检索结果-内蒙古大学图书馆

Application of the Deep Convolutional Neural Network for the Classification of Auto Immune Diseases

computers, Materials & Continua 2023年第10期77卷 647-664页

作者： Fayaz Muhammad Jahangir Khan Asad Ullah Fasee Ullah Razaullah Khan Inayat Khan Mohammed ElAffendi Gauhar Ali Department of Computer Science and Information Technology Sarhad University of Science and Information TechnologyPeshawar25000Pakistan Department of Computer Science University of Engineering and TechnologyMardan23200Pakistan EIAS Data Science and Blockchain Lab College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia

IIF(Indirect Immune Florescence)has gained much attention recently due to its importance in medical *** primary purpose of this work is to highlight a step-by-step methodology for detecting autoimmune *** use of IIF for detecting autoimmune diseases is widespread in different medical *** 80 different types of autoimmune diseases have existed in various body *** IIF has been used for image classification in both ways,manually and by using the computer-Aided Detection(CAD)*** data scientists conducted various research works using an automatic CAD system with low *** diseases in the human body can be detected with the help of Transfer Learning(TL),an advanced Convolutional Neural Network(CNN)*** baseline paper applied the manual classification to the MIVIA dataset of Human Epithelial cells(HEP)type II cells and the Sub Class Discriminant(SDA)analysis technique used to detect autoimmune *** technique yielded an accuracy of up to 90.03%,which was not reliable for detecting autoimmune disease in the mitotic cells of the *** the current research,the work has been performed on the MIVIA data set of HEP type II cells by using four well-known models of *** augmentation and normalization have been applied to the dataset to overcome the problem of overfitting and are also used to improve the performance of TL *** models are named Inception V3,Dens Net 121,VGG-16,and Mobile Net,and their performance can be calculated through parameters of the confusion matrix(accuracy,precision,recall,and F1 measures).The results show that the accuracy value of VGG-16 is 78.00%,Inception V3 is 92.00%,Dense Net 121 is 95.00%,and Mobile Net shows 88.00%accuracy,***,DenseNet-121 shows the highest performance with suitable analysis of autoimmune *** overall performance highlighted that TL is a suitable and enhanced technique compared to its ***,the proposed technique is used

关键词： Indirect immune fluorescence computer-aided diagnosis transfer learning confusion matrix

来源：评论

学校读者我要写书评

暂无评论

Secure and Efficient Deduplication for Multimedia Sharing in Privacy-Sensitive Cloud Ecosystems 3

Secure and Efficient Deduplication for Multimedia Sharing in...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Suresh, A. Murali, Erasappa Anjali Sri, V. Sumana, E. Sathwik, Gopaluni Venkata Sai Devendra Reddy, P. Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Puttur India

ISBN: (纸本)9798331527549

Current cloud-based systems face the challenge of managing storage and eliminating redundant data associated with the exponentially growing multimedia content, where numerous semantically similar but nonidentical files are included. In this paper we introduce a novel secure deduplication framework for encrypted cloud storage. This proposed system employs similarity-preserving hashing, fuzzy PoW protocol, and attribute-based encryption to perform efficient deduplication without compromising security and providing ownership verification. Security and deduplication rate scalability are improved over brute-force and ownership-faking attacks by dynamically varying thresholds based on file characteristics. Experimental evaluation shows that a 48% average deduplication rate and resistance to common attack vectors make it suitable for real-world cloud storage scenarios. The framework fills critical gaps in existing approaches and provides an innovative solution for dealing with similarity-aware data deduplication in privacy-sensitive environments. © 2025 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Uncertainty quantification in large language models through convex hull analysis

引用

Discover Artificial Intelligence 2024年第1期4卷 1-14页

作者： Catak, Ferhat Ozgur Kuzlu, Murat Department of Electrical Engineering and Computer Science University of Stavanger Rogaland Norway Department of Engineering Technology Old Dominion University NorfolkVA United States

