检索结果-内蒙古大学图书馆

Bridging research gaps in breast cancer detection: An ensemble approach informed by bibliometric analysis

Biomedical Signal Processing and Control 2025年 109卷

作者： ZainEldin, Hanaa Bamaqa, Amna Farsi, Mohammed Badawy, Mahmoud Elhosseini, Mostafa A. Computers and Control Systems Engineering Department Mansoura University Faculty of Engineering Mansoura35516 Egypt Department of Computer Science and Information Applied College Taibah University Madinah42353 Saudi Arabia Department of Information Systems College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia

One of the leading causes of cancer-related death for women is still breast cancer, which highlights the importance of early and precise diagnosis techniques. Despite medical imaging and deep learning advances, current models fail to combine innovative object identification and classification methods, limiting their diagnostic performance. A bibliometric study of 1145 research articles identified key gaps, including the lack of integration between advanced object detection models like YOLOv9 and YOLOv10 with high-performance classification architectures such as EfficientNet B7, as well as the limited utilization of diverse imaging modalities. This study proposes a novel ensemble model for Breast Cancer Classification and Detection by combining YOLOv9, YOLOv10, and EfficientNet B7 (BC2D-Y/EN) to address these gaps. The proposed model combines the advanced object detection capabilities of YOLOv9 and YOLOv10 with the high-performance classification power of EfficientNet B7. This method aims to improve detection accuracy and computational efficiency in breast cancer identification. The proposed approach is validated using four publicly available datasets: CBIS-DDSM, CBIS-DDSM RGB breast cancer dataset, The Breast1 MRI dataset, and the Breast Ultrasound Tumor Object Detection dataset, all containing expert-annotated cases of benign and malignant tumors. The experimental findings indicate that the suggested model surpasses other models, achieving precision rates of 98.56% with EfficientNet B7, 98.3% with YOLOv9, and 100% with YOLOv9. These findings highlight the advantages of advanced models and diverse imaging methodologies to enhance diagnostic accuracy and effectiveness in breast cancer detection. © 2025 Elsevier Ltd

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Using Pre-Trained Models for Sentiment Analysis in Indonesian Tweets 6

Using Pre-Trained Models for Sentiment Analysis in Indonesia...

引用

6th International Conference on Informatics and Computational sciences, ICICoS 2022

作者： Arifiyanti, Amalia Anjani Kartika, Dhian Satria Yudha Prawiro, Cahyo Joyo Universitas Pembangunan Nasional 'Veteran' Jawa Timur Faculty of Computer Science Information Systems Department East Java Surabaya Indonesia

ISBN: (数字)9781665460996

ISBN: (纸本)9781665460996

Sentiment analysis from Twitter can provide useful information about public opinion to public perceptions of a topic, product, and service provided by industry players to government. This information can be useful to be the basis for consideration in making strategies, policies, and decisions making. One of the approach methods used for sentiment analysis is supervised learning. However, the construction of the scratch form classification model requires considerable effort and time. Pre-trained model libraries for sentiment analysis namely Vader, Textblob, and Flair can be used to reduce this burden. In addition, this pre-trained model can be used for the process of labeling training data in the supervised learning method approach. In this study, the challenges of sentiment prediction by the three pre-trained models were discussed on Indonesian text data. As a result, pre-trained models outperform classifier built from scratch. In the comparison of the accuracy levels of the three pre-trained models, the sentiment predictions made by Vader were more accurate than those of Textblob and Flair. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Human Emotions Classification Using EEG via Audiovisual Stimuli and AI

引用

computers, Materials & Continua 2022年第12期73卷 5075-5089页

作者： Abdullah A Asiri Akhtar Badshah Fazal Muhammad Hassan A Alshamrani Khalil Ullah Khalaf A Alshamrani Samar Alqhtani Muhammad Irfan Hanan Talal Halawani Khlood M Mehdar Radiological Sciences Department College of Applied Medical SciencesNajran UniversityNajranSaudi Arabia Faculty of Computer Science and Engineering GIK Institute of Engineering Sciences and TechnologyTopi23460Pakistan Department of Electrical Engineering University of Engineering and TechnologyMardan23200Pakistan Department of Software Engineering University of MalakandDir LowerPakistan Department of Computer Science and Information Systems College of EngineeringNajran University Saudi ArabiaNajran61441Saudi Arabia Electrical Engineering Department College of EngineeringNajran University Saudi ArabiaNajran61441Saudi Arabia Computer Science Department College of Computer Science and Information SystemsNajran UniversityNajranSaudi Arabia Anatomy Department Medicine CollegeNajran UniversityNajranSaudi Arabia

