检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhang, Ruiteng Wei, Jianguo Lu, Xugang Lu, Wenhuan Jin, Di Zhang, Lin Xu, Junhai Tianjin University College of Intelligence and Computing Tianjin China Qinghai Nationalities University Computer College Xining China National Institute of Information and Communications Technology Kyoto Japan National Institute of Informatics Tokyo Japan

ISBN: (纸本)9781728163277

Optimal transport (OT) can be applied to cross-domain adaptation in speaker verification (SV) by converting speakers' probability distributions from source to target domains. However, in scenarios involving over-massive categories (speakers) or difficult samples in discrimination, OT often has difficulty computing effective transports. To address this challenge, we propose an OT-based unsupervised domain adaptation (UDA) framework for SV, OT with a diversified memory bank, called DMB-OT, which ensures the accuracy of transfers by two strategies: (1) It regularizes the solution space of OT, which attempts to plan transformations between audio samples from the same speaker with high confidence;(2) it integrates a dynamic curriculum learning algorithm, preventing OT from calculating transport couplings based on hard-discriminative samples in the early stage of UDA. Experiments under different target domains showed that our unsupervised DMB-OT could significantly improve the performance of OT-based UDA and could even match the performance of the supervised PLDA-based adaptation. © 2023 IEEE.

关键词： diversified memory bank domain adaptation optimal transport self-paced learning Speaker verification

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Pruned CNN Models for Tomato and Potato Disease Classification 3rd

Comparative Study of Pruned CNN Models for Tomato and Potato...

引用

3rd International Conference on Emerging Electronics and Automation, E2A 2023

作者： Dheeraj, Akshay Chand, Satish Raj, Aditya ICAR-Indian Agricultural Statistics Research Institute New Delhi India School of Computer and Systems Sciences Jawaharlal Nehru University New Delhi India National Informatics Centre Ministry of Electronics and Information Technology New Delhi India

ISBN: (纸本)9789819730896

Plant disease affects crop productivity and yield. Several machine learning and deep learning architectures have been used for plant disease classification for the last decade. Tomato and Potatoes are being grown in many parts of the world. This research study presents various pruned deep CNN models for potato and tomato disease classification where different CNN architectures were pruned, their core structure was retained, and parameter size was reduced to approximate 1.5 M. Rather than focusing solely on accuracy, this study also considers reproduction and deployment. Images of tomato and potato plants covering 13 diseases, including healthy, were taken from the PlantVillage dataset. Six deep CNN models were considered, pruned and concatenated, out of which EfficientNetB0 have a superior performance score of 99.90%, with a parameter size of 1.5 M and 0.826G computing operations (FLOPs), outperforming the remaining five pruned CNN models. The developed lightweight model can be easily deployed in mobile and portable devices with limited resources and computational power, to assist farmers in identifying potato and tomato diseases. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Performance Creativity Enhancement Method Based on Emotional Analysis and Concentration

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 1019-1048页

作者： Liu, Chang Zhang, Longfei Huang, Tianyu Wu, Yufeng Zhang, Fuquan Lin, Qi Department of Computer Science and Technology Beijing Institute of Technology 100081 China Beijing Key Laboratory of Digital Performance and Simulation Technology 100081 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu610021 China Informatics King’s College London LondonWC2R 2LS United Kingdom

Intelligent performance creativity is a new research direction of the intersection of technology and art. At present, the cutting-edge technologies such as computer simulation, emotional computing and machine learning have been applied to the evaluation and enhancement of intelligent performance creativity. The application of these technologies has greatly increased the diversity of performance forms and the complexity of performance content. For the traditional stage performance, due to the lack of timely feedback from the audience, it is difficult for the director to enhance the creativity effec-tively. In order to solve this problem, this paper proposes concentration level enhancement method (CLEM). The CLEM extracts and analyzes the physiological and emotional characteristics of the audience by collecting the multimodal physiological signal data of the audience. Through the analysis of the features, the concentration information of the audience is obtained and the concentration level (CL) is defined. Based on the physiological and emotional induction mechanism, a performance creativity enhancement strategy is proposed, which enhances the performance creativity in two aspects: " Visual-based" and " Content-based". Through the concentration level enhancement method, compare the audience’s performance attention changes before and after the performance creativity enhancement, select the effective strategies to enhance the performance creativity, and provide the director with quantifiable performance creativity enhancement feedback results. The experimental results show that the CLEM proposed in this paper can effectively induce significant changes in the audience’s emotion, and the selected creative enhancement strategy can significantly improve the audience’s concentration and achieve the purpose of enhancing the creativity of the performance. © 2023, Journal of Network Intelligence.

