检索结果-内蒙古大学图书馆

10th International Conference on Learning Representations, ICLR 2022

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering AIIS ASRI INMC ISRC NSI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Unmanned Aerial Vehicles Navigation: An Overview

引用

SN computer science 2024年第2期5卷 256页

作者： Fagundes-Junior, Leonardo A. de Carvalho, Kevin B. Ferreira, Ricardo S. Brandão, Alexandre S. Núcleo de Especialização em Robótica Department of Electrical Engineering Graduate Program in Computer Science Federal University of Viçosa-UFV Av. Petter Henry Rolfs MG Viçosa 36570-900 Brazil

Unmanned aerial vehicles (UAVs) are a valuable source of data for a wide range of real-time applications, due to their functionality, availability, adaptability, and maneuverability. Working as mobile sensors, they can provide a cost-effective solution for extremely complex tasks, such as inspection, air-to-ground communications, search and rescue, surveillance, among others. Nevertheless, the robots needs to navigate in quite distinct environments and in different dynamism levels, usually facing unpredicted situations, very often using limited sensing and computing capabilities. A large number of solutions to this problem has been featured by the scientific community in the last years, some of them based on machine-learning (ML) methods. Due to its great capability to deal with big data and complexity, as well as its speedy and high-accuracy processing, the ML framework has been used to improve existing technologies and control techniques. In this context, its adoption in several UAV navigation strategies is expected to provide solutions for various problems where UAVs are used in real-time applications. Thus, in order to contextualize the most recent advances, this work provides a detailed survey of relevant researches in which ML techniques have been used in UAV navigation to improve some functional aspects, such as energy-efficiency, communication, execution time, resource management, obstacle avoidance, and path planning. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Autonomous navigation Path planning UAV-based solutions Visual-based navigation

来源：评论

学校读者我要写书评

暂无评论

Correlating the Ambient Conditions and Performance Indicators of the LoRaWAN via Surrogate Gaussian Process-Based Bidirectional LSTM Stacked Autoencoder

引用

IEEE Transactions on Network and Service Management 2023年第3期20卷 3413-3427页

作者： Bhat, Showkat Ahmad Huang, Nen-Fu Hussain, Imtiyaz Sajjad, Uzair National Tsing Hua University College of Electrical and Computer Science Hsinchu1300044 Taiwan National Tsing Hua University Department of Computer Science Hsinchu1300044 Taiwan National Taipei University of Technology Graduate Program in Energy and Opto-Electronic Materials Taipei10608 Taiwan National Taipei University of Technology Department of Energy and Refrigerating Airconditioning Engineering Taipei10608 Taiwan

LoRa's biggest advantage is its flexibility, which is the ability to increase or decrease data rate and range while decreasing or increasing sensitivity. Whenever propagation conditions change frequently, this function allows the spreading factor to be modified accordingly. Despite their efficiency and scalability, adaptive data rate algorithms ignore and fail to factor in the complex correlation between ambient weather parameters influencing the communication channel design. In this research, a Bayesian surrogate Gaussian process-based bidirectional LSTM stacked autoencoder model (BSGP-BLSTM-SAE) is proposed to estimate the channel performance indicators such as received signal strength indicator (RSSI) and signal-to-noise ratio (SNR) and to determine the correlation between the ambient weather conditions and performance indicators for the LoRaWAN network. Bayesian optimization algorithm has been used to optimize the hyper-parameters of the developed model. A LoRaWAN experimental multivariate time series dataset has been used for the evaluation of the developed model, which upon testing and validation produces high accuracy in predicting the channel performance indicators and ambient conditions of the experimental LoRaWAN network. The mean absolute error of the developed model was around 0.45. Thus, the proposed model can predict the link performance indicators and thereby assist in real-time optimization of the transmission parameters to enhance the network performance in LoRaWAN-based systems at different ambient conditions. © 2004-2012 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time-Series Deep Learning for Joint Prediction of Temperature and Relative Humidity in a Closed Space 8

Multivariate Time-Series Deep Learning for Joint Prediction ...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Gunawan, Fergianto E. Budiman, Arief S. Pardamean, Bens Juana, Endang Romeli, Sugiarto Cenggoro, Tjeng W. Purwandari, Kartika Hidayat, Alam A. Redi, Anak A.N.P. Asrol, Muhammad Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta11440 Indonesia PT Impack Pratama Industri Jakarta14350 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Mathematics Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

An accurate predictive model of temperature and humidity plays a vital role in many industrial processes that utilize a closed space such as in agriculture and building management. With the exceptional performance of deep learning on time-series data, developing a predictive temperature and humidity model with deep learning is propitious. In this study, we demonstrated that deep learning models with multivariate time-series data produce remarkable performance for temperature and relative humidity prediction in a closed space. In detail, all deep learning models that we developed in this study achieve almost perfect performance with an R value over 0.99. © 2023 The Authors. Published by Elsevier B.V.

