检索结果-内蒙古大学图书馆

LP norm regularized deep CNN classifier based on biwolf optimization for mitosis detection in histopathology images

International Journal of Information Technology (Singapore) 2024年第6期16卷 3517-3536页

作者： Lijo, Jithy Janardhanan Subramanian, Saleema Department of Computer Science Christ University Karnataka Bengaluru India Department of Statistics and Data Science Christ University Karnataka Bengaluru India Department of Computer Science and Applications Christ Academy Institute for Advanced Studies Karnataka Bengaluru India

Mitosis detection, a crucial biomedical process, faces challenges like cell morphology variability, poor contrast, overcrowding, and limited annotated dataset availability. This research presents a novel method for mitosis detection in histopathological images highlighting two important contributions using a Bi-wolf optimization-based LP norm regularized deep Convolutional neural network (CNN) model. This hybrid optimization protocol is the key to the precise calibration of model parameters and effective training, which translates into optimal classifier performance. The results reveal that this model achieves high accuracy, sensitivity, and specificity values of 96.69%, 91.89%, and 97.74% respectively. © Bharati Vidyapeeth's Institute of computer applications and Management 2024.

关键词： Biwolf optimization Feature extraction LP Norm Regularized deep CNN Pre-processing Yolo V5

来源：评论

学校读者我要写书评

暂无评论

Advancements in Osteoporosis Prediction: Trends, Challenges and Future Perspectives 2

Advancements in Osteoporosis Prediction: Trends, Challenges ...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Ramachandran, Darsana Charles, J. Noorul Islam Centre for Higher Education Department of Computer Applications Tamilnadu India Noorul Islam Centre for Higher Education Department of Computer Science Tamilnadu India

ISBN: (纸本)9798331505745

Osteoporosis, a widespread bone illness, impacts millions globally, increasing the risk of fractures. Menopause causes significant hormonal changes, most notably a decrease in estrogen, which is essential for maintaining bone density. Even though menopause is a normal stage of life, some conditions might make osteoporosis more dangerous. This study provides a comprehensive review of recent advancements in osteoporosis prediction methodologies. The review encompasses various approaches including Deep Learning (DL) models applied to various imaging modalities such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and X-ray, as well as innovative methods integrating clinical data and advanced algorithms. Notable progress has been made in enhancing early detection and classification accuracy of osteoporosis, driven by the application of Machine Learning (ML) and Artificial Intelligence (AI) techniques. Although the research under review produced promising results, there are a number of challenges to be addressed such as dataset size and model interpretability were acknowledged, emphasizing the need for further research. Overall, these findings highlight the importance of collaborative efforts among scientists, clinicians, and technologists to enhance osteoporosis prediction and treatment, ultimately benefiting patient health. © 2025 IEEE.

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security in the Internet of Things: A Trust-Based Protocol for Resilient Communication

引用

SN computer science 2024年第1期5卷 4页

作者： Althaf Ali, A. Hussain, Mohammed Muzaffar Subramaneswara Rao, A. Lavanya, S. Feroz Khan, A.B. Department of Computer Applications Madanapalle Institute of Technology & Science (MITS) Andhra Pradesh Madanapalle India Department of Computer Science and Engineering C. Abdul Hakeem College of Engineering and Technology Tamil Nadu Melvisharam India Department of Software Applications Thiruthangal Nadar College Tamil Nadu Chennai India Department of Computer Science Syed Hameedha Arts and Science College Tamil Nadu Kilakarai India

The quick increasing in the Internet of Things (IoT) devices has raised significant security concerns, particularly in the face of reactive jamming attacks. This paper proposes a trust-based protocol named Trust-Based Protocol for Resilient Communication (TBRC) that incorporates a robust key management technique to improve the security of IoT systems and mitigate the impact of reactive jamming attacks. To assess the effectiveness of our protocol, the work is compared with existing schemes such as CKMT, EDDK, and CEMT. Through extensive simulations under realistic conditions, we analyze key performance metrics, including energy consumption, packet loss, computational time, and throughput. The comparative analysis demonstrates that our proposed protocol outperforms CKMT, EDDK, and CEMT in terms of computational efficiency, throughput, and delay, making it a more effective solution for secure IoT communication. By leveraging a robust key management technique, our protocol provides a secure and resilient communication framework for IoT environments, effectively countering reactive jamming attacks. The integration of this technique strengthens the overall security posture of IoT networks, ensuring reliable and secure communication between devices. This work contributes to advancing IoT security by introducing a trust-based protocol with a robust key management technique that effectively mitigates the impact of reactive jamming attacks. The comparative evaluation against existing schemes validates the superiority of our proposed approach in terms of security, efficiency, and reliability. The results of our evaluation highlight the improved performance of our protocol, positioning it as a promising solution for real-world IoT deployments. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： DDoS IoT Security Trusted metrics

