检索结果-内蒙古大学图书馆

A lightweight attention-driven YOLOv5m model for improved brain tumor detection

computers in Biology and Medicine 2025年 188卷 109893-109893页

作者： Muksimova, Shakhnoza Umirzakova, Sabina Mardieva, Sevara Iskhakova, Nargiza Sultanov, Murodjon Cho, Young Im Department of Computer Engineering Gachon University Sujeong-gu Seongnam-si461-701 Korea Republic of Department of Information Systems and Technologies of the Tashkent State University of Economic Tashkent100066 Uzbekistan Department of Systematic and Practical Programming Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi Tashkent100200 Uzbekistan

Brain tumors are regarded as one of the most lethal, devastating, and aggressive diseases, significantly reducing the life expectancy of affected individuals. For this reason, in pursuit of advancing brain tumor diagnostics, this study introduces a significant enhancement to the YOLOv5m model by integrating an Enhanced Spatial Attention (ESA) layer, tailored specifically for the analysis of magnetic resonance imaging (MRI) brain scans. Traditional brain tumor detection methods, heavily reliant on expert interpretation of MRI, are fraught with challenges such as high variability and the risk of human error. Our innovative approach leverages the ESA layer to acutely focus on salient features, significantly improving the method ability to differentiate between common classes of brain tumors—meningioma, pituitary, and glioma tumors. By processing spatial features with enhanced precision, the model minimizes false positives and maximizes detection reliability. Validated against a comprehensive dataset of 3064 T1-weighted contrast-enhanced MRI images from 233 patients, our modified YOLOv5m architecture demonstrates superior performance metrics compared to the standard model, highlighting its potential as a robust tool in clinical applications for automated and precise brain tumor diagnosis. © 2025 The Authors

关键词： Dynamic contrast enhanced MRI

来源：评论

学校读者我要写书评

暂无评论

Advanced convolutional neural network with attention mechanism for Alzheimer's disease classification using MRI

引用

computers in Biology and Medicine 2025年 190卷 110095-110095页

作者： Muksimova, Shakhnoza Umirzakova, Sabina Iskhakova, Nargiza Khaitov, Aziz Cho, Young Im Department of Computer Engineering Gachon University Sujeong-gu Gyeonggi-do Seongnam-si461-701 Korea Republic of Department of Systematic and Practical Programming Tashkent University of Information Technologies Named After Muhammad Al-Khwarizmi Tashkent100200 Uzbekistan Republican Scientific and Methodological Center for the Development of Education of the Republic of Uzbekistan Uzbekistan

This paper introduces a novel convolutional neural network model with an attention mechanism to advance Alzheimer disease (AD) classification using Magnetic Resonance Imaging (MRI). The model architecture is meticulously crafted to enhance feature extraction and selectively focus on crucial regions within brain images, thereby improving diagnostic accuracy. A unique component, the MRI Segmentation Block (MSB), is introduced to manage the skull stripping task effectively, highlighting the model ability to learn from complex, multilayered information. We have incorporated a detailed experimental evaluation of the MSB, demonstrating its superior performance in cranial debridement tasks compared to existing methods. The experiments involved a range of MRI scans, assessing the MSB's accuracy through metrics like the Dice Coefficient and Jaccard Index against ground truth annotations by expert radiologists. The results substantiate the MSB's effectiveness, setting a new benchmark for precision in medical imaging diagnostics. The proposed method integrates densely connected neural networks with a connection-wise attention model to extract multiscale features from MRI scans. Furthermore, the attention mechanism is fine-tuned to emphasize salient features significantly associated with various stages of Alzheimer's disease, thereby setting a new benchmark for precision in medical imaging diagnostics. Extensive experiments on the Alzheimer Disease Neuroimaging Initiative (ADNI) dataset demonstrate the superiority of our method over traditional and contemporary approaches, with our model achieving high accuracy and computational efficiency. This makes it suitable for clinical applications where resources are limited. This study represents a significant advancement in the diagnostic process for AD, with potential implications for improving patient outcomes in clinical settings. © 2025 The Authors

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on building scientific data ontology

