检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Islam, Md. Hasibul Mondal, Manishankar Khulna University Computer Science and Engineering Discipline Khulna9208 Bangladesh

ISBN: (纸本)9798350370249

Code clones, identical or substantially similar code segments in a code base, have both negative and positive impacts on evolving software. Detecting code clones is important for many reasons, such as bug fixing, change suggestions, refactoring, bug replication analysis, etc. An existing study shows that a significant number of bugs are propagated through code clones. However, Micro-clones (clones of code shorter than 5 lines long) were not considered in this study. Thus, bug propagation through micro-clones is still unexplored. This research paper presents an empirical investigation of the propagation of bugs through micro-clones. In particular, two evolutionary patterns are studied that indicate the propagation of bugs by code cloning. Initially, this paper detects micro-clones that have gone through bugfix modifications by examining the history of software evolution. Subsequently, these ascertain which of these micro-clones have evolved in accordance with the patterns of bug propagation. Based on this analysis of several hundreds of commits from four Java-based open-source systems, it has been found that as many as $\mathbf{6 3 \%}$ of the micro clone segments that have gone through bugfix modifications may contain propagating bugs. Approximately 29.41% of the bugfixes encountered by the micro clones are attributed to fixing propagating bugs. This paper's finding indicates that identical micro clones predominantly contribute to bug propagation rather than near-miss micro clones. Propagation has a greater likelihood of occurring in the clone segments that are formed during a single commit action instead of in different commits. This discovery's significance lies in the ability to prioritize micro-clones for refactoring and monitoring in terms of bug propagation. © 2024 IEEE.

关键词： bug propagation code cloning Micro-clones software evolution software maintenance

来源：评论

学校读者我要写书评

暂无评论

Discovering Bengali Consonant-Linked Vowels in Facial Images using Neural Architecture Search 3

Discovering Bengali Consonant-Linked Vowels in Facial Images...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Hasib Uddin, A. Arif, Abu Shamim Mohammad Khulna University Computer Science and Engineering Discipline Khulna9208 Bangladesh

ISBN: (纸本)9798350388282

Visual Speech Recognition (VSR) plays a crucial role in cognitive functions, particularly for individuals with hearing impairment. This research delves into the realm of Bengali VSR, addressing the scarcity of works in this domain. Our focus is on consonant-associated vowel identification. Leveraging the efficiency of Neural Architecture Search (NAS), we aim to discover the most effective Neural Network (NN) model for enhancing consonant-associated vowel recognition rates. Face images emerge as superior features compared to lip images, and our work builds upon this insight. We created a dataset with 2030 consonant and 345 vowel-pronouncing images from four speakers. For benchmarking, we applied 17 different state-of-the-art (SOAT) models. The results show that our proposed methods achieved maximum 70% accuracy, surpassing all the benchmarks. Notable contributions include: the introduction of consonant-associated vowel identification in Bangla and the application of NAS to identify optimal NN architectures. This research strives to fill critical gaps in Bangla VSR, ultimately contributing to improved recognition rates and fostering inclusivity in communication technologies. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Multiple Deep Learning Models for Image Retrieval Problems 2nd

Performance Analysis of Multiple Deep Learning Models for Im...

引用

2nd International Conference on Big Data, IoT and Machine Learning, BIM 2023

作者： Golder, Swajan Debnath, Rameswar Computer Science and Engineering Discipline Khulna University Khulna9208 Bangladesh

ISBN: (纸本)9789819989362

In modern times, the exponential growth of digital images threatens conventional image retrieval frameworks. Shallow machine learning algorithms degrade image retrieval performance owing to the semantic gap between low-level and high-level features. Hence, deep learning (DL) is a possible way to escape from this. Previous studies have yet to determine the superior DL model or combination for similarity-based image retrieval. In this paper, we apply deep features instead of traditional features for image retrieval. We first execute eight pretrained DL models individually and then all pairs combining two, three, and four models. Experimental results show that model combinations outperform single models, with increased accuracy as the number of models increases. We combine a maximum of four models. Our empirical findings from various model combinations indicate that the most effective combination includes ResNet101V2, InceptionV3, InceptionResNetV2, and DenseNet201, yielding a mean average precision (mAP) of 97.55% and mean average recall (mAR) of 19.51%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Permutation Feature Importance-Based Cardiovascular Disease (CVD) Prediction Using ANN 2nd

Permutation Feature Importance-Based Cardiovascular Disease ...

