检索结果-内蒙古大学图书馆

A mathematical reaction–diffusion model describing the connection between smokers and tuberculosis patients

Partial Differential Equations in Applied Mathematics 2025年 14卷

作者： Khaloufi, Issam Karim, Marouane Rhila, Soukaina Ben Rachik, Mostafa Laboratory of Analysis Modelling and Simulation Department of Mathematics and Computer Science Faculty of Sciences Ben M'Sik Hassan II University Casablanca Casablanca Sidi Othman BP 7955 Morocco Multidisciplinary Research and Innovation Laboratory (LPRI) Moroccan School of Engineering Sciences (EMSI) Casablanca Morocco

In this paper, we introduce a new mathematical model that incorporates both temporal and spatial factors to characterize the relationship between the smoking population and tuberculosis (TB) cases. We validate the model's relevance by demonstrating the existence and positivity of the solutions. Furthermore, we propose three control measures aimed at reducing TB and smoking transmission, focusing on limiting contact between smokers and non-smokers, improving awareness of the health risks associated with smoking, and ensuring timely and effective medical treatment for TB patients. Mathematical analysis is employed to demonstrate the existence and characteristics of optimal controls for these strategies. The theoretical results are verified using numerical simulations, which also confirm the effectiveness of the suggested control strategies. Our results underline the importance of considering spatiotemporal dynamics in disease modeling and control, and they offer crucial insights for public health initiatives aimed at reducing the prevalence of smoking and TB. © 2025 The Authors

关键词： Mathematical model Optimal control Smoking Spatiotemporal dynamics Tuberculosis

来源：评论

学校读者我要写书评

暂无评论

3D Brain Tumor Volume Reconstruction and Quantification using MRI Multi-modalities Brain Images 10

3D Brain Tumor Volume Reconstruction and Quantification usin...

引用

10th E-Health and Bioengineering Conference, EHB 2022

作者： Pana, Lenuta Moldovanu, Simona Moraru, Luminita The Modelling & Simulation Laboratory University Dunarea de Jos of Galati UGAL Galati Romania Faculty of Automation Computers Sciences Electronics and Electrical Engineering Dunarea de Jos University of Galati Galati Romania Department of Chemistry Physics and Environment Faculty of Sciences and Environment University Dunarea de Jos of Galati UGAL Galati Romania

ISBN: (纸本)9781665485579

Brain tumor volume quantification is not possible with magnetic resonance imaging (MRI) non-invasive imaging systems. Usually, the brain MR imaging modality is based on four modalities T1, T1ce (contrast-enhanced), T2, and FLAIR (Fluid-Attenuated Inversion Recovery) highlighting various complex brain structure. The aim of this study is to develop an automated brain tumor segmentation method to allow an effective 3D tumor reconstruction and volume quantification. The Local Graph Cut (LGC) and Flood fill (FF) segmentation tools are used. A 3D reconstruction is performed using the open-source ImageJ image processing package. To assess the brain tumor segmentation accuracy a 3D Dice score is used. This extensive study is conducted on the MICCAI BraTS2020 dataset and shows that the proposed model obtains good results. To evaluate the final full segmentation of 3D volume accuracy, we use three brain modalities, namely T1 and T2 weighted, and T1ce scans. Also, to measure accuracy of segmentation we take the advantage of the existing ground truth image dataset. We find an average Dice score of 0.501 ± 0.128 for T2-weighted images and LGC algorithm. Also, there are not important differences between the results provided by investigated algorithms for all images types. The 3D reconstruction and volumetric analysis via 2D segmented slices produce realistic shape samples. The computed volumes are in the limit of 71% from the tumor volume computed using the ground truth images. © 2022 IEEE.

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

Discret Wavelet Fingerprint Features for ANNs Classification Method 10

Discret Wavelet Fingerprint Features for ANNs Classification...

