检索结果-内蒙古大学图书馆

An optimized deep learning based technique for grading and extraction of diabetic retinopathy severities

Informatica (Slovenia) 2021年第5期45卷 659-665页

作者： Zhang, Qiu-Ming Luo, Jing Cengiz, Korhan School of Computer science China University of Geosciences Wuhan430074 China Practice training center Wuhan Vocational College of Software and Engineering Wuhan430205 China Department of Electrical - Electronics Engineering Trakya University Edirne22030 Turkey

The prognosis of Diabetic Retinopathy (DR) requires regular eye examinations, as ophthalmologists depends on fundus segmentation to treat DR pathologies. Automated approaches for detection, segmentation and classification have developed as an imperative area of research for the effective diagnosis of DR for the treatment of serious eye conditions that prevent visual impairment. Diagnosis of various DR lesions, as well as different severities, helping the ophthalmologists to analyze variations in fundus images and take the necessary measures before the disease progresses. Deep learning techniques have evolved as a recent advent to combat the issues of conventional machine leaning based methods. An optimized deep learning framework is proposed in this article for grading and extraction of diabetic retinopathy severities. This involves various steps like background segmentation, feature set extraction, feature optimization using Cuckoo search and Convolutional Neural Network (CNN) severity grade classification. The method was validated on two standard datasets MESSIDOR and IDRiD. The proposed method yields an accuracy value of 97.55%, cross entropy loss of 0.367 and time intricacy of 20 mins and 15 secs for MESSIDOR and 98.02% cross entropy loss of 0.345 and time intricacy of 22 mins and 21 secs for IDRiD dataset;respectively. The state-of-the-art comparison depicts that the proposed CNN based method provides a maximum accuracy improvement of 10.46% comparative to the existing methodology. The proposed framework yields better accuracy by procurement of the investigative outcomes acquired exhibits proficient DR determination. © 2021 Slovene Society Informatika. All rights reserved.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Periodic Frequent Pattern Model in AIoT Applications

Privacy-Preserving Periodic Frequent Pattern Model in AIoT A...

引用

2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021

作者： Ahmed, Usman Lin, Jerry Chun-Wei Fournier-Viger, Philippe Cheng, Chien-Fu Western Norway University of Applied Sciences Electrical Engineering and Mathematical Sciences Department of Computer Science Bergen Norway Shenzhen University College of Computer Science and Software Engineering Shenzhen China Ntaional Taiwan Ocean University Department of Computer Science and Engineering Taiwan

ISBN: (纸本)9781665419512

We begin with a sanitization strategy for concealing sensitive periodic frequent patterns in this study. The developed method employs the Term Frequency and Inverse Document Frequency (TF-IDF) to determine which transactions and objects should be sanitized based on user-defined sensitive periodic frequent patterns. Using the designed approach, it is possible to correctly and properly choose victim items in the transactional database for data sanitization. © 2021 IEEE.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Selection of Education Assistance Recipients Based on AHP and SAW 23

Selection of Education Assistance Recipients Based on AHP an...

引用

23rd International Seminar on Intelligent Technology and Its Applications, ISITIA 2022

作者： Pranoto, Gatot Tri Pebrianti, Dwi Darwis, Muhammad Yaddarabullah Krishnasari, Erneza Dewi Pelita Bangsa University Informatics Engineering Study Program Bekasi Indonesia Budi Luhur University Computer Science Jakarta Indonesia Universitas Trilogi Department of Informatics Engineering Jakarta Indonesia Universitas Trilogi Department of Visual Communication Design Jakarta Indonesia