Electroencephalogram(EEG)is a medical imaging technology that can measure the electrical activity of the scalp produced by the brain,measured and recorded chronologically the surface of the scalp from the *** recorded signals from the brain are rich with useful *** inference of this useful information is a challenging *** paper aims to process the EEG signals for the recognition of human emotions specifically happiness,anger,fear,sadness,and surprise in response to audiovisual *** EEG signals are recorded by placing neurosky mindwave headset on the subject’s scalp,in response to audiovisual stimuli for the mentioned *** a bandpass filter with a bandwidth of 1-100 Hz,recorded raw EEG signals are *** preprocessed signals then further analyzed and twelve selected features in different domains are *** Random forest(RF)and multilayer perceptron(MLP)algorithms are then used for the classification of the emotions through extracted *** proposed audiovisual stimuli based EEG emotion classification system shows an average classification accuracy of 80%and 88%usingMLP and RF classifiers respectively on hybrid features for experimental signals of different *** proposed model outperforms in terms of cost and accuracy.

关键词： Electroencephalography emotion classification signal processing multilayer perceptron random forest

来源：评论

学校读者我要写书评

暂无评论

Wastewater treatment plant site selection using advanced decision tree machine learning and remote sensing techniques

引用

Environmental science and Pollution Research 2025年第1期32卷 234-247页

作者： Thangarasu, Thenmozhi Aldehim, Ghadah Alruwais, Nuha Kandasamy, Anguraj Department of Electronics and Communication Engineering Government College of Engineering Tamil Nadu Salem India Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer Science and Engineering College of Applied Studies and Community Services King Saud University Saudi Arabia P.O.Box 22459 Riyadh11495 Saudi Arabia Department of Electronics & Communication Engineering Sona College of Technology Tamil Nadu Salem India

Wastewater treatment plants in Coimbatore South are under pressure from rapid urbanization, inadequate infrastructure, and industrial pollution, leading to environmental and public health concerns. This study aimed to identify suitable locations for wastewater treatment plants using a combination of machine learning, remote sensing, and GIS-based multicriteria decision analysis (MCDA). Several datasets were analysed, with the analytical hierarchy process (AHP) assigning weights to factors such as slope (18.51) and elevation (31.39), which were found to be crucial in site selection. The study classified the suitability of sites into five categories, with the western region being the most favourable due to its low elevation (147 to 200 m), gentle slopes (0–3%), and substantial land availability (approximately 309.00 sq. km). Overall, the site suitability analysis revealed that 14.48% (110.2 sq. km) of the area falls within "Very High Favourable Zones," while 11.21% (85.3 sq. km) is categorized as "High Favourable Zones." Moderate and low favourable zones account for 9.63% (73.3 sq. km) and 24.04% (182.9 sq. km), respectively. The remaining 40.57% (308.7 sq. km) is considered "Very Low Favourable Zones." These results can guide urban planning decisions, highlighting the importance of factors such as land availability, population growth, wastewater volume, and flood vulnerability. Integrating GIS technology with decision-making processes enhances the strategic placement of urban utilities, ensuring long-term sustainability for Coimbatore South's wastewater management. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Site selection

来源：评论

学校读者我要写书评

暂无评论

Optimal Bidirectional LSTM for Modulation Signal Classification in Communication systems

引用

computers, Materials & Continua 2022年第8期72卷 3055-3071页

作者： Manar Ahmed Hamza Siwar Ben Haj Hassine Souad Larabi-Marie-Sainte Mohamed K.Nour Fahd N.Al-Wesabi Abdelwahed Motwakel Anwer Mustafa Hilal Mesfer Al Duhayyim Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Computer Science College of Science and ArtsKing Khalid UniversityMahayil AsirSaudi Arabia Department of Computer Science College of Computer and Information SciencesPrince Sultan UniversitySaudi Arabia Department of Computer Science College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Faculty of Computer and IT Sana’a UniversitySana’aYemen Department of Natural and Applied Sciences College of Community-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia

