检索结果-内蒙古大学图书馆

Skin cancer detection with MobileNet-based transfer learning and MixNets for enhanced diagnosis

Neural Computing and Applications 2024年第34期36卷 21383-21413页

作者： Zakariah, Mohammed Al-Razgan, Muna Alfakih, Taha Department of Computer Sciences and Engineering College of Applied Science King Saud University Riyadh11543 Saudi Arabia Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11345 Saudi Arabia Department of Information Systems College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia

Skin cancer poses a significant health hazard, necessitating the utilization of advanced diagnostic methodologies to facilitate timely detection, owing to its escalating prevalence in recent years. This paper proposes a novel approach to tackle the issue by introducing a method for detecting skin cancer that uses MixNets to enhance diagnosis and leverages mobile network-based transfer learning. Skin cancer has diverse forms, each distinguishable by its structural attributes, morphological characteristics, texture, and coloration. The pressing demand for accurate and efficient diagnostic instruments has spurred the investigation of novel techniques. The present study utilizes the ISIC dataset, comprising a validation set of 660 images and a training set of 2637 images. Moreover, the research employs a combination of MixNets and mobile network-based transfer learning as its chosen approach. Transfer learning is a technique that leverages preexisting models to enhance the diagnostic capabilities of the proposed system. Integrating MobileNet and MixNets allows for utilizing their respective functionalities, resulting in a dual-model methodology that enhances the comprehensiveness of skin cancer diagnosis. The results demonstrate impressive performance metrics, with MobileNet and MixNets models, and the proposed approach achieves an outstanding accuracy rate of 99.58%. The above findings underscore the efficacy of the dual-model method in effectively discerning between benign and malignant skin lesions. Moreover, the present study aims to examine the potential integration of emerging technologies to enhance the accuracy and practicality of diagnostics within real-world healthcare settings. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Reduced Spread Risk of COVID-19 based on Tracking System Monitoring in WSNs 16

Reduced Spread Risk of COVID-19 based on Tracking System Mon...

引用

16th International Conference on Developments in esystems Engineering, DeSE 2023

作者： Fahed, Majed H. Rashid, Ahmed N. University of Anbar Computer Sciences College of Computer and Information Technology Iraq University of Anbar Computer Networking Systems College of Computer and Information Technology Iraq

ISBN: (纸本)9798350381344

The phrase 'COVID-19' has become the most popular and highly searched term on Google since its emergence in November 2019. The world must combat this pandemic. With advancements in mobile technology and sensors, Developing Internet of Things (IoT)-based healthcare solutions is now feasible. Proactive as well as preventative, these new systems, are in contrast to the traditional reactive healthcare systems. In this study, a paradigm based on the Internet of Things is proposed for detecting COVID-19 suspects. The framework presented in this research focuses on predicting COVID-19 in its early stages. To determine whether the virus is present, it uses health measurements collected from sensors and other Internet of Things devices. By gathering symptom data related to COVID-19, the behavior of the virus can be better understood. Four machine learning models are introduced in this paper: CatBoost, Decision Tree, Random Forest, and Logistic Regression. These models are used to create a Diagnostic Learning Classifier (DLC) model. The top three performing models, Decision Tree, Logistic Regression, and CatBoost, are combined using a weighted average or majority voting approach, depending on the nature of the problem. The DLC model is compared to base models such as Random Forest, Decision Tree, Logistic Regression, and CatBoost, using multiple evaluation criteria. The goal of this ensemble model is to increase forecast accuracy by utilizing the variety and advantages of the chosen models. It delivers great diagnostic accuracy when used as a machine learning model on the gathered data. Notably, the DLC classifier achieves an accuracy of 91%, followed by Random Forest (86%), CatBoost (85%), Logistic Regression (84%), and Decision Tree (82%). These results demonstrate the effectiveness of the voting classifier in efficiently managing COVID-19 by accurately diagnosing patients and notifying health authorities of suspected cases. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Average reward adjusted discounted reinforcement learning