ISBN: (数字)9781665460811

ISBN: (纸本)9781665460811

The final decision of the educational assistance recipient in GNOTA Foundation, Jakarta is still processed manually. They usually only look at the father's occupation criteria without looking at other criteria such as the age of the child, the child's orphan status, the occupation of mother, the age of father, the age of mother and other scholarships received. GNOTA Foundation needs to implement a Decision Support System (DSS) for the selection process, so the results are fast and on target. This research applies the Analytical Hierarchy Process (AHP) and Simple Additive Weighting (SAW) methods for the selection of education assistance recipients so the criteria can be weighted and the prospective recipient students can be ranked. This research determines the priority weight and importance of each criterion, namely the age of child age (0.18), the status of child (0.22), the occupation of father (0.08), the occupation of mother (0.06), the age of father (0.05), the age of mother (0.04) and other scholarship assistance (0.36). The results of the weighting of these criteria have been tested and declared consistent through the Consistency Ratio (CR) value of 0.070. This study also produces a list of the best ranking students who are prospective recipients of educational assistance. The ranking results have been tested based on compliance with the provisions of the GNOTA Foundation of 92.91%. The system in this study was developed using a prototyping system development model and utilizing the Unified Modeling Language (UML) tool. The prototype functionality in this study works well by using the Blackbox Testing (BBT) model based on Equivalence Partitioning. In addition, the level of user acceptance of the prototype in this study was 81.2% using the Technology Acceptance Method (TAM). © 2022 IEEE.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

SSAD: Self-supervised Auxiliary Detection Framework for Panoramic X-ray based Dental Disease Diagnosis

arXiv

引用

arXiv 2024年

作者： Cai, Zijian Yang, Xinquan Li, Xuguang Luo, Xiaoling Li, Xuechen Shen, Linlin Meng, He Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Stomatology Shenzhen University General Hospital Shenzhen China School of Electronics and Information Engineering Wuyi University Jiangmen China

Panoramic X-ray is a simple and effective tool for diagnosing dental diseases in clinical practice. When deep learning models are developed to assist dentist in interpreting panoramic X-rays, most of their performance suffers from the limited annotated data, which requires dentist's expertise and a lot of time cost. Although self-supervised learning (SSL) has been proposed to address this challenge, the two-stage process of pretraining and fine-tuning requires even more training time and computational resources. In this paper, we present a self-supervised auxiliary detection (SSAD) framework, which is plug- and-play and compatible with any detectors. It consists of a reconstruction branch and a detection branch. Both branches are trained simultaneously, sharing the same encoder, without the need for finetuning. The reconstruction branch learns to restore the tooth texture of healthy or diseased teeth, while the detection branch utilizes these learned features for diagnosis. To enhance the encoder's ability to capture fine-grained features, we incorporate the image encoder of SAM to construct a texture consistency (TC) loss, which extracts image embedding from the input and output of reconstruction branch, and then enforces both embedding into the same feature space. Extensive experiments on the public DENTEX dataset through three detection tasks demonstrate that the proposed SSAD framework achieves state-of-the-art performance compared to mainstream object detection methods and SSL methods. The code is available at https://***/Dylonsword/SSAD. Copyright © 2024, The Authors. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Enhanced and Robust Data Publishing Scheme for Private and Useful 1:M Microdata

引用

IEEE Transactions on Big Data 2024年

作者： Rizwan, Muhammad Hawbani, Ammar Xingfu, Wang Anjum, Adeel Angin, Pelin Sever, Yigit Chen, Sanchuan Zhao, Liang Al-Dubai, Ahmed University of Science and Technology of China School of Computer Science and Technology China Shenyang Aerospace University School of Computer Science China Quaid i Azam University Institute of Information Technology Islamabad Pakistan Middle East Technical University Department of Computer Engineering Turkey Auburn University Department of Computer Science and Software Engineering United States Computing School of Edinburgh Napier University United Kingdom

A data publishing deal conducted with anonymous microdata can preserve the privacy of people. However, anonymizing data with multiple records of an individual (1:M dataset) is still a challenging problem. After anonymizing the 1:M microdata, the vertical correlation can be exploited to launch privacy attacks. In this paper, a novel privacy preserving model lc, ls-ANGEL is proposed. To validate the new model, two privacy attacks are presented, namely, a Vertical correlation attack (Vc0) and a Vulnerable sensitive attribute attack (Vsa) on 1:M datasets, which breach the privacy of individuals. Furthermore, the proposed model is examined through High-Level Petri Nets (HLPNs). Our experiments on three real-world datasets;'INFORMS','YOUTUBE', and 'IMDb' demonstrate that the proposed model outperforms the state-of-the-art models. Our practices and lessons learned in this work can direct future concrete steps towards Multiple Sensitive Attributes, where we can expand the proposed model to dynamic datasets © 2024 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Bioinformatics exploration into potential mechanisms of Calamus draco for colorectal cancer treatment

