检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： LaBonte, Tyler Hill, John C. Zhang, Xinchen Muthukumar, Vidya Kumar, Abhishek H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Google DeepMind United Kingdom

Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper, we identify surprising and nuanced behavior of finetuned models on worst-group accuracy via comprehensive experiments on four well-established benchmarks across vision and language tasks. We first show that the commonly used class-balancing techniques of mini-batch upsampling and loss upweighting can induce a decrease in worst-group accuracy (WGA) with training epochs, leading to performance no better than without class-balancing. While in some scenarios, removing data to create a class-balanced subset is more effective, we show this depends on group structure and propose a mixture method which can outperform both techniques. Next, we show that scaling pretrained models is generally beneficial for worst-group accuracy, but only in conjunction with appropriate class-balancing. Finally, we identify spectral imbalance in finetuning features as a potential source of group disparities - minority group covariance matrices incur a larger spectral norm than majority groups once conditioned on the classes. Our results show more nuanced interactions of modern finetuned models with group robustness than was previously known. Our code is available at https://***/tmlabonte/revisiting-finetuning. © 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

AI-Based Desktop VIZ: A Voice-Activated Personal Assistant-Futuristic and Sustainable technology 10

AI-Based Desktop VIZ: A Voice-Activated Personal Assistant-F...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Subi, Martin Rajeswari, M. Rajan, J. Jerlin Sri Harshini, S. Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Karunya Institute of Technology and Sciences Karunya School of Management Coimbatore India Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350353068

Modern technology has led to the development of advanced technologies that employ a variety of cutting-edge techniques, including speech recognition, machine learning, artificial intelligence, and OpenAI. A popular example of these technologies is Voice-Activated personal assistant This is one of the most often used examples of speech recognition and machine learning technologies. Using OpenAI, these models may be adjusted and their exploratory potential can be enhanced. This AI-powered desktop has been configured to pull data that the user requests using OpenAI. Additionally, it makes use of the AutoGUI package in Python to control the mouse and click on windows in other programs. While the existing model used a standard user interface to present the user with stored outputs, this model makes use of OpenAI to deliver more precise and comprehensive results. Furthermore, Auto GUI facilitates automatic user window interaction. This model is an excellent illustration of OpenAI, GUI, and speech recognition combined into one. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A study of adaptive sampling based primitive fidelity methods 16

A study of adaptive sampling based primitive fidelity method...

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Xu, Fei Li, Xiaoli Liu, Weiyan Chen, Dong School of Computer Science and Technology Nanjing Tech University Nanjing211816 China School of Information Engineering Jiangsu Open University Nanjing210017 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

The accuracy of images is frequently compromised during the processes of pattern generation and transformation, presenting challenges for existing methodologies to achieve an optimal balance between efficiency and accuracy. To address this issue, a novel primitive fidelity method utilizing adaptive sampling is introduced. This method takes into account the constituent elements of the pattern, designating the primitive as the fundamental unit of vectorization. It initializes the path through adaptive sampling, dynamically regulates the number of segments, and employs a loss function for optimization, thereby enhancing both efficiency and accuracy. Notably, this method is model-free and does not require shape primitive labels, which allows the proposed approach to break through the limitations of specific application domains and escape the challenges of collecting and generalizing vector graphic datasets. The experimental results indicate that the proposed method demonstrates good performance in terms of generation quality and operational efficiency on both public datasets and constructed datasets. © 2025 SPIE.

关键词： Adaptive sampling Model-free Primitive fidelity method Shape primitive labels Vectorization

来源：评论

学校读者我要写书评

暂无评论

U-Net based Pancreas Segmentation from Computed Tomography Images 3

U-Net based Pancreas Segmentation from Computed Tomography I...

引用

3rd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2024

作者： Devendhar, Tirumalasetti Lakshmipriya, B. Jayalakshmy, S. Vellore Institute of Technology Chennai Campus School of Computer Science & Engineering Chennai India Jawaharlal Nehru University School of Engineering New Delhi India IFET College of Engineering Electronics & Communication Engineering India

ISBN: (纸本)9798350391565

Delineation of pancreas from computed tomography (CT) scan images is burdensome owing to its anatomic variation in size, shape and its presence with respect to adjacent organs. This work explores the U-Net architecture to delineate pancreas from the CT volume of abdomen. U-Net was trained for variable number of epochs to identify the optimal learning environment for better segmentation performance. U-Net when trained for pancreas segmentation using CT dataset taken from The Cancer Imaging Archive (TCIA) has resulted in a segmentation performance of dice similarity coefficient of 0.8138, intersection over union of 0.7962 and boundary F1 score of 0.8036. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Reliability Assessment of a New General Matching Composed Network

