检索结果-内蒙古大学图书馆

Modern Challenges and Limitations in Medical Science Using Capsule Networks: A Comprehensive Review 1

4th International Conference on Image Processing and Capsule Networks, ICIPCN 2023

作者： Shah, Milind Bhavsar, Nikunj Patel, Kinjal Gautam, Kinjal Chauhan, Mayur Gujarat Vadodara India Department of Computer Engineering School of Engineering P P Savani University Gujarat Kosamba Surat India Faculty of Computer Applications and Information Technology Gujarat Law Society University Gujarat Ahmedabad India Baroda University Gujarat Vadodara India Gujarat Mehsana India

ISBN: (数字)9789819970933

ISBN: (纸本)9789819970926

Capsule networks (CapsNet), an emerging neural network architecture, is now used in medical science to develop potential tools and applications. Particularly, in the domain of medical image analysis, CapsNet outperforms the existing CNN models in terms of disease detection and classification tasks, such as identifying abnormalities in retinal images for diabetic retinopathy and tumor detection. Moreover, capsule networks are now used in analyzing the electronic health records (EHRs) such as hospital readmissions and mortality rates. However, the implementation of capsule networks in medical science is still in the nascent stage facing several challenges due to the limited availability of high-quality medical data, lack of interpretability, and ethical considerations. In order to overcome these challenges, more research and collaboration works should be encouraged between medical professionals and artificial intelligence (AI) experts. This research study discusses about the modern challenges faced by medical science and how the challenges can be solved by using capsule networks and algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Lottery-based Spherical Evolution Algorithm with Elite Retention Strategy 14

A Lottery-based Spherical Evolution Algorithm with Elite Ret...

引用

14th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2022

作者： Li, Jiayi Zhang, Zihang Lei, Zhenyu Yi, Junyan Gao, Shangce University of Toyama Faculty of Engineering Toyama930-8555 Japan Beijing University of Civil Engineering and Architecture Department of Computer Science and Technology Beijing100044 China

ISBN: (数字)9781665461696

ISBN: (纸本)9781665461696

Spherical evolution (SE) is a recently proposed meta-heuristic algorithm. Its special search approach has been proved to be very effective in exploring the search space. SE is very powerful for optimization, but still has room for improvement due to some promising solutions usually fail to survive into the next generation. To alleviate this issue, we innovatively design a novel lottery-based elite retention strategy and propose a lottery elite spherical evolution algorithm (LESE). To verify the effectiveness of the proposed LESE, we experimentally compare it with the original SE algorithm and other representative meta-heuristics algorithms. We use 30 benchmark functions from the IEEE CEC2017 benchmark as the test set for our experiments. The effectiveness of LESE is demonstrated by analyzing the experimental results from perspectives of solution accuracy, convergence speed, solution distribution, and search dynamics. © 2022 IEEE.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Fine Tuned DBN Model for Food Ingredient Recognition: Introduction to Self-improved Tasmanian Devil Optimization Algorithm

Fine Tuned DBN Model for Food Ingredient Recognition: Introd...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Sharanabasappa A. Madival Shivkumar S. Jawaligi Department of Computer Science and Engineering Faculty of Engineering & Technology Sharnbasva University Kalburgi India Department of Electronic and Communication Engineering Faculty of Engineering & Technology Sharnbasva University Kalburgi India

Food recognition has captivated much significance for health-related appliances. The traditional schemes mainly concern on the classification of food depending on its names and disregards the basic ingredient compositions. However, owing to shortage of datasets with labels of ingredient, the issues on food ingredient recognition (FIR) is often unnoticed. This work develops a new FIR approach, where, textual features, SIFT and deep features are derived. Then, the DBN classifier is deployed for the recognition of food ingredients. To get a precise recognition, tuning the weights of DBN is done via Improved TDO (ITDO) model.