引用

Neural Computing and Applications 2025年 1-32页

作者： Schneckenreither, Manuel Moser, Georg Department of Information Systems Production and Logistics Management University of Innsbruck Universitaetsstrasse 15 Innsbruck6020 Austria Computer Science University of Innsbruck Technikerstrasse 21a Innsbruck6020 Austria

In this paper, we provide a novel view upon reinforcement learning (RL for short). In particular, we are interested in applications of RL in use cases, where average rewards may be nonzero. While RL methodologies have been extensively researched upon, this particular application area has only received scarce attention in the Literature. In part, our motivation stems from applications in Operation Research (OR for short), where it is typically the case that rewards are profit derived. Similar use cases can be found in more general applications in economics. Based on a principled study of the mathematical background of discounted reinforcement learning we establish a novel adaptation of standard RL, dubbed Average Reward Adjusted Discounted Reinforcement Learning (ARAL for short). Our approach stems from revisiting the Laurent Series expansion of the discounted state value and a subsequent reformulation of the target function guiding the learning process. While the theoretical advance is arguably incremental, we provide ample experimental evidence that the thus obtained novel RL methodology compares favorable to well-established techniques like Q-learning or R-learning. © The Author(s) 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach to Raising Digital Literacy among Adolescents in KSA Using a Mobile Application

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第5期19卷 98-114页

作者： Benaida, Mohamed Bin Youssef Shaheen, Abdul Rahman Alam, Tanweer Bin Saad Khalifa, Abdul Hakam Faculty of Computer and Information Systems Islamic University of Madinah Madinah Saudi Arabia Department of Education College of Arabic Language and Human Studies Islamic University of Madinah Madinah Saudi Arabia

As digital technologies and the Internet evolve, digital issues are becoming more prevalent and are a serious concern due to their increased level of integration in our daily lives. Many users lack the necessary digital literacy to protect themselves and their communities from such issues. Background research reveals that adolescents in Saudi Arabia are particularly vulnerable to these issues, also supported by the studies pre-test for students (15.8%). This highlights a gap regarding preventative measures that researchers aim to fill. This study investigates the effectiveness of integrating a dedicated mobile application focused on raising awareness regarding digital issues such as cyberbullying within a hybrid teaching framework amongst primary and middle school students in Saudi Arabia. The application’s features, including but not limited to pre-tests, post-tests, lecture material, and progress monitoring, along with its ease of use, are designed to efficiently achieve digital issue learning outcomes. To assess this hybrid approach toward raising awareness of digital issues, this study gathers 30 participants and splits them into three groups: group one (hybrid), group two (traditional), and group three (online only). The results, which were analysed via one-way analysis of variance (ANOVA) and Tukey’s honest significant difference (HSD) post-hoc test, demonstrate a significant advantage in the increased level of awareness of students from the first group. This indicates that our mobile application in hybrid settings is significantly more effective in enhancing knowledge retention amongst students and raising their level of awareness of digital issues. © 2025 by the authors of this article.

关键词： digital issue education learning mobile application

来源：评论

学校读者我要写书评

暂无评论

Designing a Blockchain-based System for Wholesale Central Bank Digital Currency 7

Designing a Blockchain-based System for Wholesale Central Ba...

引用

7th International Conference on New Media Studies, CONMEDIA 2023

作者： Taufik, Derryl Kusuma, Marchel Budi Gunawan, Alexander Agung Santoso Richard School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia

ISBN: (纸本)9798350307504

Driven by advancements in financial technology, Central Bank Digital Currency (CBDC) has garnered significant interest, with over eighty percent of central banks worldwide exploring its potential in 2021. This paper aims to design and implement a wholesale Central Bank Digital Currency (w-CBDC) prototype using the Hyperledger Besu, an Ethereum Virtual Machine-based blockchain platform. To extend the contribution of this paper, an experiment is conducted by creating smart contracts as the basis of digital currency. The smart contract will handle w-CBDC functionalities, such as issuance, redemption, transfer, and Delivery versus Payment (DvP). The results show that implementing w-CBDC functionalities in Hyperledger Besu private blockchain can address the required functionalities. However, privacy remains a notable concern, as anyone running the node can see all the transaction activities on the blockchain. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Language-Independent Text Tokenization Using Unsupervised Deep Learning