引用

Procedia computer Science 2024年 245卷 127-136页

作者： Christian Kenneth Rudi Nirwantono Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Biotechnology Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

As one of the cancer types with the highest incidence rates, colorectal cancer (CRC) would benefit from treatments with fewer side effects and reduced treatment-resistant potential. One of the options is to harness the anti-CRC potential of natural products. Previous studies have shown that Calamus draco exudate, dragon's blood, has anticancer activity in liver cancer and acute myeloid leukemia, but its bioactivity has not been studied in CRC. Here we conduct a bioinformatics study based on network pharmacology to explore the anti-CRC potential and mechanism of C. draco -derived compounds. The bioinformatics pipeline is composed of compound and target collection, biological network evaluation, and enrichment analysis. We found that there are 43 bioactive compounds from C. draco targeting 91 CRC-related targets, of which most compounds target MEN1, PTGS2, and IDH1. Further analyses show that the targets of C. draco are involved in the cellular response to hypoxia. By inhibiting those targets, C. draco bioactive compounds can potentially hinder angiogenesis and increase treatment response efficacy.

关键词： bioinformatics network pharmacology Calamus draco colorectal cancer drug discovery

来源：评论

学校读者我要写书评

暂无评论

An Ensemble of Machine Learning Models for Classifying Bangla-English Code-Mixed SMS as Spam or Ham

An Ensemble of Machine Learning Models for Classifying Bangl...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Babe Sultana Mahmuda Rahman Md Gulzar Hussain Department of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering United International University Dhaka Bangladesh Department of ICT Mohammadpur Preparatory School and College Dhaka Bangladesh School of Software Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

In the ever-changing world of digital communication, the proliferation of code-mixed languages raises new challenges for content classification, particularly in the context of spam identification. SMS ( Short Message Service) is a popular form of communication, but there are security flaws in it, such as an increase in spam from online fraudsters. This research aims to develop an ensemble of machine-learning models that can classify Bangla-English code-mixed SMS as spam or ham. Our method, which uses a large dataset of code-mixed SMS, includes several classification algorithms, including Logistic Regression, Support Vector Machines, Random Forests, and Multi-Layer Perceptron Classifier (MLPC). To increase the robustness of our model, we employ feature extraction techniques such as TF-IDF for code-mixing scenarios. The ensemble technique employs a voting procedure to integrate individual model predictions, enhancing accuracy while minimizing the risk of misclassification. The experimental results reveal that our ensemble model outperforms single classifiers, with a 96.92% accuracy and high recall and precision metrics. This study enhances the science of natural language processing and has practical implications for SMS filtering systems in multilingual settings, hence boosting user experience and security in digital communications.

关键词： Support vector machines Accuracy Predictive models Message services Digital communication User experience Robustness Natural language processing Multilingual Random forests

来源：评论

学校读者我要写书评

暂无评论

Formation control and coordination of swarm robotic systems 21

Formation control and coordination of swarm robotic systems

引用

7th International Conference on engineering and MIS, ICEMIS 2021

作者： Kyzyrkanov, Abzal Ermekbayuly Atanov, Sabyrzhan Kubeisinovich Aljawarneh, Shadi Abdel Rahman Computer and Software Engineering Department L.N. Gumilyov Eurasian National University Nur-Sultan Kazakhstan L.N. Gumilyov Eurasian National University Senior Lecturer of Computer and Software Engineering Department Eurasian National University Nur-Sultan Kazakhstan Software Engineering Department Jordan University of Science and Technology Al Ramtha Irbid Jordan

ISBN: (纸本)9781450390446

In many applications, a group of autonomous mobile robots must follow a given trajectory while maintaining a certain geometric structure. If the motion in formation is properly organized, many advantages over traditional systems can be obtained: system cost can be reduced, system reliability and efficiency can be increased, while ensuring the reconfigurability and flexibility of the system's structure. Movement while maintaining a certain geometric structure has a wide range of applications. For example, in military missions, autonomous vehicles must maintain a certain structure of formation to cover terrain and conduct reconnaissance;in Smart Highway systems, the capacity of the transportation network can be greatly increased if vehicles can be grouped together at the same speed while maintaining a certain distance between them. This paper provides an algorithm for movement with a certain geometric structure of a group of autonomous mobile robots. © 2021 ACM.

