检索结果-内蒙古大学图书馆

Conference on Technologies for Sustainability (Sustech)

作者： Alan Yuan Guang Wei Too Yihan Xu Ziqian Dong Huanying Gu Roberto Rojas-Cessa Dept. of Computer Science New York Institute of Technology New York City NY USA Dept. of Electrical and Computer Engineering New York Institute of Technology New York City NY USA Dept. Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

ISBN: (数字)9798331504311

ISBN: (纸本)9798331504328

In this paper, we present a web-based tool that maps and visualizes datasets from New York City (NYC) Open Data, specifically on building energy efficiency and fallen trees reported to NYC311, as heatmap or pin map to show building energy efficiency and weather event impact at a neighborhood level over time. To evaluate its effectiveness in addressing climate-related urban challenges, we applied the tool to two case studies from NYC Open Data: the ENERGY STAR Score and Fallen Trees datasets. We demonstrate the heat map function for the ENERGY STAR Score dataset and the use of a combination of heat and pin map functions of the Fallen Trees dataset to highlight spatial and temporal patterns. The interactive visualization tool effectively provides data distribution and trend analysis based on postal codes while also allowing for precise, location-specific insights using longitude and latitude. Beyond its applications in data visualization, the tool can facilitate decision-making in the design of future urban environments.

关键词： Heating systems Visualization Urban areas Buildings Stars Energy efficiency Pins Heat maps Sustainable development Open data

来源：评论

学校读者我要写书评

暂无评论

ATL Model Checking for Analysis of Ethereum Smart Contracts

引用

Transactions of the Korean Institute of electrical Engineers 2021年第12期70卷 2006-2014页

作者： Nam, Wonhong Kil, Hyunyoung Dept. of Software Korea Aerospace University Korea Republic of Dept. of Computer Science and Engineering Konkuk University Korea Republic of

A blockchain is a growing list of cryptographically secured blocks to maintain shared data on decentralized systems, in order to archive transactions between untrusted participants. Smart contracts are computer programs that automatically execute legal events according to the terms of contracts. Although the Ethereum blockchain has been successfully applied to a number of interesting applications, there have been several events that subtle flaws in smart contracts induce a huge amount of financial loss such as the DAO attack. Accordingly, to analyze smart contracts, we propose a novel formal verification technique to employ ATL (Alternating-time Temporal Logic) model checking. Our methodology represents the interaction between users and smart contracts with a two-player game and verify game properties by using MCMAS that is an efficient ATL model checker. © The Korean Institute of electrical Engineers

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Trust management based multidimensional secure cluster with RSA cryptography algorithm in WSN for secure data transmission

引用

Measurement: Sensors 2023年 29卷

作者： Anitha, S. Saravanan, S. Chandrasekar, A. Dept. of Computer Science and Engineering Annamalai University Annamalainagar 608002 India Dept. of Computer Science and Engineering St.Joseph's College of Engineering Chennai India

WSNs are now widely used for information gathering and transmission using WSN. Due to its low cost and simple communication, this type of network is widely used in many applications. Although hierarchical routing protocols may handle a variety of applications, choosing a Cluster Head (CH) and balancing network overload are difficult problems. This recommended strategy provides LEACH Protocol based on Novel Trust Management with Cryptographic RSA algorithm (NTM-LEACH-RSA) to extend the lifetime of network and to consume less energy. Here the proposed methodology includes two aspects for improving Security in WSN. Using the suggested NTM-LEACH technique, cluster formation and cluster head election are carried out in the first phase. Here, the threshold function value, the distance and density between nearby nodes, and the trust value are used to elect the cluster head. Based on the energy domain and the distance domain, the threshold function value is estimated in this case. The RSA cryptography technique is employed in the second phase to protect data transmission and guarantee data integrity. By using simulation tools, the proposed NTM-LEACH-RSA methodology's performance analysis is estimated. In comparison to other algorithms currently in use, it also offers higher performance results. © 2023

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

ENSEMBLE DISTILLATION FOR UNSUPERVISED CONSTITUENCY PARSING 12

ENSEMBLE DISTILLATION FOR UNSUPERVISED CONSTITUENCY PARSING

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Shayegh, Behzad Cao, Yanshuai Zhu, Xiaodan Cheung, Jackie C.K. Mou, Lili University of Alberta Canada Borealis AI Canada Dept. Electrical and Computer Engineering Queen's University Canada Ingenuity Labs Research Institute Queen's University Canada McGill University Canada Canada CIFAR AI Canada