Uncertainty quantification approaches have been more critical in large language models (LLMs), particularly high-risk applications requiring reliable outputs. However, traditional methods for uncertainty quantification, such as probabilistic models and ensemble techniques, face challenges when applied to the complex and high-dimensional nature of LLM-generated outputs. This study proposes a novel geometric approach to uncertainty quantification using convex hull analysis. The proposed method leverages the spatial properties of response embeddings to measure the dispersion and variability of model outputs. The prompts are categorized into three types, i.e., ’easy’, ’moderate’, and ’confusing’, to generate multiple responses using different LLMs at varying temperature settings. The responses are transformed into high-dimensional embeddings via a BERT model and subsequently projected into a two-dimensional space using Principal Component Analysis (PCA), Isomap, Multidimensional Scaling (MDS). The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is utilized to cluster the embeddings and compute the convex hull for each selected cluster. The experimental results indicate that the uncertainty of the model for LLMs depends on the prompt complexity, the model, and the temperature setting. © The Author(s) 2024.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

EMPATH: MediaPipe-Aided Ensemble Learning with Attention-Based Transformers for Accurate Recognition of Bangla Word-Level Sign Language 27th

EMPATH: MediaPipe-Aided Ensemble Learning with Attention-Bas...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Hasan, Kazi Reyazul Adnan, Muhammad Abdullah Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh

ISBN: (纸本)9783031783043

In this paper, we introduce EMPATH, an advanced computational framework developed to substantially enhance the recognition of Bangla Sign Language (BdSL). By integrating Ensemble Learning, MediaPipe Holistic for gesture tracking, and an Attention-based Transformer model, EMPATH addresses the challenges of sign language interpretation, setting new accuracy benchmarks and significantly surpassing previous records: achieving 79.81% on SignBD-Word-90 (previously best at 66.05%), 70.58% on SignBD-Word (previously best at 57%), and 99.25% on BdSL40 (previously best at 89%). A pioneering feature of EMPATH is its innovative interpolation model, built to overcome the limitations posed by missing Hand keypoints of MediaPipe. Validated in both EMPATH and a basic MLP framework, this model showcases remarkable versatility across architectures. EMPATH strategically selects its preprocessing and postprocessing techniques, optimizing each for maximum impact on accuracy and performance. Extensively trained across various word-level datasets beyond Bangla, including INCLUDE-50, INCLUDE, WLASL-100, and the Malaysian Sign Language Medical Dataset, EMPATH demonstrates its broad applicability and global potential. This diverse training scheme establishes superior accuracy benchmarks: achieving an impressive 100% on INCLUDE-50, 94.67% on INCLUDE, and 93.46% on the MSL Medical Dataset. Through EMPATH, we aspire to bridge communication barriers for the deaf and hard-of-hearing communities, showcasing the profound impact of integrating advanced technological solutions to tackle the complexities of sign language recognition. Source code is available at https://***/kreyazulh/EMPATH. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Early-stage stroke prediction based on Parkinson and wrinkles using deep learning

引用

Neural Computing and Applications 2024年第30期36卷 18781-18805页

作者： Haritha, T. Babu, A. V. Santhosh Department of Information Technology Vivekanandha College of Engineering for Women Tamilnadu Tiruchengode India Department of Computer Science and Engineering Vivekanandha College of Engineering for Women Tamilnadu Tiruchengode India

The application of noninvasive methods to enhance healthcare systems has been facilitated by the development of new technology. Among the four major cardiovascular diseases, stroke is one of the deadliest and potentially fatal, but, if detected early enough, a patient's life may be spared. Most stroke research has centered on MRI and CT scans for uncomplicated categorization. This medical approach (imaging) is costly, time-consuming and needs the utilization of complex technology. To make up for these shortcomings, however, there has been a lot of interest in adopting noninvasive, measurable EEGs. Nevertheless, the raw data should be classified before the proper characteristics can be formed, both the forecasting algorithms and the analytical techniques demand time. As a result, this work proposes a deep learning-based model that aims to predict the chance of stroke at an early stage utilizing Parkinson's disease and wrinkles as markers. A patient may have a stroke disease if they are diagnosed with both Parkinson's disease and wrinkles. To the best of our knowledge, this research is the first to use these biomarkers to predict the risk of having a stroke. The proposed model achieves a higher accuracy of 94.7% on the considered dataset. Additionally, the recommended model was evaluated and tested in terms of loss, training time, accuracy, recall, and F1-score versus the other existing models. With less price and pain than present testing approaches, these discoveries are predicted to result in major enhancements in the early detection of strokes. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