引用

China Communications 2024年第2期21卷 245-257页

作者： Zhengyuan Liang Junbin Liang Guoxuan Zhong Guangxi Key Laboratory of Multimedia Communications and Network Technology School of ComputerElectronics and InformationGuangxi UniversityNanning 530004China Jiangxi Engineering Laboratory of IoT Technologies for Crop Growth Ji’an 343000China

The reliability of a network is an important indicator for maintaining communication and ensuring its stable operation. Therefore, the assessment of reliability in underlying interconnection networks has become an increasingly important research issue. However, at present, the reliability assessment of many interconnected networks is not yet accurate,which inevitably weakens their fault tolerance and diagnostic capabilities. To improve network reliability,researchers have proposed various methods and strategies for precise assessment. This paper introduces a novel family of interconnection networks called general matching composed networks(gMCNs), which is based on the common characteristics of network topology structure. After analyzing the topological properties of gMCNs, we establish a relationship between super connectivity and conditional diagnosability of gMCNs. Furthermore, we assess the reliability of g MCNs, and determine the conditional diagnosability of many interconnection networks.

关键词： conditional diagnosability interconnection networks network reliability super connectivity

来源：评论

学校读者我要写书评

暂无评论

IoT Meets computer Vision: An Improved Detection of Tomato Pests and Diseases 17

IoT Meets Computer Vision: An Improved Detection of Tomato P...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Wang, Junling Wu, Dongyang Wang, Yupeng Nanjing University of Science and Technology ZiJin College School of Computer and Artificial Intelligence Nanjing China Nanjing Forestry University College of Information Science and Technology Nanjing China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350351637

Accurate detection of tomato pests and diseases is essential for efficient agriculture as global food demand continues to grow. Traditional methods often struggle with accurate localization and detection, highlighting the need for advanced solutions. Leveraging the Internet of Things (IoT), which facilitates interconnected devices for data acquisition and transmission, this study introduces the TPDDM algorithm to significantly enhance detection capabilities in tomato farming. To address existing challenges, we employ innovative techniques within TPDDM. Data augmentation and mosaic optimization methods are utilized to enrich the dataset and enhance image information, improving model robustness. Integration of a pre-trained Vision Transformer (ViT) into the YOLOX model boosts feature extraction and enriches the model's ability to detect subtle patterns. Additionally, the design of the Adaptive Multi-scale Feature Pyramid Network (AMFPN) enables effective fusion of features across different scales, optimizing target detection accuracy. Evaluation using comprehensive performance metrics demonstrates TPDDM's superiority over traditional approaches and other contemporary models. Real-world application of TPDDM on diverse datasets validates its high accuracy and practical utility in tomato pest and disease detection. This research underscores the transformative potential of IoT-driven technologies in advancing precision agriculture, offering scalable solutions to meet the demands of modern farming practices. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Investigation on compressed air energy storage system for efficient utilisation of renewable power sources

引用

International Journal of Power and Energy Conversion 2024年第3期15卷 281-293页

作者： Karthika, J. Annamalai, T. Kumar, P. Veera Sanjeeva Olana, Firew Dereje Rasu, N. Govindha Department of Electrical and Electronics Engineering Sri Krishna College of Engineering and Technology Kuniamuthur Coimbatore641008 India Department of Electrical and Electronics Engineering Sri Venkateswara College of Engineering Tamil Nadu Sriperumbudur602117 India Department of Mechanical Engineering Annamacharya Institute of Technology and Sciences Andhra Pradesh Rajampet516126 India Department of Electrical and Computer Engineering Mattu University Post-318 Mattu Ethiopia School of Mechanical Engineering Vellore Institute of Technology Vellore India

In recent years, emerging nations have shifted their focus to renewable energy sources for electricity production. This shift has happened in both industrialised and underdeveloped countries. The percentage of electricity produced overall in most developed countries that originates from renewable sources of energy is rising significantly. Currently, the grid is going through a number of modifications to improve its intelligence and stability. These adjustments are becoming more pronounced. Although there are many various types of storage systems available, the CAES system is the most appropriate for large-capacity storage that is ideal for grid integration. However, the overall roundtrip efficiency is less than that of a pumped hydro storage system when it comes to large-scale renewable energy storage. © 2024 Inderscience Enterprises Ltd.