引用

2nd International Conference on Big Data, IoT and Machine Learning, BIM 2023

作者： Joly, Nurzahan Akter Arif, Abu Shamim Mohammad Computer Science and Engineering Discipline Khulna University Khulna9208 Bangladesh

ISBN: (纸本)9789819989362

Diseases affecting heart and blood arteries are often referred to as cardiovascular diseases. It is crucial to predict and diagnose accurately cardiovascular disease in order to provide proper treatment. For detection of hidden patterns of cardiovascular diseases from massive amounts of data, deep learning techniques are commonly used. Different predictive models are used in health care to anticipate patient’s future ailments by learning from their prior data. This study seeks to create an intelligent agent for making such predictions automatically. This research mainly contributed to discover the most important attributes that best define the relationship with the target attribute and to find a proper algorithm for the prediction of cardiovascular disease. Using methods like Pearson correlation analysis and permutation feature importance along with effective data preprocessing techniques, the most crucial characteristics of cardiovascular diseases have been determined. A consolidated dataset from IEEEDataPort was used in this study. This study achieved 95% accuracy in predicting cardiac disease using Artificial Neural Network (ANN). This research will help healthcare people to predict a person’s cardiovascular disease at early stage. It will also help researchers discover more ways to anticipate cardiovascular illnesses. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Skin Disease Classification Using LIME and Weighted Average Ensemble Model

Enhancing Skin Disease Classification Using LIME and Weighte...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Ahmed, Md. Estiak Pinki, Farhana Tazmim Khulna University Computer Science and Engineering Discipline Khulna9208 Bangladesh

ISBN: (纸本)9798331529765

Skin diseases (SD) include a broad spectrum of skin-related problems, such as cancer, autoimmune diseases, and infections. They can manifest as rashes, bumps, discoloration, or changes in texture, often requiring precise diagnostic methods for effective management. Timely and efficient treatment of skin diseases depends on an accurate diagnosis. This study introduces a weighted ensemble model designed to enhance the diagnostic accuracy of various skin conditions, specifically classifying eight different categories. The model combines multiple classifiers to boost predictive performance, achieving remarkable results: 99% precision, 99% recall, and an F1 score of 99%. Additionally, it attained an overall accuracy of 99%, a Cohen's Kappa of 99%, and a minimal Hamming loss of *** used LIME (Local Interpretable Model-agnostic Explanations) to offer clear insights into the model's predictions, helping to explain how the model makes its decisions. LIME promotes transparency and aiding clinical decision-making in dermatology. These interpretable models allow practitioners to understand which features are most influential in diagnosing specific skin conditions. These results indicate a highly reliable system that could significantly support clinical decision-making in dermatology. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Identification of Lung Cancer Using Particle Swarm Optimization and Machine Learning Technique 3rd

Identification of Lung Cancer Using Particle Swarm Optimiza...

引用

3rd International Conference on Trends in Electronics and Health Informatics, TEHI 2023

作者： Kabir, Sheikh Ridwan Raihan Mondal, Hirak Nag, Anindya Jamil, S. M. Hasan Das, Piya Department of Computer Science and Engineering North Western University Khulna9000 Bangladesh Computer Science and Engineering Discipline Khulna University Khulna9208 Bangladesh

ISBN: (纸本)9789819739363

Lung cancer is a specific kind of malignancy that arises in the tissues of the lungs, specifically in the cells that comprise the lining of the respiratory passages. Smoking is well recognized as the primary etiological factor contributing to the development of lung cancer. The inhalation of secondhand smoke, as well as exposure to asbestos or radon inside one’s own residence, Being employed, and having a familial predisposition to the ailment are further factors. Factors contributing to the chance of developing lung cancer. In their lifetime, 1 in 16 men and 1 in 17 women were diagnosed with lung cancer. The variability in survival rates may be attributed to the extent of illness dissemination at the time of its identification. Early detection may have substantial benefits. The term "impact" refers to the effect or influence that something has on a particular situation. The dataset was collected from a website. The study used a global-based Particle swarm Optimization (PSO) algorithm for feature selection. With our approach, we want to improve the dataset’s statistical feature accuracy and predict lung cancer accurately based on the given data. Among the employed classifiers, the Support vector machine and Naive Bayes obtained maximum accuracy of 97% with 8 out of 16 features. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Towards Accurate Renal Micro-Structure Segmentation: An Assessment of YOLOv8 and Mask R-CNN Models

Towards Accurate Renal Micro-Structure Segmentation: An Asse...