Modulation signal classification in communication systems can be considered a pattern recognition *** works have focused on several feature extraction approaches such as fractal feature,signal constellation reconstruction,*** recent advent of deep learning(DL)models makes it possible to proficiently classify the modulation *** this view,this study designs a chaotic oppositional satin bowerbird optimization(COSBO)with bidirectional long term memory(BiLSTM)model for modulation signal classification in communication *** proposed COSBO-BiLSTM technique aims to classify the different kinds of digitally modulated *** addition,the fractal feature extraction process takes place by the use of Sevcik Fractal Dimension(SFD)***,the modulation signal classification process takes place using BiLSTM with fully convolutional network(BiLSTM-FCN).Furthermore,the optimal hyperparameter adjustment of the BiLSTM-FCN technique takes place by the use of COSBO *** order to ensure the enhanced classification performance of the COSBO-BiLSTM model,a wide range of simulations were carried *** experimental results highlighted that the COSBO-BiLSTM technique has accomplished improved performance over the existing techniques.

关键词： Complex systems communication system signal processing modulation signals classification artificial intelligence deep learning parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Exploring Student Performance Patterns Using Tree-Based Techniques 3

Exploring Student Performance Patterns Using Tree-Based Tech...

引用

3rd International Conference on Smart Cities, Automation and Intelligent Computing systems, ICON-SONICS 2023

作者： Kurniadi, Felix Indra Dewi, Meta Amalya Murad, Dina Fitria Rabiha, Sucianna Ghadati Romli, Awanis Bina Nusantara University School of Computer Science Computer Science Department Jakarta11530 Indonesia Bina Nusantara University BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Faculty of Computing Universiti Malaysia Pahang Pahang26600 Malaysia

ISBN: (纸本)9781509062805

Due to its direct impact on the development and progress of nations, predicting student performance has acquired considerable importance in modern society. The evaluation of student performance measures the effectiveness of educational institutions and their capacity to influence the next generation. As a result, enhancing the educational process has become a necessity, compelling governments and institutions to devote significant resources to its ongoing development. Based on the Student Grade Data obtained from the Binus Online Learning platform at Bina Nusantara University, this study analyzes and predicts student performance using tree-based methods, specifically Decision Tree and Random Forest. The dataset includes pupil information and variables pertaining to performance. By contrasting the performance of these tree-based models, it is possible to gain insight into their accuracy and efficacy in predicting student outcomes. The experimental results demonstrate that both the Decision Tree and Random Forest models predict student performance with high accuracy. These results demonstrate the potential of tree-based methods in educational data analysis and prediction, providing educators, administrators, and policymakers with valuable insights for identifying at-risk students and implementing timely interventions to enhance educational outcomes. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Double Pepper: Mediated Human-Robot Interaction and Its Influence on Human Perception

Double Pepper: Mediated Human-Robot Interaction and Its Infl...

引用

International Conference on Behavior, Economic and Social Computing (BESC)

作者： Lisa Keller Nicholas H. Müller Faculty of Computer Science and Business Information Systems Technical University of Applied Sciences Würzburg-Schweinfurt Würzburg Germany

Remote communication solutions have grown in our globalized world. Combining this area with robotics, telepresence robots enable people to feel more present at distant locations and allow the operator to move freely. Seemingly, there is no difference in perceived human affinity whether a person interacts with another person directly or through a telepresence robot, as a preliminary study demonstrates. In contrast to the preliminary study focusing on affinity towards a human interaction partner, the study in this paper deploys a humanoid robot as interaction partner. Hence, this work aims to explore if human affinity towards a humanoid robot varies if people interact with it directly or through a telepresence robot (so called mediated human-robot interaction). A Double 2 robot was used as telepresence robot and a Pepper as humanoid robot interlocutor. To measure participants’ mood, the Multidimensional Mood State Questionnaire was applied before and after interacting with Pepper. Also, human affinity was measured through a questionnaire. The results indicate that there is no significant difference regarding mood and perceived human affinity whether someone interacts with a humanoid robot in person or through a telepresence robot. However, participants were significantly more awake after interacting in person. Concluding, the field of mediated human-robot interaction can enable new successful use cases e.g. deploying a humanoid robot in a telepresence robot tour as a guide instead of a person. Thereby, neither attendees nor a human guide have to be onsite which is beneficial in health hazard crises such as the corona pandemic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fuzzy System of Wind Turbine Defect Image Processing 14

Fuzzy System of Wind Turbine Defect Image Processing

引用

14th International Conference on Advanced computer information Technologies, ACIT 2024

