检索结果-内蒙古大学图书馆

The beauty of binomial coverage curves

Significance 2023年第2期20卷 26-27页

作者： Stapleton, Matt Matt Stapleton is an industrial statistician and data scientist who leads the data science team at Infineum a speciality chemicals company

Matt Stapleton sheds light on the baffling behaviour of binomial interval coverage and demonstrates how to find your way through the chaos

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Model Deep Learning Framework for Precise Detection of Potato Leaf Diseases

A Multi-Model Deep Learning Framework for Precise Detection ...

引用

2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024

作者： Adithya, G. Kiran, M Lalith Sofi, Mohammad Azhar Kalpana, A.V. Srm Institute Of Science And Technology Department Of Data Science And Business Systems Kattankulathur India

ISBN: (纸本)9798350352689

A variety of leaf diseases that can negatively impact crop output and quality present major problems to the development of potatoes. In this paper, a multi-model deep learning approach utilizing single convolutional neural networks (SCNN), long short-term memory networks (LSTM), and convolutional neural networks (CNN) is presented for the detection of potato leaf disease. The CNN classifies diseases in potato leaves based on RGB images, the LSTM analyzes temporal patterns, and the SCNN focuses on spatial features. Trained on a diverse dataset, the models are evaluated using performance metrics and compared with traditional methods, showcasing the effectiveness of deep learning. The CNN model is deployed as a user-friendly application for real-time disease prediction, enhancing practical usability in agriculture. This comprehensive approach offers a versatile solution for automated potato leaf disease detection, benefiting farmers in crop health management. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Drug Abuse Face Recognition: A Study on Image Corruption and Restoration 18

Enhancing Drug Abuse Face Recognition: A Study on Image Corr...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Dhake, Hruturaj Agarwal, Akshay Indian Institute of Science Education and Research Department of Data Science and Engineering Bhopal India

ISBN: (纸本)9798350364132

Drug abuse poses a pressing societal issue and limits the success of face recognition algorithms. Further, when the faces are acquired in an unconstrained environment, they get affected by several environmental factors including snow, noise, and blur. One prominent limitation of the existing research is that no work has been done to mitigate the impact of drug abuse on deep face recognition. Further, the problem became complicated in the presence of input corruption. Through this study, we aim to fill the gap by investigating the effects of drug-induced facial alterations coupled with input corruptions on deep face recognition. Our study indicates that drug alteration drastically alters facial features and on top of that the corruption further degrades the image quality and hence leads to poor performance by deep face recognition networks. Therefore, the one question we asked inspired by the success of generative networks is whether these models can help mitigate the impact of drug abuse and image corruption to boost performance. Through experiments simulating real-world scenarios, we demonstrate several interesting observations about the success of generative models including diffusion and generative architectures. The efficacy of these models is not only observed for face recognition but also for the improvement of gender classification performance. To the best of our knowledge mitigation of illicit drug abuse is not explored in the literature and hence, this research contributes to enhancing the reliability of face recognition systems amidst the challenges posed by drug abuse, thus advancing both understanding and application in practical settings. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

STPGTN-AMulti-Branch Parameters Identification Method Considering Spatial Constraints and Transient Measurement data

引用

Computer Modeling in Engineering & sciences 2023年第9期136卷 2635-2654页

作者： Shuai Zhang Liguo Weng Jiangsu Key Laboratory of Big Data Analysis Technology Nanjing University of Information Science and TechnologyNanjing210044China

Transmission line(TL)Parameter Identification(PI)method plays an essential role in the transmission *** existing PI methods usually have two limitations:(1)These methods only model for single TL,and can not consider the topology connection of multiple branches for simultaneous identification.(2)Transient bad data is ignored by methods,and the random selection of terminal section data may cause the distortion of PI and have serious ***,a multi-task PI model considering multiple TLs’spatial constraints and massive electrical section data is proposed in this *** Graph Attention Network module is used to draw a single TL into a node and calculate its influence coefficient in the transmission ***-Task strategy of Hard Parameter Sharing is used to identify the conductance ofmultiple branches *** show that themethod has good accuracy and *** to the consideration of spatial constraints,the method can also obtain more accurate conductance values under different training and testing conditions.