We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data. We observe that existing unsupervised parsers capture different aspects of parsing structures, which can be leveraged to enhance unsupervised parsing performance. To this end, we propose a notion of "tree averaging," based on which we further propose a novel ensemble method for unsupervised parsing. To improve inference efficiency, we further distill the ensemble knowledge into a student model;such an ensemble-then-distill process is an effective approach to mitigate the over-smoothing problem existing in common multi-teacher distilling methods. Experiments show that our method surpasses all previous approaches, consistently demonstrating its effectiveness and robustness across various runs, with different ensemble components, and under domain-shift conditions. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Fabrication of Vitreous Carbon Mold for Glass Moled Microarray 13

Fabrication of Vitreous Carbon Mold for Glass Moled Microarr...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Asgar, Md. Ali Kim, Yong Kyu Jin, Chengjun Kim, Jun Byeon, Seongyoung Ali, Muzahir Hussain, Tasadduq Kim, Seok-Min Jatiya Kabi Kazi Nazrul Islam University Dept. Electrical and Electronic Engineering Mymensingh Bangladesh Chung-Ang University Dept. Computer Science and Engineering Seoul Korea Republic of Chung-Ang University Dept. Mechanical Engineering Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Glass micro-lens array (MLA) are attractive optical elements for light manipulation. Glass molding has been utilized for fabricating the MLA pattern for mass-scale production with high accuracy. Herein, a method to fabricate vitreous carbon (VC) mold with MLA pattern has been demonstrated for glass molding. The VC mold with MLA pattern was obtained by carbonization of furan precursor which was replicated from a PDMS mold. The intermediate PDMS mold was casted from a metal master mold using soft lithography method. © 2022 IEEE.

关键词： Carbonization

来源：评论

学校读者我要写书评

暂无评论

Learning Bayes-Optimal Channel Estimation for Holographic MIMO in Unknown EM Environments

Learning Bayes-Optimal Channel Estimation for Holographic MI...

引用

IEEE International Conference on Communications (ICC)

作者： Wentao Yu Hengtao He Xianghao Yu Shenghui Song Jun Zhang Ross D. Murch Khaled B. Letaief Dept. of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Dept. of Electrical Engineering City University of Hong Kong Hong Kong

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Holographic MIMO (HMIMO) has recently been recognized as a promising enabler for future 6G systems through the use of an ultra-massive number of antennas in a compact space to exploit the propagation characteristics of the electromagnetic (EM) channel. Nevertheless, the promised gain of HMIMO could not be fully unleashed without an efficient means to estimate the high-dimensional channel. Bayes-optimal estimators typically necessitate either a large volume of supervised training samples or a priori knowledge of the true channel distribution, which could hardly be available in practice due to the enormous system scale and the complicated EM environments. It is thus important to design a Bayes-optimal estimator for the HMIMO channels in arbitrary and unknown EM environments, free of any supervision or priors. This work proposes a self-supervised minimum mean-square-error (MMSE) channel estimation algorithm based on powerful machine learning tools, i.e., score matching and principal component analysis. The training stage requires only the pilot signals, without knowing the spatial correlation, the ground-truth channels, or the received signal-to-noise-ratio. Simulation results will show that, even being totally self-supervised, the proposed algorithm can still approach the performance of the oracle MMSE method with an extremely low complexity, making it a competitive candidate in practice.

关键词： Training 6G mobile communication Machine learning algorithms Simulation Channel estimation Estimation Machine learning

来源：评论

学校读者我要写书评

暂无评论

Face Mask Detection Using MobileNetV2 and VGG16 11th

Face Mask Detection Using MobileNetV2 and VGG16

引用

11th International Conference on Recent Trends in Computing, ICRTC 2022

作者： Kumar, Ujjwal Arora, Deepak Sharma, Puneet Department of Computer Science and Engineering Amity University Lucknow Campus Uttar Pradesh Lucknow India Dept. of CSE Amity University Uttar Pradesh Noida India

ISBN: (纸本)9789811988240

As the COVID-19 situation is not over yet, a new strain of corona virus is again affecting population. Strain like Omicron and Deltacron still poses thread to the society. It is very necessary to keep our self-safe. To prevent spread of COVID few precautions are suggested by governments in the world like maintaining distance of 1 m, use of hand sanitizer, and always wear a mask. The new variant of COVID is now reported by the WHO on November 28, 2021;it was first designated as B.1.1.529 and then named as omicron and later a hybrid variant of delta and omicron was also reported. As these are affecting large population and seeing continuous straggle, it can conclude that corona virus can affect people for few more years considering the current scenario. Keeping that in mind people made face detection software which can be used to tell that a person wearing a mask not. This project is based on same object by using two different technologies MobileNetV2 and VGG16 so that a detail comparing can be done. By comparing both of them it can be known that which perform better and people can choose according to their necessity. This research paper is based on machine learning algorithm and deep learning using different Python libraries like OpenCV, TensorFlow with Keras, MobileNetV2, and VGG16. In this project, the main aim this to detect and then identify that person is wearing a mask or not then comparing both technologies and analyzes the result. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

A Fusion-Based Approach to Multiclass Retinal Disease Classification: Transfer Learning Strategy with CBAM Integration

A Fusion-Based Approach to Multiclass Retinal Disease Classi...

