检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Du, Hanwen Peng, Bo Ning, Xia Department of Computer Science and Engineering The Ohio State University United States Division of Medicinal Chemistry and Pharmacognosy College of Pharmacy The Ohio State University United States Department of Biomedical Informatics The Ohio State University United States Translational Data Analytics Institute The Ohio State University United States

Conversational Recommender Systems (CRS) proactively engage users in interactive dialogues to elicit user preferences and provide personalized recommendations. Existing methods train Reinforcement Learning (RL)-based agent with greedy action selection or sampling strategy, and may suffer from suboptimal conversational planning. To address this, we present a novel Monte Carlo Tree Search (MCTS)-based CRS framework SAPIENT. SAPIENT consists of a conversational agent (S-agent) and a conversational planner (S-planner). S-planner builds a conversational search tree with MCTS based on the initial actions proposed by S-agent to find conversation plans. The best conversation plans from S-planner are used to guide the training of S-agent, creating a self-training loop where S-agent can iteratively improve its capability for conversational planning. Furthermore, we propose an efficient variant SAPIENT-e for trade-off between training efficiency and performance. Extensive experiments on four benchmark datasets validate the effectiveness of our approach, showing that SAPIENT outperforms the state-of-the-art baselines. © 2024, CC BY.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

A Full wCDM Analysis of KiDS-1000 Weak Lensing Maps using Deep Learning

arXiv

引用

arXiv 2022年

作者： Fluri, Janis Kacprzak, Tomasz Lucchi, Aurelien Schneider, Aurel Refregier, Alexandre Hofmann, Thomas Institute of Particle Physics and Astrophysics Department of Physics ETH Zurich Switzerland Data Analytics Lab Department of Computer Science ETH Zurich Switzerland Swiss Data Science Center Paul Scherrer Institute Switzerland Department of Mathematics and Computer Science University of Basel Switzerland Center for Theoretical Astrophysics and Cosmology Institute for Computational Science University of Zurich Switzerland

We present a full forward-modeled wCDM analysis of the KiDS-1000 weak lensing maps using graph-convolutional neural networks (GCNN). Utilizing the CosmoGrid, a novel massive simulation suite spanning six different cosmological parameters, we generate almost one million tomographic mock surveys on the sphere. Due to the large data set size and survey area, we perform a spherical analysis while limiting our map resolution to HEALPix nside = 512. We marginalize over systematics such as photometric redshift errors, multiplicative calibration and additive shear bias. Furthermore, we use a map-level implementation of the non-linear intrinsic alignment model along with a novel treatment of baryonic feedback to incorporate additional astrophysical nuisance parameters. We also perform a spherical power spectrum analysis for comparison. The constraints of the cosmological parameters are generated using a likelihood-free inference method called Gaussian Process Approximate Bayesian Computation (GPABC). Finally, we check that our pipeline is robust against choices of the simulation parameters. We find constraints on the degeneracy parameter of S8 ≡ σ8pΩM/0.3 = 0.78+0−00606 for our power spectrum analysis and S8 = 0.79+0−00505 for our GCNN analysis, improving the former by 16%. This is consistent with earlier analyses of the 2-point function, albeit slightly higher. Baryonic corrections generally broaden the constraints on the degeneracy parameter by about 10%. These results offer great prospects for full machine learning based analyses of on-going and future weak lensing surveys. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Stochastic gradient descent estimation of generalized matrix factorization models with application to single-cell RNA sequencing data

arXiv

引用

arXiv 2024年

作者： Castiglione, Cristian Segers, Alexandre Clement, Lieven Risso, Davide Bocconi Institute for Data Science and Analytics Bocconi University Via Röntgen 1 Milan20136 Italy Department of Applied Mathematics Computer Science and Statistics Ghent University Krijgslaan 281-S9 Ghent9000 Belgium Department of Statistical Sciences University of Padova Via Cesare Battisti 241 Padova35121 Italy