Research on building scientific data ontology

引用

4th International Conference on Developments in eSystems Engineering, DeSE 2011

作者： Goranova, Mariana Shishedjiev, Bogdan Georgieva, Juliana Department of Programming and Computer Technologies Technical University of Sofia Sofia Bulgaria

ISBN: (纸本)9781457721861

When dealing with complex systems design and application the notion of ontologies helps the process of application integration. To solve the problems with discover, interpret and reuse data we have to recognize ontology as a concept that formalizes the management and integration of information, services and processes. In this paper we present our work towards the development and evaluation of scientific data ontology that helps the system integration architect achieve interoperability between different systems. © 2011 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Healthcare Data Analytics Based on Machine Learning

Healthcare Data Analytics Based on Machine Learning

引用

2024 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2024

作者： Gancheva, Veska Technical University of Sofia Faculty of Computer Systems and Technologies Department of Programming and Computer Technologies Sofia1000 Bulgaria

ISBN: (纸本)9798350349832

Technology advancements have transformed medical science and practice, leading to the vast gathering of a wide range of medical data. Medical researchers use artificial intelligence techniques extensively because they enable the identification and creation of models of complicated datasets and the interactions between them. This, in turn, enables the successful prediction of future outcomes associated with a specific sickness type. An artificial intelligence-based approach to healthcare data analytics is presented, which leverages data to build a desired model and solve a particular issue. The suggested approach for healthcare data analytics uses a random forest and feedforward artificial neural network with two hidden layers as its basis to get the best model. © 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

Speech recognition with Transformers - Creating and testing datasets for Bulgarian language 30

Speech recognition with Transformers - Creating and testing ...

引用

30th International Scientific Conference Electronics, ET 2021

作者： Mateva, Maya Angelova, Maria Faculty of Computer Systems and Technologies Technical University of Sofia Department of Programming and Computer Technologies Sofia1000 Bulgaria

ISBN: (纸本)9781665445184

Speech is a natural way of communicating between human beings and as such, it triggers an interest of transforming it to a way of interaction with a computer as well. Once it is converted into a sequence of words, it can easily be applied for executing commands, thus enabling people to perform tasks easily or in some cases - tasks that are even impossible for them to be performed. The automatic speech recognition becomes a task solved with various success based on the accuracy, online/offline availability, speed. However, with the constant improvement of the neural networks, it is getting easier to solve and the most prominent solution seems to be the Transformer architecture of neural networks. In this paper, we describe the design of an encoder-decoder TensorFlow architecture and the process of training the model with a specially created Bulgarian dataset. © 2021 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Application of Logistic Regression Technique for Predicting Student Dropout 31

Application of Logistic Regression Technique for Predicting ...

引用

31st International Scientific Conference Electronics, ET 2022

作者： Ujkani, Berat Minkovska, Daniela Stoyanova, Lyudmila Technical University of Sofia Faculty of Computer Systems and Technologies Department of Programming and Computer Technologies Sofia1000 Bulgaria

ISBN: (数字)9781665498784

ISBN: (纸本)9781665498784

Student dropout in higher education is a complex issue and as a process it includes many factors which may affect each other. This paper explores the use and application of a probabilistic supervised machine learning technique for predicting university student dropout to obtain insights on the students at risk and prevent them from dropping out the studies. Data from a public university in the Republic of Kosovo were obtained and examined. The dataset comprises instances of students' dropouts for the past six academic years along with their demographics, grades, enrollment details etc. Logistic Regression, as one of the most widely used Machine Learning and Artificial Intelligence algorithms, was used to build the model and produce the predictions. First, a statistical analysis was conducted and after the data preprocessing, logistic regression classifier was implemented. The results show that a high prediction accuracy was reached, with a percentage of 90%, and a F1 score of 0.85, indicating that the model is performing great and the predictions results are reliable. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Predicting Student Enrollment in the University 30

A Machine Learning Approach for Predicting Student Enrollmen...