关键词： Physiology

来源：评论

学校读者我要写书评

暂无评论

TRADE: Transfer of Distributions between External Conditions with Normalizing Flows

arXiv

引用

arXiv 2024年

作者： Wahl, Stefan Rousselot, Armand Draxler, Felix Schopmans, Henrik Köthe, Ullrich Computer Vision and Learning Lab Heidelberg University Germany Institute of Theoretical Informatics Karlsruhe Institute of Technology Germany

Modeling distributions that depend on external control parameters is a common scenario in diverse applications like molecular simulations, where system properties like temperature affect molecular configurations. Despite the relevance of these applications, existing solutions are unsatisfactory as they require severely restricted model architectures or rely on energy-based training, which is prone to instability. We introduce TRADE, which overcomes these limitations by formulating the learning process as a boundary value problem. By initially training the model for a specific condition using either i.i.d. samples or backward KL training, we establish a boundary distribution. We then propagate this information across other conditions using the gradient of the unnormalized density with respect to the external parameter. This formulation, akin to the principles of physics-informed neural networks, allows us to efficiently learn parameter-dependent distributions without restrictive assumptions. Experimentally, we demonstrate that TRADE achieves excellent results in a wide range of applications, ranging from Bayesian inference and molecular simulations to physical lattice models. Our code is available at https://***/vislearn/trade © 2024, CC BY.

关键词： Molecular modeling

来源：评论

学校读者我要写书评

暂无评论

Monotone Arithmetic Complexity of Graph Homomorphism Polynomials 49

Monotone Arithmetic Complexity of Graph Homomorphism Polynom...

引用

49th EATCS International Conference on Automata, Languages, and Programming, ICALP 2022

作者： Komarath, Balagopal Pandey, Anurag Rahul, Chengot Sankaramenon Indian Institute of Technology Gandhinagar India Department of Computer Science Universität des Saarlances Saarland Informatics Campus Saarbrücken Germany School of Mathematics and Computer Science Indian Institute of Technology Goa India

ISBN: (纸本)9783959772358

We study homomorphism polynomials, which are polynomials that enumerate all homomorphisms from a pattern graph H to n-vertex graphs. These polynomials have received a lot of attention recently for their crucial role in several new algorithms for counting and detecting graph patterns, and also for obtaining natural polynomial families which are complete for algebraic complexity classes VBP, VP, and VNP. We discover that, in the monotone setting, the formula complexity, the ABP complexity, and the circuit complexity of such polynomial families are exactly characterized by the treedepth, the pathwidth, and the treewidth of the pattern graph respectively. Furthermore, we establish a single, unified framework, using our characterization, to collect several known results that were obtained independently via different methods. For instance, we attain superpolynomial separations between circuits, ABPs, and formulas in the monotone setting, where the polynomial families separating the classes all correspond to well-studied combinatorial problems. Moreover, our proofs rediscover fine-grained separations between these models for constant-degree polynomials. © Balagopal Komarath, Anurag Pandey, and Chengot Sankaramenon Rahul;licensed under Creative Commons License CC-BY 4.0

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

AI Based Prediction for Heart Disease: A Comparative Analysis and an Improved Machine Learning Approach 6

AI Based Prediction for Heart Disease: A Comparative Analysi...

