检索结果-内蒙古大学图书馆

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

COMPETING FAILURE MODELING AND ANALYSIS OF PHASED-MISSION UNMANNED AERIAL VEHICLES 14

COMPETING FAILURE MODELING AND ANALYSIS OF PHASED-MISSION UN...

引用

14th International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, QR2MSE 2024

作者： Wang, Sidi Zhao, Guilin Mandava, Lavanya Meng, Sa School of Computing & Artificial Intelligence Southwest Jiaotong University Chengdu China Computer Science & Information Systems Department Bradley University Peoria United States

ISBN: (纸本)9781837242672

Unmanned aerial vehicles (UAVs) can be outfitted with ground sensors to offer substantial benefits across a range of applications. Nonetheless, ensuring their reliability in delivering services throughout the designated mission time remains crucial. UAV integrated systems are typically phased-mission systems, which undergo multiple, consecutive, non-overlapping operational phases, each with unique system configurations and component behaviors due to changing tasks and environmental conditions. Components within UAV-integrated systems exhibit statistical dependencies across phases. Furthermore, UAV-integrated systems usually employ relayed communications, where some UAVs (dependent components) rely on other UAVs (relays) to communicate with the base station. If the relay fails, dependent components may increase transmission power to establish a direct link with the base station, but only for a limited and uncertain duration until their power is depleted below the necessary threshold. The competition between isolation and propagated failures is also considered. This paper proposes a combinatorial reliability modeling methodology for phased-mission UAVs subject to competition and random isolation time. The methodology applies to arbitrary types of time-to-failure and time-to-isolation distributions for components. A detailed case study demonstrates the approach. The correctness of the proposed method is verified through Monte Carlo simulations. © The Institution of Engineering & Technology 2024.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Real-Time Road Damage Detection and Infrastructure Evaluation Leveraging Unmanned Aerial Vehicles and Tiny Machine Learning

引用

IEEE Internet of Things Journal 2024年第12期11卷 21347-21358页

作者： Khan, Muhammad Waseem Obaidat, Mohammad S. Mahmood, Khalid Batool, Dania Badar, Hafiz Muhammad Sanaullah Aamir, Muhammad Gao, Wu Comsats University Islamabad Sahiwal Campus Department Of Computer Science Sahiwal57000 Pakistan Superior University Department Of Computer Science Lahore54000 Pakistan The University Of Jordan King Abdullah Ii School Of Information Technology Amman11942 Jordan University Of Science And Technology Beijing School Of Communication And Computing Engineering Beijing100083 China Amity University Amity School Of Engineering And Technology Uttar Pradesh Noida201301 India National Yunlin University Of Science And Technology Graduate School Of Intelligent Data Science Douliu64002 Taiwan University Of Palermo Department Of Engineering Palermo90133 Italy Emerson University Department Of Emerging Computing Technologies Multan60000 Pakistan Northwestern Polytechnical University Center For Bio-Inspired System-on-Chip School Of Computer Science Xi'an710060 China

Road damage detection (RDD) through computer vision and deep learning techniques can ensure the safety of vehicles and humans on the roads. Integrating unmanned aerial vehicles (UAVs) in RDD and infrastructure evaluation (IE) has also emerged as a key enabler, contributing significantly to data acquisition and real-time monitoring of road damages, such as potholes, cracks, and surface anomalies, facilitating proactive maintenance and improved road conditions. These UAVs are low-powered and resource-constrained devices that work autonomously to perform pattern detection and decision making leveraging tiny machine learning (Tiny ML) algorithms. These Tiny ML algorithms are designed to run on edge devices, IoT devices, UAVs, etc. In this study, the RDD2022 data set collected using UAVs and dashboard cameras of vehicles was utilized to train pure and mixed models that exhibit class instance imbalance in certain classes which is addressed by implementing data augmentation as a regularization technique. State-of-the-art two-stage detectors: Faster R-CNN ResNet101 and one-stage detectors: SSD MobileNet V1 FPN, YOLOv5, and Efficientdet D1 are employed. The results indicate that the two-stage detector achieved an impressive mean average precision (mAP) of 88.49% overall and 96.62% for focused classes. Notably, the state-of-the-art Efficientdet D1 approach achieved a competitive mAP of 86.47% overall and 95.12% for focused classes, with significantly lower computational cost. These findings highlight the potential of advanced object detection techniques, particularly Efficientdet D1, to enhance the accuracy and efficiency of RDD systems, thereby improving passenger safety and overall performance. © 2014 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Kathakali Mudras: An AI-Enhanced Predictive Approach 11

