检索结果-内蒙古大学图书馆

12th International Conference on Bridge Maintenance, Safety and Management, IABMAS 2024

作者： Wang, X. Bocchini, P. Venkitasubramaniam, P. Xie, S. Civil and Environmental Engineering Department Lehigh University BethlehemPA United States Electrical and Computer Engineering Department Lehigh University BethlehemPA United States Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China

ISBN: (纸本)9781032770406

Quality resilience assessment for transportation systems relies on realistic representations of the network and traffic demand, and credible network traffic modeling. This paper presents a framework that incorporates time-dependent functionality analysis of disrupted networks and dynamic traffic simulations. Focusing on bridge disruptions, two distinct types of events are considered, earthquake and civil protest. The mesoscopic traffic flow model and the dynamic traffic assignment approach (as opposed to the static assignment approach) are utilized to realistically represent traffic dynamics. The presented results show that the dynamic traffic simulations provide traffic measures at a fine-grained spatiotemporal level which are valuable for post-event performance assessment. Traffic congestion effects are identified in earthquake-disrupted networks. Despite the limited disruption scope, protests on bridges can have significant impact on local travel cost. These findings promote using dynamic traffic modeling for transportation network analysis, highlighting the usefulness of more reliable and granular metrics for decision-making. © 2024 The Author(s).

关键词： Earthquakes

来源：评论

学校读者我要写书评

暂无评论

LEARNING CONTINUOUS NORMALIZING FLOWS FOR FASTER CONVERGENCE TO TARGET DISTRIBUTION VIA ASCENT REGULARIZATIONS 11

LEARNING CONTINUOUS NORMALIZING FLOWS FOR FASTER CONVERGENCE...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Chen, Shuangshuang Ding, Sihao Karayiannidis, Yiannis Björkman, Mårten School of Electrical Engineering and Computer Science Royal Institute of Technology Sweden AI Lab Volvo Car Corporation Sweden Department of Automatic Control Lund University Sweden

Normalizing flows (NFs) have been shown to be advantageous in modeling complex distributions and improving sampling efficiency for unbiased *** this work, we propose a new class of continuous NFs, ascent continuous normalizing flows (ACNFs), that makes a base distribution converge faster to a target *** solving such a flow is non-trivial and barely possible, we propose a practical implementation to learn flexibly parametric ACNFs via ascent regularization and apply it in two learning cases: maximum likelihood learning for density estimation and minimizing reverse KL divergence for unbiased sampling and variational *** learned ACNFs demonstrate faster convergence towards the target distributions, therefore, achieving better density estimations, unbiased sampling and variational approximation at lower computational ***, the flows show to stabilize themselves to mitigate performance deterioration and are less sensitive to the choice of training flow length T. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

ResViT: A Hybrid Vision Transformer Model for Onychomycosis Detection

ResViT: A Hybrid Vision Transformer Model for Onychomycosis ...

引用

International Conference on electrical, computer and Communication engineering (ECCE)

作者： Musad Hasan Propa Punam Tahmina Islam Department of Electrical and Electronic Engineering Bangladesh University of Engineering and Technology Bangladesh Department of Computer Science and Engineering University of Information Technology and Sciences Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Onychomycosis is a very common fungal nail disease. It has no life risk but can be sickening. If it is not diagnosed at an early stage, it can be severe. AI can play a vital role in detecting Onychomycosis precisely and faster. We used a hybrid network, ResViT, consisting of a pre-trained ResNet-50 model for feature extraction and a Vision Transformer (ViT) for classification in our paper to detect Onychomycosis. As we got a small dataset consisting of 1355 diseased data, we could not use conventional ViT. We got 99.77 percent accuracy using our hybrid ResViT model, which was identical to the pre-trained ResNet-50 model. But for conventional ViT, our accuracy decreased to 96.99 percent while time per epoch increased. Overall, our proposed hybrid ResViT performed better than any state-of-the art techniques.

关键词： Measurement computer vision Accuracy Codes Computational modeling Nails Transformers Feature extraction Skin Diseases

来源：评论

学校读者我要写书评

暂无评论

Efficient Planning in Large-scale Systems Using Hierarchical Finite State Machines

arXiv

引用

arXiv 2025年

作者： Stefansson, Elis Johansson, Karl H. School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm11428 Sweden

We consider optimal planning in a large-scale system formalised as a hierarchical finite state machine (HFSM). A planning algorithm is proposed computing an optimal plan between any two states in the HFSM, consisting of two steps: A pre-processing step that computes optimal exit costs of the machines in the HFSM, with time complexity scaling with the number of machines;and a query step that efficiently computes an optimal plan by removing irrelevant subtrees of the HFSM using the optimal exit costs. The algorithm is reconfigurable in the sense that changes in the HFSM are handled with ease, where the preprocessing step recomputes only the optimal exit costs affected by the change. The algorithm can also exploit compact representations that groups together identical machines in the HFSM, where the algorithm only needs to compute the optimal exit costs for one of the identical machines within each group, thereby avoid unnecessary recomputations. We validate the algorithm on large systems with millions of states and a robotic application. It is shown that our approach outperforms Dijkstra’s algorithm, Bidirectional Dijkstra and Contraction Hierarchies. Copyright © 2025, The Authors. All rights reserved.