引用

6th Asian Conference on Artificial Intelligence technology, ACAIT 2022

作者： Raval, Jay Verma, Jai Prakash Islam, Sardar N.M. Jain, Rachna Thakur, Narina Institute of Technology Nirma University Computer Science Engineering Department Ahmedabad India Victoria University Applied Informatics Research Melbourne Australia Bhagwan Parshuram Institute of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9781665453110

Heart disease problems are growing day by day in the world. Many factors are responsible for increasing the chance of heart attack and any other disease. Many countries have a low level of cardiovascular competence in predicting heart disease-related issues. Finding the best accurate machine learning classifiers for various diagnostic uses by data mining and machine learning techniques aids in predicting whether or not the heart disease-related issue will occur. To predict heart disease, a number of supervised machine-learning algorithms are used and their effectiveness are evaluated. With the exceptionof MLP and KNN, all applied algorithms had their estimated feature significance scores for each feature. This helps to find the main factors affecting heart disease and the accuracy of the model, which helps to get the best prediction. At the end of the research the support vector machine gives us 87.91 % highest testing accuracy compare with all applied machine learning algorithm. © 2022 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Parameterized Saga of First-Fit and Last-Fit Coloring 42

Parameterized Saga of First-Fit and Last-Fit Coloring

引用

42nd International Symposium on Theoretical Aspects of computer Science, STACS 2025

作者： Agrawal, Akanksha Lokshtanov, Daniel Panolan, Fahad Saurabh, Saket Verma, Shaily Indian Institute of Technology Madras India University of California Santa BarbaraCA United States School of Computer Science University of Leeds United Kingdom The Institute of Mathematical Sciences HBNI Chennai India Department of Informatics University of Bergen Norway Algorithm Engineering Group Hasso Plattner Institute Potsdam Germany

ISBN: (纸本)9783959773652

The classic greedy coloring algorithm considers the vertices of an input graph G in a given order and assigns the first available color to each vertex v in G. In the Grundy Coloring problem, the task is to find an ordering of the vertices that will force the greedy algorithm to use as many colors as possible. In the Partial Grundy Coloring, the task is also to color the graph using as many colors as possible. This time, however, we may select both the ordering in which the vertices are considered and which color to assign the vertex. The only constraint is that the color assigned to a vertex v is a color previously used for another vertex if such a color is available. Whether Grundy Coloring and Partial Grundy Coloring admit fixed-parameter tractable (FPT) algorithms, algorithms with running time f(k)nO(1), where k is the number of colors, was posed as an open problem by Zaker and by Effantin et al., respectively. Recently, Aboulker et al. (STACS 2020 and Algorithmica 2022) resolved the question for Grundy Coloring in the negative by showing that the problem is W[1]-hard. For Partial Grundy Coloring, they obtain an FPT algorithm on graphs that do not contain Ki,j as a subgraph (a.k.a. Ki,j-free graphs). Aboulker et al. re-iterate the question of whether there exists an FPT algorithm for Partial Grundy Coloring on general graphs and also asks whether Grundy Coloring admits an FPT algorithm on Ki,j-free graphs. We give FPT algorithms for Partial Grundy Coloring on general graphs and for Grundy Coloring on Ki,j-free graphs, resolving both the questions in the affirmative. We believe that our new structural theorems for partial Grundy coloring and "representative-family" like sets for Ki,j-free graphs that we use in obtaining our results may have wider algorithmic applications. © Akanksha Agrawal, Daniel Lokshtanov, Fahad Panolan, Saket Saurabh, and Shaily Verma.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Interdisciplinary perspectives on privacy awareness in lifelogging technology development

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2291-2312页

作者： Wilkowska, Wiktoria Offermann, Julia Colonna, Liane Florez-Revuelta, Francisco Climent-Pérez, Pau Mihailidis, Alex Poli, Angelica Spinsante, Susanna Ziefle, Martina Human-Computer Interaction Center RWTH Aachen University Aachen Germany Swedish Law and Informatics Research Institute Stockholm University Stockholm Sweden Department of Computer Technology University of Alicante Alicante Spain Department of Occupational Science and Occupational Therapy University of Toronto Toronto Canada Department of Information Engineering Marche Polytechnic University Ancona Italy

