检索结果-内蒙古大学图书馆

Smart Computing and Application (ICSCA), International Conference on

作者： PSVS Sridhar Premkumar Chithaluru Sunil Kumar Omar Cheikhrouhou Habib Hamam Computer Science and Engineering Koneru Lakshmaiah Education Foundation (KLEF) Vaddeswaram Andhra Pradesh India Department of Computer Science and Engineering Chaitanya Bharathi Institute of Technology (A) Hyderabad India School of Computer Science University of Petroleum and Energy Studies Dehradun India CES Laboratory National School of Engineers of Sfax University of Sfax Sfax Tunisia Faculty of Engineering University de Moncton Moncton NB Canada 5Higher Institute of Computer Science of Mahdia University of Monastir Mahdia Tunisia International Institute of Technology and Management Commune d'Akanda Libreville Gabon Department of Electrical and Electronic Engineering Science School of Electrical Engineering University of Johannesburg Johannesburg South Africa Spectrum of Knowledge Production and Skills Development Sfax Tunisia

Gender identification software is becoming increasingly popular in the age of machine-to-machine interactions, as the need for person-aligned, effective, and ethical systems become more apparent. In this age of machine-to-machine interactions, automated gender identification software is becoming more popular. The bulk of the systems for gender identification that were examined used either textual or audiovisual data as input to determine their gender. Many different approaches to automatically detect gender based on traits gathered from people's bodies and/or behaviors have been suggested, and there are simply too many to include here. The accuracy of automated gender identification, on the other hand, has always been a topic of worry or a source of criticism. Initial face identification is accomplished by the use of the Haar Cascade face detection method, which is based on the Viola-J ones face recognition algorithm. Facial characteristics such as the eyes, mouth, and nose are then identified. Second, using the Viola-Jones face detection algorithm, the faces and facial characteristics such as the eyes, mouth, and nose are recognized, and the results are shown. In order to increase the accuracy of gender identification, adaptive filters are employed to reduce the amount of noise present before the detection process is carried out. The facial qualities that have been gathered are utilized as input or test data for the neural network, which is subsequently trained on these characteristics. It is intended that the neural network acquires the features of the genders and then functions as a classifier when it comes to detecting them. Instead of saying it another way, a neural network known as Keras is used for feature extraction and gender identification, which is free and open-source software.

关键词： Ethics Face recognition Neural networks Nose Mouth Feature extraction Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Humidity Effects on the Growth of ZnO Nanorods using Hydrothermal Method 12

Humidity Effects on the Growth of ZnO Nanorods using Hydroth...

引用

12th International Symposium on Modern Optics and Its Applications, ISMOA 2019

作者： Jali, Mohd Hafiz Rahim, Hazli Rafis Abdul Yusof, Haziezol Helmi Mohd Johari, Md Ashadi Md Thokchom, Siddharth Harun, Sulaiman Wadi Department of Electrical Engineering Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia Faculty of Electrical Engineering Universiti Teknikal Malaysia Melaka Melaka76100 Malaysia Faculty of Electronic and Computer Engineering Universiti Teknikal Malaysia Melaka Melaka76100 Malaysia Faculty of Electrical and Electronic Engineering Technology Universiti Teknikal Malaysia Melaka Melaka76100 Malaysia School of Technology Assam Don Bosco University Guwahati Assam781017 India

The effects of ZnO nanorod samples with different growth times samples to the morphological structures and output light intensity are reported. The proposed structure comprises of silica microfiber integrated with Zinc Oxide (ZnO) nanorods coated glass surface. The silica microfiber is tapered into constant waist diameter of 10 μm using flame brushing technique. While the glass surface is coated with ZnO nanorods using hydrothermal method for 6 hours, 9 hours, 12 hours, 15 hours and 18 hours growth times. The samples are exposed to the different humidity levels ranging from 35%RH to 85%RH to observe the effect of the morphological structures such as length, diameter and density and the output light intensity. The resulted measurements provide the correlation between the growth time during the synthesis process to the ZnO nanorods physical structure as well as the output light intensity in different humidity levels. It utilizes the unique features of the scattering and surface absorption of the microfiber and ZnO nanomaterials coated glass surface to alter the output light intensity. The reported results may contribute to the optimal ZnO nanorods growth time for humidity sensing applications. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Silica

来源：评论

学校读者我要写书评

暂无评论

A comparative literature review on extensive research on dynamic time warping and its variants for crop forecasting and vegetation using environmental parameters