关键词： Large scale systems

来源：评论

学校读者我要写书评

暂无评论

Predictive Modelling of Economic Indicators using Machine learning and Data Analytics 4

Predictive Modelling of Economic Indicators using Machine le...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Singh, Akshita Singh, Ramendra Chauhan, Davendra Kumar Shrivastava, Ashok Kumar Alabdeli, Haider Amity International School Noida India Ghaziabad India Engineering Raj Kumar Goel Institute of Technology Department of Electrical & Electronics Ghaziabad India Engineering Amity University Department of Computer Science Gwalior India The Islamic University Najaf Iraq

ISBN: (纸本)9798350364729

This study defines the use of machine learning models to predict car production volume for better planning and correspond them with market desirability. This work assesses three different models: Artificial Neural Network (ANN), Support Vector Machine (SVM) and Long Short-Term Memory (LSTM), using an extensive dataset composed of 10,332 historical production volume records over the past ten years accompanied by raw material prices, energy costs along with labor cost attributes as well as experiments will market demand, seasonal trends economic indicators. The dataset was preprocessed with some techniques like handling of missing data, normalization and also encoding for categorical variables to make it strong. The models were trained and tested using a 70-30 training - test split, evaluated on different performance metrics such as accuracy, precision and other criteria. The bestcase accuracy of 97.75 % was achieved by the ANN, hence showing its capability to capture complex non-linear relationships within data. The SVM reached 93.40% accuracy, much stronger with high precision and recall tradeoff post update to the split point. The LSTM model providing an accuracy rate of 91.22%, considering it was best suited for handling sequential data. The above results have shown the ANN model better accuracy in predictions and because of this, we can use an ANN for future demand prediction efficiently. This has valuable implications for car manufacturing and is a good direction to elaborate on predictive models in the future. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Network Anomaly Detection with Stacked Sparse Shrink Autoencoders and Improved XGBoost

Network Anomaly Detection with Stacked Sparse Shrink Autoenc...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Bi, Jing Guan, Ziyue Yuan, Haitao Zhang, Jia Beijing University of Technology Faculty of Information Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Southern Methodist University Dept. of Computer Science Lyle School of Engineering DallasTX United States

ISBN: (纸本)9798350337020

Efficient and accurate identification of network anomalies is of great significance to the construction of network security systems in the information age. It is highly challenging to accurately detect abnormal behaviors in the increasing network data. Currently, classification methods based on feature extraction of autoencoders have been proven to be suitable for network anomaly detection. However, traditional detection models with autoencoders have poor detection accuracy in the face of massive network features. In addition, the hyperparameter optimization of their models cannot be effectively solved. For network anomaly detection, this work proposes a new network anomaly detection method named SAXP, which integrates Stacked sparse shrink Autoencoders and a XGBoost model based on genetic simulated annealing Particle swarm optimization (GSPSO). Specifically, features extracted by stacked sparse shrink autoencoders are introduced into the XG Boost model for classification, and GSPSO is used to optimize the hyperparameters of XGBoost. Experimental results based on two real-life data sets demonstrate that the proposed SAXP achieves higher recognition accuracy than several state-of-the-art algorithms. © 2023 IEEE.

关键词： autoencoders feature extraction Network anomaly detection particle swarm optimization XGBoost

来源：评论

学校读者我要写书评

暂无评论

A Novel Radial-Flux IPM Eddy-Current Coupler for Wind Generator Applications

arXiv

引用

arXiv 2024年

作者： Mohammadi, Sajjad Davarpanah, Gholamreza Kirtley, James L. Electrical Engineering and Computer Science MIT Cambridge United States Department of Electrical Engineering Amirkabir University of Technology Tehran Iran

A novel radial-flux eddy-current coupler with interior permanent magnets (IPM) is proposed, providing higher demagnetization tolerance, making it well-suited for applications with limited accessibility, such as offshore wind generation. Finite element analysis is employed in the design and derivation of coupler quantities. Finally, the coupler is prototyped to experimentally validate the design and the simulation results. Copyright © 2024, The Authors. All rights reserved.

关键词： Demagnetization

来源：评论

学校读者我要写书评

暂无评论

Programmable Plasmonic-Nanopixels for High- Density Chromatic Information Encryption

Programmable Plasmonic-Nanopixels for High- Density Chromati...