作者： Dubchak, Lesia Sachenko, Anatoliy Wolff, Carsten Vasylkiv, Nadia West Ukrainian National University Department of Computer Engineerin Ternopil Ukraine West Ukrainian National University Research Institute for Intelligent Computer Systems Ternopil Ukraine Kazimierz Pulaski University of Technology and Humanities in Radom Department of Tele-Informatics Radom Poland Dortmund University of Applied Science and Arts Dortmund Germany West Ukrainian National University Department of Information Computer Systems and Control Ternopil Ukraine

ISBN: (纸本)9798350350036

Wind turbines are an important component of the global strategy for the transition to renewable energy sources and the fight against climate change. Their implementation contributes to sustainable development and to improving the ecological situation of the planet. Detecting and elimination of defects helps reduce the wear of the components and prevent premature failure. This can significantly extend the life of wind turbines, which is economically beneficial for owners and operators. The use of UAVs allows for minimizing the risks for personnel, as inspection and diagnosis of defects can be carried out without the need to lift people to great heights or stay in dangerous areas. This is especially important for turbines located in places of difficult access. The images taken by the UAV contain many extraneous objects and fuzzy data. Fuzzy logic allows you to create models for pattern recognition and object classification in images, taking into account uncertainty and variation in the data. This increases the accuracy and reliability of pattern recognition systems. This article proposes an image processing system to detect wind turbine defects, with a fuzzy system module that selects images from a video stream for further processing. © 2024 IEEE.

关键词： Windmill

来源：评论

学校读者我要写书评

暂无评论

Load Balancing Framework for Cross-Region Tasks in Cloud Computing

引用

computers, Materials & Continua 2022年第1期70卷 1479-1490页

作者： Jaleel Nazir Muhammad Waseem Iqbal Tahir Alyas Muhammad Hamid Muhammad Saleem Saadia Malik Nadia Tabassum Department of Software Engineering The Superior CollegeLahorePakistan Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Department of Statistics and Computer Science University of Veterinary and Animal SciencesLahore54000Pakistan Department of Industrial Engineering Faculty of EngineeringRabighKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology-RabighKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science Virtual University of PakistanLahore54000Pakistan

Load balancing is a technique for identifying overloaded and underloaded nodes and balancing the load between *** maximize various performance parameters in cloud computing,researchers suggested various load balancing *** store and access data and services provided by the different service providers through the network over different regions,cloud computing is one of the latest technology systems for both end-users and service *** volume of data is increasing due to the pandemic and a significant increase in usage of the internet has also been *** of the cloud are looking for services that are intelligent,and,can balance the traffic load by service providers,resulting in seamless and uninterrupted *** types of algorithms and techniques are available that can manage the load balancing in the cloud *** this paper,a newly proposed method for load balancing in cloud computing at the database level is *** database cloud services are frequently employed by companies of all sizes,for application development and business *** balancing for distributed applications can be used to maintain an efficient task scheduling process that also meets the user requirements and improves resource *** balancing is the process of distributing the load on various nodes to ensure that no single node is *** avoid the nodes from being overloaded,the load balancer divides an equal amount of computing time to all *** results of two different scenarios showed the cross-region traffic management and significant growth in revenue of restaurants by using load balancer decisions on application traffic gateways.

关键词： Load balancing performance database region virtualization

来源：评论

学校读者我要写书评

暂无评论

Semantic Literature Review on Non-Fungible Token: Expansion Area of Usage & Trends 8

Semantic Literature Review on Non-Fungible Token: Expansion ...

引用

8th International Conference on information Management and Technology, ICIMTech 2023

作者： Martha, Gede Indra Raditya Warnars, Harco Leslie Hendric Spits Prabowo, Harjanto Meyliana Hidayanto, Achmad Nizar Bina Nusantara University Binus Graduate Program - Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia Binus Business School Undergraduate Program Bina Nusantara University Management Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information System Department Jakarta11480 Indonesia University of Indonesia Faculty of Computer Science Depok Indonesia

ISBN: (纸本)9798350326093

Blockchain, Metaverse & NFT are technologies that were booming during the Pandemic. As a derivative product of blockchain, the Non-Fungible Token (NFT) is one of the technologies that has attracted the most interest from investors and the public because of its potential benefits and has always been closely associated with the Metaverse as a main purposes research of the NFTs. This paper is to explore the possibilities and provide an overview of the current use of NFT technology so that it can provide insight for further research & gap with the big picture that it is trying to present in this paper. However, after exploring further related to NFT in this research, it was found that the problem that most people are trying to solve through NFT is related to the topic of Decentralization & Web3 not as a Metaverse main backbone. © 2023 IEEE.

关键词： Blockchain

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：