检索结果-内蒙古大学图书馆

CNN segmentation of skin melanoma in pre-processed dermoscopy images

Procedia computer Science 2024年 235卷 2775-2782页

作者： Seifedine Kadry Elena Verdú Robertas Damasevicius Laith Abualigah Vijendra Singh Venkatesan Rajinikanth Department of Applied Data Science Noroff University College Kristiansand Norway Artificial Intelligence Research Center (AIRC) Ajman University Ajman 346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Higher School of Engineering and Technology Universidad Internacional de La Rioja Logroño 26006 Spain Department of Applied Informatics Vytautas Magnus University 53361 Kaunas Lithuania Computer Science Department Al al-Bayt University Mafraq 25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan MEU Research Unit Middle East University Amman 11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang 11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya 27500 Malaysia School of Computer Science University of Petroleum and Energy Studies Dehradun 248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India

Using medical data to improve diagnosis accuracy has recently become common practice in hospitals. A modern computing environment has enabled real-time diagnosis of medical data using Convolutional Neural Networks (CNNs). To extract and evaluate skin melanoma recorded with digital dermatoscopy images (DDI), we developed a CNN segmentation framework. In this proposal, four phases are proposed: (i) DDI collection and resizing, (ii) DDI enhancement using pre-processing techniques, (iii) CNN segmentation for lesion extraction, (v) Comparing the extracted sections to the ground truth images, and (v) Verifying whether the framework is valid. Using DDI pre-processed with (i) Traditional procedures, (ii) Otsu’s thresholding, (iii) Kapur’s thresholding, and (iv) Fuzzy-Tsallis thresholding, this proposal examines the different CNN segmentation schemes presented in the literature. For mining skin lesions, the Moth-Flame Algorithm (MFA) combined with tri-level thresholding achieves an optimal threshold for the DDI. With Fuzzy-Tsallis thresholding images, the VGG-UNet performs better than the alternatives. This framework helps to achieve better values of Jaccard (88.47±2.13%), Dice (93.08±1.17%), and Accuracy (98.64±0.71%) on the chosen DDI database.

关键词： Watershed-algorithm skin melanoma segmentation Fuzzy-Tsallis entropy Moth-Flame algorithm evaluation

来源：评论

学校读者我要写书评

暂无评论

Influence of defects on the femtosecond laser damage resistance of multi-layer dielectric grating

Influence of defects on the femtosecond laser damage resista...

引用

CLEO: Science and Innovations, S and I 2022

作者： Zhang, Simin Su, Ziyao Menoni, Carmen S. Chowdhury, Enam A. The Ohio State University Department of Materials Science and Engineering ColumbusOH43210 United States The Ohio State University Department of Physics ColumbusOH43210 United States Colorado State University Electrical and Computer Engineering Department Fort CollinsCO80523 United States XUV Lasers Inc. Fort CollinsCO80525 United States

The influence of various defects on the femtosecond laser damage resistance of a HfO2/SiO2/Ta2O5-based 48-layer grating designed for 800 nm is studied using the finite-difference time-domain method incorporated with t... 详细信息

ISBN: (纸本)9781557528209

关键词： Femtosecond lasers

来源：评论

学校读者我要写书评

暂无评论

Eigenvalue Topology of Non-Hermitian Band Structures in Two and Three Dimensions

Eigenvalue Topology of Non-Hermitian Band Structures in Two ...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Casey Wojcik Kai Wang Avik Dutt Janet Zhong Shanhui Fan Department of Electrical Engineering Ginzton Laboratory Stanford University Stanford CA USA Department of Applied Physics Stanford University Stanford CA USA

In one dimension, eigenvalue topology of non-Hermitian photonic systems is classified by the braid group. Here, we give a complete description of the much richer eigenvalue topology in two and three dimensions.

