检索结果-内蒙古大学图书馆

International Conference on computer, Electrical & Communication Engineering (ICCECE)

作者： Mohammad Alamgir Hossain Fazal Imam Shahi Sadia Husain Abdelrazig Suliman Mohammad Shahid Kamal Yasir Ahmad Mohammad Mazedul Huq Talukdar R. John Martin Department of computer Science College of Engineering & Computer Science Jazan University Jazan Saudi Arabia eLearning Center Jazan University Jazan Saudi Arabia Department of Information Technology Faculty of Computers Information Technology University of Bisha Saudi Arabia Department of Foreign Languages College of Arts and Humanities Jazan University Jazan Saudi Arabia

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

The automated segmentation of lungs within chest CT scans remains crucial for many medical applications that require disease diagnosis and treatment design. The presented deep incremental learning (DIL) system addresses fundamental limitations that arise during lung segmentation processes. The exceptional segmentation outcomes result from the neural network structure which includes masked RCNN+UNet for tissue segmentation and GAN+VARMA for classification. Medical literature identifies lung tissue structures as difficult to study because they present irregular forms and complex structures. The task of obtaining precise segmentation proves very challenging. The application of masked RCNN+UNet enables shape control and improves segmentation precision of the lung system. The DIL function helps maintain improved features within segmented images. The applied framework enables improved performance through DSC and MAE and JI metrics evaluation. Experimental evidence shows that the new framework achieves superior performance compared to current top-ranking methods for lung segmentation. The proposed framework exhibits excellent precision and detection efficiency with a DSC value of 0.96 and JI value of 0.93 and a low MAE $\lt 0.01$. The new extraction method could advance medical image examination systems within healthcare settings.

关键词： Deep learning Image segmentation Shape control Lungs Pulmonary diseases Computed tomography Predictive models Real-time systems Medical diagnostic imaging Electronics packaging

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Prediction using Ensemble Learning Techniques: A Stacking Approach

Cardiovascular Disease Prediction using Ensemble Learning Te...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Zahiriddin Rustamov Jaloliddin Rustamov Most Sarmin Sultana Jeanne Ywei Vimala Balakrishnan Nazar Zaki Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia College of Information Technology United Arab Emirates University Al Ain United Arab Emirates

Cardiovascular diseases (CVDs) are group disorders affecting the heart or involving constricted blood arteries. Early disease detection increases the likelihood of survival. As a result, newer methods such as machine learning emerged, capable of processing and analysing vast quantities of complex medical data and providing a more accurate prediction of diseases, including CVDs. However, due to factors such as overfitting and bias, the single classifier could not ensure optimum prediction. Thus, this study proposes a stacking ensemble classifier, which combines several single classifiers to produce an optimal predictive model. The Framingham Heart Study dataset was used to train the machine learning algorithms. The exploratory data analysis indicates that CVD was more common in males and diabetic individuals. Furthermore, individuals above the age of 65 were more susceptible to CVDs. Feature selection, missing value imputation, and data sampling were performed as part of data preprocessing. The results show that the proposed stacked ensemble classifier achieved 88.33% accuracy, 89.95% precision, 86.27% recall and 88.07% F1-score. Furthermore, the significance test results indicate that the proposed model performs significantly better than most models evaluated in this research. Finally, the comparative analysis showed that the proposed ensemble classifier performs better than most studies using the same dataset. The proposed model achieved a high F1-score, indicating it can accurately predict the cases with and without CVD.

关键词： Heart Data analysis Machine learning algorithms Stacking Data preprocessing Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Clustering the Academician Knowledge Qualification: K-Means for Performance Measurement Analysis

Clustering the Academician Knowledge Qualification: K-Means ...

引用

Student Conference on Research and Development (SCOReD)

作者： Novi Yanti Sarjon Defit Okfalisa Department of Informatics Engineering Faculty of Science and Technology Universitas Islam Negeri Sultan Syarif Kasim Riau Pekanbaru Riau Indonesia Department of Information Technology Faculty of Computer Science Universitas Putra Indonesia YPTK Padang Padang Sumatera Barat Indonesia

