检索结果-内蒙古大学图书馆

15th International Conference on Graphics and Image Processing, ICGIP 2023

作者： Pang, Yu Huang, Yang Yu, Xiaosheng Wu, Chengdong School of Artificial Intelligence Shenyang University of Technology Shenyang110870 China Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China

ISBN: (纸本)9781510675018

In this paper, we propose a novel salient object detection framework by constructing a novel saliency tree model integrating low-level and high-level features. In our model, numerous features containing low-level features (e.g., color, texture, gradient, contrast, etc.) and high-level features (e.g., deep features extracted from pre-trained VGG19 net) are firstly selected as candidate features. We develop a novel feature integrating mechanism to acquire an integrated feature descriptor which is more discriminative to capture the contrast between foreground and background for the input image. Then, we construct a novel saliency tree model relied on the integrated features to generate saliency map. We compare the proposed method and other state-of-the-art methods on three datasets, experimental results indicate that the proposed saliency detection algorithm has achieved the top performance. © 2024 SPIE. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient Evaluation Methods for Neural Architecture Search: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2024年第12期5卷 5990-6011页

作者： Song, Xiaotian Xie, Xiangning Lv, Zeqiong Yen, Gary G. Ding, Weiping Lv, Jiancheng Sun, Yanan Sichuan University College of Computer Science Chengdu610065 China Oklahoma State University School of Electrical and Computer Engineering StillwaterOK74078 United States Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

Neural architecture search (NAS) has received increasing attention because of its exceptional merits in automating the design of deep neural network (DNN) architectures. However, the performance evaluation process, as a key part of NAS, often requires training a large number of DNNs. This inevitably makes NAS computationally expensive. In past years, many efficient evaluation methods (EEMs) have been proposed to address this critical issue. In this article, we comprehensively survey these EEMs published up to date, and provide a detailed analysis to motivate the further development of this research direction. Specifically, we divide the existing EEMs into four categories based on the number of DNNs trained for constructing these EEMs. The categorization can reflect the degree of efficiency in principle, which can in turn help quickly grasp the methodological features. In surveying each category, we further discuss the design principles and analyze the strengths and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs. Furthermore, we also discuss the current challenges and issues to identify future research directions in this emerging topic. In summary, this survey provides a convenient overview of EEM for interested users, and they can easily select the proper EEM method for the tasks at hand. In addition, the researchers in the NAS field could continue exploring the future directions suggested in the article. © 2020 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wound Care in Healthcare Systems with Logistic Regression for Infection Detection 1

Enhancing Wound Care in Healthcare Systems with Logistic Reg...

引用

1st International Conference on Innovations in Communications, Electrical and Computer engineering, ICICEC 2024

作者： Ramalingam, L. Amarnath, Raveendra N. Arun, V. Sendhilkumar, N.C. Ravi, Rupavathy Srinivasan, C. Loyola Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Mphasis Corporation MelissaTX United States SRM Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computing Technologies Tamil Nadu Chennai India Sri Indu College of Engineering and Technology Department of Electronics and Communication Engineering Hyderabad India Agni College of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376517

In healthcare systems, wound care management is essential for reducing infections and promoting faster recovery. To improve wound care, this paper proposes a data-driven method that combines machine learning (ML), more particularly, Logistic Regression (LR), with Internet of Things (IoT) sensors to identify early infections. The system provides real-time data streams to healthcare providers by continually monitoring important wound parameters, including temperature, moisture, pH levels, and exudate presence via IoT-enabled sensors. Using LR, the system predicts the potential of wound infections based on these physiological indicators, allowing for more effective patient care and early treatments. When tested for accuracy and dependability in infection prediction, the proposed model shows significant detection skills with few false positives. This approach optimizes clinical processes by reducing the need for manual wound examination, enhancing patient safety, and lowering the possibility of complications from infections. Wound care management might improve patient outcomes and expedite infection control measures in medical institutions. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Optimizing beyond boundaries: empowering the salp swarm algorithm for global optimization and defective software module classification

引用

Neural Computing and Applications 2024年第30期36卷 18727-18759页

作者： Kassaymeh, Sofian Al-Betar, Mohammed Azmi Rjoubd, Gaith Fraihat, Salam Abdullah, Salwani Almasri, Ammar Software Engineering Department Faculty of Information Technology Aqaba University of Technology Aqaba Jordan College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Information Technology Al-Huson University College Al-Balqa Applied University Irbid Jordan Concordia Institute for Information Systems Engineering Concordia University Montreal Canada Artificial Intelligence Department Faculty of Information Technology Aqaba University of Technology Aqaba Jordan Data Mining and Optimization Research Group Center for Artificial Intelligence Technology Universiti Kebangsaan Malaysia Bangi Malaysia Management Information Systems Department Al-Balqa Applied University Amman Jordan