Single–cell RNA sequencing allows the quantitation of gene expression at the individual cell level, enabling the study of cellular heterogeneity and gene expression dynamics. Dimensionality reduction is a common preprocessing step to simplify the visualization, clustering, and phenotypic characterization of samples. This step, often performed using principal component analysis or closely related methods, is challenging because of the size and complexity of the data. In this work, we present a generalized matrix factorization model assuming a general exponential dispersion family distribution and we show that many of the proposed approaches in the single–cell dimensionality reduction literature can be seen as special cases of this model. Furthermore, we propose a scalable adaptive stochastic gradient descent algorithm that allows us to estimate the model efficiently, enabling the analysis of millions of cells. Our contribution extends to introducing a novel warm start initialization method, designed to accelerate algorithm convergence and increase the precision of final estimates. Moreover, we discuss strategies for dealing with missing values and model selection. We benchmark the proposed algorithm through extensive numerical experiments against state-of-the-art methods and showcase its use in real-world biological applications. The proposed method systematically outperforms existing methods of both generalized and non-negative matrix factorization, demonstrating faster execution times while maintaining, or even enhancing, matrix reconstruction fidelity and accuracy in biological signal extraction. Finally, all the methods discussed here are implemented in an efficient open-source R package, sgdGMF, available at github/CristianCastiglione/sgdGMF. © 2024, CC BY.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

A Comparison of the Instructor-Trainee Dance dataset Using Cosine similarity, Euclidean distance, and Angular difference

A Comparison of the Instructor-Trainee Dance Dataset Using C...

引用

International computer science and Engineering Conference (ICSEC)

作者： Thanawat Srikaewsiew Khatadet Khianchainat Atima Tharatipyakul Suporn Pongnumkul Sarunya Kanjanawattana Department of Computer Engineering Institute of Engineering Suranaree University of Technology Nakhon Ratchasima Thailand Data Science and Analytics Research Group National Electronics and Computer Technology Center (NECTEC) Pathumthani Thailand

ISBN: (纸本)9781665462730

The COVID-19 outbreak has restricted most outdoor activities, leads to increasing interest in exercise at home with online trainers. One issue of online exercise technology is the safety since improper motion might result in injury. As a basis to prevent improper motion, methods for evaluating the motion similarity between an instructor and a trainee are essential. Cosine similarity, Angular difference, and Euclidean distance are three general ways for the motion evaluation. This study aimed to determine the most effective way for analyzing the similarity of human motion on the dataset of instructor-led dances. We first experimented with the data to find the appropriate cut-off value for classifying posture into two classes based on the similarity score. Confusion matrix, precision, recall, F1-score, accuracy of the results were then used to compare the efficiency. We discovered that Cosine similarity had the highest accuracy, 82.77 percent at cut-off 93.

关键词： computer science COVID-19 Humanities Euclidean distance Safety Injuries

来源：评论

学校读者我要写书评

暂无评论

Smart Cap: A deep learning and iot based assistant for the visually impaired 3

Smart Cap: A deep learning and iot based assistant for the v...

引用

3rd International Conference on Smart Systems and Inventive Technology, ICSSIT 2020

作者： Hengle, Amey Kulkarni, Atharva Bavadekar, Nachiket Kulkarni, Niraj Udyawar, Rutuja PVG's COET SPPU Computer Engineering Department Pune India Data Science and AI Optimum Data Analytics Pune India

ISBN: (纸本)9781728158211

India is home to the largest number of visually impaired people in the world, about 40 million, which accounts for 20% of the world's blind population. Moreover, more than 90% of these people have little to no access to the necessary assistive technologies. The paper proposes 'Smart Cap, ' a first-person vision-based assistant, aimed at bringing the world as a narrative to these visually impaired people of India. The Smart Cap acts as a conversational agent bringing together the disciplines of Internet of Things and Deep Learning and provides features like face recognition, image captioning, text detection and recognition, and online newspaper reading. The hardware architecture consists of a Raspberry Pi, a USB webcam, a USB microphone, earphones, power source, and extension cables. The user can interact with the Smart Cap by giving specific commands, which trigger the corresponding feature module that returns an audio output. The face recognition module is based on the dlib's face recognition project. It is a two-step process of detecting a face in the image and identifying it. The image captioning task synthesizes an attention-based CNN-LSTM encoder-decoder model coupled with beam search for finding the best caption. Google's Vision API service is used for text detection and recognition. An additional feature of online newspaper reading is also provided, thus, keeping the blind person up to date with the daily news. © 2020 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

HOW MANY DIRECTIONS DETERMINE A SHAPE AND OTHER SUFFICIENCY RESULTS FOR TWO TOPOLOGICAL TRANSFORMS

引用

Transactions of the American Mathematical Society Series B 2022年第32期9卷 1006-1043页