来源：评论

学校读者我要写书评

暂无评论

Spine Disease Detection in Spinal X-Ray Images using Machine Learning 13

Spine Disease Detection in Spinal X-Ray Images using Machine...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Sisodia, Ankur Vishnoi, Swati Khenwar, Medha Chauhan, Dushyant Sharma, Nandini Gupta, Priyanka Gla University Department of Computer Engineering and Applications Mathura India Banasthali Vidyapith Department of Computer Science Rajasthan India G.L. Bajaj Group of Institutions Department of Computer Science and Engineering Mathura India Sanskriti University Department of Computer Science and Engineering Mathura India

ISBN: (纸本)9798350380583

Millions of individuals globally experience spinal ailments. This stresses the importance of swift detection for achieving better treatment results. Traditional diagnosis techniques can be lengthy. They might lack precision. So here the aim is to design a powerful yet budget-friendly system that employs a deep neural network which has been trained on a vast X-ray image database. The system aims at carrying out X-ray scans of spinal vertebrae with improved accuracy. The method proposed utilizes a lite deep neural network to gather information. This is done from numerous levels to aid. In the detection of spinal health conditions, the autonomous system for finding spine illnesses consist crucial elements. These include photo filtering tools attribute excavation methods and efficient classification algorithms. Moreover, Clinical information and patient past records are added to the analyses. This augments the diagnostic precision and dependability of the system. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Integration of fault-tolerant feature to OMIEEPB routing protocol in wireless sensor network

引用

International Journal of Intelligent Computing and Cybernetics 2022年第3期15卷 414-424页

作者： I.Nasurulla R.Kaniezhil Research Scholar Department of Computer SciencePeriyarUniversitySalemIndia Department of Computer Applications MIT College of Arts and Science for WomenTrichyIndia

Purpose-Whereas a human operator is hard to observe the networking infrastructure and its functions on a continuous basis,wireless sensor network(WSN)nodes must overcome faults and route the perceived data to the sink/base stations(BS).The main target of this research article is to ensure the fault-tolerance(FT)capability,especially for transmission of sensed data to its destinationwithout ***,through this paper,a fuzzy-based subordinate support(FSS)system is introduced as an additional feature to the existing optimized mobile sink improved energy efficient Power-Efficient Gathering in Sensor Information Systems(PEGASIS)-based(OMIEEPB)routing protocol,which lacks focus on ensuring the FT capabilities to the selected leaders of the corresponding *** central focus of FSS is to prevent the incident of fault,especially to the cluster ***/methodology/approach-WSNs encounter several issues owing to random events or different causes such as energy exhaustion,negative influences of the deployed region,signal interference,unbalanced supply routes,instability of motes due to misalignments and collision,which ultimately intends the failure of the *** the past investigation periods,researchers gain an understanding of fault-tolerant strategies that may improve the data integrity or reliability,precision,energy efficiency,the life expectancy of the system and reduce/prevent the failure of deployed *** that is the case,the maximum chances of data packets(sensed)needed to be transferred reliably and accurately to the sink node or BS are ***-The FSS system utilizes the fuzzy logic concepts that have been proved to be beneficial since it permits several parameters to be combined effectively and ***,near-point,residual energy,total operation time and past average processing time are considered as vital ***,the FSS system ensures the key performance activities of the network,such as optimization

关键词： WSN Fuzzy logic Fault-tolerance Response time Optimization Subordinate support Near-point Residual energy Total operation time Average processing time

来源：评论

学校读者我要写书评

暂无评论

Digital Evidence Management: Modern Techniques in Digital Forensics 3

Digital Evidence Management: Modern Techniques in Digital Fo...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Venkataramanan, N. Jayalakshmi, V. Anitha, S. Ganesan, R. Jenifer, V. Drbccc Hindu College Department of Computer Applications Pattabiram Chennai600072 India Department of Computer Science and Applications Ramapuram600089 India Anna University St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai600119 India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai600062 India Department of Computer Science and Applications Ramapuram Campus 600089 India

ISBN: (纸本)9798331509675

This research study reviews the significance of digital forensic analysis in modern criminal investigations, highlighting the way it complements conventional methods of inquiry and the difficulties it encounters in the information era. To solve crimes effectively, investigators must combine digital knowledge with traditional forensic techniques. This will enable them to use evidence from many different types of digital and physical sources. The specific intricacies of digital crime scenes need specialized methods for the proper storage and analysis of digital evidence to identify criminal intent and patterns of conduct. To propose Modern Techniques for Digital Evidence Management [MT-DEM] based Digital Forensics Service. Multidisciplinary teams and cutting-edge technology are becoming necessities in digital forensic investigation as the field adjusts to new threats like data encryption and massive amounts of data. The admissibility of evidence in the legal world depends on digital forensic procedures being transparent and adhering to set criteria. Digital forensic analysis has become an indispensable tool for contemporary investigators with the rise of digital evidence. © 2025 IEEE.

