检索结果-内蒙古大学图书馆

Classification of Colorectal Cancer using ResNet and EfficientNet Models

Open Biomedical Engineering Journal 2024年 18卷

作者： Abhishek Ranjan, Abhishek Srivastva, Priyanshu Prabadevi, B. Rajagopal, Sivakumar Soangra, Rahul Subramaniam, Shamala K. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Department of Sensor and Biomedical Technology Vellore Institute of Technology Crean College of Health and Behavioral Sciences Chapman University Department of Communication Technology and Networks Universiti Putra Malaysia

Introduction: Cancer is one of the most prevalent diseases from children to elderly adults. This will be deadly if not detected at an earlier stage of the cancerous cell formation, thereby increasing the mortality rate. One such cancer is colorectal cancer, caused due to abnormal growth in the rectum or colon. Early screening of colorectal cancer helps to identify these abnormal growth and can exterminate them before they turn into cancerous cells. Aim: Therefore, this study aims to develop a robust and efficient classification system for colorectal cancer through Convolutional Neural Networks (CNNs) on histological images. Methods: Despite challenges in optimizing model architectures, the improved CNN models like ResNet34 and EfficientNet34 could enhance Colorectal Cancer classification accuracy and efficiency, aiding doctors in early detection and diagnosis, ultimately leading to better patient outcomes. Results: ResNet34 outperforms the EfficientNet34. Conclusion: The results are compared with other models in the literature, and ResNet34 outperforms all the other models. © 2024 The Author(s).

关键词： CNN Colorectal cancer Deep learning EfficientNetB4 Histology Learning rate Loss function Optimizer ResNet34 ROC curve Transforms

来源：评论

学校读者我要写书评

暂无评论

On-chip metamaterial-enabled high-order mode-division multiplexing

引用

Advanced Photonics 2023年第5期5卷 106-113页

作者： Yu He Xingfeng Li Yong Zhang Shaohua An Hongwei Wang Zhen Wang Haoshuo Chen Yetian Huang Hanzi Huang Nicolas KFontaine Roland Ryf Yuhan Du Lu Sun Xingchen Ji Xuhan Guo Yingxiong Song Qianwu Zhang Yikai Su Shanghai Jiao Tong University Department of Electronic EngineeringState Key Laboratory of Advanced Optical Communication Systems and NetworksShanghaiChina Nokia Bell Labs Murray HillNew JerseyUnited States Shanghai University Key Laboratory of Specialty Fiber Optics and Optical Access NetworksJoint International Research Laboratory of Specialty Fiber Optics and Advanced CommunicationShanghaiChina Shanghai Jiao Tong University School of Electronic Information and Electrical EngineeringJohn Hopcroft Center for Computer ScienceShanghaiChina

Mode-division multiplexing(MDM)technology enables high-bandwidth data transmission using orthogonal waveguide modes to construct parallel data ***,few demonstrations have been realized for generating and supporting high-order modes,mainly due to the intrinsic large material groupvelocity dispersion(GVD),which make it challenging to selectively couple different-order spatial *** show the feasibility of on-chip GVD engineering by introducing a gradient-index metamaterial structure,which enables a robust and fully scalable MDM *** demonstrate a record-high-order MDM device that supports TE_(0)–TE_(15)modes simultaneously.40-GBaud 16-ary quadrature amplitude modulation signals encoded on 16 mode channels contribute to a 2.162 Tbit∕s net data rate,which is the highest data rate ever reported for an on-chip single-wavelength *** method can effectively expand the number of channels provided by MDM technology and promote the emerging research fields with great demand for parallelism,such as high-capacity optical interconnects,high-dimensional quantum communications,and large-scale neural networks.

关键词： integrated photonics metamaterial mode-division multiplexing subwavelength grating

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligent based Models for Event Extraction using Customer Support Applications

Artificial Intelligent based Models for Event Extraction usi...