TechRxiv

引用

TechRxiv 2023年

作者： Bediako-Kyeremeh, Bright Wornyo, Dickson Keddy Dashantha, Maheesha Pokuaa, Henrietta Adjei Badu, Benjamin Agyemang Agyemang, Sylvester Osibo, Benjamin Kwapong Ambitosoa, Lorenzo Mamelona Ye, Wenzheng Li, Jia Appau, Oppong Kofi Nanjing University of Information Science and Technology School of Electronic and Information Engineering Nanjing210044 China Nanjing University of Information Science and Technology School of Computer and Software Nanjing210044 China Sunyani Technical University Department of Computer Science Faculty of Applied Science Box 206 Sunyani Ghana University of Professional Studies Accra Department of Information & Communication Studies Box LG 149 Accra Ghana Sunyani Technical University Ghana

Dynamic Time warping (DTW) is a technique to estimate the best match between two common temporal sequences that are insensitive to synchronize well. This work looked to determine how DTW, and some common environmental parameters influence crop yield or vegetation. This was set out to identify literature using DTW and its variants in the direction of crop yield or vegetation. A total of 14 DTW and its variants and 10 environmental parameters that promoted crop yield or vegetation were adopted. Some DTW and its variants such as Time Weighted DTW, Derivative DTW, Weighted DTW, Vector DTW, Mahalanobis Distance DTW, Gaussian DTW, Open Locally Weighted DTW, and classical DTW recorded some 45 research works in their respective directions. Graphical DTW, Sparse DTW, Fast DTW, multiscale DTW, and Continuous DTW had no research about crop yield or vegetation in its direction. Environmental parameters such as wind speed and wind direction had no DTW and its variants modeled with them in crop yield or vegetation mapping, other environmental parameters recorded a total of 45 works in its direction. This points out gaps in DTW and its variants in crop yield and the concentration of variants and environmental parameters often used in crop yield and vegetation mapping. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Proactive Monitoring via Jamming in Fluid Antenna Systems

arXiv

引用

arXiv 2023年

作者： Yao, Junteng Wu, Tuo Lai, Xiazhi Jin, Ming Pan, Cunhua Elkashlan, Maged Wong, Kai-Kit The Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom The School of Computer Science Guangdong University of Education Guangdong Guangzhou China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Department of Electronic and Electrical Engineering University College London LondonWC1E 6BT United Kingdom The Yonsei Frontier Laboratory The School of Integrated Technology Yonsei University Seoul03722 Korea Republic of

This paper investigates the efficacy of utilizing fluid antenna system (FAS) at a legitimate monitor to oversee suspicious communication. The monitor switches the antenna position to minimize its outage probability for enhancing the monitoring performance. Our objective is to maximize the average monitoring rate, whose expression involves the integral of the first-order Marcum Q function. The optimization problem, as initially posed, is non-convex owing to its objective function. Nevertheless, upon substituting with an upper bound, we provide a theoretical foundation confirming the existence of a unique optimal solution for the modified problem, achievable efficiently by the bisection search method. Furthermore, we also introduce a locally closed-form optimal resolution for maximizing the average monitoring rate. Empirical evaluations confirm that the proposed schemes outperform conventional benchmarks considerably. © 2023, CC BY.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

On Performance of Fluid Antenna System using Maximum Ratio Combining

arXiv

引用

arXiv 2023年

作者： Lai, Xiazhi Wu, Tuo Yao, Junteng Pan, Cunhua Elkashlan, Maged Wong, Kai-Kit The School of Computer Science Guangdong University of Education Guangdong Guangzhou China The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom The Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Department of Electronic and Electrical Engineering University College London LondonWC1E 6BT United Kingdom The Yonsei Frontier Laboratory The School of Integrated Technology Yonsei University Seoul03722 Korea Republic of

This letter investigates a fluid antenna system (FAS) where multiple ports can be activated for signal combining for enhanced receiver performance. Given M ports at the FAS, the best K ports out of the M available ports are selected before maximum ratio combining (MRC) is used to combine the received signals from the selected ports. The aim of this letter is to study the achievable performance of FAS when more than one ports can be activated. We do so by analyzing the outage probability of this setup in Rayleigh fading channels through the utilization of Gauss-Chebyshev integration, lower bound estimation, and high signal-to-noise ratio (SNR) asymptotic approximations. Our analytical results demonstrate that FAS can harness rich spatial diversity, which is confirmed by computer simulations. © 2023, CC BY.