ISBN: (数字)9781957171050

ISBN: (纸本)9781665466660

关键词： Band structures Eigenvalues and eigenfunctions Topology Electrooptical waveguides Photonics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Object Tracking with Adaptive Spatial-Temporal Regularization Correlation Filter Models

SSRN

引用

SSRN 2024年

作者： Aryanfar, Ehsan Aliyari-Shoorehdeli, Mahdi Seydi, Vahid The Department of Computer Engineering Artificial Intelligence South Tehran Branch Islamic Azad University Tehran Iran The Department of Electrical Engineering Khajeh Nasirodin Toosi University of Technology Tehran Iran The Centre for Applied Marine Sciences School of Ocean Sciences Bangor University Menai Bridge United Kingdom

Despite the rise of deep learning-based tracking models, Correlation Filter models remain favored for their balance of accuracy and efficiency in real-time tracking. However, they struggle with challenges like occlusion, boundary effects, and scale variations. While existing trackers use basic regularization and multi-scale approaches to address these, they often lack adaptability to diverse target appearances and dynamic scale *** study proposes an adaptive spatial-temporal regularization correlation filter model that responds to changing target appearances. We create a spatial regularization map based on a reliability criterion by integrating results from local correlation filters across overlapping parts of varying sizes and positions. Additionally, we leverage spatial relationships to estimate scale variations and propose an adaptive temporal regularization coefficient. Experiments on TC128, OTB2013, and OTB2015 datasets show significant gains in accuracy and success rates with minimal speed compromise. © 2024, The Authors. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Sandbox Integrated Gateway for the Discovery of Cybersecurity Vulnerabilities

Sandbox Integrated Gateway for the Discovery of Cybersecurit...

引用

International Symposium on Electronics and Telecommunications (ISETC)

作者： Alexandre Rekeraho Titus Balan Daniel T. Cotfas Petru A. Cotfas Rebecca Acheampong Cristian Musuroi Department of Electronics and Computers Transilvania University of Brasov Brasov Romania Department of Electrical Engineering and Applied Physics Transilvania University of Brasov Brasov Romania

ISBN: (纸本)9781665451512

Emails are widely used as a form of communication and sharing files in an organization. However, email is widely used by cybercriminals to spread malware and carrying out cyber-attacks. We implemented an open-source email gateway in conjunction with a security sandbox for securing emails against malicious attachments. The email gateway scans all incoming and outgoing emails and stops emails containing suspicious files. An automated python script would then send the suspected email to the sandboxing element through sandbox API for further analysis, while the script is used also for the prevention of duplicate results. Moreover, the mail server administrator receives notifications from the email gateway about suspicious attachments. If detected attachment is a true positive based on the sandbox analysis result, email is deleted, otherwise, the email is delivered to the recipient. The paper describes in an empirical way the steps followed during the implementation, results, and conclusions of our research.

关键词： Organizations Logic gates Electronic mail Telecommunications Servers Trojan horses Engines

来源：评论

学校读者我要写书评

暂无评论

Identification of the structural characteristics, optical properties, and adsorption performance of Bi and Sn co-doped Co0.5Zn0.5Fe2O4 nanoparticles

引用

South African Journal of Chemical engineering 2025年 53卷 267-280页

作者： Rmeid, Sajida Aridi, Amani Habanjar, Khulud Elsharkawy, Sherif G. Awad, Ramadan Physics Department Faculty of Science Beirut Arab University Beirut Lebanon Public Health Department Faculty of Health Sciences Modern University for Business and Science Beirut Lebanon Basic and Applied Sciences College of Engineering and Technology Arab Academy for Science Technology and Maritime Transport Alexandria Egypt Physics Department Faculty of Science Alexandria University Alexandria Egypt Department of Basic Sciences Faculty of Computer Science and Artificial Intelligence Pharos University in Alexandria Alexandria Egypt