关键词： Forensic science

来源：评论

学校读者我要写书评

暂无评论

Optic disc pallor diagnosis using ROMF based optic disc segmentation in fundus images

引用

Multimedia Tools and applications 2025年第2期84卷 517-546页

作者： Jency, J. Shunmugan, S. Research Scholar Department of Computer Science S. T. Hindu College Nagercoil Affiliated to Manonmaniam Sundaranar University Tirunelveli India Associate Professor Department of Computer Science & Applications S.T. Hindu College Nagercoil. Affiliated to Manonmaniam Sundaranar University Tirunelveli India

Disc pallor is a pale yellow discoloration of the optic disc (OD) that causes irreversible damage to the fiber of the retina's anterior visual pathway. Automatic disc pallor diagnosis has obstacles such as increased time consumption and reduced accuracy due to less powerful OD segmentation algorithms. Hence, a new development for pallor diagnosis through the enhanced version of OD segmentation, namely, 'Optic Disc Pallor Diagnosis using ROMF-based OD segmentation in fundus images (ODPD_ROMF)', is proposed. Herein, the essential contribution is a new OD segmentation method, namely 'Optic disc segmentation using Retinex and ONH structure-specific Membership based FCM method (ROMF)’. The ROMF method is constituted based on a new variant of Fuzzy C Means (FCM), namely 'Optic Nerve Head (ONH) structure-influenced Fuzzy C Means (FCM)', where the membership function and the objective function are redefined to calibrate according to the refined or updated ONH structure, which results in fast and accurate OD segmentation. The second-best approach has an average classification accuracy of 93.00, while the proposed ODPD_ROMF method has an average accuracy of 96.17. The suggested ROMF method's average segmentation accuracy in OD segmentation is 97.52, while the second-best method's average segmentation accuracy is 96.66. Because of its great competence, the proposed ODPD_ROMF method can be utilized to identify disc pallor more effectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

HFANet: Hierarchical Feature-Enhanced Aggregation Network for Camouflaged Object Detection

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Zhang, Xinchao Zhu, Hengliang Mao, Guojun Department of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China

Camouflaged object detection (COD) aims to identify target objects in complex scenes with extremely high similarity to their surroundings, and has significant applications in military, medical, and other fields. This paper proposes a hierarchical feature-enhanced aggregation network (HFANet) for COD, aiming to address the situations that the target object is highly similar to the background. First, we adopt the pyramid vision Transformer model as the backbone for feature extraction. On top of it, the object-region amplification module and deep interaction guidance module are stacked to enhance the perception of camouflaged objects in complex scenes. Second, an enhanced receptive field module is designed to improve edge perception of camouflaged objects. At last, a multi-scale interactive fusion module is designed by cross-scale connection through adjacent layers, effectively improving the accuracy of COD. The proposed method is evaluated on three challenging datasets: CAMO, CHAMELEON, and COD10K. Evaluation results demonstrate superior performance compared to the state-of-the-art methods. © Shanghai Jiao Tong University 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Document Classification and Data Extraction 3

Document Classification and Data Extraction

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Khurana, Madhav Chaturvedi, Ravi Prakash Mishra, Annu Gupta, Devika Negi, Ishika Mishra, Ambuj Sharma, Hirdesh Jemtec Department of Computer Science & Engineering Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Applications Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350384598

T- Data classification and extraction are fundamental tasks in the field of computer vision and data analysis. This abstract presents an overview of these concepts along with the utilization of Python and OpenCV, a popular computer vision library, in building data extraction tools. Data classification involves organizing data into categories or classes based on certain characteristics or features. It enables efficient data management and analysis by grouping similar data together. In the context of computer vision, data classification often involves categorizing images or videos based on their content, such as identifying objects, scenes, or patterns within them. Data extraction, on the other hand, involves retrieving specific information or features from a dataset. This process is crucial for tasks like data mining, information retrieval, and automated document processing. In computer vision applications, data extraction often entails locating and extracting relevant information from images or videos, such as text, objects, or numerical data. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Data Aggregation Point Placement and Subnetwork Optimization for Smart Grids

引用

computers, Materials & Continua 2025年第4期83卷 407-434页

作者： Tien-Wen Sung Wei Li Chao-Yang Lee Yuzhen Chen Qingjun Fang Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and MathematicsFujian University of TechnologyFuzhou350118China Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin640301TaiwanChina

To transmit customer power data collected by smart meters(SMs)to utility companies,data must first be transmitted to the corresponding data aggregation point(DAP)of the *** number of DAPs installed and the installation location greatly impact the whole *** the traditional DAP placement algorithm,the number of DAPs must be set in advance,but determining the best number of DAPs is difficult,which undoubtedly reduces the overall performance of the ***,the excessive gap between the loads of different DAPs is also an important factor affecting the quality of the *** address the above problems,this paper proposes a DAP placement algorithm,APSSA,based on the improved affinity propagation(AP)algorithm and sparrow search(SSA)algorithm,which can select the appropriate number of DAPs to be installed and the corresponding installation locations according to the number of SMs and their distribution locations in different *** algorithm adds an allocation mechanism to optimize the subnetwork in the *** is evaluated under three different areas and compared with other DAP placement *** experimental results validated that the method in this paper can reduce the network cost,shorten the average transmission distance,and reduce the load gap.

关键词： Smart grid data aggregation point placement network cost average transmission distance load gap

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：