关键词： Rayleigh fading

来源：评论

学校读者我要写书评

暂无评论

Research on reversible functions having component functions with specified properties: An overview 12th

Research on reversible functions having component functions ...

引用

12th International Conference on Reversible Computation, RC 2020

作者： Kerntopf, Pawel Moraga, Claudio Podlaski, Krzysztof Stanković, Radomir Institute of Computer Science Warsaw University of Technology Warsaw Poland Faculty of Computer Science Technical University of Dortmund Dortmund Germany Faculty of Physics and Applied Informatics University of Lódź Lódź Poland Department of Computer Science Faculty of Electronic Engineering University of Niš Niš Serbia

ISBN: (纸本)9783030473600

In the traditional logic synthesis, different classifications of non-reversible Boolean functions have found many applications. Recently, some attempts to deal with classifications of reversible functions have been published. In this paper, an overview of our results towards constructing a new classification of reversible functions is presented. These results were obtained due to our discussions during two Short Term Scientific Missions (STSMs) as well as during our further research in the framework of COST Action IC1405 "Reversible Computation - Extending Horizons of Computing" and were published in five papers. © The Author(s) 2020.

关键词： Logic Synthesis

来源：评论

学校读者我要写书评

暂无评论

A Bpnn-Transformer for Air Quality Index Prediction

SSRN

引用

SSRN 2023年

作者： Wu, Xiankui Li, Penghua Gu, Xinyu See, K.W. Li, Junhong College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Faculty of Engineering Institute for Superconducting and Electronic Materials University of Wollongong Innovation Campus WollongongNSW2500 Australia Key Laboratory for Nonlinear Science and System Structure Chongqing Three Gorges University Chongqing404000 China

The Air Quality Index (AQI) is a key metric for evaluating the extent of atmospheric pollution. Accurate forecasting of the AQI is a challenging task due to the unpredictable nature of meteorological factors and the complex interactions between various pollutants. In this paper, we proposed a novel method that combines a backward propagation neural network (BPNN) and the Transformer model for improved AQI prediction. The method incorporates single exponential smoothing (SES) and Pearson correlation coefficient (PCC) analysis to enhance the predictive capabilities of the model. The proposed method has been evaluated using a comprehensive dataset, and the results demonstrate that it can significantly reduce the maximum error of AQI prediction to less than 3.4\%, which surpassed baseline learning methods, including BPNN, Long Short-Term Memory (LSTM), and Transformer model. Furthermore, visual analysis has been performed to confirm the effectiveness of the proposed method. This approach can serve as a valuable tool for policymakers and researchers to monitor and mitigate the harmful effects of air pollution, promoting sustainable development and enhancing the quality of life worldwide. © 2023, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

arXiv

引用

arXiv 2024年

作者： Bassi, Pedro R.A.S. Li, Wenxuan Tang, Yucheng Isensee, Fabian Wang, Zifu Chen, Jieneng Chou, Yu-Cheng Roy, Saikat Kirchhoff, Yannick Rokuss, Maximilian Huang, Ziyan Ye, Jin He, Junjun Wald, Tassilo Ulrich, Constantin Baumgartner, Michael Maier-Hein, Klaus H. Jaeger, Paul Ye, Yiwen Xie, Yutong Zhang, Jianpeng Chen, Ziyang Xia, Yong Xing, Zhaohu Zhu, Lei Sadegheih, Yousef Bozorgpour, Afshin Kumari, Pratibha Azad, Reza Merhof, Dorit Shi, Pengcheng Ma, Ting Du, Yuxin Bai, Fan Huang, Tiejun Zhao, Bo Wang, Haonan Li, Xiaomeng Gu, Hanxue Dong, Haoyu Yang, Jichen Mazurowski, Maciej A. Gupta, Saumya Wu, Linshan Zhuang, Jiaxin Chen, Hao Roth, Holger Xu, Daguang Blaschko, Matthew B. Decherchi, Sergio Cavalli, Andrea Yuille, Alan L. Zhou, Zongwei Department of Computer Science Johns Hopkins University United States Department of Pharmacy and Biotechnology University of Bologna Italy Center for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia Italy NVIDIA United States Germany Germany ESAT-PSI KU Leuven Belgium Faculty of Mathematics and Computer Science Heidelberg University Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Germany Shanghai Jiao Tong University China Shanghai Artificial Intelligence Laboratory China Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Germany DKFZ Germany School of Computer Science and Engineering Northwestern Polytechnical University China Australian Institute for Machine Learning The University of Adelaide Australia College of Computer Science and Technology Zhejiang University China Hong Kong University of Science and Technology Guangzhou China Hong Kong University of Science and Technology Hong Kong Faculty of Informatics and Data Science University of Regensburg Germany Faculty of Electrical Engineering and Information Technology RWTH Aachen University Germany Fraunhofer Institute for Digital Medicine MEVIS Germany Electronic & Information Engineering School Harbin Institute of Technology Shenzhen China China The Chinese University of Hong Kong Hong Kong Peking University China Department of Electrical and Computer Engineering Duke University United States Stony Brook University United States Department of Computer Science and Engineering Department of Chemical and Biological Engineering Division of Life Science Hong Kong University of Science and Technology Hong Kong Data Science and Computation Facility Fondazione Istituto Italiano di Tecnologia Italy Ecole Polytechnique Fédérale de Lausanne Switzerland