关键词： Support vector machines Measurement Integrated circuits Finite impulse response filters Communication systems Classification algorithms Tuning

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a decentralized trustless data standardization framework for blockchain interoperability using smart contracts

引用

Alexandria engineering Journal 2025年 129卷 168-191页

作者： Abdulrahman Alzahrani Amin Noaman Ahmed A.A. Gad-Elrab Fathy Eassa Maher Khemakhem Faisal Albalwy Hosam Aljihani Department of Computer Science Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Department of Cybersecurity College of Computer Science and Engineering Taibah University Madinah 42353 Saudi Arabia Department of Computer Science College of Computer Science and Engineering Taibah University Madinah 42353 Saudi Arabia

Interoperability among heterogeneous blockchain platforms remains a significant challenge in decentralized ecosystems, especially with the growing adoption of blockchain across various industries. This research introduces the Data Standardization Module (DSM). This framework facilitates seamless communication between platforms like Ethereum and Hyperledger Fabric using a unified schema for data transformation and exchange. DSM leverages Concise Binary Object Representation (CBOR) encoding, which reduces data size by 60 % and achieves a compression ratio (CR) of 2.5. This outperforms conventional JSON-based methods, typically achieving only 20–30 % compression with lower CR values. The system ensures data security and integrity through end-to-end encryption, access control, and validation mechanisms. Performance evaluations show that DSM supports an average throughput of 250 transactions per second (TPS). In comparison, interoperability frameworks like Cosmos and Polkadot typically achieve 100–150 TPS, while early implementations of Hyperledger Fabric reported TPS as low as 300. However, optimized settings of Hyperledger Fabric now achieve over 100,000 TPS. DSM strikes a balance by providing high throughput with minimal resource overhead, making it suitable for real-world applications. This work advances blockchain interoperability by offering a lightweight, secure, and scalable framework, ideal for high-frequency use cases in healthcare, finance, and supply chains.

关键词： Blockchain interoperability Decentralized systems Data standardization module CBOR compression SHA-256 hashing

来源：评论

学校读者我要写书评

暂无评论

An Optimized Sensors Associated Forest Fire Prediction and Reporting System Based on Internet of Things technology

An Optimized Sensors Associated Forest Fire Prediction and R...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Deepak, P. Srinu, Nidamanuri Xavier, Benisha Maria Sravani, R. Nandurkar, Y. Afaneh, Suha Einstein Engineering college Dept of Computer Science and Engineering Tirunelveli India Qis College of Engineering and Technology Department of Cse Pondur Road Vengamukkapalem Ongole Prakasam AndhraPradesh PrakasamDistrict523272 India Jeppiaar Institute of Technology Department of Ece Kunnam Tamilnadu Chennai India Qis College of Engineering and Technology Department of S&h Pondur Road Vengamukkapalem Ongole Prakasam AndhraPradesh Prakasam District523272 India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Zarqa university Faculty of information technology Department of cybersecurity Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Forest fires pose a significant threat to the environment, leading to the destruction of ecosystems and contributing to climate change. This paper presents an optimized sensor-based forest fire prediction and reporting system leveraging Internet of Things (IoT) technology. The system integrates Wireless Sensor Networks (WSNs) and IoT-enabled devices to monitor environmental parameters, including temperature, CO2, and smoke levels. The system demonstrated high sensor accuracy, with temperature sensors showing a maximum deviation of ±0.5°C and gas sensors displaying an accuracy of ±2 ppm for CO2. Smoke detection accuracy was within ±0.05 ppm, making the system reliable for early fire detection. The system's response time improved significantly with increasing temperatures, detecting fire events within 10 seconds for temperatures above 100°C. The Wireless Sensor Network maintained a packet delivery ratio (PDR) of over 99% and an average latency of 200ms under high node density, ensuring timely transmission of critical data. With power consumption optimized for long-term deployment, sensor nodes were estimated to operate for up to 24 months. Overall, this system offers a cost-effective, accurate, and efficient solution for real-time forest fire monitoring and response, with potential applications in large, remote forest areas. © 2024 IEEE.

