检索结果-内蒙古大学图书馆

Explainable Artificial Intelligence in Malignant Lymphoma Classification: Optimized DenseNet121 Deep Learning Approach with Particle Swarm Optimization and Genetic Algorithm.

引用

IEEE Access 2025年 13卷 98639-98655页

作者： Elwahsh, Haitham Bakhiet, Ali Alirr, Omar Ibrahim Khalifa, Tarek Alsabaan, Maazen Ibrahem, Mohamed I. El-Shafeiy, Engy Applied Science Private University Faculty of Information Technology Amman 11931 Jordan Kafrelsheikh University Faculty of Computers and Information Department of Computer Science Kafrelsheikh 33516 Egypt Badya University Faculty of Computing and Data Science Egypt American University of the Middle East College of Engineering and Technology Egaila 54200 Kuwait King Saud University College of Computer and Information Sciences Department of Computer Engineering P.O.Box 51178 Riyadh 11543 Saudi Arabia Augusta University School of Computer and Cyber Sciences Augusta 30912 GA United States University of Sadat City Faculty of Computers and Artificial Intelligence Department of Computer Science Sadat City 32897 Egypt

One of the forms of cancerous tumors that can be fatal is malignant lymphoma. Histopathological examination of lymphoma tissue images is a diagnostic technique for detecting malignant lymphomas. Differentiating lymphoma subtypes manually is challenging due to their similar morphological features. This paper introduces a cutting-edge methodology for classifying malignant lymphoma using Hematoxylin and Eosin (H&E)-stained biopsy images. It integrates feature reduction using Particle Swarm Optimization (PSO) and model optimization through a Genetic Algorithm (GA) in conjunction with DenseNet121 architecture. The DenseNet121 model, which employs four distinct freezing strategies, extracts features from the images, generating an initial 4096 features per image. These features are subsequently reduced by more than 54.4% using PSO, thereby enhancing the computational efficiency without sacrificing classification accuracy. The trained GA Deep Neural Network (DNN) model achieved a significant score of 96.77% testing accuracy with high precision, recall and F1 scores as well. The results after comparison with other existing state-of-the-art models showed the usefulness of the proposed approach in terms of performance as well as the consumption of resources for medical imaging classification. It is recommended that the combined application of PSO for feature reduction and GA for model optimization can be successfully used for improving accuracy rate of such algorithms while reducing computation time. This technique is expected to be further developed and applied in different tasks of computer aided diagnosis of malignant lymphoma in particular the tasks with requirements for explainable artificial intelligence. © 2013 IEEE.

关键词： Artificial intelligent Deep Learning Genetic Algorithm malignant lymphoma Optimized DenseNet121 Particle Swarm Optimization

来源：评论

学校读者我要写书评

暂无评论

Applications of Explainable Artificial Intelligent Algorithms to Age-related Macular Degeneration Diagnosis: A Case Study Based on CNN, Attention, and CAM Mechanism 1

Applications of Explainable Artificial Intelligent Algorithm...

引用

1st IEEE International Conference on Contemporary Computing and Communications, InC4 2023

作者： Wang, Mini Lin, Zhiyuan Zhou, Junjie Xing, Lumin Zeng, Peijin The Faculty of Data Science City University of Macau China The Faculty of Medicine The Chinese University of Hong Kong Hong Kong Zhuhai China Guangdong Twise Information Technology Co. Ltd Zhuhai China Beijing Institute of Technology Zhuhai China The Department of AI and Big Data Application Zhuhai Institute of Advanced Technology Chinese Academy of Sciences Zhuhai China Hong Kong Baptist University Hong Kong The First Affiliated Hospital of Shandong First Medical University and Shandong Provincial Qianfoshan Hospital Jinan China

ISBN: (纸本)9798350335774

The recent years have witnessed extensive research on Explainable Artificial Intelligence (XAI) algorithms in the field of ophthalmology. This paper introduces an improved deep learning model for Age-related Macular Degeneration (AMD) classification by incorporating XAI techniques such as Convolutional Neural Networks (CNN), Attention, and Class Activation Mapping (CAM). The study compares the model's explainable indicators, accuracy, and test time (per image) with those of the original model. The results demonstrate that the utilization of interpretable algorithms in ophthalmology holds significant clinical potential, serving as an effective means to establish trust between artificial intelligence and the medical field. Moreover, it proves to be a viable approach to enhance accuracy. Therefore, this research contributes to the reference significance of XAI application in ophthalmology. © 2023 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Leveraging CNN-Transformer Hybrid Architecture for Accurate Breast Tumor Segmentation in Mammograms

Leveraging CNN-Transformer Hybrid Architecture for Accurate ...