引用

Power, electrical, and Electronics and Industrial Applications (PEEIACON), IEEE International Conference on

作者： Bijoy Deb Nath Shyla Afroge Dept. of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (数字)9798331517984

ISBN: (纸本)9798331517991

Eye diseases pose significant global public health challenges, often resulting to irreversible blindness if untreated. Early, precise diagnosis of these disorders is critical. In this paper, we address this crucial issue using transfer learning methods for the categorization of multiple eye disorders. The proposed architecture features a fusion-based technique that combines EfficientNetB0 and MobileNetV3Large convolutional neural networks (CNNs) for feature extraction and incorporates Convolutional Block Attention Module (CBAM), which dynamically focuses on significant regions of the images, enhancing the model's discriminative capability. Our proposed model achieves outstanding performance on two separate datasets: 97.85% accuracy on the Eye Disease Classification (EDC) dataset and 91.96% on the Ocular Disease Intelligent Recognition (ODIR) dataset, surpassing existing state-of-the-art approaches in ocular disease classification. By developing the proposed model, we intend to contribute to the creation of more effective diagnostic tools and eventually enhance patient outcomes in ophthalmology.

关键词： Accuracy Transfer learning Refining Retina Feature extraction Eye diseases Ophthalmology Reliability Public healthcare Image classification

来源：评论

学校读者我要写书评

暂无评论

Person Re-Identification using Deep Learning 4

Person Re-Identification using Deep Learning

引用

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

作者： Saini, Taruna Gandhi, Ridhima Roy, Sanu Diwakar, Manoj Singh, Prabhishek Mishra, Amit Kumar Graphic Era Deemed to Be University Department of Cse Dehradun India Bennett University School of Computer Science Engineering and Technology Greater Noida India Graphic Era Hill University Dept. of Cse Dehradun India

ISBN: (纸本)9798350364729

Re-identification of person (re-ID) is a computer vision task, which is trying to find out the same individual's pictures through a single camera scenario. For addressing Re-ID, we have proposed a deep learning architecture i.e. ResNet, and open Visual Inference and Neural Optimization (Open VINO) toolkit from intel. In this paper, we have utilized the probable feature of learning in the ResNet model that is instructed on enormous datasets and fine-turned on strenuous market-1501 re-ID standard dataset. This process implicates data preprocessing, model selection, training, and optimization steps that are important for acceptable results. We have used data augmentation and triplet loss function to construct implanting more selective as a final step in this pipeline and our developed ResNet model is supported by OpenVINO for hardware-specific optimizations and model conversion. Our Solution on ResNet delivers real-time processing speeds using GPU. This approach shows that is possible and easy to deploy precise person Re-Id for surveillance, forensic identification, and security monitoring. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Impact Analysis of Contributing Factors of NYC Flash Floods with Interpre table Machine Learning

Impact Analysis of Contributing Factors of NYC Flash Floods ...

引用

Conference on Technologies for Sustainability (Sustech)

作者： Yihan Xu Alan Yuan Guang Wei Too Yordan Nikolov Ziqian Dong Roberto Rojas-Cessa Dept. of Electrical and Computer Engineering New York Institute of Technology New York City NY USA Dept. of Computer Science New York Institute of Technology New York City NY USA Dept. of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

ISBN: (数字)9798331504311

ISBN: (纸本)9798331504328

In this paper, we analyze multi-modal data including environmental, geographic, infrastructure, demographic, and socioeconomic data from New York City (NYC), to examine their impact on flood risk. We applied XGBoost machine learning model combined with SHapley Additive exPlanations (SHAP) function to analyze and interpret the contributions of these factors to flood risks. We tested the model with a window of 1 to 7 days to determine optimum time scales to capture the essential information in the time series and factors’ dependencies over various time periods. Our findings reveal that although environmental and geographic factors have a strong correlation with flood risk, socioeconomic factors, such as median age, median house value, population density, and race also play an important role in such risks. Low-income household areas have higher flood risks, which happen to also be minority communities, making them more vulnerable to flooding than higher-income communities. Furthermore, population density and level of education may also have impact on flood risks. These insights can be used to facilitate planning and preparing future flood prevention and mitigation strategies.

关键词： Analytical models Temperature dependence Prevention and mitigation Education Urban areas Time series analysis Machine learning Floods Socioeconomics Population density

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：