引用

10th E-Health and Bioengineering Conference, EHB 2022

作者： Dinca Lazarescu, Andreea-Monica Moldovanu, Simona Moraru, Luminita The Modelling & Simulation Laboratory University Dunarea de Jos of Galati UGAL Galati Romania Faculty of Automation Computers Electrical Engineering and Electronics University Dunarea de Jos of Galati UGAL Galati Romania Faculty of Sciences and Environment Department of Chemistry Physics and Environment University Dunarea de Jos of Galati UGAL Galati Romania

ISBN: (纸本)9781665485579

The current study examines the impact of discrete wavelet transforms (DWT) and their success rate in the fingerprint images classification. The analyzed fingerprint images belong to the FVC2004 database. Two datasets consist of 80 real images acquired using an optical sensor and 80 synthetic images, respectively, are built. Four discrete wavelet transform families (Coiflets, Symlets, Fejer - Korovkin and Biorthogonal) are implemented for one level of wavelet decomposition. For Low-Low (LL) and High-High (HH) sub-bands, the entropy and energy features are extracted as they contain rich descriptions of the pattern. For each dataset, eight features are extracted, for each image. To reduce the dimensionality of the feature space, the Principal Component Analysis (PCA) is used. The first three principal components (PCs) fed a neural network classifier. The Radial Base Function Neural Network (RBFNN) model efficiently classified the fingerprint images based on PCs obtained for LL frequency level images features, with an accuracy of 88.13% and sensitivity of 95%. © 2022 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Texture Analysis of Breast US Images Using Morphological Transforms, Hausdorff Dimension and Bagging Ensemble Method

Texture Analysis of Breast US Images Using Morphological Tra...

引用

Mediterranean Conference on Control and Automation (MED)

作者： Gigi Tăbăcaru Simona Moldovanu Marian Barbu Department of Automatic Control and Electrical Engineering Faculty of Automation Computers Electrical Engineering and Electronics “Dunarea de Jos” University of Galati Romania Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics “Dunarea de Jos” University of Galati The Modelling & Simulation Laboratory Dunarea de Jos University of Galati Galati Romania

ISBN: (数字)9798350395440

ISBN: (纸本)9798350395457

In this work, an attempt is made for the first time to use the measurement pattern generated by morphological transformation quantified by Hausdorff fractal dimension (HFD) and classified with ensemble learning based on bagging. The proposed work uses three morphological transformations for image preprocessing: hit-and-miss transform (HMT), white (WHT), and black top-hat (BHT). The pattern texture of US breast images is described by extracting the HFD from the regions of interest (ROI) after the ultrasound (US) images have been preprocessed. The main objective of this study was achieved by comparatively analyzing the classification performance of features using the Random Forest (RF), Extra Trees (ET) classifier, and bagging ensemble method based on XGBoot classifier. In presented study, the XGBoost classifier and BHT image processing method give an accuracy of 89.8% in a binary classification, benign versus malignant breast cancer.

关键词： Ultrasonic imaging Transforms Feature extraction Time measurement Fractals Ensemble learning Image preprocessing

来源：评论

学校读者我要写书评

暂无评论

Autonomous Path Optimization in Unfamiliar Map Through Deep Reinforcement Learning

Autonomous Path Optimization in Unfamiliar Map Through Deep ...

引用

IEEE International Conference on Artificial Intelligence in engineering and Technology (IICAIET)

作者： Longxin Wei Kit Guan Lim Min Keng Tan Chung Fan Liau Tianlei Wang Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia Faculty of The Internet of Things and Artificial Intelligence Fujian Polytechnic of Information Technology Fuzhou China Faculty of Intelligent Manufacturing Wuyi University Jiangmen China

The application of mobile robot's path planning and navigation in known map scenarios has been well-established. However, with the absence of a known map, the challenge lies in how a robot can effectively navigate through an unfamiliar environment and generate a sensible path towards its destination. This paper delves into the path planning quandary that mobile robot encountered in unknown environments. It employs a deep reinforcement learning (DRL) algorithm within a simulated environment, where the robot explores its objective. Additionally, an enhanced reward selection strategy is introduced through a performance-based comparison. This strategy tackles issues such as robot freezing and high collision rates during the exploration of uncharted territory. The outcome of this study is an enhancement in search performance and learning efficiency within path planning. The integration of this algorithm into the Robot Operating System (ROS) robot simulation platform, coupled with testing within the Gazebo simulation environment, demonstrates that the proposed strategy effectively diminishes obstacle collisions and boosts the success rate of reaching the intended destination.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Q-Learning Algorithm for Path Planning of an Automated Guided Vehicle (AGV)

Improved Q-Learning Algorithm for Path Planning of an Automa...