ISBN: (数字)9798331510077

ISBN: (纸本)9798331510084

The assessment of an academic’s performance is not solely based on the tangible results achieved. Nonetheless, the formation aspect of the Knowledge Management (KM) process, which arises in the pursuit of outcomes, must be acknowledged. This emphasizes the significance of KM process development for academics in achieving their essential responsibilities including teaching and learning, research and publishing, and community service. Consequently, it is essential to develop a KM model for assessing the accomplishments of academics in higher education. An evaluation of academic performance in higher education was conducted to identify the success factors of knowledge management, by considering five key elements viz, knowledge creation, knowledge acquisition, knowledge storage, knowledge sharing, and knowledge application. Accordingly, sixty-five sub-variables were identified as success model factors for evaluating academic knowledge management performance. A K-Means clustering method was utilized to assess the KM qualifications of academics at an Islamic public institution in Indonesia (University X) as the primary study. Herein, a 5-point Likert scale questionnaire was administered to 500 academics and subsequently categorized into three performance levels such as low, medium, and high performance. As a result, 140 academicians were categorized as low KM performance, 139 were clustered as medium qualification, and 221 academicians were positioned in high performance. Furthermore, a recommendation analysis is presented to elucidate the accomplishments of academic credentials for each cluster and propose corrective actions for enhancement. Therefore, the scholars at University X might enhance their knowledge management practices to get a superior quality university.

关键词： Measurement Technological innovation Publishing Knowledge acquisition Education Knowledge management Filling Space exploration Research and development Qualifications

来源：评论

学校读者我要写书评

暂无评论

Predicting Employees' Turnover in IT Industry using Classification Method with Feature Selection 2

Predicting Employees' Turnover in IT Industry using Classifi...

引用

2nd International Conference on computer science and Engineering, IC2SE 2021

作者： Mohamad, Mas Rahayu Hanum Nasaruddin, Fariza Hamid, Suraya Bukhari, Sarah Ijab, Mohamad Taha University Malaya Faculty of Computer Science and Information Technology Kuala Lumpur Malaysia National Fertilizer Corporation Institute of Engineering and Technology Computer Science Department Multan Pakistan Selangor Malaysia

ISBN: (纸本)9781665400459

Nowadays many IT companies are concerned about retaining their employees due to the competitiveness of employment landscape where highly skilled and quality IT knowledge workers are in huge demand. However, the growing pace of technological change and the socio-economic factors have transmuted employees in various organizations on how best to make their skills and talents proffered to be more attractive toward employers. Challenges pertaining to the turnover rate can be attributed to several factors such as failure employees to meet the company's objectives, less motivating work environment, employees losing out to their employers, their skills are not put to best use, low wages, and many other turnover factors. On the other hand, the growing interest of machine learning (ML) lead to the prediction of the turnover factors. This research aims to explore the factors contributing to high turnover rate based on employee productivity using ML. For this purpose, dataset of 1,470 employees with 26 variables undergo feature selection processing which is to identify the correlation between employees' productivity and turnover features which are (i) Pearson's Square for categorical value and (ii) Correlation for numerical value have been applied to the dataset. The analysis shows higher accuracy after going through feature selection (18 variables) instead of without feature selection (26 variables). Thus, the best algorithm that can be used for the prediction of employees' turnover is Random Forest with a model accuracy value of 87.76%, precision 0.643, recall 0.75, and F1-Score of 0.692. © 2021 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Measurement System and its Suitability for Examining Indoor Millimeter Wave Propagation at (28-33GHz) 1

Measurement System and its Suitability for Examining Indoor ...

引用

1st IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer Engineering, MI-STA 2021

作者： Alabish, Ahmed Goweder, Abduelbaset Dowa, Ali Information Technology College Computer Science Zawia Joudiem Libya Libyan Academy Computer Science Tripoli Libya University of Zawia Faculty of Education Zawia Libya

ISBN: (纸本)9781665418560

This study is the continuation of a research carried out by Alabish etal [1]. The purpose of this study is to determine the suitability of system measurements on indoor radio wave propagation at (28-33GHz) which might be used by 5G communication. This paper presents some experimental work to evaluate the effects of system measurements on short range links at (28-33GHz). To the best of our knowledge, no research has yet been examined the suitability of measurement systems at this frequency range. In this paper, a previous measurement system called (VNA) used by Alabish etal [1] is adopted. Another measurement system is suggested. A set of experiments along with some obtained results are presented. The obtained results reveal that the suggested measurement system is suitable for measuring the impact of scattering objects around indoor links in the millimeter wave band (28-33GHz). © 2021 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Improved harris hawks optimization algorithm based on collaborative quantization 6

Improved harris hawks optimization algorithm based on collab...