关键词： closed space deep learning humity prediction indoor temperature prediction

来源：评论

学校读者我要写书评

暂无评论

A Discontinuous Galerkin Time-Domain Scheme to Simulate Semiconductor Lasers

A Discontinuous Galerkin Time-Domain Scheme to Simulate Semi...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Ming Dong Liang Chen Ran Zhao Hakan Bagci Electrical and Computer Engineering Program Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia

A computational framework, which relies on the discontinuous Galerkin time-domain scheme, is proposed to simulate transient lasing generated by interactions of light with an active medium. The proposed scheme solves a coupled system of the Maxwell and the rate equations. The active medium inside the laser region is described quantum-mechanically by the rate equations to account for the atomic transitions of a multi-level system, while electromagnetic field interactions are described classically by the Maxwell equations. Numerical examples are provided to demonstrate the accuracy and the applicability of the proposed framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fully Geometric Panoramic Localization

Fully Geometric Panoramic Localization

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Junho Kim Jiwon Jeong Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Dept. of Electrical Engineering Stanford University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

We introduce a lightweight and accurate localization method that only utilizes the geometry of 2D-3D lines. Given a pre-captured 3D map, our approach localizes a panorama image, taking advantage of the holistic 360° view. The system mitigates potential privacy breaches or domain discrepancies by avoiding trained or hand-crafted visual descriptors. However, as lines alone can be ambiguous, we express distinctive yet compact spatial contexts from relationships between lines, namely the dominant directions of parallel lines and the intersection between non-parallel lines. The resulting representations are efficient in processing time and memory compared to conventional visual descriptor-based methods. Given the groups of dominant line directions and their intersections, we accelerate the search process to test thousands of pose candidates in less than a millisecond without sacrificing accuracy. We empirically show that the proposed 2D-3D matching can localize panoramas for challenging scenes with similar structures, dramatic domain shifts or illumination changes. Our fully geometric approach does not involve extensive parameter tuning or neural network training, making it a practical algorithm that can be readily deployed in the real world. Project page including the code is available through this link: https://***/fgpl/.

关键词： Location awareness Geometry Training Visualization Accuracy Three-dimensional displays Pipelines

来源：评论

学校读者我要写书评

暂无评论

SoC-Oriented Implementation of Machine Learning Based Breast Cancer Classification Algorithm 12

SoC-Oriented Implementation of Machine Learning Based Breast...

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Saeed, Abdelrahman Tawfik, Ayman Mostafa, Hassan Khalil, Ahmed Hussein Cairo University Electronics and Communications Engineering Department Giza12613 Egypt Ajman University Department of Electrical and Computer Engineering United Arab Emirates University of Science and Technology Nanotechnology and Nanoelectronics Program Zewail City of Science and Technology Giza Egypt

ISBN: (纸本)9798350322910

Convolutional Neural Networks (CNN) have drawn the attention of researchers in the medical imaging field. Many researchers have exploited CNN for breast cancer detection. This study provides an Internet of Things (IoT) friendly implementation of CNN for breast cancer detection. To achieve faster time to Market, Deep-learning Processing Unit (DPU) on Field programmable Gate Array (FPGA) is adopted for the CNN hardware implementation. CNN inference on the proposed system achieves a 1.6x speed-up factor and 91.5% reduction in energy consumption compared to the conventional general-purpose multi-core Central Processing Unit (CPU). © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

KenCoh: A Ranked-Based Canonical Coherence 1

arXiv

引用

arXiv 2024年

作者： Talento, Mara Sherlin D.P. Roy, Sarbojit Ombao, Hernando Statistics Program Computer Electrical and Mathematical Science & Engineering King Abdullah University of Science and Technology Saudi Arabia