引用

Women in data science at Prince Sultan University (WiDS PSU), International Conference of

作者： Mudassar Ali Muhammad Zeeshan Tahir Iqra Mariam Khadija Nawaz Tariq Mahmood Samia Allaoua Chelloug College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Department of Computer Science and Technology Zhejiang University Hangzhou China School of Electronics and Information Engineering Liaoning University of Technology Jinzhou China Faculty of Information Sciences University of Education Vehari Pakistan Artificial Intelligence and Data Analytics Lab CCIS PSU Riyadh SA Department of Information Technology CCIS PNU Riyadh SA

ISBN: (数字)9798331520922

ISBN: (纸本)9798331520939

Breast cancer detection through mammograms is very crucial for early diagnosis, and tumor segmentation is an important step in treatment planning. This paper proposes a novel approach by combining CNNs with transformers, which we call the Hybrid CNN + Transformer model, for the task of breast tumor segmentation. It leverages the strengths of CNN s in local feature extraction to capture fine details, such as tumor boundaries, and combines them with transformers that model long-range dependencies and contextual relationships across images for the exact delineation of tumor regions in complex tissue structures. Our methodology will be tested on the high-quality mammog-raphy dataset annotated with both benign and malignant lesions, the so-called INbreast dataset. Herein, the CNN backbone-first for instance, ResNet or EfficientNet-extracts the input mammo-gram hierarchically; features are fed into a transformer layer in order to capture global dependencies, after which the final segmentation mask is generated by using a U-Net style decoder for a pixel-wise tumor classification. The segmentation accuracies of our models demonstrated the significant improvement achieved in tumor segmentation, using Hybrid CNN + Transformer when compared with tra-ditional CNN-based models on challenging tumor boundaries and complex tissue patterns. An accurate, robust, completely automatic method for tumor segmentation will thus enable improved diagnostic feasibility on clinical grounds. Furthermore, the combination of learning at both local and global features improved generalizability to previously unseen mammogram images and therefore strengthened clinical applicability.

关键词： Image segmentation Adaptation models Accuracy Breast tumors Computational modeling Transformers Mammography Breast cancer Convolutional neural networks Tumors

来源：评论

学校读者我要写书评

暂无评论

Empowering Smart Environments: Dynamic Beamforming for Optimal TUAV Coverage in B5G Networks 3

Empowering Smart Environments: Dynamic Beamforming for Optim...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Saif, Abdu Shahida Mohd Shah, Nor Ameen Fattah, Soreen Kumar, Santosh Saad Al Khuraib, Ali Hamood Alsamhi, Saeed Taiz University Faculty of Engineering& It Taiz Yemen Universiti Tun Hussein Onn Malaysia Faculty of Engineering Technology Johor Malaysia College of Medicine University of Babylon Babylon Iraq Iiit Naya Raipur Department of Cse Chhattisgarh India Information Science and Technology Ukm Riyadh Saudi Arabia University of Galway Insight Centre for Data Analytics Galway Ireland Ibb University Ibb Yemen

ISBN: (纸本)9798350305333

Integrating unmanned aerial vehicles (UAVs) into smart environments has ushered in a new era of energy harvesting possibilities. This paper explores the collaborative potential of tethered and untethered UAVs for optimizing energy harvesting in smart environments. Environments with various sensors and IoT devices demand sustainable and efficient energy sources. Tethered UAVs, with a constant power supply, and untethered UAVs, equipped with onboard energy systems, offer a complementary synergy that can revolutionize energy-harvesting strategies. This paper delves into the technical aspects of UAV collaboration, including communication protocols, coordination algorithms, and energy-sharing mechanisms. We present experimental results demonstrating the enhanced efficiency achieved through the harmony of the UAV types. Our findings contribute to the growing knowledge of UAV technology and offer practical insights into the sustainable development of smart environments. By harnessing the power of the skies through tethered and untethered UAV harmony, we unlock new opportunities for reliable and eco-friendly energy harvesting, paving the way for a smarter and greener future. © 2023 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

A Learning Support Method for Multi-threaded Programs Using Trace Tables

arXiv

引用

arXiv 2024年

作者： Murata, Takumi Hashiura, Hiroaki Electronics Information and Media Engineering Major Graduate School of Engineering Nippon Institute of Technology Saitama Japan Dept. of Data Science Faculty of Advanced Engineering Nippon Institute of Technology Saitama Japan

Multi-threaded programs are expected to improve responsiveness and conserve resources by dividing an application process into multiple threads for concurrent processing. However, due to scheduling and the interaction of multiple threads, their runtime behavior is more complex than that of single-threaded programs, making which makes debugging difficult unless the concepts specific to multi-threaded programs and the execution order of instructions can be understood. In this paper, we propose a learning tool for multi-threaded programs using trace tables. Copyright © 2024, The Authors. All rights reserved.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Advanced Convolutional Neural Networks for Plastic Classification in Recycling Systems

Advanced Convolutional Neural Networks for Plastic Classific...