关键词： Transmission lines parameter identification graph modeling method deep learning

来源：评论

学校读者我要写书评

暂无评论

Boosting Graph Pooling with Persistent Homology 38

Boosting Graph Pooling with Persistent Homology

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ying, Chaolong Zhao, Xinjian Yu, Tianshu School of Data Science The Chinese University of Hong Kong Shenzhen China

Recently, there has been an emerging trend to integrate persistent homology (PH) into graph neural networks (GNNs) to enrich expressive power. However, naively plugging PH features into GNN layers always results in marginal improvement with low interpretability. In this paper, we investigate a novel mechanism for injecting global topological invariance into pooling layers using PH, motivated by the observation that filtration operation in PH naturally aligns graph pooling in a cut-off manner. In this fashion, message passing in the coarsened graph acts along persistent pooled topology, leading to improved performance. Experimentally, we apply our mechanism to a collection of graph pooling methods and observe consistent and substantial performance gain over several popular datasets, demonstrating its wide applicability and flexibility. © 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

data Processing Efficiency Aware User Association and Resource Allocation in Blockchain Enabled Metaverse over Wireless Communications 24

Data Processing Efficiency Aware User Association and Resour...

引用

2024 International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, MobiHoc 2024

作者： Qian, Liangxin Zhao, Jun College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400705212

In the rapidly evolving landscape of the Metaverse, enhanced by blockchain technology, the efficient processing of data has emerged as a critical challenge, especially in wireless communication systems. Addressing this need, our paper introduces the innovative concept of data processing efficiency (DPE), aiming to maximize processed bits per unit of resource consumption in blockchain-empowered Metaverse environments. To achieve this, we propose the DPE-Aware User Association and Resource Allocation (DAUR) algorithm, a tailored solution for these complex systems. The DAUR algorithm transforms the challenging task of optimizing the sum of DPE ratios into a solvable convex optimization problem. It uniquely alternates the optimization of key variables like user association, work offloading ratios, task-specific computing resource distribution, bandwidth allocation, user power usage ratios, and server computing resource allocation ratios. Our extensive numerical results demonstrate the DAUR algorithm’s effectiveness in DPE. © 2024 Copyright held by the owner/author(s).

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Advancements in Breast Imaging: CNN-based Thermogram Quality Enhancement 2

Advancements in Breast Imaging: CNN-based Thermogram Quality...

引用

2nd International Conference on Intelligent data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Venkatachalam, Nirmala Risha Dharshini, S. Charanya, B. Ashwati, K. Easwari Engineering College Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350327533

Breast thermography is a medical imaging technique that is free from radiation and is non-invasive which apprehends variations in temperature on the breast surface. The significant information, like early detection of potential abnormalities for breast health assessments, are provided. This study proposes an innovative approach to enhance the visual quality of breast thermograms utilizing a specialized Convolutional Neural Networks. The proposed methodology involves a tailored image enhancement model that is CNN-based to ascend the resolution, contrast, and overall quality of breast thermogram images. This research not only advances the state-of-the-art in breast thermogram image processing but also holds promise for enhancing the diagnostic capabilities of thermography in early breast cancer detection. The proposed CNN-based framework demonstrates its potential as a valuable tool in the realm of medical image analysis, contributing to improved clinical decision-making and patient outcomes in breast health assessments. © 2024 IEEE.

关键词： Abnormality Detection Breast Health Assessment Breast Thermography Convolutional Neural Network Diagnostic accuracy Image Enhancement Non-invasive Radiation free

来源：评论

学校读者我要写书评

暂无评论

OpenAI-Enhanced Personal Desktop Assistant: A Revolution in Human-Computer Interaction 2

OpenAI-Enhanced Personal Desktop Assistant: A Revolution in ...