Highly effective techniques, such as adsorption, play an important role in removing hazardous pollutants from wastewater. Spinel ferrite nanoparticles have proven to be effective adsorbents for removing dyes from wastewater. Thus, the preparation, characterization, and application of (Co0.5−xZn0.5−xBixSnx)Fe2O4 nanoparticles (0 ≤ x≤ 0.1) as adsorbents for brilliant blue dye removal were reported in this study. The XRD analysis confirmed sample purity with minimal hematite phase. The synthesized nanoparticles exhibit spherical morphology, as revealed by SEM analysis. Additionally, EDX measurements revealed the successive substitution of the Co²⁺ and Zn²⁺ host ions by Bi²⁺ and Sn²⁺ dopants. UV–vis spectroscopy analysis yielded an increase in the direct and indirect bandgap energies upon co-doping. Among the prepared nanoparticles, the highest recombination rate was exhibited by (Co0.5−xZn0.5−xBixSnx)Fe2O4 nanoparticles with x= 0.02, while the slowest recombination rate was observed for x= 0.04, as revealed from photoluminescence (PL) analysis. Adsorption experiments examined the effects of contact time, adsorbent dosage, pH, temperature, and initial dye concentration. Co-doped ferrite nanoparticles demonstrated efficient dye removal under various conditions. Kinetic and isotherm studies revealed a favourable adsorption process, following pseudo-second-order kinetics and best fitting the Freundlich isotherm. These findings highlight the potential of co-doped ferrite nanoparticles as effective adsorbents for wastewater treatment.

关键词： (Co0.5−xZn0.5−xBixSnx)Fe2O4 nanoparticles Adsorption isotherm Adsorption kinetics Brilliant blue removal Optical properties Structural characteristics

来源：评论

学校读者我要写书评

暂无评论

Special relativity effects on chaos and periodic orbits - a semianalytic approach

引用

Physical Review Research 2025年第1期7卷 013241-013241页

作者： Jun-Yin Huang Hong-Ya Xu Liang Huang Ying-Cheng Lai School of Electrical Computer and Energy Engineering Arizona State University Tempe Arizona 85287 USA Lanzhou Center for Theoretical Physics Key Laboratory of Theoretical Physics of Gansu Province Key Laboratory for Quantum Theory and Applications of MOE and School of Physical Science and Technology Lanzhou University Lanzhou Gansu 730000 China Department of Physics Arizona State University Tempe Arizona 85287 USA

In the study of nonlinear dynamics and chaos, analytically solvable physical models are rare. We investigate the classical motion of a trapped relativistic particle, subject to an electric and a magnetic field. When the directions of the electric and magnetic fields coincide, the dynamics are integrable. As the magnetic field rotates away from the direction of the electric field, a transition to chaos occurs. Based on the approach in a previous work in the nonrelativistic regime [Narimanov et al., Phys. Rev. B 57, 9807 (1998)], we introduce a particular Lorentz transformation to extend the framework to the relativistic regime, which enables us to derive the Poincaré map and obtain semianalytic formulas for periodic orbits of low periods. The transformation also makes it possible to assess, semianalytically, the role of the degree of the relativistic motion of the particle in its dynamics, revealing that the special relativity effects can enhance chaos. As numerical simulations have played a dominant role in investigating nonlinear physical systems exhibiting chaos and in many cases are the only feasible tool to probe into the system dynamics, our semianalytic approach is unique and leads to additional insights into the interplay between special relativity and chaos.

关键词： Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Combining Dense and Sparse Rewards to Improve Deep Reinforcement Learning Policies in Reach-Avoid Games with Faster Evaders in Two vs. One Scenarios

Combining Dense and Sparse Rewards to Improve Deep Reinforce...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Jefferson Silveira Kalena McCloskey Camille-Alain Rabbath Craig Williams Sidney Givigi Department of Electrical & Computer Engineering The Ingenuity Labs Research Institute Queen’s University Kingston Canada Department of Applied Mathematics and Engineering Queen’s University Kingston Canada School of Computing Queen’s University Kingston Canada Department of Physics and Space Science Royal Military College of Canada Kingston Canada School of Computing and the Ingenuity Labs Research Institute Queen’s University Kingston Canada

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

This paper investigates a variation of the reach-avoid game, a multi-agent pursuit and evasion scenario applicable to aerial defense, with faster evaders. Using Deep Reinforcement Learning techniques, the study proposes a different reward function that combines dense (distance-based) and sparse (outcome-based) rewards. Focused on the defender’s perspective in aerial defense, this new reward function resulted in effective learned policies against faster evaders, outperforming traditional differential game and DRL strategies with dense-only rewards. Moreover, the learned policy demonstrated versatility across different instances of the problem, including changes in pursuer speeds and winning radii, illustrating its versatility in unseen situations during training.