引用

International Conference on Computer science and Engineering (UBMK)

作者： Nazym Alimbekova Ainur Zhumadillayeva Sunggat Aiymbay Faculty of Information Technology L.N. Gumilyov Eurasian National University Astana International University Astana Kazakhstan Faculty of Information Technology L.N. Gumilyov Eurasian National University Astana Kazakhstan Department of Computational and Data Science Astana IT University Astana Kazakhstan

ISBN: (数字)9798350365887

ISBN: (纸本)9798350365894

This research examines the utilization of sophisticated convolutional neural networks (CNN) for the automated categorization of plastic waste in order to augment recycling effectiveness. A comparative analysis of three CNN architectures - MobileNet, ResNet-34, and EfficientNet-B1 - was conducted, alongside the introduction of an innovative model, EfficientNet-SED, aimed at enhancing both accuracy and computational efficiency. Empirical evaluations utilizing a dataset comprised of plastic bottles revealed that EfficientNet-SED attained a classification accuracy of 99.1%, exceeding the performance metrics of the other models. These results underscore the potential of modern machine learning methodologies to refine waste sorting systems, thereby facilitating more efficient recycling practices and resource preservation.

关键词： Analytical models Accuracy Computational modeling Computer architecture Recycling Convolutional neural networks Resource management Plastic products Plastic waste Sorting

来源：评论

学校读者我要写书评

暂无评论

WIT-Greedy: Hardware System Design of Weighted ITerative Greedy Decoder for Surface Code

WIT-Greedy: Hardware System Design of Weighted ITerative Gre...

引用

Asia and South Pacific Design Automation Conference

作者： Wang Liao Yasunari Suzuki Teruo Tanimoto Yosuke Ueno Yuuki Tokunaga Photon Science Center the University of Tokyo Japan NTT Computer and Data Science Laboratories Japan Faculty of Information Science and Electrical Engineering Kyushu University Japan Graduate School of Information Science and Technology the University of Tokyo Japan

Large error rates of quantum bits (qubits) are one of the main difficulties in the development of quantum computing. Performing quantum error correction (QEC) with surface codes is considered the most promising approach to reduce the error rates of qubits effectively. To perform error correction, we need an error-decoding unit, which estimates errors in the noisy physical qubits repetitively, to create a robust logical qubit. While complicated graph-matching problems must be solved within a strict time restriction for the error decoding, several hardware implementations that satisfy the restriction at a large code distance have been proposed. However, the existing decoder designs are still challenging in reducing the logical error rate. This is because they assume that the error rates of physical qubits are uniform while they have large variations in practice. According to our numerical simulation based on the quantum chip with the largest qubit number, neglecting the non-uniform error properties of a real quantum chip in the decoding process induces significant degradation of the logical error rate and spoils the benefit of QEC. To take the non-uniformity into account, decoders need to solve matching problems on a weighted graph, but they are difficult to solve using the existing designs without exceeding the time limit of decoding. Therefore, a decoder that can treat both the non-uniform physical error rates and the large surface code is strongly demanded. In this paper, we propose a hardware design of decoding units for the surface code that can treat the non-identical error properties with small latency at a large code distance. The key idea of our design is 1) constructing a look-up table for calculating the shortest paths between nodes in a weighted graph and 2) enabling parallel processing during decoding. The implementation results in field programmable gate array (FPGA) indicate that our design scales up to code distance 11 within a microsecond-level delay,

关键词： Codes Error analysis Qubit Hardware Decoding Delays Table lookup

来源：评论

学校读者我要写书评

暂无评论

Assessing the Validity of Automated data Analysis Methods Based on Artificial Intelligence 3