Kathakali Mudras: An AI-Enhanced Predictive Approach

引用

11th International Conference on Soft computing and Machine Intelligence, ISCMI 2024

作者： Mulerikkal, Jaison Paul Janani, K. Sreelakshmi, P.S. James, Divya Lakshmi, K.S. Sajanraj, T.D. Binu, A. Department of Information Technology India Rajagiri School of Engineering & Technology Kochi India Department of Computer Science and Engineering India Department of Computer Science and Business Systems India Department of Artificial Intelligence and Data Science India Department of Computer Science Loughborough University Leicester United Kingdom

ISBN: (纸本)9798331518127

The goal of this research is to integrate an artificial intelligence framework for predicting Kathakali mudras, a crucial component of the traditional Indian dance style that is renowned for its complex hand and facial motions. Our goal is to protect and improve the accessibility of this traditional art form by utilising deep learning technology. To be more precise, we used the object identification model YOLOv8 together with convolutional neural networks (CNNs) like VGG 19, Inception V3, and ResNet 152 to predict and analyse Kathakali mudras. Furthermore, Few-shot learning (FSL) and support vector machines (SVMs) were used to offer a comparative viewpoint on the efficacy of machine learning method in this situation. The study entailed a thorough analysis of how well-performing different deep learning techniques performed. The predictive accuracy of VGG 19, Inception V3, and ResNet 152 for intricate mudras of Kathakali was subjected to a thorough evaluation process. In addition, an evaluation of YOLOv8's real-time object identification capabilities was conducted in order to investigate its potential in live performance circumstances. The results of the experiment showed that VGG 19 performed better than the other models and had the highest accuracy in mudra prediction. As a result, VGG 19 was chosen as the best algorithm for this particular application. The results of this study demonstrate how artificial intelligence (AI) technologies may support and preserve traditional artistic forms. This AI-integrated framework is a useful tool for scholars, educators, and dancers, promoting a deeper knowledge and enjoyment of this cultural legacy through its accurate analysis and prediction of Kathakali mudras. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Responsibility Attribution in Human Interactions with Everyday AI systems 25

Responsibility Attribution in Human Interactions with Everyd...

引用

2025 CHI Conference on Human Factors in computing systems, CHI 2025

作者： Brailsford, Joe Vetere, Frank Velloso, Eduardo School of Computing and Information Systems The University of Melbourne Melbourne Australia School of Computer Science University of Sydney Sydney NSW Australia

ISBN: (纸本)9798400713941

How do individuals perceive AI systems as responsible entities in everyday collaborations between humans and AI? Drawing on psychological literature from attribution theory, praise-blame asymmetries and negativity bias, this study investigated the effects of perspective (actor vs observer) and outcome favorability (positive vs negative) on how participants (N=321) attributed responsibility for outcomes resulting from shared human-AI decision-making. Both Bayesian modelling and reflexive thematic analysis of results revealed that, overall, participants were more likely to attribute greater responsibility to the AI systems. When the outcome was positive, participants were more likely to ascribe shared responsibility to both Human and AI systems, rather than either separately. When the outcome was negative, participants were more likely to attribute responsibility to a single entity, but not consistently towards the human or the AI. These results build on the understanding of how individuals cast blame and praise for shared interactions involving AI systems. © 2025 Copyright held by the owner/author(s).

关键词： Algorithmic Decision-Making Artificial Intelligence Blame Human-AI Teams Praise Responsibility Attribution Responsible AI

来源：评论

学校读者我要写书评

暂无评论

Outage Prediction and Improvement in 6G for UAV Swarm Relays Using Machine Learning

引用

Progress In Electromagnetics Research B 2024年 107卷 33-45页

作者： Khalil, Hisham Ali, Gauhar Rahman, Saeed Ur Asim, Muhammad Affendi, Mohammed El Department of Intelligent Systems Faculty of Information Technology University of Lahore Pakistan EIAS Data Science and Block chain Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia School of Electronic Engineering Xidian University Xi’an China