关键词： Training Games Differential games Deep reinforcement learning Information technology

来源：评论

学校读者我要写书评

暂无评论

SugarcaneNet: An Optimized Ensemble of LASSO-Regularized Pre-trained Models for Accurate Disease Classification

arXiv

引用

arXiv 2024年

作者： Talukder, Md Simul Hasan Akter, Sharmin Nur, Abdullah Hafez Aljaidi, Mohammad Sulaiman, Rejwan Bin Alkoradees, Ali Fayez Department of Electrical and Electronic Engineering Dhaka University of Engineering & Technology Gazipur Bangladesh Department of Biomedical Engineering Jashore University of Science and Technology Jashore Bangladesh Department of Electronic and Telecommunication Engineering International Islamic University Chittagong Chittagong Bangladesh Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan School of Computer science and Technology Northumbria University United Kingdom Unit of Scientific Research Applied College Qassim University Saudi Arabia

Sugarcane, a key crop for the world's sugar industry, is prone to several diseases that have a substantial negative influence on both its yield and quality. To effectively manage and implement preventative initiatives, diseases must be detected promptly and accurately. In this study, we present a unique model called SugarcaneNet that outperforms previous methods for automatically and quickly detecting sugarcane disease through leaf image processing. Our proposed model consolidates an optimized weighted average ensemble of seven customized and LASSO-regularized pre-trained models, particularly InceptionV3, InceptionResNetV2, DenseNet201, DenseNet169, Xception, and ResNet152V2. Initially, we added three more dense layers with 0.0001 LASSO regularization, three 30% dropout layers, and three batch normalizations with "renorm" enabled at the bottom of these pre-trained models to improve the performance. The accuracy of sugarcane leaf disease classification was greatly increased by this addition. Following this, several comparative studies between the average ensemble and individual models were carried out, indicating that the ensemble technique performed better. The average ensemble of all modified pre-trained models produced outstanding outcomes: 100%, 99%, and 99.45% for f1 score, precision, recall, and accuracy, respectively. Performance was further enhanced by the implementation of an optimized weighted average ensemble technique incorporated with grid search. This optimized "sugarcaneNet" model performed the best for detecting sugarcane diseases, having achieved accuracy, precision, recall, and F1 score of 99.67%, 100%, 100%, and 100%, respectively. © 2024, CC BY.

关键词： Sugar industry

来源：评论

学校读者我要写书评

暂无评论

Spectral Properties of Quasiparticle Interacting With Three-Mode Phonons, Taking Into Account Damping

Spectral Properties of Quasiparticle Interacting With Three-...

引用

IEEE International Conference on Electronics and Nanotechnology (ELNANO)

作者： Mykola Tkach Julia Seti Oxana Voitsekhivska Igor Boyko Department of Information Technologies and Computer Physics Yuriy Fedkovych Chernivtsi National University Chernivtsi Ukraine Ukraine Department of Applied Mathematics Lviv Polytechnic National University Lviv Ukraine Department of Software Engineering Ternopil Ivan Puluj National Technical University Ternopil Ukraine

ISBN: (数字)9798350368178

ISBN: (纸本)9798350368185

Within the model of quasiparticle in two states interacting with three-mode polarization phonons at T=0K, the Fourier image of the Green's function is calculated considering non-phonon scattering mechanisms, which are taken into account by phenomenological damping. Accurate analytical expressions are obtained for the stationary energy spectrum of such system and the shape-function of its absorption band. It made possible to analyze the spectral properties of the system with and without the non-phonon damping.

关键词： Damping Couplings Satellites Accuracy Temperature Absorption Scattering Phonons Green's function methods Nanotechnology

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：