关键词： Temperature sensors

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Authentication Protocol Suitable for Constrained RFID Systems

引用

IEEE Access 2024年 12卷 61610-61628页

作者： Hosseinzadeh, Mehdi Servati, Mohammad Reza Rahmani, Amir Masoud Safkhani, Masoumeh Lansky, Jan Janoscova, Renata Ahmed, Omed Hassan Tanveer, Jawad Lee, Sang-Woong Duy Tan University Institute of Research and Development Da Nang550000 Viet Nam Duy Tan University School of Medicine and Pharmacy Da Nang550000 Viet Nam Shahid Rajaee Teacher Training University Department of Computer Engineering Tehran16788-15811 Iran National Yunlin University of Science and Technology Future Technology Research Center Douliou Yunlin64002 Taiwan School of Computer Science Tehran19395-5746 Iran University of Finance and Administration Faculty of Economic Studies Department of Computer Science and Mathematics Prague101 00 Czech Republic University of Human Development Department of Information Technology Sulaymaniyah0778-6 Iraq Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of Gachon University Pattern Recognition and Machine Learning Laboratory Department of Ai Software Seongnam-si13557 Korea Republic of

RFID technology offers an affordable and user-friendly solution for contactless identification of objects and individuals. However, the widespread adoption of RFID systems raises concerns regarding security and privacy. Vulnerabilities such as message tampering, interception, and eavesdropping pose significant risks to the integrity of the system. This study examines the effectiveness of two recently proposed ultra-lightweight RFID authentication protocols, URASP and KUAJB, in addressing these security challenges. Surprisingly, our findings reveal that both URASP and KUAJB protocols are susceptible to secret disclosure attacks, despite their claims of providing robust security. Consequently, the development of a truly ultra-lightweight protocol that ensures adequate security becomes a formidable task. As a potential solution, the enhancement of the URASP protocol through the integration of a simple cryptographic primitive is suggested to bolster its security measures. © 2013 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Physics-Driven Self-Supervised Deep Learning for Free-Surface Multiple Elimination

arXiv

引用

arXiv 2025年

作者： Sun, Jing Wang, Tiexing Verschuur, Eric Vasconcelos, Ivan Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Netherlands R&D Department Shearwater GeoServices United Kingdom Faculty Of Civil Engineering and Geosciences Delft University of Technology Netherlands

In recent years, deep learning (DL) has emerged as a promising alternative approach for various seismic processing tasks, including primary estimation (or multiple elimination), a crucial step for accurate subsurface imaging. In geophysics, DL methods are commonly based on supervised learning from large amounts of high-quality labelled data. Instead of relying on traditional supervised learning, in the context of free-surface multiple elimination, we propose a method in which the DL model learns to effectively parameterize the free-surface multiple-free wavefield from the full wavefield by incorporating the underlying physics into the loss computation. This, in turn, yields high-quality estimates without ever being shown any ‘ground truth’ data. Currently, the network reparameterization is performed independently for each dataset. We demonstrate its effectiveness through tests on both synthetic and field data. We employ industry-standard Surface-Related Multiple Elimination (SRME) using, respectively, global least-squares adaptive subtraction and local least-squares adaptive subtraction as benchmarks. The comparison shows that the proposed method outperforms the benchmarks in estimation accuracy, achieving the most complete primary estimation and the least multiple energy leakage, but at the cost of a higher computational burden. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Recruitment Algorithm in Edge-Cloud Servers based on Mobile Crowd-Sensing in Smart Cities

