is developed. It harnesses the inherent heterogeneity among training clients, effectively transforming it into an advantage for out-of-distribution generalization on unseen working conditions or equipment types. Additionally, an adaptive interpolation method that calculates the optimal combination of local and global models as the initialization of local training is proposed. This helps to further utilize local information to mitigate the negative effects of domain discrepancy. As a result, high diagnostic accuracy can be achieved on unseen working conditions or equipment types with limited training data. Compared with the state-of-the-art methods, such as FedProx, the proposed REFML framework achieves an increase in accuracy by 2.17%-6.50% when tested on unseen working conditions of the same equipment type and 13.44%-18.33% when tested on totally unseen equipment types, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Training fully connected neural networks is Ǝℝ-complete 23

Training fully connected neural networks is Ǝℝ-complete

引用

Proceedings of the 37th International Conference on Neural information Processing Systems

作者： Daniel Bertschinger Christoph Hertrich Paul Jungeblut Tillmann Miltzow Simon Weber Department of Computer Science ETH Zurich Zurich Switzerland Department of Mathematics London School of Economics and Political Science London United Kingdom Institute of Theoretical Informatics Karlsruhe Institute of Technology Karlsruhe Germany Department of Information and Computing Sciences Utrecht University Utrecht The Netherlands

We consider the algorithmic problem of finding the optimal weights and biases for a two-layer fully connected neural network to fit a given set of data points, also known as empirical risk minimization. We show that the problem is Ǝℝ-complete. This complexity class can be defined as the set of algorithmic problems that are polynomial-time equivalent to finding real roots of a multivariate polynomial with integer coefficients. Furthermore, we show that arbitrary algebraic numbers are required as weights to be able to train some instances to optimality, even if all data points are rational. Our result already applies to fully connected instances with two inputs, two outputs, and one hidden layer of ReLU neurons. Thereby, we strengthen a result by Abrahamsen, Kleist and Miltzow [NeurIPS 2021]. A consequence of this is that a combinatorial search algorithm like the one by Arora, Basu, Mianjy and Mukherjee [ICLR 2018] is impossible for networks with more than one output dimension, unless NP = Ǝℝ.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble Modeling for the Classification of Birth Data

引用

Intelligent Automation & Soft computing 2024年第4期39卷 765-781页

作者： Fiaz Majeed Abdul Razzaq Ahmad Shakir Maqbool Ahmad Shahzada Khurram Muhammad Qaiser Saleem Muhammad Shafiq Jin-Ghoo Choi Habib Hamam Osama E.Sheta Department of Information Technology University of GujratGujrat50700Pakistan School of Digital Convergence Business University of Central PunjabRawalpindi46000Pakistan Faculty of Computing The Islamia University of BahawalpurBahawalpur63100Pakistan College of Computer Science and Information Technology Al Baha UniversityAl Baha1988Saudi Arabia School of Computer Science and Engineering Yeungnam UniversityGyeongsan38541Republic of Korea Faculty of Engineering Uni de MonctonMonctonNB E1A3E9Canada International Institute of Technology and Management Commune d’AkandaLibreville1989Gabon Department of Electrical and Electronic Engineering Science School of Electrical EngineeringUniversity of JohannesburgJohannesburg2006South Africa Spectrum of Knowledge Production&Skills Development Sfax3027Tunisia College of Computer Science and Engineering University of Ha’ilHa’il55476Saudi Arabia College of Science Zagazig UniversityZagazig44511Egypt

Machine learning(ML)and data mining are used in various fields such as data analysis,prediction,image processing and especially in *** in the past decade have focused on applying ML and data mining to generate conclusions from historical data in order to improve healthcare systems by making predictions about the *** ML algorithms,researchers have developed applications for decision support,analyzed clinical aspects,extracted informative information from historical data,predicted the outcomes and categorized diseases which help physicians make better *** is observed that there is a huge difference between women depending on the region and their social *** to these differences,scholars have been encouraged to conduct studies at a local level in order to better understand those factors that affect maternal health and the expected *** this study,the ensemble modeling technique is applied to classify birth outcomes based on either cesarean section(C-Section)or normal delivery.A voting ensemble model for the classification of a birth dataset was made by using a Random Forest(RF),Gradient Boosting Classifier,Extra Trees Classifier and Bagging Classifier as base *** is observed that the voting ensemble modal of proposed classifiers provides the best accuracy,i.e.,94.78%,as compared to the individual *** algorithms are more accurate due to ensemble models,which reduce variance and classification *** is reported that when a suitable classification model has been developed for birth classification,decision support systems can be created to enable clinicians to gain in-depth insights into the patterns in the *** such a system will not only allow health organizations to improve maternal health assessment processes,but also open doors for interdisciplinary research in two different fields in the region.

关键词： Birth data classification ensemble model machine 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：