The issue of signal outages in sub-THz frequency communication for future 6G networks is addressed by this research. A machine learning method is proposed, employing Random Forest and K-Means algorithms to predict the optimal frequency band and outage probabilities for UAV relays. Both space and frequency diversity are explored to enhance signal strength, and metasurface-carrying UAVs are introduced with a 16 × 16 mm2 design. This design significantly reduces the predicted outage probability from 0.1% to 0.0178%. Finally, triangular and hexagonal UAV swarm formations with metasurfaces are investigated, demonstrating improved performance through heatmap results. © (2024), (Electromagnetics Academy). All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Augmenting IoT Intrusion Detection System Performance Using Deep Neural Network

引用

computers, Materials & Continua 2023年第1期74卷 1351-1374页

作者： Nasir Sayed Muhammad Shoaib Waqas Ahmed Sultan Noman Qasem Abdullah M.Albarrak Faisal Saeed Department of Computer Science Islamia College PeshawarPeshawar25120Pakistan Department of Computer Science CECOS University of IT and Emerging SciencesPeshawar25000Pakistan Department of Electrical Engineering HITEC University TaxilaTaxila47080Pakistan Computer Science Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia DAAI Research Group Department of Computing and Data ScienceSchool of Computing and Digital TechnologyBirmingham City UniversityBirminghamB47XGUK

Due to their low power consumption and limited computing power,Internet of Things(IoT)devices are difficult to ***,the rapid growth of IoT devices in homes increases the risk of *** detection systems(IDS)are commonly employed to prevent *** systems detect incoming attacks and instantly notify users to allow for the implementation of appropriate *** have been made in the past to detect new attacks using machine learning and deep learning techniques,however,these efforts have been *** this paper,we propose two deep learning models to automatically detect various types of intrusion attacks in IoT ***,we experimentally evaluate the use of two Convolutional Neural Networks(CNN)to detect nine distinct types of attacks listed in the NF-UNSW-NB15-v2 *** accomplish this goal,the network stream data were initially converted to twodimensional images,which were then used to train the neural network *** also propose two baseline models to demonstrate the performance of the proposed ***,both models achieve high accuracy in detecting the majority of these nine attacks.

关键词： Internet of things intrusion detection system deep learning convolutional neural network supervised learning

来源：评论

学校读者我要写书评

暂无评论

Accountable Policy-Based Sanitizable Signature for Medical data Sharing 12

Accountable Policy-Based Sanitizable Signature for Medical D...

引用

12th International Conference on Communication and Network Security, ICCNS 2022

作者： Yang, Yang Wei, Zengtao Huang, Minming College of Computer and Data Science Fuzhou University China School of Computing and Information Systems Singapore Management University Singapore

ISBN: (纸本)9781450397520

With the Internet and cloud computing development, signed electronic medical data can be stored on the cloud server for flexible data sharing. However, the signed medical data contains much private information, and directly sharing the entire medical data may lead to privacy leakage. The sanitizable signatures can solve this problem well. However, in the existing sanitizable signature schemes, few schemes achieve access control to sanitizer while achieving invisibility and unlinkability. In addition, the existing schemes only consider a signer and a single sanitizer situation. If the sanitizer is not online or unwilling to perform the sanitization operation, the data cannot be sanitized in time. The existing methods to achieve the accountability of sanitizer cannot be directly expanded to the situation of multiple sanitizers because the existing methods are less flexible, and the signer is required to regenerate the signature to assign sanitization rights to a new sanitizer. We propose an accountable policy-based invisible and unlinkable sanitizable signature scheme to solve the above problems. This scheme contains a signer and multiple sanitizers and can achieve signer and multiple sanitizer accountability. Specifically, the medical data provider can specify the access policy when signing the data. Only those who meet the access policy can sanitize the signed data and generate valid signatures. When there is a dispute, not only can the medical data provider generate a proof tag, but all medical data sanitizers can also generate proof tags to identify the actual generator of the data-signature pair. In addition, this paper proposes an electronic medical data-sharing scheme based on the above-mentioned sanitizable signature. Finally, the security analysis and performance analysis show that the scheme of this paper is feasible. © 2022 ACM.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Greening Large Language Models of Code 46