This work presents a new version of the salp swarm optimizer (SSA), called "mSSA," that uses complex mathematical expressions to dynamically manipulate the crucial control parameter (c1) during optimization. These expressions are carefully designed to modulate the shift in search strategy from exploratory to exploitative, improving the flexibility and speed of convergence of the algorithm. To evaluate the performance of the developed mSSA variants, a thorough examination is carried out on twenty-three benchmark test functions alongside their application to the complex task of software module classification. The process of classifying defective software modules involves developing a multilayer perceptron (MLP) classifier that is suited to the particular complexity and heterogeneity of the task. Selecting the best optimizer is made easier by systematically evaluating the different mSSA versions as MLP classifier trainers. Based on metrics like classification accuracy, convergence speed, and avoidance of local minima, a comparative analysis in opposition to six previously published metaheuristic optimizers shows that mSSA3, when combined with the developed MLP classifier, outperforms both other mSSA variations and state-of-the-art metaheuristic optimizers in terms of overall performance. The excellent classification accuracy, swift convergence, and ability to avoid local minima of mSSA3 highlight its superiority and establish it as a cutting-edge method in the application of metaheuristic algorithms. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Lung Tumor Detection Using Deep Convolutional Neural Network 7

Lung Tumor Detection Using Deep Convolutional Neural Network

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Shermila, P. Josephin Anna Devi, E. Poojitha, G. Sanjay, M. Ashika, V. R.M.K. College of Engineering and Technology Department of Artificial Intelligence and Data Science India Sathyabama Institute of Science and Technology Department of ECE Chennai India Arunachala College of Engineering for Women Department of ECE India

ISBN: (纸本)9798350372816

In simple terms, lung cancer is a significant challenge that the fields of science and medicine are working hard to overcome, which gives the highest mortality rate, besides being one of the smallest survival rates after diagnosis. Thereby, early detection is essential for diagnosis and treatment. All people in this universe require a proper diagnosis of the tumor. Diagnosis need to be in maximizing the payoff. Increasing the payoff is much important mainly in medical diagnosis. Machines need to do an intelligent task in diagnosis of tumor and in this case the lung tumor. Here, the investigation is done with different solvers. Deep learning with a Convolutional Neural Network compatible with the analysis of Computer tomography scans with tumors, the level of accuracy in predictions sees a tremendous enhancement. Classification of tumors by Convolutional Neural Network as malignant or benign with good accuracy is obtained. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Evaluating Pretrained Deep Learning Models for COVID-19 Detection in Medical Imaging 1

Evaluating Pretrained Deep Learning Models for COVID-19 Dete...

引用

1st Renewable Energy Technologies and Modern Communications Systems: Future and Challenges Conference, RETMCS 2024

作者： AL-Shehri, Bushra A. Sabbeh, Sahar F. Dessouky, Mohamed M. Department of Data Science College of Computer Science and Engineering University of Jeddah Jeddah23218 Saudi Arabia Faculty of Computers and Artificial Intelligence Information Systems Department Benha University Benha13518 Egypt Department of Computer Science and Artificial Intelligence College of Computer Science and Engineering University of Jeddah Jeddah23218 Saudi Arabia Department of Computer Science and Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt

ISBN: (纸本)9798331519445

COVID-19 is a respiratory disease for which reverse transcription-polymerase chain reaction (RT-PCR) is the standard detection method. This study introduces a hybrid deep learning approach to support the diagnosis of respiratory abnormalities, using COVID-19 as a case study. Multiple datasets were utilized, including the COVID-19 Radiography dataset (Kaggle), the SARS-CoV-2 CT-Scan dataset, and proprietary data from the King Faisal Medical Complex. Seven pre-trained deep learning models—VGG16, VGG19, MobileNet, DenseNet201, ResNet50, InceptionResNetV2, and InceptionV3—were evaluated for their performance. InceptionResNetV2 and InceptionV3 achieved perfect accuracy (100%) on the COVID-19 Radiography dataset and 99% accuracy on the SARS-CoV-2 CT-Scan dataset. Additionally, augmentation techniques were explored to improve model robustness. This research contributes significantly to medical imaging, offering practical insights for advancing diagnostic and monitoring practices for COVID-19 and other respiratory conditions. ©2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Prediction Of Chronic Kidney Disease On Ct Images Using Deep Learning: Resnet-34 And Vggnet-16

Prediction Of Chronic Kidney Disease On Ct Images Using Deep...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Revathi, M. Nithiya, R. Ohm Shankar, S. Maheshwari, D. St.Joseph's Institute of Technology Artificial Intelligence & Data Science Chennai India Agni College of Technology BioMedical Engineering Chennai India Agni College of Technology Electronics & Communication Engineering Chennai India