关键词： Compressors

来源：评论

学校读者我要写书评

暂无评论

Partial Discharge Classification with Transformer Neural Networks 14

Partial Discharge Classification with Transformer Neural Net...

引用

14th International Conference on the Properties and Applications of Dielectric Materials, ICPADM 2024

作者： Cheypoca, Thepjit Promphanich, Wiboon Thway, Aung Ye Hankae, Angelina Phimpissada Jeenmuang, Siwakorn Pattanadech, Norasage School of Engineering King Mongkut's Institute of Technology Ladkrabang Instrumentation and Control Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Computer Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Electrical Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Mechatronics Engineering Dept. Bangkok Thailand

ISBN: (纸本)9798350374605

This paper introduces an approach with the Transformer Neural Networks model for partial discharge patterns classification, that consists of corona discharge, internal discharge and surface discharge. The PD measuring circuit suggested in IEC 60270:2000 is used to record Partial discharge signals. Independent parameters such as phase and charge of PD patterns were recorded. The phase value will be encoded into the charge array and Transformer Neural Network is constructed using Positional Embedding and Transformer Encoder Layer. 80% of the recorded data will be used as a training data and 20% recorded data was used for testing of the classification models. Impacts of neuron numbers and network architecture on the PD classification performance will be observed © 2024 IEEE.

关键词： Electric corona

来源：评论

学校读者我要写书评

暂无评论

A novel robust blind medical image watermarking using rank-based DWT

引用

International Journal of Information technology (Singapore) 2023年第4期15卷 1901-1909页

作者： Devi, Hidangmayum Saxena Mohapatra, Hitesh Department of Computer Science and Engineering National Institute of Technology Manipur Takyelpat Imphal Imphal India School of Computer Engineering Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Odisha Bhubaneswar 751024 India

This paper aims at producing a novel, robust, and efficient blind medical image watermarking scheme on MRI, CT, X-ray, and Ultrasound dicom images. In this, the binary watermark image of sized is first encrypted with a logistic chaotic map and inserted into the cover dicom image. The insertion of the watermark is done by dividing the host dicom image into blocks and each block is transformed using first level Discrete Wavelet Transform. For each block, a set of DWT coefficients are selected at random using a key and the encrypted watermark is embedded to the selected coefficients using rank-based criterion. The proposed system is explored using distinct cover dicom images namely CT scan images, Magnetic Resonance Imaging images, X-Ray images, Ultrasound images, and Experimental results show that the suggested scheme accomplish PSNR (Peak Signal to Noise Ratio) values above 49dB and is resistant to several attacks revealed from its NCC (Normalized Correlation Coefficient) values. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Discrete wavelet transform Logistic chaotic map Medical image watermarking Rank based embedding

来源：评论

学校读者我要写书评

暂无评论

Identification of Drug-Side-Effect Association via Multiview Semisupervised Sparse Model

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2151-2162页

作者： Ding, Yijie Guo, Fei Tiwari, Prayag Zou, Quan Quzhou324000 China Central South University School of Computer Science and Engineering Changsha410083 China Halmstad University School of Information Technology Halmstad301 18 Sweden University of Electronic Science and Technology of China Institute of Fundamental and Frontier Sciences Chengdu610054 China

The association between drugs and side effects encompasses information about approved medications and their documented adverse drug reactions. Traditional experimental approaches for studying this association tend to be time consuming and expensive. To represent all drug-side-effect associations, a bipartite network framework is employed. Consequently, numerous computational methods have been devised to tackle this problem, focusing on predicting new potential associations. However, a significant gap lies in the neglect of the multiview learning algorithm, which has the ability to integrate diverse information sources and enhance prediction accuracy. In our study, we have developed a novel predictor named multiview semisupervised sparse model (Mv3SM) to address the drug side effect prediction problem. Our approach aims to explore the distinctive characteristics of various view features obtained from fully paired multiview data and mitigate the influence of noisy data. To test the performance of Mv3SM and other computational approaches, we conducted experiments using three benchmark datasets. The obtained results clearly demonstrate that our proposed method achieves superior predictive performance compared to alternative approaches. © 2023 IEEE.

关键词： Forecasting

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：