引用

2nd International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2024

作者： Benny, Rijo Muralidharan, Ashwin Subramanian, Malathi Panimalar Engineering College Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350328202

The creation of a natural conversation between humans and machines is the primary objective of Artificial Intelligence (AI). One of the greatest advancements in AI that has the potential to significantly alter people's way of life are voice assistants. We know that the role of AI based voice assistants is to recognize the input human voice and respond to the given input via integrated voices. A lot of IT based organizations have been using dialogue systems technology to create various types of Virtual Personal Assistants (VPAs) based on their application requirements and areas for increasing interaction between human and a machine, for example, Apple's Siri, Microsoft's Cortana, Amazon Alexa and Google Assistant. By early 2023, Amazon Alexa was used daily by approximately 70% of users, yielding satisfaction levels surpassing 70%. Google Assistant boasted a global user base of 500 million per month, enjoying satisfaction rates over 80%. Apple Siri similarly engaged around 500 million users monthly, maintaining a satisfaction rate of about 78%. Microsoft Cortana had limited usage data but attained satisfaction rates around 60-65%. Roughly 60-70% of users across platforms expressed worries regarding data privacy and security when utilizing these desktop assistants. So, the main objective of our work is to create a personalized desktop assistant embedded with the OpenAI technology and improvement in security. Like the Microsoft's Cortana (which was discontinued by Microsoft), we aim to design a more efficient and personal desktop assistant, enhanced with OpenAI solely for Windows using Python, which can be accessed using any of the Windows Explorer like Windows 7,8,9,10,11. Here we use Python as the major programming language as it has a lot of inbuilt libraries that could make the task even easier. The way of developing a personal desktop assistant without requiring cloud services is discussed in this paper, which will also allow the future extension of such devices. ©

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Analysis of Vegetation Chemistry Using Feature Selection and Learning Methods on Hyperspectral Images 14

Analysis of Vegetation Chemistry Using Feature Selection and...

引用

14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024

作者： Yang, Meesun Basener, William University of Virginia School of Data Science CharlottesvilleVA United States

ISBN: (纸本)9798331513139

The spectrum provided for each pixel in a hyperspectral image provides information about the chemical composition present in the material. The presence of some constituents can be estimated from simple computations from values at specific wavelengths, for example using NDVI to estimate chlorophyll. There are many other molecular and elemental constituents that are essential for understanding vegetation type, health, and function, including water, nitrogen, and carbon, which do not have analogous known wavelength values and formulae. In this paper, we provide a machine learning framework for choosing sets of wavelengths and models for estimating the amounts of these constituents. Using data from the publicly available ECOSTRESS spectral library, 40 regression models, including both linear and nonlinear methods, are evaluated for estimating the constituent concentrations in vegetation. We test each model in conjunction with several feature selection methods, and combined with regularization within some of the models, identify specific wavelengths that are the most useful for quantifying the constituent concentrations, thereby reducing the high dimensionality of this data to a core set of the most critical wavelengths (top bands). Furthermore, our models test both the aggregated vegetation data and data subset by species, and show that while the concentrations can be estimated with accuracy in general on aggregated data, focusing the analysis on individual species can greatly improve accuracy. We also compare results from data collected using an ASD spectrometer with data collected using a Nicolet spectrometer. Implications of these findings are discussed. © 2024 IEEE.

关键词： Vegetation

来源：评论

学校读者我要写书评

暂无评论

Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations 38

Neural Pfaffians: Solving Many Many-Electron Schrödinger Eq...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Gao, Nicholas Günnemann, Stephan Department of Computer Science Munich Data Science Institut Technical University of Munich Germany

Neural wave functions accomplished unprecedented accuracies in approximating the ground state of many-electron systems, though at a high computational cost. Recent works proposed amortizing the cost by learning generalized wave functions across different structures and compounds instead of solving each problem independently. Enforcing the permutation antisymmetry of electrons in such generalized neural wave functions remained challenging as existing methods require discrete orbital selection via non-learnable hand-crafted algorithms. This work tackles the problem by defining overparametrized, fully learnable neural wave functions suitable for generalization across molecules. We achieve this by relying on Pfaffians rather than Slater determinants. The Pfaffian allows us to enforce the antisymmetry on arbitrary electronic systems without any constraint on electronic spin configurations or molecular structure. Our empirical evaluation finds that a single neural Pfaffian calculates the ground state and ionization energies with chemical accuracy across various systems. On the TinyMol dataset, we outperform the 'gold-standard' CCSD(T) CBS reference energies by 1.9 mEh and reduce energy errors compared to previous generalized neural wave functions by up to an order of magnitude. © 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

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：