引用

IEEE/LEOS International Conference on Optical MEMS

作者： Ji-Eun Yeo Joo Hwan Ko Young Min Song School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology (GIST) Gwangju Republic of Korea

ISBN: (数字)9798350384925

ISBN: (纸本)9798350384932

Efficiently modulating light-matter interactions in visible wavelength range holds significant importance for various applications such as optical encryption, switching mechanisms, and structural color displays. In this study, we introduce a novel approach for achieving electrochromic nanopixels by combining polyaniline (PANI) with metal-coated Si nanowires (Si NWs). Our optical modulation technique enables operation within an expanded color spectrum at a remarkably low voltage level below 1V, thereby ensuring energy-efficient performance. The intrinsic optical properties transition of PANI from reduced (dielectric) to oxidized (lossy) form, resulting in significant changes in its complex refractive index. Oxidation of PANI induces the effective cancellation of surface plasmon polaritons (SPPs) while simultaneously leading to strong broadband absorption due to an increased extinction coefficient. The fabrication process is versatile and can be tailored to meet various optical information encryption needs, scalable up to 8-inch wafers. A unique chromatic modulation capability enables the data encryption while leveraging the angle dependency of the waveguide to amplify the information capacity to 10 bits per unit cell. To further enhance the data storage capacity, our proposed system can incorporate multiple resonant structures based on diverse nanowire domains with varying dimensions to enhance chromatic changes.

关键词： Image color analysis Optical device fabrication Optical variables control Optical coupling Encryption Nanowires Optical modulation

来源：评论

学校读者我要写书评

暂无评论

ArcText: A Unified Text Approach to Describing Convolutional Neural Network Architectures

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第4期3卷 526-540页

作者： Sun, Yanan Yen, Gary G. Xue, Bing Zhang, Mengjie Lv, Jiancheng Sichuan University College of Computer Science Chengdu610065 China Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China Oklahoma State University School of Electrical and Computer Engineering StillwaterOK74078 United States Victoria University of Wellington School of Engineering and Computer Science Wellington6140 New Zealand

The superiority of convolutional neural networks (CNNs) largely relies on their architectures that are usually manually crafted with extensive human expertise. Unfortunately, such kind of domain knowledge is not necessarily owned by every interested user. Data mining on existing CNNs can discover useful patterns and fundamental comments from their architectures, providing researchers with strong prior knowledge to design effective CNN architectures when they have no expertise in CNNs. There are various state-of-the-art data mining algorithms at hand, while there is only rare work on mining CNN architectures. One of the main reasons is the gap between CNN architectures and data mining algorithms. Specifically, the current CNN architecture descriptions cannot be exactly vectorized to feed to a data mining algorithm. In this article, we propose a unified approach, named ArcText, to describing CNN architectures based on text. Particularly, four different units and an ordering method have been elaborately designed in ArcText, to uniquely describe the same CNN architecture with sufficient information. Also, the resulted description can be exactly converted back to the corresponding CNN architecture. ArcText bridges the gap between CNN architectures and data mining researchers, and has the potential to be utilized to wider scenarios. © 2020 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Hashtag Activism on Social Media Twitter

Sentiment Analysis of Hashtag Activism on Social Media Twitt...

引用

2023 International Conference on computer science, Information technology and engineering, ICCoSITE 2023

作者： Sidharta, Sidharta Heryadi, Yaya Lukas, Lukas Suparta, Wayan Arifin, Yulyani Bina Nusantara University BINUS Graduated Program Computer Science Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9798350320954

Currently, the performance of the police in Indonesia is often in the spotlight of the public with cases that occur, both on a national and regional scale, including personal experiences who also feel disappointed with the performance of the police. The cases, such as the rape of three children by a biological father in East Luwu, and the barrage of other cases that have occurred, in their handling have left the public disappointed, giving rise to the hashtag percumlaporpolisi on social media, especially on twitter. This hashtag became trending and was widely responded to by the public. Using free hashtag keywords, tweet data is collected using Twitter's API for sentiment analysis. The datasets obtained from the crawling results is the latest data with a total of 100 datasets. This study applies the naïve bayes algorithm using textblob which aims to determine the value of polarity and subjectivity. From the results of the analysis carried out, the words that appear most often are useless police, police chief, and policeman. While the results of the sentiment analysis that has been carried out are 40 percent positive sentiment, 40 percent are neutral sentiment and 10 percent are negative sentiment from the hashtags used. From these results, according to the keywords used, the percentage of negative sentiment should be greater than positive and neutral sentiment. It is necessary to conduct a more in-depth study related to the model used in the next research. © 2023 IEEE.

关键词： Sentiment analysis

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：