引用

Augmented Intelligence and Sustainable systems (ICAISS), International Conference on

作者： M. Mayuranathan Akilandasowmya G B. Jayaram K. Sundara Velrani M Jogendra Kumar R G Vidhya Department of Computer Science Engineering SRM Valliammai Engineering College Department of Computer Communication and Engineering Sri Sairam Institute of Technology Department: Computer Science and Business Systems RMK Engineering College Kavaraipettai Gummidipoondi Taluk Tiruvallur District Tamilnadu Information Technology School of Computing Sathyabama Institute of Technology Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram AP India Department of ECE HKBK College of Engineering Bangalore

Recently, AI and NLP have been used to improve customer care. Customer support relies on event extraction and relevant data. In customer support applications, AI-based algorithms extract events. Event extraction identifies and extracts specific events or activities from textual data like customer service chats, emails, and social media interactions. Customer support teams may discover issues, trends, and improve the customer experience by automatically extracting events. Customer support event extraction can be done using AI-based models. Event extraction relies on named entity recognition (NER), sentiment analysis, and text classification. NER classifies customer names, product names, and problem keywords. Text classification classifies client issues into preset categories like billing, technical support, or product feedback, while sentiment analysis assesses the customer's emotional tone. Event extraction AI models use machine learning algorithms. Support vector machines (SVM) and random forests can be trained on annotated customer support data to reliably classify events. Recurrent neural networks (RNNs) and transformers can capture complicated patterns in textual data, making them promising event extraction methods. Customer support applications benefit from AI-based event extraction algorithms. It frees up support teams to focus on client issues by automating evaluation and categorization. It also helps firms identify emerging trends and enhance their products and services to answer client complaints. AI-based customer support event extraction models face hurdles. Labeled training data is costly and time-consuming to obtain. Ensuring model generalizability across multiple domains or languages is ongoing research. In conclusion, AI-based event extraction in customer support systems can improve customer experiences and support team efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Increasing Depth of Neural Networks for Life-long Learning

arXiv

引用

arXiv 2022年

作者： Kozal, Jedrzej Wozniak, Michal Department of Systems and Computer Networks Faculty of Information and Communication Technology Wroclaw University of Science and Technology Wybrzeze Wyspianskiego 27 Wroclaw50-370 Poland

Purpose: We propose a novel method for continual learning based on the increasing depth of neural networks. This work explores whether extending neural network depth may be beneficial in a life-long learning setting. Methods: We propose a novel approach based on adding new layers on top of existing ones to enable the forward transfer of knowledge and adapting previously learned representations. We employ a method of determining the most similar tasks for selecting the best location in our network to add new nodes with trainable parameters. This approach allows for creating a treelike model, where each node is a set of neural network parameters dedicated to a specific task. The Progressive Neural Network concept inspires the proposed method. Therefore, it benefits from dynamic changes in network structure. However, Progressive Neural Network allocates a lot of memory for the whole network structure during the learning process. The proposed method alleviates this by adding only part of a network for a new task and utilizing a subset of previously trained weights. At the same time, we may retain the benefit of PNN, such as no forgetting guaranteed by design, without needing a memory buffer. Results: Experiments on Split CIFAR and Split Tiny ImageNet show that the proposed algorithm is on par with other continual learning methods. In a more challenging setup with a single computer vision dataset as a separate task, our method outperforms Experience Replay. Conclusion: It is compatible with commonly used computer vision architectures and does not require a custom network structure. As an adaptation to changing data distribution is made by expanding the architecture, there is no need to utilize a rehearsal buffer. For this reason, our method could be used for sensitive applications where data privacy must be considered. © 2022, CC BY.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Challenges and Solutions in the Digital Age: An Analysis

Cybersecurity Challenges and Solutions in the Digital Age: A...