Population aging resulting from demographic changes requires some challenging decisions and necessary steps to be taken by different stakeholders to manage current and future demand for assistance and support. The consequences of population aging can be mitigated to some extent by assisting technologies that can support the autonomous living of older individuals and persons in need of care in their private environments as long as possible. A variety of technical solutions are already available on the market, but privacy protection is a serious, often neglected, issue when using such (assisting) technology. Thus, privacy needs to be thoroughly taken under consideration in this context. In a three-year project PAAL (‘Privacy-Aware and Acceptable Lifelogging Services for Older and Frail People’), researchers from different disciplines, such as law, rehabilitation, human-computer interaction, and computer science, investigated the phenomenon of privacy when using assistive lifelogging technologies. In concrete terms, the concept of Privacy by Design was realized using two exemplary lifelogging applications in private and professional environments. A user-centered empirical approach was applied to the lifelogging technologies, investigating the perceptions and attitudes of (older) users with different health-related and biographical profiles. The knowledge gained through the interdisciplinary collaboration can improve the implementation and optimization of assistive applications. In this paper, partners of the PAAL project present insights gained from their cross-national, interdisciplinary work regarding privacy-aware and acceptable lifelogging technologies. © 2022, The Author(s).

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Optimized Price Prediction of Cryptocurrencies using Deep Learning on High-Volume Time Series Data

Optimized Price Prediction of Cryptocurrencies using Deep Le...

引用

International Conference on Information, Intelligence, Systems and Applications (IISA)

作者： Gerasimos Vonitsanos Andreas Kanavos Foteini Grivokostopoulou Spyros Sioutas Computer Engineering and Informatics Department University of Patras Patras Greece Department of Informatics Ionian University Corfu Greece Computer Technology Institute and Press “Diophantus“ Patras Greece

ISBN: (数字)9798350368833

ISBN: (纸本)9798350368840

Statistical models, enhanced by deep learning techniques, have become pivotal in various predictive tasks, including financial forecasting. This paper addresses the challenge of predicting cryptocurrency prices, utilizing a dataset comprising various cryptocurrencies treated as time series. We employ several deep neural network architectures-including Multilayer Perceptrons (MLP), Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM), and Bidirectional LSTM networks-to forecast future prices. Our methodology involves a detailed analysis of cryptocurrency time series to inform the design of these networks. The performance of each model is rigorously compared, highlighting their predictive capabilities in the context of cryptocurrency markets. This study not only contributes to the empirical literature by applying advanced neural networks to high-volume financial data but also provides a comparative analysis that may guide future applications of deep learning in economic forecasting.

关键词： Deep learning Biological system modeling Time series analysis Predictive models Multilayer perceptrons Economic forecasting Big Data applications Cryptocurrency Context modeling

来源：评论

学校读者我要写书评

暂无评论

Neural Fast Full-Rank Spatial Covariance Analysis for Blind Source Separation 31

Neural Fast Full-Rank Spatial Covariance Analysis for Blind ...

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Bando, Yoshiaki Masuyama, Yoshiki Nugraha, Aditya Arie Yoshii, Kazuyoshi National Institute of Advanced Industrial Science and Technology Japan RIKEN Tokyo Japan Department of Computer Science Tokyo Metropolitan University Japan Graduate School of Informatics Kyoto University Japan

ISBN: (纸本)9789464593600

This paper describes an efficient unsupervised learning method for a neural source separation model that utilizes a probabilistic generative model of observed multichannel mixtures proposed for blind source separation (BSS). For this purpose, amortized variational inference (AVI) has been used for directly solving the inverse problem of BSS with full-rank spatial covariance analysis (FCA). Although this unsupervised technique called neural FCA is in principle free from the domain mismatch problem, it is computationally demanding due to the full rankness of the spatial model in exchange for robustness against relatively short reverberations. To reduce the model complexity without sacrificing performance, we propose neural FastFCA based on the jointly-diagonalizable yet full-rank spatial model. Our neural separation model introduced for AVI alternately performs neural network blocks and single steps of an efficient iterative algorithm called iterative source steering. This alternating architecture enables the separation model to quickly separate the mixture spectrogram by leveraging both the deep neural network and the multichannel optimization algorithm. The training objective with AVI is derived to maximize the marginalized likelihood of the observed mixtures. The experiment using mixture signals of two to four sound sources shows that neural FastFCA outperforms conventional BSS methods and reduces the computational time to about 2 % of that for the neural FCA. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Blind source separation

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：