作者： Curry, Justin Mukherjee, Sayan Turner, Katharine Department of Mathematics and Statistics University at Albany SUNY Albany 12222 NY United States Departments of Statistical Science Mathematics Computer Science Biostatistics & Bioinformatics Duke University Durham 27708 NC United States Center for Scalable Data Analytics and Artificial Intelligence Universität Leipzig Germany Max Planck Institute for Mathematics in the Natural Sciences Leipzig Germany Mathematical Sciences Institute Australian National University Canberra Australia

In this paper we consider two topological transforms that are pop-ular in applied topology: the Persistent Homology Transform and the Euler Characteristic Transform. Both of these transforms are of interest for their mathematical properties as well as their applications to science and engineer-ing, because they provide a way of summarizing shapes in a topological, yet quantitative, way. Both transforms take a shape, viewed as a tame subset M of R^d, and associates to each direction v ∈ S^d−1 a shape summary obtained by scanning M in the direction v. These shape summaries are either persistence diagrams or piecewise constant integer-valued functions called Euler curves. By using an inversion theorem of Schapira, we show that both transforms are injective on the space of shapes, i.e. each shape has a unique transform. Moreover, we prove that these transforms determine continuous maps from the sphere to the space of persistence diagrams, equipped with any Wasserstein p-distance, or the space of Euler curves, equipped with certain L^p norms. By making use of a stratified space structure on the sphere, induced by hyperplane divisions, we prove additional uniqueness results in terms of distributions on the space of Euler curves. Finally, our main result proves that any shape in a certain uncountable space of PL embedded shapes with plausible geometric bounds can be uniquely determined using only finitely many directions. © 2022 by the author(s) under Creative Commons Attribution 3.0 License (CC BY 3.0).

关键词： Euler calculus persistent homology statistical shape analysis

来源：评论

学校读者我要写书评

暂无评论

Reservoir Water Level Forecasting using Deep Learning

Reservoir Water Level Forecasting using Deep Learning

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Archita Mallick Surajit Ghosh Kounik De Sarkar Sudip Roy Centre of Excellence in Disaster Mitigation and Management Indian Institute of Technology Roorkee Roorkee India Water Futures Data and Analytics International Water Management Institute Colombo Sri Lanka Environmental Science and Engineering Department Indian Institute of Technology Bombay Mumbai India Department of Computer Science and Engineering Indian Institute of Technology Roorkee Roorkee India

ISBN: (数字)9798350390346

ISBN: (纸本)9798350390353

Reservoirs play a vital role in water resource management and provide essential ecosystem services. The study focuses on extracting the water extent of Maithon reservoir, Jharkhand, India, from 2017 to 2023 by delineating the boundaries between the water and non-water class extracted from Sentinel-1 data. The scenes were processed using Google Earth Engine to obtain water extent using the Otsu method. This research extends the application of the extracted water extent values, precipitation data from CHIRPS, and weekly historical water level data of the reservoir obtained from the Central Water Commission to monthly forecasts of the water level using the Long Short-Term Memory (LSTM) model. The forecasts were obtained with a mean absolute error of around 80 cm with test data. The study provides initial results and is under further modification, where the improved estimation shall be integrated into flood early warning systems and help to provide actionable insights to stakeholders and decision-makers to mitigate risks and optimize water usage.

关键词： Precipitation Ecosystems Sentinel-1 Alarm systems Reservoirs Floods data mining Stakeholders Long short term memory Streams

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dental Caries Identification with Deep Learning: A Study of Convolutional Neural Networks and Transfer Learning Approaches

SSRN

引用

SSRN 2024年

作者： Mannan, Fayqa Adeel, Muhammad Arif, Erssa Li, Jianqiang Ullah, Amin Nawazish, Samra Mahmood, Tariq Rehman, Amjad Shoukat, Ijaz Faculty of Information Technology Beijing University of Technology Beijing100124 China Department of Computer Science Government College University Faisalabad38000 Pakistan Department of Computer Science School of Science National Textile University Faisalabad37610 Pakistan Department of Computer Science Faculty of Computing Riphah International University Faisalabad38000 Pakistan Beijing Engineering Research Center for IoT Software and Systems 100124 China Department of Computer Science Faculty of IT and Computer Science University of Central Punjab Lahore Pakistan School of Computer Science and Engineering Southeast University Nanjing China Software Engineering Department University of Engineering and Technology Taxila Pakistan Artificial Intelligence & Data Analytics Lab CCIS Prince Sultan University Riyadh11586 Saudi Arabia Faculty of information Sciences University of Education Vehari Campus Vehari61100 Pakistan