引用

30th International Scientific Conference Electronics, ET 2021

作者： Ujkani, Berat Minkovska, Daniela Stoyanova, Lyudmila Faculty of Computer Systems and Technologies Technical University of Sofia Department of Programming and Computer Technologies Sofia1000 Bulgaria

ISBN: (纸本)9781665445184

The Matura exam is the final national examination that high school students in many countries must pass to be eligible for admission to a university. This paper discusses the key factors that have the most impact in producing a reliable machine learning model for predicting students' enrollment in the university. These factors include the final grades from each high school year, matura exam results and the university entry exam points. It should be noted that demographic factors were not taken into consideration in this study. Four machine learning (ML) techniques with a total of sixteen algorithms were implemented using the Weka software: Bayes (Bayes Net, Naive Bayes, etc.), Logistic Regression (Logistic and SimpleLogistic), K-Nearest Neighbors (IBK, KStar, and LWL) and Decision Tree (J48, Random Forest, RepTree, etc.). According to the results, The RepTree algorithm performed the best with a True Positive (TP) rate of 0.902 and a False Positive (FP) rate of 0.148. The algorithm with the lowest performance was NaiveMulti with a TP rate of only 0.790. However, the range between the worst and the best-performing algorithms was 14.18%. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Data security and validation framework for a scientific data processing SOA based system

Data security and validation framework for a scientific data...

引用

4th International Conference on Developments in eSystems Engineering, DeSE 2011

作者： Gancheva, Veska Programming and Computer Technologies Department Technical University of Sofia Sofia Bulgaria

ISBN: (纸本)9781457721861

A data security and validation framework of a SOA based system for management, storage, processing and visualization of data obtained from scientific experiments is proposed in this paper. The framework covers the three levels of data security: authorized user access;data encryption and data validation. To ensure authorized user access three access levels are provided: ownership, distribution rights and read rights. To ensure the data encryption an asymmetric 128-bit encrypting method based on public and private key is implemented. A universal approach for complete data validation has been suggested and implemented as web service. Data validation service allows validating the input data processed by each of the modules in the system. A declarative language defining the data validation and their interpretation based on XML standard is specified, by which precise rules in XML format are established and simultaneously with a library that supports this grammar is performed. In the language structures are included elements describing the data, rules and logic, which have to satisfy the input data. The actual definition is supported by a definition repository XML file and allows adding additional field types or complex validation logic as needed and easy modification of the validation rules. © 2011 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Automatic conversion of scientific data into canonical format

Automatic conversion of scientific data into canonical forma...

引用

IEEE EUROCON-International Conference on computer As A Tool

作者： Goranova, Mariana Shishedjiev, Bogdan Georgieva, Juliana Achev, Velin Department of Programming and Computer Technologies Technical University of Sofia Sofia Bulgaria

ISBN: (纸本)9781424474868

The purpose of the automatic conversion of scientific data into canonical format is to provide a link between raw representation of data and database schemas. On the basis of these concepts Web services are developed for automatic XML description. They describe structurally and semantically scientific data and the conversion of the raw data layout description into canonical form based on data semantics. The canonical form looks like a relational data model where efficient methods for storage and retrieval of scientific data have been used. This paper describes the implementation of the converter compiler of raw scientific data layout description into canonical format. Using canonical XML form we have achieved better standardization of the input for data manipulation and visualization routines and minimization of their number. © 2011 IEEE.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

Estimation of Energy Performance Classes of Concrete Structures with Artificial Intelligence Models 3

Estimation of Energy Performance Classes of Concrete Structu...

引用

3rd International Conference on High Technology for Sustainable Development, HiTech 2020

作者： Can, Hamit Minkovska, Daniela Stoyanova, Lyudmila Technical University of Sofia Department of Programming and Computer Technologies Sofia Bulgaria

ISBN: (纸本)9781728186511

The construction sector is one of the sectors that make energy efficiency a must. In almost every field related to the construction sector, there is a need for studies in which high performance can be achieved by including artificial intelligence in energy. In this study, energy class models, which are an area of artificial intelligence, which show the efficiency level of energy systems that determine the energy performance of buildings, are examined. © 2020 IEEE.

关键词： Energy efficiency

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：