Assessing the Validity of Automated Data Analysis Methods Ba...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Yuvaraj, K. Balakumar, P. Kadam, Prema S. Mishra, Prakash Raja Kumar, Jambi Ratna Verma, Anupama Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Information Technology Chennai India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Mangalayatan University Department of Management Jabalpur India Genba Sopanrao Moze College of Engineering Balewadi Department of Computer Engineering Maharashtra Pune India Usha Martin University Faculty of Business Mangagement & Commerce Ranchi India

ISBN: (纸本)9798350319125

Automated records analysis strategies primarily based on artificial intelligence (AI) have become increasingly famous in recent years because of their capability to quickly and effectively method enormous quantities of facts. However, concerns about the validity of those methods and their potential for introducing bias or mistakes have been raised. This study aims to assess the validity of automatic facts evaluation methods based on AI. It entails evaluating those methods' accuracy, reliability, and consistency compared to conventional guide evaluation methods. An expansion of study methods may be used, which includes experimental research, case research, and surveys. Facts will be gathered from computerized AI techniques and manual strategies, after which they will be compared and evaluated to decide the extent of agreement between them. One capability mission in this research is the dearth of a gold standard for statistics analysis. Unlike in medical fields wherein there may be a clean popular for prognosis, information analysis methods can also vary depending on the unique dataset and research question. Expanding a hard and fast of criteria or metrics for evaluating the validity of different AI techniques is essential. Another challenge is the rapidly evolving nature of the AI era. As new techniques and algorithms constantly evolve, keeping up with modern-day improvements and their potential impact on records analysis could be challenging. © 2023 IEEE.

关键词： evolved mission modern potential research

来源：评论

学校读者我要写书评

暂无评论

An empirical review of Machine Learning models for Energy Optimizations in IoT Networks

An empirical review of Machine Learning models for Energy Op...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Pallavi Charde Bhupesh B. Lonkar Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Sawangi Wardha India Department of Information Technology Datta Meghe Institute of Engineering Technology & Research Sawangi Wardha

The Internet of Things (IoT) has transformed how users interact with their devices and enabled the accumulation of enormous quantities of data from various sources. There has been an increase in energy consumption due to the expanding use of IoT devices, resulting in environmental concerns and higher operational costs. The use of Machine Learning (ML) algorithms to optimize energy consumption in IoT networks is widespread for different scenarios. This paper empirically analyzes the most widely used machine learning models for energy optimization in IoT networks. The researchers evaluate the efficacy of various ML models regarding energy efficiency, precision, and scalability. The review includes a summary of the most recent research in this field and a comparison of different algorithms, including Decision Trees, Random Forests, Support Vector Machines, Neural Networks, and Deep Learning methods. In addition, this paper discusses the difficulties and limitations of ML-based energy optimization in IoT networks, including data acquisition and processing, model selection, and scalability levels. Finally, this paper presents recommendations for future research and prospective machine-learning applications in energy optimization for IoT networks. This review emphasizes the potential of machine learning (ML) models to reduce energy consumption in IoT networks. It provides researchers and practitioners with insight into this field under real-time scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-aware data Fusion and Prediction for Smart City Services in Edge Computing Environment 15

Privacy-aware Data Fusion and Prediction for Smart City Serv...

引用

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart data, Smartdata 2022

作者： Qi, Lianyong Chi, Xiaoxiao Zhou, Xiaokang Liu, Qi Dai, Fei Xu, Xiaolong Zhang, Xuyun School of Computer Science Qufu Normal University China Faculty of Data Science Shiga University Japan Riken Center for Advanced Intelligence Project Japan School of Computer and Software Nanjing University of Information Science and Technology China School of Big Data and Intelligence Engineering Southwest Forestry University China Department of Computing Macquarie University Australia

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

With fast development of Cyber Physical System, the variety and volume of data generated from different edge servers are fairly considerable. Mining and exploiting the data would definitely bring huge advantages. However, there are two major issues exposed in the process. First, utilizing the data with high efficiency is challenging in edge computing environment. Second, data from multiple edge servers often contain sensitive information such as user preferences, which will give rise to privacy breach risks when using the data. Locality-Sensitive Hashing and amplified technology are utilized for dealing with two problems. In this paper, we propose a novel privacy-protection approach named SRchain-LSH in edge computing environment which is based on amplified Locality-Sensitive Hashing technique. In order to verify high accuracy and efficiency of our proposal, large sets of experiments are conducted. According to experimental results, our proposal shows better performance than those of comparative methods in terms of MAE , RMSE and time costs. For our method, the best value of MAE is about 0.41 and time cost is about 0.1 seconds, which are more accurate and efficient than comparative methods. © 2022 IEEE.

关键词： Smart city

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：