关键词： Military applications

来源：评论

学校读者我要写书评

暂无评论

SiamIRPN: Siamese Visual Tracking with Improved Region Proposal Networks

SiamIRPN: Siamese Visual Tracking with Improved Region Propo...

引用

2023 International Conference on Frontiers of Robotics and software engineering, FRSE 2023

作者： Cao, Dun Dai, Renhua Zhao, Tianyu Alqahtani, Fayez Tolba, Amr Sherratt, R. Simon Zhu, Min Changsha University of Science and Technology School of Computer and Communications Engineering Hunan Changsha China Nanjing University of Posts and Telecommunications Ministry of Education Key Lab of Broadcast Wireless Communication and Sensor Network Technology China King Saud University College of Computer and Information Sciences Software Engineering Department Riyadh12372 Saudi Arabia King Saud University Community College Computer Science Department Riyadh11437 Saudi Arabia The University of Reading School of Biomedical Engineering RG6 6AY United Kingdom Zhejiang Shuren University College of Information Science and Technology Zhejiang31000 China

ISBN: (纸本)9798350301113

Though introducing the Region Proposal Network (RPN) from object detection enabled Siamese trackers' success, RPN-based trackers still struggle in challenging scenarios. We posit that the reason comes from two major limitations of the introduced RPN, where one is that the external structure of the RPN is simple and straight, the other is that the internal components used in RPN cannot cope with complex scenes. In this paper, we propose an Improved RPN (IRPN) suitable for visual tracking. Externally, we place a Convolutional Block Attention Mechanism (CBAM) to the IRPN, and internally, we adopt the advanced component groups for the IPRN. Using multiple IRPN blocks and deep architecture, we propose a Siamese tracker (SiamIRPN) having a layer-wise structure. Comprehensive experiments and ablation studies on five benchmarks (VOT-2019, OTB100, UAV123, GOT-10k, and NFS) show our proposed SiamIRPN achieves competitive performance. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Optimizing Depression Prediction in Older Adults: A Comparative Study of Feature Extraction and Machine Learning Models

Optimizing Depression Prediction in Older Adults: A Comparat...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Ashir Javeed Peter Anderberg Ahmad Nauman Ghazi Asim Javeed Ana Luiza Dallora Johan Sanmartin Berglund Department of Health Blekinge Institute of Technology Blekinge Sweden Department of Software Engineering Blekinge Institute of Technology Blekinge Sweden Department of Computer Science Times Institute Multan Pakistan

ISBN: (数字)9798350361025

ISBN: (纸本)9798350361032

Depression emerged as a major public health concern in older adults, and timely prediction of depression has become a difficult problem in medical informatics. The latest studies have attentiveed on feature transformation and selection for better depression prediction. In this study, we assess the performance of various feature extraction algorithms, including principal component analysis (PCA), independent component analysis (ICA), locally linear Embedding (LLE), and t-distributed stochastic neighbor embedding (TSNE). These algorithms are combined with machine learning (ML) classifier algorithms such as Gaussian Naive Bayes (GNB), Logistic Regression (LR), K-nearest-neighbor (KNN), and Decision Tree (DT) to enhance depression prediction. In total, sixteen automated integrated systems are constructed based on the above-mentioned feature extraction methods and ML classifiers. The performance of all of these integrated models is assessed using data from the Swedish National Study on Aging and Care (SNAC). According to the experimental results, the PCA algorithm combined with the Logistic Regression (LR) model provides 89.04% depression classification accuracy. As a result, it is demonstrated that the PCA is a more suitable feature extraction method for depression data than ICA, LLE, and TSNE.

关键词： Logistic regression Machine learning algorithms Machine learning Depression Feature extraction Prediction algorithms Classification algorithms

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：