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第16期17卷 116-128页

作者： Wildan, Muhammad Alkirom Widyaningrum, Mahmudah Enny Padmapriya, T. Sah, Basant Pani, Niroj Kumar Department of Management Faculty of Economics and Business University of Trunojoyo Madura Jawa Timur Bangkalan Indonesia Faculty of Economics and Business Universitas Bhayangkara Surabaya Surabaya Indonesia Melange Publications Puducherry India Department of CSE Koneru Lakshmaiah Education Foundation AP Vaddeswaram India Department of Computer Science Engineering and Applications Indira Gandhi Institute of Technology Odisha Sarang India

As more and more mobile devices rely on cloud services since the introduction of cloud computing, data privacy has emerged as one of the most pressing security concerns. Users typically encrypt their important data before uploading it to cloud servers to safeguard data privacy, which makes data usage challenging. On the other side, this also increases the possibility of brand-new issues in cities. A clever, effective and efficient urban monitoring system is required to address possible challenges that may arise in urban settings. In the smart city concept, which makes use of sensors, one strategy that might be used in IoT and cloud computing is to monitor and gather data on problems that develop in cities in real-time. However, it will take a while and be rather expensive to install IoT and sensors throughout the city. The Mobile Crowd-Sensing (MCS) method is proposed to be used in this study to retrieve and gather data on issues that arise in metropolitan areas from citizen reports made using mobile devices. And we suggest a budget-constrained, reputation-based collaborative user recruitment (RCUR) procedure for a MCS system. To construct an edge-assisted MCS system in urban situations, we first integrate edge computing into MCS. We also examine how user reputation affects user recruitment. Finally, we create a collaborative sensing approach using the edge nodes’ sensing capabilities. © 2023 by the authors of this article. Published under CC-BY.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Fault Detection using a Reduced Data-Driven Methods

Fault Detection using a Reduced Data-Driven Methods

引用

Computing and Information technology (ICCIT-1441), 2020 International Conference on

作者： Maroua Said Okba Taouali University of Sousse Tunisia ENISO Electrical Departement National school of Engineering Sousse Computer Engineering Department Faculty of Computer and Information Technology University of Tabuk Tabuk Saudi Arabia

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

In this paper, the fault detection phase is presented using a reduced number of observations. Indeed, monitoring systems is a very important task, which helps to characterize normal variations and detect or determine any abnormal changes. In this area, Data driven approach is a very important context for system monitoring based on the principle of machine learning. Howver, the main objective of this paper is to validate the fault detection performance using two methods based on (Kernel Partial Least Square) KPLS method with optimal values determined by Tabu search algorithm. Then, a complete description is provided exclusively of the techniques used in static mode and in dynamic mode. In this work, a static mode is presented with the Reduced KPLS (RKPLS) method and the Moving Window RKPLS (MW-RKPLS) method in dynamic mode. The detection performance of these methods are compared and evaluated using a CSTR chemical process.

关键词： Machine learning algorithms Fault detection Optimization methods Machine learning Chemical reactions Search problems Indexes Kernel Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

RFBES at SemEval-2024 Task 8: Investigating Syntactic and Semantic Features for Distinguishing AI-Generated and Human-Written Texts

arXiv

引用

arXiv 2024年

作者： Rad, Mohammad Heydari Farsi, Farhan Bali, Shayan Etezadi, Romina Shamsfard, Mehrnoush Computer Engineering Department Amirkabir University of Technology Tehran Iran School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran

Nowadays, the usage of Large Language Models (LLMs) has increased, and LLMs have been used to generate texts in different languages and for different tasks. Additionally, due to the participation of remarkable companies such as Google and OpenAI, LLMs are now more accessible, and people can easily use them. However, an important issue is how we can detect AI-generated texts from human-written ones. In this article, we have investigated the problem of AI-generated text detection from two different aspects: semantics and syntax. Finally, we presented an AI model that can distinguish AI-generated texts from human-written ones with high accuracy on both multilingual and monolingual tasks using the M4 dataset. According to our results, using a semantic approach would be more helpful for detection. However, there is a lot of room for improvement in the syntactic approach, and it would be a good approach for future work. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

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：