引用

6th International Conference on Mechatronics and Intelligent Robotics, ICMIR 2022

作者： Li, Yan Zhang, Xiang Qian, Qian Pan, Jiawen Feng, Yong Fu, Yunfa Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming Yunnan650500 China Yunnan Key Laboratory of Computer Technology Applications Kunming University of Science and Technology Kunming Yunnan650500 China Logistic Service Group Yunnan University Kunming Yunnan650500 China

ISBN: (纸本)9781510656635

Harris hawk optimization algorithm (HHO) is one of the population-based algorithms proposed by in *** has received great attention from researchers. However, HHO algorithm still has some problems, such as the exploitation ability is too large compared with the exploration ability, which leads to low optimization accuracy, slow convergence speed and so on. Therefore, the collaborative strategy and quantization strategy are introduced. With the support of the two strategies, the algorithm can avoid falling into local extremum in the early phase of iteration and improve its optimization accuracy at the late phase of iteration. Through the test of four representative functions, compared with the other three basic algorithms, the proposed algorithm greatly improves the optimization accuracy and convergence speed of the optimal solution, and the ability to find global extremum is greatly improved. © 2022 SPIE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Life on land: An accurate centralized system for ensuring the safety and wellbeing of domestic and wild animals

TechRxiv

引用

TechRxiv 2023年

作者： Heshan, Adithya B.M. Wickramathilake, Shamilka K.W.D. Gunathilake, Dulmi W.M.P. Herath, Hiruni H.M.S. Samarasekara, Piyumika de Silva, Dilshan Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Sri Lanka Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

The web application described above has the potential to make a significant contribution to the conservation of endangered wildlife and the responsible management of domestic animals. The application addresses a critical issue that has far-reaching implications for the health of ecosystems and the well-being of animals. By providing users with tools to track and manage animal populations, monitor their health and behavior, and implement conservation efforts, the application empowers individuals and organizations to take action and make a positive impact on the environment. In addition to its practical benefits, the web application also includes educational resources and supports community engagement to raise awareness about the importance of preserving biodiversity and protecting animal welfare. This holistic approach recognizes the complex and interconnected nature of conservation and management efforts, and highlights the need for collaboration and cooperation among stakeholders. The user-friendly interface of the application ensures that it is accessible to a wide range of users, including individuals with limited technical expertise. The ability to collaborate and share data also promotes transparency and accountability, which are essential for effective conservation and management efforts. Overall, this web application has the potential to be a valuable tool for those involved in animal conservation and management, and it offers hope for the protection of endangered wildlife and the responsible management of domestic animals. © 2023, CC BY.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Self Decoupling-Reconstruction Network for Facial Expression Recognition

Self Decoupling-Reconstruction Network for Facial Expression...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Linhuang Wang Xin Kang Fei Ding Hai-Tao Yu Yunong Wu Kazuyuki Matsumoto Satoshi Nakagawa Fuji Ren Graduate School of Advanced Technology and Science Tokushima University Tokushima Japan Faculty of Library Information and Media Science University of Tsukuba Tsukuba Japan Dataa Robotics Chengdu China Graduate School of Information Science & Technology The University of Tokyo Tokyo Japan School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Facial Expression Recognition (FER) poses significant challenges due to various imaging conditions, including diverse head poses, lighting conditions, resolutions, and occlusions. Additionally, different personal attributes such as age, gender, and racial background further contribute to the complexity of FER. To accurately extract meaningful expression features amidst these interfering factors to enhance recognition accuracy and the model’s generalization, we propose a Self Decoupling-Reconstruction Network (SDRNet). Specifically, our approach involves two learning processes. In the first phase, the network is trained to decouple facial images with expressions into expression and neutral components. This process involves reconstructing neutral facial images and the original input, ensuring the preservation of meaningful expression components devoid of interference in the decoupling process. In the second learning phase, we employ simple convolutional neural networks (CNNs) to recognize the extracted expression components. Our method has achieved state-of-the-art results across multiple widely used datasets, providing substantial evidence of its effectiveness. Additionally, we demonstrate the robust generalization performance of our approach through cross-database evaluations.