SWIFT: Swarm Intelligence Driven ESL Synthesis for Functional Trojan Fortification 10

SWIFT: Swarm Intelligence Driven ESL Synthesis for Functiona...

引用

10th IEEE International Symposium on Smart Electronic Systems, iSES 2024

作者： Sengupta, Anirban Chaurasia, Rahul Indian Institute of Technology Department of Computer Science and Engineering Indore India Indian Institute of Information Technology Department of Computer Science and Engineering Bhopal India

ISBN: (纸本)9798331533229

This paper presents a novel Swarm Intelligence driven Electronic System-Level (ESL) synthesis-based security methodology for functional Trojan fortification (called 'SWIFT'). Backdoor functional Trojan covertly inserted in the reusable hardware designs is a major concern for ensuring reliability functionality of consumer electronics (CE) systems and also for ensuring consumer trust. Erroneous computed output due to malicious functional Trojan can cause malfunctioning of such reusable IP cores. Therefore, the proposed methodology introduces a framework that integrates triple modular redundancy (TMR) along with a unique multi-vendor allocation that enables the generation of Trojan fortified (resistant) reusable hardware intellectual property (IP) designs capable of countering functional Trojan, if present and producing the correct output. The proposed approach integrates the swarm intelligence-based design space exploration (DSE) process with Trojan fortification design process to optimize any possible design overhead incurred due to TMR design. Results of the experimental evaluation prove that the proposed approach can generate low-cost Trojan fortified IP designs at meagre exploration time and at the expense of nominal overhead compared to prior work (that handle Trojan detection only). Further, the presented approach can handle a several potential vulnerabilities in the DSP design, which shows its robust security strength. © 2024 IEEE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

A novel workload forecasting model for cloud computing using ALAA-DBN algorithm

引用

Multimedia Tools and Applications 2025年第13期84卷 11383-11407页

作者： Karimunnisa, Syed Gopu, Arunkumar Rao, T. Prabhakara Ayyadurai, M. Kumar, ESaravana Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation AP VaddeswaramGuntur-522501 India School of Computer Science and Engineering VIT - AP University Amaravati522237 India Department of CSE Godavari Institute Of Engineering And Technology AP Rajahmundry533296 India Department of ECE SRM Institute of Science and Technology Ramapuram Campus Chennai India Department of CSE The Oxford College of Engineering Bengaluru India

Cloud Computing (CC) generally exhibits varying workload patterns. This autoscaling feature of CC has been extensively managed through predictive cloud resource management approaches. For this reason, a solitary forecasting model is not sufficient to forecast various workload patterns of CC web applications. With the intention of developing a proficient CC model, this paper implements a novel cloud workload forecasting model with the efficiency of DL algorithms like Deep Belief Network (DBN) and Lion Algorithm (LA). Here, the previous workload models are assessed and trained via DBN, and the prediction efficacy is enhanced by optimizing the DBN's hidden neurons through LA. The proposed workload forecast model for the cloud is accomplished by tuning the significant parameters via the Adaptive Lion Algorithm Assisted-DBN (ALAA-DBN)model. Besides, a well-organized resource provisioning pattern is followed to manage the under/over provisioning issues. The proposed CC model also considers providing better Quality of Service (QoS) to the users without violating the Service Level Agreement (SLA). Eventually, the significance of the proposed ALAA-DBN is verified through a comparative analysis with state-of-the-art models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Cricket Team Selection and Player Analysis using Data Analytics 6