How can we test AI performance? This question seems trivial, but it isn’t. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms. In addition, we also evaluated pre-existing AI frameworks—which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain. Copyright © 2024, The Authors. All rights reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Performance of Hybrid Satellite-UAV NOMA Systems

TechRxiv

引用

TechRxiv 2022年

作者： ElHalawany, Basem M. Gamal, Christina An, Kang Li, Xingwang Menon, Varun G. Ragesh, G.K. Fouda, Mostafa M. Faculty of Engineering at Shoubra Benha University Egypt Sixty-third Research Institute National University of Defense Technology Nanjing China Physics and Electronic Information Engineering Henan Polytechnic University China SCMS School of Engineering and Technology Ernakulam683576 India Indian Institute of Information Technology Kottayam India Department of Electrical and Computer Engineering Idaho State University PocatelloID United States

This paper investigates the performance of non-orthogonal multiple access (NOMA) based hybrid satellite-unmanned aerial vehicle (UAV) systems, where a low Earth orbit (LEO) satellite communicates with the ground users via a decode and forward (DF) UAV relay. We investigate a two NOMA users system, where a far user (FU) and a near user (NU) are served by the UAV which is located at a certain height above the origin of the coverage circle. The channel between satellite and UAV is assumed to follow a Shadowed-Rician fading and the channels between UAV and users are assumed to follow a Nakagami-m fading. New closed-form expressions of the outage probabilities for the two users and the system are derived. Different from other work in literature, we take into consideration different parameters affecting the total link budget. Additionally, we propose an algorithm for minimizing the system outage probability. The mathematical analysis is verified by extensive representative Monte-Carlo (MC) simulations. Finally, simulations are provided to demonstrate the impact of important parameters on the considered system as well as the superiority of the NOMA scheme the over reference scheme. © 2022, CC BY.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning

arXiv

引用

arXiv 2023年

作者： Wang, Qiannan Yin, Changchun Liu, Zhe Fang, Liming Wang, Run Lin, Chenhao College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Nanjing University of Aeronautics Astronautics Shenzhen Research Institute Shenzhen China Research Institute of Basic Theories Zhejiang Lab Hangzhou China School of Cyber Science and Engineering Wuhan University Wuhan China Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an China

Within the realm of computer vision, self-supervised learning (SSL) pertains to training pre-trained image encoders utilizing a substantial quantity of unlabeled images. Pre-trained image encoders can serve as feature extractors, facilitating the construction of downstream classifiers for various tasks. However, the use of SSL has led to an increase in security research related to various backdoor attacks. Currently, the trigger patterns used in backdoor attacks on SSL are mostly visible or static (sample-agnostic), making backdoors less covert and significantly affecting the attack performance. In this work, we propose GhostEncoder, the first dynamic invisible backdoor attack on SSL. Unlike existing backdoor attacks on SSL, which use visible or static trigger patterns, GhostEncoder utilizes image steganography techniques to encode hidden information into benign images and generate backdoor samples. We then fine-tune the pre-trained image encoder on a manipulation dataset to inject the backdoor, enabling downstream classifiers built upon the backdoored encoder to inherit the backdoor behavior for target downstream tasks. We evaluate GhostEncoder on three downstream tasks and results demonstrate that GhostEncoder provides practical stealthiness on images and deceives the victim model with a high attack success rate without compromising its utility. Furthermore, GhostEncoder withstands state-of-the-art defenses, including STRIP, STRIP-Cl, and SSL-Cleanse. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

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：