检索结果-内蒙古大学图书馆

Globally Conditioned Conditional FLOW (GCC-FLOW) for Sea Clutter Data Augmentation

APPLIED SCIENCES-BASEL 2024年第15期14卷 6538页

作者： Lee, Seokwon Chung, Wonzoo Korea Univ Dept Artificial Intelligence Seoul 02841 South Korea

In this paper, a novel deep learning approach based on conditional FLOW is proposed for sea clutter augmentation. Sea clutter data augmentation is important for testing detection algorithms for maritime remote sensing and surveillance due to the expensive and time-consuming nature of sea clutter data acquisition. Whereas the conventional parametric methods face challenges in finding appropriate distributions and modeling time correlations of sea clutter data, the proposed deep learning approach, GCC-FLOW, can learn the data distribution from the data without explicitly defining a mathematical model. Furthermore, unlike the existing generative deep learning approaches, the proposed GCC-FLOW is able to synthesize sea clutter data of arbitrary length with the stable autoregressive structure using conditional FLOW. In addition, the proposed algorithm generates sea clutter data not only with the same characteristics of the training data, but also with the interpolated characteristics of different training data by introducing a global condition variable corresponding to the target characteristic, such as sea state. Experimental results demonstrate the effectiveness of the proposed GCC-FLOW in generating sea clutter data of arbitrary length under different sea state conditions.

关键词： sea clutter data augmentation generative algorithm conditional flow

来源：评论

学校读者我要写书评

暂无评论

Integration of parametric design into modular coordination: A construction waste reduction workflow

引用

AUTOMATION IN CONSTRUCTION 2018年 88卷 1-12页

作者： Banihashemi, Saeed Tabadkani, Amir Hosseini, M. Reza Univ Canberra Fac Arts & Design Canberra ACT Australia Politecn Milan Dept Bldg & Architectural Engn Milan Italy Deakin Univ Sch Architecture & Built Environm Geelong Vic Australia

The construction industry is under pressure as to reduce the sizable quantities of construction waste generated during construction operations. Modular coordination (MC) and parametric design both have great potentials in reducing waste at the design stage. And anecdotal evidence suggests that great volumes of waste can be reduced through integration of parametric design into MC. The issue of proposing workflows in this context, however, is under-researched, and practical applications, if any, are at the rhetorical stage. To accomplish this, an integration attempt is made in this study to provide the details of a developed-and-experimented workflow for this purpose;a generative algorithm is developed through the Rhinoceros 3D-Grasshopper platform, subject to MC rules. Two sets of horizontal and vertical modules are obtained from a prototype model, while an evolutionary solver function is applied in reducing the generated construction waste volume. According to a pre-defined standard specification, different modular design variants that fully conform to the design constraints in modules array are developed, providing an operational workflow in construction waste reduction at the design stage. Introducing this workflow, and how the proposed workflow reduces the volume of post-optimization paneling waste by 2% at its minimum are the major findings here. The insights derived from this study, would promote the interest of both the construction practitioners and researchers;the practicality of integrating parametric design into MC is proven.

关键词： Waste reduction Design stage Parametric design Modular coordination (MC) generative algorithm BIM Workflow

来源：评论

学校读者我要写书评

暂无评论

Data-driven design of deployable structures: Literature review and multi-criteria optimization approach

引用

CURVED AND LAYERED STRUCTURES 2021年第1期8卷 241-258页

作者： Dragoljevic, Milan Viscuso, Salvatore Zanelli, Alessandra Politecn Milan Dept Architecture Built Environm & Construct Engn Via Ponzio 31 I-20133 Milan Italy

Classification and development of the deploy-able structures is an ongoing process that started at the end of 20th century and is getting more and more attention throughout 21st. With the development of the technology, constructive systems and materials, these categorizations changed - adding new typologies and excluding certain ones. This work is giving a critical review of the work done previously and on the change of the categories. The special interest is given to the pantographs (or scissor structures) and the Zeigler's dome as the form of their application. It is noticeable that after its introduction in 1977, the dome was a part of the initial classification, but with the time it lost its place. The reason for this is the introduction of more efficient scissor dome structures. However, perhaps with the use of data-driven design, this dome can be optimized and become relevant again. The second part of the paper is dedicated to the development of the structural optimization algorithm for panto-graph structures and its application on the example of Zei-gler's dome. Besides the direct analysis, the final part in-cludes the generative optimization algorithm which could help to a decision-maker in the early stages of the design to understand and select the options for the structure.