ISBN: (纸本)9798331541170

Kidney is considered as the most essential and important organ of our human body. Many factors such as diabetes, high blood pressure, inherited kidney disease, abnormal structure of kidney etc., affects the filtration rate of the kidney and in turn leads to chronic kidney disease. İf disease is identified and properly treated at early stages, human life can be saved. But in most cases, it cannot be done since there is no proper symptoms in the early stages. Huge of data is produced in the medical industry daily and it is left unattended. If this data is utilized properly, many useful information can be found. The use of artificial intelligence to assist medical professionals is increasing day by day. In this research work, we have used two famous deep learning architectures: RESNET and VGGNET to predict the existence of Chronic Kidney Disease. To improve the prediction accuracy, artificial Bee Colony algorithm is used for segmentation. Instead of giving the original image as input, segmented image is given. The experiments shows that the VGGNET architecture produces higher accuracy of 98% than the RESNET architecture which gives an accuracy of 96%. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Zero Trust Architecture: Enhancing Cyber-Security Resilience 8

AI-Driven Zero Trust Architecture: Enhancing Cyber-Security ...

引用

8th IEEE International Conference on Computational System and Information technology for Sustainable Solutions, CSITSS 2024

作者： Chokkanathan, K. Karpagavalli, S.M. Priyanka, G. Vanitha, K. Anitha, K. Shenbagavalli, P. Madanapalle Institute of Technology & Science Department of Artificial Intelligence India Erode Sengunthar Engineering College Department of M.Tech Computer Science and Engineering Erode India Karpagam Academy of Higher Education Department of Computer Science and Engineering Coimbatore India Csi College of Engineering Department of Information Technology Coimbatore India Department of Artificial Intelligence and Data Science Rathinam Technical Campus Coimbatore India

ISBN: (纸本)9798331505462

In the ever-changing field of cybersecurity, conventional defenses that rely on boundaries are no longer adequate to safeguard against sophisticated and persistent assaults. The Zero Trust Architecture (ZTA) paradigm, powered by AI, provides a strong answer by removing the concept of inherent trust within a network and demanding ongoing verification for each access request. This article examines the combination of artificial intelligence (AI) with Zero Trust principles to improve the resilience of cyber-security. This study demonstrates the enhanced accuracy, sensitivity, and specificity of AI-driven techniques in comparison to conventional security models. The findings highlight the significance of utilizing AI-driven Zero Trust Architecture (ZTA) to protect contemporary digital infrastructures. It provides robust protection against emerging cyber threats as well as addressing challenges related to data privacy and system integration. The paper also explores potential areas for future study and the practical consequences of implementing AI-driven Zero Trust Architecture (ZTA) in different organizational settings. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Automated Framework for Exploring Potential Biomarkers in Lung Cancer 5

Automated Framework for Exploring Potential Biomarkers in Lu...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Kumar, Mohan Kumar Sunil Venkataramanan, S. Sambandam, Palaniappan Aashiq Shareef, A. Saifuddin, S. Anna University Kcg College of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Management and Science University Faculty of Health and Life Science Department of Diagnostic and Allied Health Science Malaysia

ISBN: (纸本)9798331504403

Lung cancer has experienced a concerning increase in incidence with smoking, genetics, and air pollution identified as major contributing factors. Early detection is crucial for improving patient outcomes, as the disease can be difficult to diagnose in its early stages. This research presents a machine learning-based approach to predict lung cancer risk by identifying potential biomarkers. The proposed framework utilizes a streamlined pipeline of validated tools, ensuring a user-friendly and efficient process. By analyzing genetic data and identifying predictive biomarkers, this research aims to empower individuals with a family history of cancer or early symptoms to take proactive steps towards prevention and early detection. This approach contributes to the fight against lung cancer by providing valuable insights into disease risk and facilitating timely intervention. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis of Load Balancing Issues in Fog Computing Environment 2

An Empirical Analysis of Load Balancing Issues in Fog Comput...

引用

2nd International Conference on data science and Information System, ICDSIS 2024

作者： Kumar, K. R. Prasanna Siddesh, G.M. Ananda Babu, J. M S Ramaiah Institute Of Technology Department Of Computer Science & Engineering Bangalore India M S Ramaiah Institute Of Technology Department Of Artificial Intelligence & Data Science Bangalore India Malnad College Of Engineering Department Of Information Science And Engineering Hassan India

ISBN: (纸本)9798350381665

Fog Computing (FC) is a distributed paradigm that complements cloud computing in terms of service delivery. By extending storage and computation of the network edge, fog systems enable location awareness and mobility support, while also resolving the issue of service computing for delay-sensitive applications. A crucial component of fog networks is load balancing, which prevents fog nodes from becoming under or overloaded. In recent years, only a limited number of studies have been conducted on load-balancing methods in fog networks. This paper provides a thorough assessment of the load-balancing techniques used in fog computing, covering approximate, accurate, fundamental, and hybrid methods. This paper also examines load balancing metrics in fog networks, including all benefits and drawbacks associated with the selected load balancing algorithms. The evaluation methods considered for each study are investigated. Additionally, the primary unresolved issues and potential developments for these systems are discussed. © 2024 IEEE.

关键词： Virtualization

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：