Greening Large Language Models of Code

引用

46th ACM/IEEE International Conference on Software Engineering: Software Engineering in Society, ICSE-SEIS 2024

作者： Shi, Jieke Yang, Zhou Kang, Hong Jin Xu, Bowen He, Junda Lo, David School Of Computing And Information Systems Singapore Management University Singapore Department Of Computer Science University Of California Los Angeles United States Department Of Computer Science North Carolina State University Raleigh United States

ISBN: (纸本)9798400704994

Large language models of code have shown remarkable effectiveness across various software engineering tasks. Despite the availability of many cloud services built upon these powerful models, there remain several scenarios where developers cannot take full advantage of them, stemming from factors such as restricted or unreliable internet access, institutional privacy policies that prohibit external transmission of code to third-party vendors, and more. Therefore, developing a compact, efficient, and yet energy-saving model for deployment on developers' devices becomes essential. To this aim, we propose Avatar, a novel approach that crafts a deployable model from a large language model of code by optimizing it in terms of model size, inference latency, energy consumption, and carbon footprint while maintaining a comparable level of effectiveness (e.g., prediction accuracy on downstream tasks). The key idea of Avatar is to formulate the optimization of language models as a multi-objective configuration tuning problem and solve it with the help of a Satisfiability Modulo Theories (SMT) solver and a tailored optimization algorithm. The SMT solver is used to form an appropriate configuration space, while the optimization algorithm identifies the Pareto-optimal set of configurations for training the optimized models using knowledge distillation. We evaluate Avatar with two popular language models of code, i.e., CodeBERT and GraphCodeBERT, on two popular tasks, i.e., vulnerability prediction and clone detection. We use Avatar to produce optimized models with a small size (3 MB), which is 160× smaller than the original large models. On the two tasks, the optimized models significantly reduce the energy consumption (up to 184× less), carbon footprint (up to 157× less), and inference latency (up to 76× faster), with only a negligible loss in effectiveness (1.67%). © 2024 Copyright held by the owner/author(s).

关键词： Carbon footprint

来源：评论

学校读者我要写书评

暂无评论

Resource Exhaustion Attack Detection Scheme for WLAN Using Artificial Neural Network

引用

computers, Materials & Continua 2023年第3期74卷 5607-5623页

作者： Abdallah Elhigazi Abdallah Mosab Hamdan Shukor Abd Razak Fuad A.Ghalib Muzaffar Hamzah Suleman Khan Siddiq Ahmed Babikir Ali Mutaz H.H.Khairi Sayeed Salih Faculty of Engineering Future UniversityKhartoum 10553Sudan Faculty of Computing and Informatics Universiti Malaysia SabahKota Kinabalu88400Malaysia Information Assurance and Security Research School of ComputingUniversiti Teknologi MalaysiaJohor81310Malaysia School of Psychology and Computer Science University of Central LancashirePreston PR12HEUK Deaptement of Management Information Systems College of Administrative ScienceApplied Science UniversityAl Eker623Bahrain Deaptement of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh11461Saudi Arabia

IEEE 802.11 Wi-Fi networks are prone to many denial of service(DoS)attacks due to vulnerabilities at the media access control(MAC)layer of the 802.11 *** to the data transmission nature of the wireless local area network(WLAN)through radio waves,its communication is exposed to the possibility of being attacked by illegitimate ***,the security design of the wireless structure is vulnerable to versatile *** example,the attacker can imitate genuine features,rendering classificationbased methods inaccurate in differentiating between real and false *** security standards have been proposed over the last decades to overcome many wireless network attacks,effectively detecting such attacks is crucial in today’s real-world *** paper presents a novel resource exhaustion attack detection scheme(READS)to detect resource exhaustion attacks *** proposed scheme can differentiate between the genuine and fake management frames in the early stages of the attack such that access points can effectively mitigate the consequences of the *** scheme is built through learning from clustered samples using artificial neural networks to identify the genuine and rogue resource exhaustion management frames effectively and efficiently in *** proposed scheme consists of four modules whichmake it capable to alleviates the attack impact more effectively than the related *** experimental results show the effectiveness of the proposed technique by gaining an 89.11%improvement compared to the existing works in terms of detection.

关键词： 802.11 media access control(MAC) wireless local area network(WLAN) artificial neural network denial-of-service(DoS)

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：