引用

IEEE International Conference on Artificial Intelligence in engineering and Technology (IICAIET)

作者： Hao Guo Min Keng Tan Kit Guan Lim Helen Sin Ee Chuo Baojian Yang Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia Department of Automation Baotou Light Industry Vocational and Technical College Baotou City China Department of Intelligent Manufacturing Wuyi University Jiangmen China

With the development of modern industry 4.0, intelligent path planning is an essential research direction of schedule systems for an automated guided vehicle (AGV), which has been widely used in logistics distribution centers of enterprises. This work implements the improved Q-learning algorithm to solve the typical obstacle avoidance problems in path planning. Specifically, the conventional Q-learning algorithm has shortcomings including low operational efficiency and slow learning speed. The improved Q-learning algorithm is successively proposed by adding a learning process based on the original Q-learning algorithm, which enables AGV to find obstacles and target locations within the shortest time, thus improving the efficiency of path planning. Finally, the simulation experiments are carried out in the grid environment with MATLAB. In comparison to the conventional Q-learning algorithm, the improved Q-learning algorithm has faster convergence and higher learning efficiency, improved by 20%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based segmentation of breast masses using convolutional neural networks 12

Deep learning-based segmentation of breast masses using conv...

引用

12th International Conference on Mathematical Modeling in Physical Sciences, IC-MSQUARE 2023

作者： Anghelache Nastase, I.-N. Moldovanu, S. Moraru, L. The Modelling & Simulation Laboratory Dunarea de Jos University of Galati 47 Domneasca Street Galati800008 Romania Emil Racovita Theoretical Highschool 12-14 Regiment 11 Siret Street Galati800332 Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati 47 Domneasca Street Galati800008 Romania Department of Chemistry Physics & Environment Faculty of Sciences and Environment Dunarea de Jos University of Galati 47 Domneasca Street Galati800008 Romania

Automatic breast tumor segmentation based on convolutional neural networks (CNNs) is significant for the diagnosis and monitoring of breast cancers. CNNs have become an important method for early diagnosis of breast cancer and, thus, can help decrease the mortality rate. In order to assist medical professionals in breast cancer investigation a computerized system based on two encoder-decoder architectures for breast tumor segmentation has been developed. Two pre-trained DeepLabV3+ and U-Net models are proposed. The encoder generates a high-dimensional feature vector while the decoder analyses the low-resolution feature vector provided by the encoder and generates a semantic segmentation mask. Semantic segmentation based on deep learning techniques can overcome the limitations of traditional algorithms. To assess the efficiency of breast ultrasound image segmentation, we compare the segmentation results provided by CNNs against the Local Graph Cut technique (a semi-automatic segmentation method) in the Image Segmenter application. The output segmentation results have been evaluated by using the Dice similarity coefficient that compares the ground truth images provided by the specialists against the predicted segmentation results provided by the CNNs and Local Graph Cut algorithm. The proposed approach is validated on 780 breast ultrasonographic images of the BUSI public database of which 437 are benign and 210 are malignant. The BUSI database provides classification (benign or malignant) labels for ground truth in binary mask images. The average Dice scores computed between the ground truth images against CNNs were as follows: 0.9360 (malignant) and 0.9325 (benign) for the DeepLabV3+ architecture and of 0.6251 (malignant) and 0.6252 (benign) for the U-Net, respectively. When the segmentation results provided by CNNs were compared with the Local Graph Cut segmented images, the Dice scores were 0.9377 (malignant) and 0.9204 (benign) for DeepLabV3+ architecture and 0.61

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

CFD-DEM modelling of mixing and segregation of binary mixtures of ellipsoidal particles in liquid fluidizations

引用

Journal of Hydrodynamics 2019年第6期31卷 1190-1203页

作者： Esmaeil Abbaszadeh Molaei Aibing Yu Zongyan Zhou Laboratory for Simulation and Modelling of Particulate Systems Department of Chemical EngineeringMonash UniversityClaytonVic 3800Australia