关键词： deployable structures classification pantographs Zeigler's dome scissor mechanism deployable dome structural optimization generative algorithm

来源：评论

学校读者我要写书评

暂无评论

Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation

引用

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA 2022年第40期119卷 e2209524119-e2209524119页

作者： Khare, Eesha Yu, Chi-Hua Obeso, Constancio Gonzalez Milazzo, Mario Kaplan, David L. Buehler, Markus J. MIT Lab Atomist & Mol Mech Cambridge MA 02139 USA MIT Dept Mat Sci & Engn Cambridge MA 02139 USA Natl Cheng Kung Univ Dept Engn Sci Tainan 701 Taiwan Tufts Univ Dept Biomed Engn Medford MA 02155 USA Univ Pisa Dept Civil & Ind Engn I-56122 Pisa Italy MIT Schwarzman Coll Comp Ctr Computat Sci & Engn Cambridge MA 02139 USA Ctr Mat Sci & Engn Cambridge MA 02139 USA

Collagen is the most abundant structural protein in humans, providing crucial mechan-ical properties, including high strength and toughness, in tissues. Collagen-based bio-materials are, therefore, used for tissue repair and regeneration. Utilizing collagen effectively during materials processing ex vivo and subsequent function in vivo requires stability over wide temperature ranges to avoid denaturation and loss of structure, mea-sured as melting temperature (T-m). Although significant research has been conducted on understanding how collagen primary amino acid sequences correspond to Tm values, a robust framework to facilitate the design of collagen sequences with specific Tm remains a challenge. Here, we develop a general model using a genetic algorithm within a deep learning framework to design collagen sequences with specific Tm values. We report 1,000 de novo collagen sequences, and we show that we can efficiently use this model to generate collagen sequences and verify their T-m values using both experimen-tal and computational methods. We find that the model accurately predicts T-m values within a few degrees centigrade. Further, using this model, we conduct a high -throughput study to identify the most frequently occurring collagen triplets that can be directly incorporated into collagen. We further discovered that the number of hydrogen bonds within collagen calculated with molecular dynamics (MD) is directly correlated to the experimental measurement of triple-helical quality. Ultimately, we see this work as a critical step to helping researchers develop collagen sequences with specific Tm values for intended materials manufacturing methods and biomedical applications, realizing a mechanistic materials by design paradigm.

关键词： collagen deep learning thermal stability generative algorithm mechanics

来源：评论

学校读者我要写书评

暂无评论

Quantum conditional generative adversarial network based on patch method for abnormal electrocardiogram generation

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2023年 166卷 107549-107549页

作者： Qu, Zhiguo Shi, Wenke Tiwari, Prayag Nanjing Univ Informat Sci & Technol Jiangsu Collaborat Innovat Ctr Atmospher Environm Equipment Technol Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp Sci Nanjing 210044 Peoples R China Halmstad Univ Sch Informat Technol Halmstad Sweden

To address the scarcity and class imbalance of abnormal electrocardiogram (ECG) databases, which are crucial in AI-driven diagnostic tools for potential cardiovascular disease detection, this study proposes a novel quantum conditional generative adversarial algorithm (QCGAN-ECG) for generating abnormal ECG signals. The QCGAN-ECG constructs a quantum generator based on patch method. In this method, each sub-generator generates distinct features of abnormal heartbeats in different segments. This patch-based generative algorithm conserves quantum resources and makes QCGAN-ECG practical for near-term quantum devices. Additionally, QCGAN-ECG introduces quantum registers as control conditions. It encodes information about the types and probability distributions of abnormal heartbeats into quantum registers, rendering the entire generative process controllable. Simulation experiments on Pennylane demonstrated that the QCGAN-ECG could generate completely abnormal heartbeats with an average accuracy of 88.8%. Moreover, the QCGAN-ECG can accurately fit the probability distribution of various abnormal ECG data. In the anti-noise experiments, the QCGANECG showcased outstanding robustness across various levels of quantum noise interference. These results demonstrate the effectiveness and potential applicability of the QCGAN-ECG for generating abnormal ECG signals, which will further promote the development of AI-driven cardiac disease diagnosis systems. The source code is available at ***/VanSWK/QCGAN_ECG.

关键词： Quantum generative adversarial network Abnormal electrocardiogram generative algorithm Data imbalance

来源：评论

学校读者我要写书评

暂无评论

SYNCOPATION AND GROOVE IN POLYPHONIC MUSIC: PATTERNS MATTER

引用

MUSIC PERCEPTION 2022年第5期39卷 503-531页

作者： Sioros, George Madison, Guy Cocharro, Diogo Danielsen, Anne Gouyon, Fabien Univ Oslo Oslo Norway Univ Umea Umea Sweden INESC TEC Porto Portugal

MUSIC OFTEN EVOKES A REGULAR BEAT AND A pleasurable sensation of wanting to move to that beat called groove. Recent studies show that a rhythmic pattern's ability to evoke groove increases at moderate levels of syncopation, essentially, when some notes occur earlier than expected. We present two studies that investigate that effect of syncopation in more realistic polyphonic music examples. First, listeners rated their urge to move to music excerpts transcribed from funk and rock songs, and to algorithmically transformed versions of these excerpts: 1) with the original syncopation removed, and 2) with various levels of pseudorandom syncopation introduced. While the original excerpts were rated higher than the de-syncopated, the algorithmic syncopation was not as successful in evoking groove. Consequently, a moderate level of syncopation increases groove, but only for certain syncopation patterns. The second study provides detailed comparisons of the original and transformed rhythmic structures that revealed key differences between them in: 1) the distribution of syncopation across instruments and metrical positions, 2) the counter-meter figures formed by the syncopating notes, and 3) the number of pickup notes. On this basis, we form four concrete hypotheses about the function of syncopation in groove, to be tested in future experiments.