引用

communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Sargunavathi S Talluri Upender Sowmiya B Sundar R Rajasekaran E S.Sree Dharinya Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India Department of CSE CMR College of Engineering and Technology Hyderabad Telangana Department of Computing Technologies SRM Institute of Science and Technology Department of CSE Sathyabama Institute of Science and Technology Department of Science and Humanities V.S.B Engineering College Karur India School of Computer Science Engineering and Information Systems. VIT University Vellore

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

In the digital age, cybersecurity has become a critical concern for individuals, organizations, and governments worldwide. The rapid advancement of technology and the increasing interconnectedness of systems have introduced numerous vulnerabilities, making cybersecurity a complex and ever-evolving challenge. This paper provides a comprehensive analysis of the current cybersecurity landscape, identifying key challenges such as sophisticated cyber-attacks, data breaches, and the growing threat of ransomware. Additionally, it explores innovative solutions and strategies to mitigate these risks, including the implementation of advanced threat detection systems, and the adoption of robust security protocols. Furthermore, the paper delves into the importance of cyber hygiene, the role of regulatory frameworks, and the necessity of continuous education and awareness programs to foster a culture of cybersecurity. It also examines the impact of emerging technologies like the Internet of Things (IoT) and 5G networks on cybersecurity, highlighting both opportunities and vulnerabilities. Special attention is given to the integration of blockchain technology for secure transactions and identity verification. The paper also addresses the significance of international collaboration and information sharing to combat global cyber threats. By examining both the threats and the potential countermeasures, this paper aims to offer valuable insights into safeguarding digital assets, ensuring the integrity and confidentiality of information, and promoting a proactive and resilient approach to cybersecurity in an increasingly digital world.

关键词： Training Protocols Government Data breach Information age Threat assessment Blockchains Ransomware computer security Cyberattack

来源：评论

学校读者我要写书评

暂无评论

40 Gb/s High-speed mode-division multiplexing transmission employing NRZ modulation format

引用

Journal of Optical communications 2023年第S1期44卷 S1157-S1165页

作者： Sabitu, Rabiu Imam Khan, Nafizah Goriman Malekmohammadi, Amin Affiliated to the George Green Institute for Electromagnetics Research Nottingham United Kingdom Photonics Communication Systems and Signal Processing Research Group Kano University of Science and Technology Wudil KanoPMB 3244 Nigeria Semenyih Malaysia Department of Electrical and Computer Engineering California State University BakersfieldCA93311 United States Photonics Communication Systems and Signal Processing Research Group Kano University of Science and Technology Wudil KanoPMB 3244 Nigeria

This report examines the performance of a high-speed MDM transmission system supporting four nondegenerate spatial modes at 10 Gb/s. The analysis adopts the NRZ modulation format to evaluate the system performance in terms of a minimum power required (PN) and the nonlinear threshold power (PTH) at a BER of 10−9. The receiver sensitivity, optical signal-to-noise ratio, and the maximum transmission distance were investigated using the direct detection by employing a multimode erbium-doped amplifier (MM-EDFA). It was found that by properly optimizing the MM-EDFA, the system performance can significantly be improved. © 2023 Walter de Gruyter GmbH. All rights reserved.

关键词： Erbium doped fiber amplifiers

来源：评论

学校读者我要写书评

暂无评论

Any Bluetooth device can be hacked. Know how?

Cyber Security and Applications

引用

Cyber Security and Applications 2024年 2卷

作者： Muraleedhara, Prathibha Christo, Mary Subaja J, Jaya Yuvasini  D College of Technology – Information Security and Program Management University of Houston 77204 TX United States Department of Networking and Communication School of Computing SRM Institute of Science and Technology Kantankulathur Chennai India Department of Electronics and Communication Engineering Hindustan College of Engineering and Technology India Assistant Professor Department of Computer Science and Business Systems Thiagarajar College of Engineering Madurai 625015 India