Various deep learning techniques have been employed to diagnose dental caries using X-ray images. In this study, we utilized deep learning models, including Convolutional Neural Networks (CNNs) and transfer learning models such as Visual Geometry Group (VGG16), VGG19, ResNet50, and Inception V3, to identify dental caries in periapical radiographs. The traditional CNN model comprises three sets of 2D convolutional layers, followed by an activation layer, a max-pooling layer, a flatten layer, one dense layer, another activation layer, dropout, another dense layer, and a final activation layer. For the VGG models, ResNet50, and Inception V3, the top convolutional layers were frozen to prevent retraining of the model, with only the last layers trained to produce the required output. The accuracy achieved by CNN, VGG16, VGG19, ResNet50, and Inception V3 was 90%, 96%, 73%, 70%, and 73%, respectively. VGG16 exhibited the highest accuracy among the models. Hyperparameters were carefully selected using a grid search approach, and the results were validated using the Shuffle-Split-Cross (SSC) validation method. These findings underscore the effectiveness of transfer learning in analyzing medical images, particularly in the diagnosis of dental caries. © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transfer and Alignment Network for Generalized Category Discovery

arXiv

引用

arXiv 2023年

作者： An, Wenbin Tian, Feng Shi, Wenkai Chen, Yan Wu, Yaqiang Wang, Qianying Chen, Ping School of Automation Science and Engineering Xi’an Jiaotong University China School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Laboratory for Big Data Analytics China Lenovo Research China Department of Engineering University of Massachusetts Boston United States

Generalized Category Discovery (GCD) is a crucial real-world task that aims to recognize both known and novel categories from an unlabeled dataset by leveraging another labeled dataset with only known categories. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge transfer between labeled and unlabeled data and noisy representation learning on the unlabeled data. The former leads to unreliable estimation of learning targets for novel categories and the latter hinders models from learning discriminative features. To mitigate these two issues, we propose a Transfer and Alignment Network (TAN), which incorporates two knowledge transfer mechanisms to calibrate the biased knowledge and two feature alignment mechanisms to learn discriminative features. Specifically, we model different categories with prototypes and transfer the prototypes in labeled data to correct model bias towards known categories. On the one hand, we pull instances with known categories in unlabeled data closer to these prototypes to form more compact clusters and avoid boundary overlap between known and novel categories. On the other hand, we use these prototypes to calibrate noisy prototypes estimated from unlabeled data based on category similarities, which allows for more accurate estimation of prototypes for novel categories that can be used as reliable learning targets later. After knowledge transfer, we further propose two feature alignment mechanisms to acquire both instance- and category-level knowledge from unlabeled data by aligning instance features with both augmented features and the calibrated prototypes, which can boost model performance on both known and novel categories with less noise. Experiments on three benchmark datasets show that our model outperforms SOTA methods, especially on novel categories. Theoretical analysis is provided for an in-depth understanding

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Feature-Oriented Sampling for Fast and Scalable GNN Training

Feature-Oriented Sampling for Fast and Scalable GNN Training

引用

IEEE International Conference on data Mining (ICDM)

作者： Xin Zhang Yanyan Shen Lei Chen Division of Emerging Interdisciplinary Areas The Hong Kong University of Science and Technology Department of Computer Science and Engineering Shanghai Jiao Tong University Data Science and Analytics Thrust The Hong Kong University of Science and Technology (Guangzhou)

Recently Graph Neural Networks (GNNs) have achieved great success in many applications. To apply GNNs to large graphs, mini-batch training and sampling are widely adopted by recent works. However, existing works generate mini-batches following a topology-oriented sampling style, which first samples a subgraph and then fetches the corresponding node features to construct a mini-batch. This inevitably incurs intensive random access of graph data, the exponential growth of the batch size, and constrained candidates during sampling. In this work, we advocate adopting a feature-oriented sampling style which can overcome these drawbacks. We first sample the node features and then induce the corresponding subgraph to form a mini-batch. We apply the feature-oriented sampling method to three mainstream GNN models to demonstrate the effectiveness and efficiency of this sampling style. Experiments on four large-scale datasets show that feature-oriented sampling can achieve comparable accuracy as topology-oriented sampling while speeding up the training procedure by 2.2 ~ 7.9 times.

关键词： Training Social networking (online) Scalability Sampling methods Graph neural networks data mining

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：