关键词： groove syncopation predictive coding meter generative algorithm

来源：评论

学校读者我要写书评

暂无评论

Design of Video Background Music Generation algorithm Based on Music Feature Matching algorithm

Design of Video Background Music Generation Algorithm Based ...

引用

2023 Asia-Europe Conference on Electronics, Data Processing and Informatics, ACEDPI 2023

作者： Shen, Wei Wuhan International Trade University Hubei Wuhan430205 China

ISBN: (纸本)9798350301151

Background music is a kind of music, which is used in many occasions, such as movies, short videos, etc. How to choose the most suitable background music to match with the corresponding scenes has important practical application value. With the popularity of short video platform, more and more Internet users choose to share their life bits and pieces through short video. As an indispensable part of short video, the background music of video plays a very important role in setting off the video atmosphere and expressing users' emotions. However, as far as the current research on automatic music generation is concerned, at present, the background music styles of most short video platforms are similar and lack of new ideas, and they all focus on simply generating music, and learning one or more styles of music to output music with similar styles. The background music used as the background of video, that is, music, has little correlation with other multimedia content. The design of video background music generation algorithm based on music feature matching algorithm can automatically generate background music for video with high efficiency and high quality. © 2023 IEEE.

关键词： background music Feature matching generative algorithm

来源：评论

学校读者我要写书评

暂无评论

Generating Constructal Networks for Area-to-Point Conduction Problems Via Moving Morphable Components Approach

引用

JOURNAL OF MECHANICAL DESIGN 2019年第5期141卷 051401-051401页

作者： Li, Baotong Xuan, Chengbin Liu, Guoguang Hong, Jun Xi An Jiao Tong Univ Sch Mech Engn Educ Minist Modern Design & Rotor Bearing Syst Key Lab Xian 710049 Shaanxi Peoples R China

In this article, we focus on a generative design algorithm for area-to-point (AP) conduction problems in a Lagrangian framework. A physically meaningful continuous area to point path solution is generated through an adaptive growth procedure, which starts from the source point and extends spreading the whole conduction domain. This is achieved by using a set of special moving morphable components (MMCs) whose contour and skeleton are described explicitly by parameterized level-set surfaces. Unlike in the conventional methods where topology optimization was carried out in an Eulerian framework, the proposed optimizer is Lagrangian in nature, which is consistent with classical shape optimization approaches, giving great potential to reduce the total number of design variables significantly and also yielding more flexible modeling capability to control the structural feature sizes. By doing this, the growth elements are separated from the underlying finite element method (FEM) grids so that they can grow toward an arbitrary direction to form an optimized area-to-point path solution. The method is tested on an electromagnetic bandgap (EBG) power plane design example;both simulation and experiment verified the effectiveness of the proposed method.

关键词： generative algorithm topology optimization area-to-point problem moving morphable component (MMC) EBG power plane design

来源：评论

学校读者我要写书评

暂无评论

Data Mining Approach for Evil Twin Attack Identification in Wi-Fi Networks

引用

DATA 2024年第10期9卷 119页

作者： Banakh, Roman Nyemkova, Elena Justice, Connie Piskozub, Andrian Lakh, Yuriy Lviv Polytech Natl Univ Dept Informat Technol Secur UA-79013 Lvov Ukraine Purdue Univ Indianapolis Purdue Sch Engn & Technol Indiana Univ Indianapolis IN 46202 USA

Recent cyber security solutions for wireless networks during internet open access have become critically important for personal data security. The newest WPA3 network security protocol has been used to maximize this protection;however, attackers can use an Evil Twin attack to replace a legitimate access point. The article is devoted to solving the problem of intrusion detection at the OSI model's physical layers. To solve this, a hardware-software complex has been developed to collect information about the signal strength from Wi-Fi access points using wireless sensor networks. The collected data were supplemented with a generative algorithm considering all possible combinations of signal strength. The k-nearest neighbor model was trained on the obtained data to distinguish the signal strength of legitimate from illegitimate access points. To verify the authenticity of the data, an Evil Twin attack was physically simulated, and a machine learning model analyzed the data from the sensors. As a result, the Evil Twin attack was successfully identified based on the signal strength in the radio spectrum. The proposed model can be used in open access points as well as in large corporate and home Wi-Fi networks to detect intrusions aimed at substituting devices in the radio spectrum where IEEE 802.11 networking equipment operates.

关键词： data machine learning model KNN generative algorithm intrusion detection IEEE 802.11 Evil Twin attack

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：