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 321-334页

作者： Hanan A.Hosni Mahmoud Alaaeldin M.Hafez Eatedal Alabdulkreem Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computer and Information SciencesKing Saud UniversityRiyadhSaudi Arabia

Languages–independent text tokenization can aid in classification of languages with few *** is a global research effort to generate text classification for any *** text classification is a slow ***-quently,the text summary generation of different languages,using machine text classification,has been considered in recent *** is no research on the machine text classification for many languages such as Czech,Rome,*** research proposes a cross-language text tokenization model using a Transformer *** proposed Transformer employs an encoder that has ten layers with self-attention encoding and a feedforward *** model improves the efficiency of text classification by providing a draft text classification for a number of *** also propose a novel Sub-Word tokenization model with frequent vocabulary usage in the *** Sub-Word Byte-Pair Tokenization technique(SBPT)utilizes the sharing of the vocabulary of one sentence with other *** Sub-Word tokenization model enhances the performance of other Sub-Word tokenization models such pair encoding model by+10%using precision metric.

关键词： Text classification language-independent tokenization sub word tokenization

来源：评论

学校读者我要写书评

暂无评论

Airstacknet: A Stacking Ensemble-Based Approach for Air Quality Prediction

引用

computers, Materials & Continua 2023年第1期74卷 2073-2096页

作者： Amel Ksibi Amina Salhi Ala Saleh Alluhaidan Sahar A.El-Rahman Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadhSaudi Arabia Electrical Engineering Department Faculty of Engineering-ShoubraBenha UniversityCairoEgypt

The quality of the airwe breathe during the courses of our daily lives has a significant impact on our health and well-being as ***,personal air quality measurement remains *** this study,we investigate the use of first-person photos for the prediction of air *** main idea is to harness the power of a generalized stacking approach and the importance of haze features extracted from first-person images to create an efficient new stacking model called AirStackNet for air pollution *** consists of two layers and four regression models,where the first layer generates meta-data fromLight Gradient Boosting Machine(Light-GBM),Extreme Gradient Boosting Regression(XGBoost)and CatBoost Regression(CatBoost),whereas the second layer computes the final prediction from the meta-data of the first layer using Extra Tree Regression(ET).The performance of the proposed AirStackNet model is validated using public Personal Air Quality Dataset(PAQD).Our experiments are evaluated using Mean Absolute Error(MAE),Root Mean Square Error(RMSE),Coefficient of Determination(R2),Mean Squared Error(MSE),Root Mean Squared Logarithmic Error(RMSLE),and Mean Absolute Percentage Error(MAPE).Experimental Results indicate that the proposed AirStackNet model not only can effectively improve air pollution prediction performance by overcoming the Bias-Variance tradeoff,but also outperforms baseline and state of the art models.

关键词： Personal air quality prediction airstacknet ensemble learning feature extraction stacking

来源：评论

学校读者我要写书评

暂无评论

An information-Dense Summary and Prediction Model Based on Machine Learning for the Atherosclerotic Heart Disease 24

An Information-Dense Summary and Prediction Model Based on M...