In today's world, Bluetooth technology is integrated into almost every device we use, from wireless headsets, mice, and keyboards to cars and smart home devices. But with the convenience of this technology comes the risk of privacy and security breaches. Each Bluetooth device has potential vulnerabilities that cybercriminals can exploit and take advantage of. It is important to create awareness about various Bluetooth vulnerabilities, exploits, and ways to prevent them. This article examines the dark side of Bluetooth technology by explaining how hackers can find ways to bypass the advanced security features of laptops, phones, cars, or smart home devices to compromise the devices and steal personal sensitive data. Whether it is a casual user of Bluetooth technology or a business owner with multiple devices, understanding these risks is crucial to protecting yourself and your information. This article begins by explaining the basics of Bluetooth technology and how it works. Followed by a list of security risks involved while using Bluetooth and finally, it highlights the best practices to protect the devices and the data they contain. © 2024

关键词： Ad hoc networks and security risk Bluetooth Exploit Threat Vulnerability

来源：评论

学校读者我要写书评

暂无评论

Effects of Different Recommendation Algorithms on Structure of Social Networks

Effects of Different Recommendation Algorithms on Structure ...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Sepideh Banihashemi Abdolreza Abhari Department of Computer Science Distributed Systems and Multimedia Processing Laboratory (DSMP lab) Ryerson University Toronto Canada

ISBN: (纸本)9781665458429

In this paper, the effects of two algorithms (i.e., K-means clustering, Cosine similarity) on the structure of a social network (i.e., Twitter, scientific research papers) is studied to examine the formation of communities when the users follow the recommendations provided by a simulator. The relationship among the users can be either follower-followee in a Twitter dataset or a paper-publication venue in a scientific research paper dataset. The purpose is to evaluate how detected communities and the resulted network graph differ when following the recommendations provided by the employed algorithms after the system recommends the top-N recommendations for a selected user.

关键词： Social networking (online) Scientific computing Blogs Clustering algorithms Recommender systems Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Revisiting Matching Pursuit Beyond Approximate Submodularity

SSRN

引用

SSRN 2023年

作者： Tohidi, Ehsan Coutino, Mario Gesbert, David Fraunhofer HHI Berlin Germany Technische Universität Berlin Berlin Germany Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands Communication Systems Department EURECOM Biot France

We study the problem of selecting a subset of vectors from a large set, to obtain the best signal representation over a family of functions. Although greedy methods have been widely used for tackling this problem and many of those have been analyzed under the lens of (weak) submodularity, none of these algorithms are explicitly devised using such a functional property. Here, we revisit the vector-selection problem and introduce a function which is shown to be submodular in expectation. This function does not only guarantee near-optimality through a greedy algorithm in expectation, but also alleviates the existing deficiencies in commonly used matching pursuit (MP) algorithms. We further show the relation between the single-point-estimate version of the proposed greedy algorithm and MP variants. Our theoretical results are supported by numerical experiments for the angle of arrival estimation problem, a typical signal representation task;the experiments demonstrate the benefits of the proposed method with respect to the traditional MP algorithms. © 2023, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Revisiting Matching Pursuit: Beyond Approximate Submodularity

arXiv

引用

arXiv 2023年

—We study the problem of selecting a subset of vectors from a large set, to obtain the best signal representation over a family of functions. Although greedy methods have been widely used for tackling this problem and many of those have been analyzed under the lens of (weak) submodularity, none of these algorithms are explicitly devised using such a functional property. Here, we revisit the vector-selection problem and introduce a function which is shown to be submodular in expectation. This function does not only guarantee near-optimality through a greedy algorithm in expectation, but also alleviates the existing deficiencies in commonly used matching pursuit (MP) algorithms. We further show the relation between the single-point-estimate version of the proposed greedy algorithm and MP variants. Our theoretical results are supported by numerical experiments for the angle of arrival estimation problem, a typical signal representation task;the experiments demonstrate the benefits of the proposed method with respect to the traditional MP algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Numerical methods

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：