Solid-liquid fluidized beds of binary mixtures are widely used in many *** segregation may occur as particles can differ in size,density,or *** studies have been conducted in the past to understand the effects of particlesize and density on the mixing and segregation,but the effect of particle shape has not been well ***,in the present work,CFD-DEM approach is employed to perform a numerical analysis of the effect of particle shape on the particle mixing and segregation phenomenon in liquid fluidization *** particle shapes from oblate to prolate are produced by varying aspect ratio of ellipsoids from 0.25 to 3,and eight binary mixtures of spheres and ellipsoids are *** results show that when oblate or prolate particles are added to spheres,the segregation takes *** segregation degree increases with particle aspect ratio diverging from 1.0 and also liquid superficial *** relationship of mixing index with aspect ratio under different liquid velocities is established,and a detailed explanation is *** is revealed that increasing the projected area and hence the drag force results in the separation of ellipsoidal particles from spheres.

关键词： Mixing segregation binary mixture ellipsoids liquid fluidization CFD-DEM

来源：评论

学校读者我要写书评

暂无评论

Melanoma Detection using a Random Forest Algorithm 10

Melanoma Detection using a Random Forest Algorithm

引用

10th E-Health and Bioengineering Conference, EHB 2022

作者： Damian, Felicia-Anisoara Moldovanu, Simona Moraru, Luminita The Modelling & Simulation Laboratory University Dunarea de Jos of Galati UGAL Galati Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics University Dunarea de Jos of Galati UGAL Galati Romania Department of Chemistry Physics and Environment Faculty of Sciences and Environment University Dunarea de Jos of Galati UGAL Galati Romania

ISBN: (纸本)9781665485579

In recent years, statistical evidence has identified melanoma as a major cause of skin cancer deaths. In this study, we propose a skin analysis lesions based on colour features (C) and Hu (H) moments to differentiate benign (nevi) and malignant (melanoma) lesions and, a classification based on Random Forest algorithm. Colour features are found as follows. Pre-processing for hair removing using the Dull-razor method;image segmentation based on the optimal colour threshold set on each RGB colour channel (red, green, blue);23 colour features extraction using the minimum and maximum RGB intensity and Hu moments;Random Forest (RF) algorithm to accurately differentiate benign and malignant skin lesions. This study used three datasets: 7-Point, Med-Node, PH2. RF classifier performance in terms of accuracy was: 94% for the 7-point dataset with H5, H7, H6, H2, C08 selected as relevant features;98.1% for the Med-Node dataset and H7, H5, H6, H2, H1 ACC the relevant features;and, 96.5% for the PH2 dataset and H5, H6, H7, C03, H1 selected as relevant features, respectively. Shape features based on Hu moments are found to improve the classification performance of the skin lesions compared to the colour features. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improved Classification of Benign and Malignant Breast Lesions Based on Contrast Manipulation and Gradient Map 10

Improved Classification of Benign and Malignant Breast Lesio...

引用

10th E-Health and Bioengineering Conference, EHB 2022

作者： Nastase, Iulia-Nela Anghelache Moldovanu, Simona Moraru, Luminita The Modelling & Simulation Laboratory University Dunarea de Jos of Galati UGAL Galati Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics University Dunarea de Jos of Galati UGAL Galati Romania Department of Chemistry Physics and Environment Faculty of Sciences and Environment University Dunarea de Jos of Galati UGAL Galati Romania

ISBN: (纸本)9781665485579

This study proposes an approach to enhance the contrast breast ultrasound (BUS) images with the preservation of the finer details. The main idea is to use the relevant and most important features in the classification of BUS images as benign or malignant. Among the contrast manipulation techniques, both linear under- and overexposure methods, contrast limiting adaptive histogram equalization (CLAHE) method and homomorphic filtering are used. The gradient maps of original images are generated for further analysis. Also, the gradient maps of original images are improved by the local mean subtraction and divisive normalization. Eight structural features are extracted from each gradient map image type. The extracted features feed a Random Forest (RF) classifier to determine their relevance for BUS images classification. An accuracy of 97.12% has been obtained for improved gradient map images and 93.03% for gradient map images. © 2022 IEEE.

关键词： Image classification

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：