In this paper, we consider the problem of characterizing a robust global dependence between two brain regions where each region may contain several voxels or channels. This work is driven by experiments to investigate the dependence between two cortical regions and to identify differences in brain networks between brain states, e.g., alert and drowsy states. The most common approach to explore dependence between two groups of variables (or signals) is via canonical correlation analysis (CCA). However, it is limited to only capturing linear associations and is sensitive to outlier observations. These limitations are crucial because brain network connectivity is likely to be more complex than linear and that brain signals may exhibit heavy-tailed properties. To overcome these limitations, we develop a robust method, Kendall canonical coherence (KenCoh), for learning monotonic connectivity structure among neuronal signals filtered at given frequency bands. Furthermore, we propose the KenCoh-based permutation test to investigate the differences in brain network connectivity between two different states. Our simulation study demonstrates that KenCoh is competitive to the traditional variance-covariance estimator and outperforms the later when the underlying distributions are heavy-tailed. We apply our method to EEG recordings from a virtual-reality driving experiment. Our proposed method led to further insights on the differences of frontal-parietal cross-dependence network when the subject is alert and when the subject is drowsy and that left-parietal channel drives this dependence at the beta-band. © 2024, CC BY.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula 39

MathSpeech: Leveraging Small LMs for Accurate Conversion in ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Hyeon, Sieun Jung, Kyudan Won, Jaehee Kim, Nam-Joon Ryu, Hyun Gon Lee, Hyuk-Jae Do, Jaeyoung Department of Electrical and Computer Engineering Seoul National University Korea Republic of Department of Mathematics Chung-Ang University Korea Republic of College of Liberal Studies Seoul National University Korea Republic of NVIDIA United States Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

ISBN: (纸本)157735897X

In various academic and professional settings, such as mathematics lectures or research presentations, it is often necessary to convey mathematical expressions orally. However, reading mathematical expressions aloud without accompanying visuals can significantly hinder comprehension, especially for those who are hearing-impaired or rely on subtitles due to language barriers. For instance, when a presenter reads Euler's Formula, current Automatic Speech Recognition (ASR) models often produce a verbose and error-prone textual description (e.g., e to the power of i x equals cosine of x plus i side of x), instead of the concise LATEX format (i.e., eix = cos(x) + isin(x)), which hampers clear understanding and communication. To address this issue, we introduce MathSpeech, a novel pipeline that integrates ASR models with small Language Models (sLMs) to correct errors in mathematical expressions and accurately convert spoken expressions into structured LATEX representations. Evaluated on a new dataset derived from lecture recordings, MathSpeech demonstrates LATEX generation capabilities comparable to leading commercial Large Language Models (LLMs), while leveraging fine-tuned small language models of only 120M parameters. Specifically, in terms of CER, BLEU, and ROUGE scores for LATEX translation, MathSpeech demonstrated significantly superior capabilities compared to GPT-4o. We observed a decrease in CER from 0.390 to 0.298, and higher ROUGE/BLEU scores compared to GPT-4o. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stunting Classification in Toddlers: Implementation and Evaluation of the Decision Tree Algorithm

Stunting Classification in Toddlers: Implementation and Eval...

引用

2024 International Conference on Information Technology and Computing, ICITCOM 2024

作者： Alita, Debby Ahmad, Imam Jafar Rumandan, Rhaishudin Erkamim, Moh Widyasmoro Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandarlampung Indonesia Institut Agama Islam Negeri Ambon Islamic Education Management Study Program Ambon Indonesia Universitas Tunas Pembangunan Smart City Information Systems Study Program Surakarta Indonesia Universitas Muhammadiyah Yogyakarta Faculty of Engineering Department of Electrical Engineering Yogyakarta Indonesia

ISBN: (纸本)9798350379839

Stunting in toddlers is a chronic nutritional issue that affects the physical and cognitive development of children, with serious long-term consequences such as reduced cognitive function and an increased risk of chronic diseases in adulthood. Therefore, early identification and prevention efforts for stunting are crucial. Classifying toddlers into categories of at-risk for stunting or not is essential to provide timely and appropriate interventions. This study employs data mining techniques using the decision tree algorithm to expedite the stunting detection process and improve the accuracy of nutritional status classification in children. The results indicate that the constructed decision tree model can classify children's nutritional status with an accuracy of 83.26%. The decision tree achieves high accuracy in classifying stunting in toddlers due to its ability to handle complex data and identify significant patterns within the data. © 2024 IEEE.

关键词： Classification Data Mining Decision Tree Stunting

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

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

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：