关键词： Image resolution Image recognition Head Face recognition Neural networks Lighting Imaging

来源：评论

学校读者我要写书评

暂无评论

Data Assimilation Enhances WRF-Chem Performance in Modeling Volcanic Ash Clouds from Hunga Tonga–Hunga Ha’apai Eruption

引用

Journal of Meteorological Research 2024年第6期38卷 1122-1140页

作者： Hosni SNOUN Mohammad Mosaed ALAHMADI Amirhossein NIKFAL Abderrazak ARIF William HATHEWAY Meznah A.ALAMRO Alaeddine MIHOUB Moez KRICHEN Numthaja Co. Ltd.Jeddah23345Saudi Arabia Jülich Supercomputing Centre(JSC) Forschungszentrum JülichJülich52428Germany Institut National de la Météorologie Tunis Carthage2035Tunisia Free Researcher AustinTexas78666USA Department of Information Technology College of Computer&Information SciencePrincess Nourah Bint Abdul Rahman UniversityRiyadh11564Saudi Arabia Department of Management Information Systems and Production Management College of Business and EconomicsQassim UniversityBuraidah51452Saudi Arabia Faculty of Computer Science and Information Technology(FCSIT) Al-Baha UniversityAl-Baha65528Saudi Arabia ReDCAD Laboratory University of SfaxSfax3038Tunisia

Volcanic eruptions release large amounts of ash clouds and gas aerosols into the atmosphere,which can be simulated by air quality prediction ***,the performance of these models remains unsatisfactory,even though both relevant physics and chemistry are ***,exploring the approaches for improvement such as inclusion of data assimilation is *** this study,we depict the modeling of the volcanic ash dispersion from the Hunga Tonga–Hunga Ha’apai underwater volcano,which erupted in a series of large explosions in late December 2021 and early January *** 15 January 2022,a particularly significant explosion sent a massive ash cloud high into the *** used the inline Weather Research and Forecasting model coupled with chemistry(WRF-Chem)and incorporated meteorological data assimilation within the Flux Adjusting Surface Data Assimilation System(FASDAS).We compared three forecast scenarios:one with only meteorology and no chemistry(OMET),one with gas and aerosol chemistry and no assimilation(NODA),and one with both chemistry and assimilation(FASDAS).We found that FASDAS resulted in lower planetary boundary layer height(PBLH),downward surface shortwave flux,and 2-m temperature by up to 800 m,200 W m^(−2),and 6℃ on the land portion,respectively,while the opposite was observed near the eruption *** validated the model against the observations and the results showed that FASDAS significantly enhanced the model performance in retrieving meteorological ***,the simulations also revealed significant biases in the concentration of volcanic ash around the ash *** from the Copernicus TROPOspheric Monitoring Instrument Sentinel-5 Precursor(TROPOMI-S5P)showed a westward trend of the total SO2 *** work demonstrates the significant contribution of data assimilation to the results of operational air quality predictions during violent volcanic eruption events.

关键词： Hunga Tonga-Hunga Ha’apai volcano WRF-Chem Flux Adjusting Surface Data Assimilation System(FASDAS) data assimilation SO2 TROPOspheric Monitoring Instrument Sentinel-5 Precursor(TROPOMI-S5P)

来源：评论

学校读者我要写书评

暂无评论

StyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning

arXiv

引用

arXiv 2023年

作者： Jing, Peiguang Liu, Xianyi Wang, Ji Wei, Yinwei Nie, Liqiang Su, Yuting School of Electrical and Information Engineering Tianjin University Tianjin China Faculty of Information Technology Monash University Victoria Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

Emotion distribution learning has gained increasing attention with the tendency to express emotions through images. As for emotion ambiguity arising from humans’ subjectivity, substantial previous methods generally focused on learning appropriate representations from the holistic or significant part of images. However, they rarely consider establishing connections with the stylistic information although it can lead to a better understanding of images. In this paper, we propose a style-guided high-order attention network for image emotion distribution learning termed StyleEDL, which interactively learns stylistic-aware representations of images by exploring the hierarchical stylistic information of visual contents. Specifically, we consider exploring the intra- and inter-layer correlations among GRAM-based stylistic representations, and meanwhile exploit an adversary-constrained high-order attention mechanism to capture potential interactions between subtle visual parts. In addition, we introduce a stylistic graph convolutional network to dynamically generate the content-dependent emotion representations to benefit the final emotion distribution learning. Extensive experiments conducted on several benchmark datasets demonstrate the effectiveness of our proposed StyleEDL compared to state-of-the-art methods. The implementation is released at: https://***/liuxianyi/StyleEDL. © 2023, CC BY.

关键词：

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：