引用

24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023

作者： Miranda, Eka Madyatmadja, Evaristus Didik Sano, Albert Verasius Dian Alvand, Khalfani Wijaya, Marcel Pretycia, Valen Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350313956

According to WHO, cardiovascular illnesses are the main cause of death globally, killing 17.9 million people every year. Machine learning analysis of patients' Electronic Medical Records (EMR) data was helpful for disease risk prediction. Goal of our research was for constructing machine learning-based prediction model for atherosclerotic heart disease prediction. This research investigated machine learning algorithms, namely AdaBoost, Random Forest and Naive Bayes. The study began with data collection based on the electronic medical records from Harapan Kita National Heart Center patients from the period of 2016-2021. Data pre-processing produced 4691 records for dataset. Discussion with a medical professional was used to select the features predictions, which were thrombocyte, khermchc, erythrocyte, hematocrit, hermch, hemoglobin, age, leukocyte, and gender. The outcomes revealed AdaBoost reached the utmost ROC AUC score (68%), followed by Naive Bayes (66%) and Random Forest (56%). Subsequently we used Shapley Additive Explanations (SHAP) and beeswarm plot to reveal information-dense summary, to interpret the prediction result and to describe how each attribute affected the prediction model. We revealed that thrombocyte was the most important feature for the prediction model. This research contributed by paving the way a framework for predicting and improved the information-dense summary of arteriosclerosis heart disease prediction model. © 2023 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Arabic Cyberbullying Detection with End-to-End Transformer Model

引用

computer Modeling in Engineering & Sciences 2024年第11期141卷 1651-1671页

作者： Mohamed A.Mahdi Suliman Mohamed Fati Mohamed A.G.Hazber Shahanawaj Ahamad Sawsan A.Saad Information and Computer Science Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Information Systems Department College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Software Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Computer Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia

Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online *** tackle this challenge,our study introduces a new approach employing Bidirectional Encoder Representations from the Transformers(BERT)base model(cased),originally pretrained in *** model is uniquely adapted to recognize the intricate nuances of Arabic online communication,a key aspect often overlooked in conventional cyberbullying detection *** model is an end-to-end solution that has been fine-tuned on a diverse dataset of Arabic social media(SM)tweets showing a notable increase in detection accuracy and sensitivity compared to existing *** results on a diverse Arabic dataset collected from the‘X platform’demonstrate a notable increase in detection accuracy and sensitivity compared to existing methods.E-BERT shows a substantial improvement in performance,evidenced by an accuracy of 98.45%,precision of 99.17%,recall of 99.10%,and an F1 score of 99.14%.The proposed E-BERT not only addresses a critical gap in cyberbullying detection in Arabic online forums but also sets a precedent for applying cross-lingual pretrained models in regional language applications,offering a scalable and effective framework for enhancing online safety across Arabic-speaking communities.

关键词： Cyberbullying offensive detection Bidirectional Encoder Representations from the Transformers(BERT) continuous bag of words Social Media natural language processing

来源：评论

学校读者我要写书评

暂无评论

Challenges Towards VR Technology: VR Architecture Optimization 13

Challenges Towards VR Technology: VR Architecture Optimizati...

引用

13th International Conference on Dependable systems, Services and Technologies, DESSERT 2023

作者： Lysenko, Sergii Kachur, Artem Khmelnitsky National University Department of Computer Engineering and Information Systems Khmelnitsky Ukraine

ISBN: (纸本)9798350396119

This paper provides an exhaustive exploration of the challenges faced in the development and application of Virtual Reality (VR) technology. Despite VR's revolutionary potential across various sectors, its full-fledged realization is impeded by technical, financial, and ethical hurdles. Technical issues involve the development of high-quality hardware and software, seamless integration with existing infrastructures, and the demand for extensive computational resources. Financial constraints arise from high production and maintenance costs, which limit accessibility. Ethically, VR's immersive nature presents the potential for addiction, antisocial behavior, and data privacy concerns. The paper further discusses the trade-off decisions, complexity, technological limitations, hardware-software co-optimization, future-proofing, testing, and validation associated with VR development. Furthermore, a survey of resolutions to these challenges, as proposed in recent scientific literature, is presented. The article underscores the need for continued exploration, innovation, and refinement to overcome these hurdles and unlock the transformative power of VR technology. © 2023 IEEE.

关键词： Virtual reality

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：