Cricket Team Selection and Player Analysis using Data Analyt...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Raajesh, Sanjay Martin, Noel Jiji, Jyothsna Nair, Aakash Haritha, H. Muthoot Institute of Technology and Science Department of Computer Science and Engineering India

ISBN: (纸本)9798350381689

The inception of the 'Cricket Team Selection and Player Analysis using Data Analytics' project arose from the imperative to introduce precision through data-driven methods in the process of selecting cricket teams. Recognizing the pivotal role of team composition in the sport, our project employs the K-means clustering algorithm to categorize players based on their historical performance data with the strike rate. This approach facilitates the streamlined creation of well-balanced teams, targeting cricket enthusiasts, coaches, and team selectors. The ultimate goal is to enhance their decision-making processes, optimizing team performance and strategy. The project adopts a comprehensive approach, heralding a new era in cricket by leveraging data. It enables the formation of playing elevens derived from historical player performance metrics, ensuring a more resilient and strategic selection process. The project also has a selection of top players based on the attributes provided by the user. The tangible outcome of this project is a tool designed to serve cricket stakeholders, aiding them in making informed decisions for improved performance on the field. Representing a significant stride towards a more data-driven approach to cricket, the 'Cricket Team Selection and Player Analysis using Data Analytics' project is poised to redefine team selection and strategy in the sport. Its applicability extends to a broad audience, promising to be a transformative force in the realm of cricket decision-making. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Gene Variant Analysis for the Detection of Hemophilia: A Literature Review

引用

Recent Patents on engineering 2024年第9期18卷 48-62页

作者： Sumathi, N. Anitha Kumari, K. Department of Computer Science and Engineering Dr. Mahalingam College of Engineering and Technology Tamil Nadu Pollachi India Department of Information Technology PSG College of Technology Tamil Nadu Coimbatore641004 India

Background: Proteins act as clotting factors to stop bleeding at the lesion site. This implies that people with hemophilia tend to bleed longer after an injury and are more prone to internal bleeding. Depending on the type of hemophilia, individuals with hemophilia will have lesser amounts of factor VIII or factor IX than people without it. Objective: By analyzing the gene variant of hemophilia affected patient we can predict the severity of disease at earlier stage which helps to avoid further complications. Methods: Predicting hemophilia can be achieved through potential technologies like machine learning. Using these technologies, one can detect and predict the severity of hemophilia, such as mild, moderate, or severe. Results: By comparing the methods used in protein structure analysis, the advantages and limitations of methods used in protein structure analysis are discussed. Conclusion: The best practices in predicting hemophilia are highlighted in this patent study and particularly aim at the basic understanding of applying the potential technologies in the prediction of hemophilia and its severity. This study represents recent research on hemophilia and the use of different machine learning techniques (MLT) in this area. © 2024 Bentham science Publishers.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

A Study of Contrastive Learning Methods for Bengali Social Analysis 6

A Study of Contrastive Learning Methods for Bengali Social A...

引用

6th International Conference on Electrical engineering and Information and Communication technology, ICEEICT 2024

作者： Maisha, Jannatim Swarnali, Farhana Hossain Iftikar, M. Saymon Islam Ahammed, Sarkar Bulbul Shah, Faisal Muhammad Ahsanullah University of Science and Technology Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350385779

Across various domains, Contrastive Learning (CL) has already proven to be a powerful technique but using the Bengali language in the domain of Natural Language Processing (NLP) its' application is still unexplored. In this research, we introduce the implementation of CL in Bengali NLP by presenting a comprehensive benchmark study on two distinct datasets: Bengali Hate Speech, and Rokomari Book Review. The efficiency of the supervised contrastive techniques is emphasized by our methodology. We have implemented a contrastive learning technique through Bangla Bert. The superiority of supervised contrastive learning techniques over traditional Cross Entropy (CE) methods has been showcased by our result. Detailed experiments reveal performance variations across datasets, models, and hyperparameters but ensure the superiority of CL techniques over CE. Our findings show the significance of contrastive learning methods in low-resource settings, contributing to the advancement of Bengali NLP research. © 2024 IEEE.

关键词： Learning systems

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：