引用

2024 IEEE International Women in engineering (WIE) Conference on Electrical and computer engineering, WIECON-ECE 2024

作者： Ahmed, Md. Estiak Pinki, Farhana Tazmim Quader, Mozdaher Abdul Quader, Montaser Abdul Ayrin, Fateha Jannat Anwar, Ahmed Selim Roy, Prosenjit Computer Science and Engineering Discipline Bangladesh Department of Computer Science and Engineering Bangladesh Department of Computer Science and Engineering Bangladesh Department of Eee Bangladesh Prairie View A & M University Department of Computer Science TX United States

ISBN: (纸本)9798331535476

In the field of medical imaging, correct instance segmentation is essential. This work attempts to address the problems related to renal micro-structure segmentation by using the power of YOLOv8 and special MASK R-CNN models to facilitate the development of more rapid and accurate nephrology diagnosis, which will benefit physicians and other healthcare providers. Improved medical imaging analysis is made possible by the model's high precision rate of 'glomerulus' and 'blood vessel' structure detection. The application of the MASKRCNN framework, which successfully integrated pertinent annotations to boost visual understanding, increased the clarity of image interpretation. Additionally, this work uses the HuBMAP dataset to segregate renal microstructures using the YOLOv8 and Mask R-CNN techniques. Strong performance was shown by the YOLOv8 model, which received an IoU score of 84.55%. The Mask R-CNN model received an IoU score of 80.66%, indicating its potential. It is an impressive accomplishment to obtain a high IoU score for YOLOv8 in the context of medical photo segmentation, since this suggests that there is still room for further improvement and optimization of the model. For medical professionals, the IoU scores are crucial since they offer a technique to improve accuracy and reliability when it comes to nephrology diagnosis. In order to improve diagnosis accuracy and enable broader clinical adoption, future research aims to improve these IoU ratings. The observed disparity underscored the inherent complexities associated with differentiating between ambiguous kidney structures and also the pressing need for further advancement. Our preliminary work demonstrates the potential of MASK-RCNN and YOLOv8 in the challenging field of renal micro-structure segmentation. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Comparison of multiclass classification techniques using dry bean dataset

引用

International Journal of Cognitive Computing in engineering 2023年第1期4卷 6-20页

作者： Salauddin Khan, Md Nath, Tushar Deb Murad Hossain, Md Mukherjee, Arnab Bin Hasnath, Hafiz Manhaz Meem, Tahera Khan, Umama Statistics Discipline Science Engineering and Technology School Khulna University Khulna-9208 Bangladesh Department of Computer Science and Engineering Jahangirnagar University Dhaka Bangladesh Modeling and Data Science University of Turin Italy Mathematics Discipline Science Engineering and Technology School Khulna University Khulna-9208 Bangladesh Biotechnology and Geneetic Engineering Discipline Life Science School Khulna University Khulna-9208 Bangladesh

Background: The application of classsification methods through multivariate and machine learning techniques has enormous significance in agricultural sector. It is vital to classify various types of seeds as well as identify the quality of seeds which has a great impact on the production of crops. There is a wide range of genetic variations in dry beans all over the world. Many studies have been conducted previously on various dataset to indentify the sorts of dry beans, however most of them focused on machine learning techniques with binary classification. Objective: The aim of this study is to investigate a reliable classifier which has the lowest noise implications and establish an algorithm for dry bean classification effectively. This paper focuses on outlier removals, oversampling with Adaptive Synthetic (ADASYN) algorithm and finding the best classifier to guarantee the highest possible accuracy. Methods: The raw dataset for this study was accessed from UCI Machine Learning Repository. The dataset contained grains having 16 features, 12 dimensions, and 4 distinct shapes. For the purpose of eliminating missing values from the dataset, interquartile range (IQR) with python programming was utilized. Eight most popular classifiers were used in this study which are Logistic Regression (LR), Naïve Bayes (NB), k-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGB), Support Vector Machine (SVM), and Multilayer Perception (MLP) with balanced and imbalanced classes. The authors utilized frequency tables, bar diagrams, boxplots, analysis of variance for descriptive analysis as well as data preprocessing. Results: The XGB classifier preferably outperformed than other classifiers with balanced and imbalanced distribution of dry beans within each class. It has acquired accuracy (ACC) 93.0% and 95.4% in imbalanced and balanced classes respectively. In case of balanced dataset, after application of ADASYN algorithm both KNN and RF t

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Churn Prediction with Explainability for the Customers of Telecom Industry 2

Churn Prediction with Explainability for the Customers of Te...

引用

2nd International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2023

作者： Mohajon, Joydwip Mohammad Arif, Abu Shamim Khulna University Computer Science and Engineering Discipline Khulna Bangladesh

ISBN: (纸本)9798350358667

Customer churn prediction is an essential task in any market segment that deals with customers. The Telecom industry is one such market sector where customer management plays a crucial role. From existing research, it is clear that the cost of retaining the current customers is much lower than the cost of gaining new customers. Hence, the prior detection of the churn customers becomes very important. This paper presents a churn prediction methodology for the telecom industry that aims at better identifying the customers who might churn. Seven machine learning models are trained using three publicly available datasets. The experimental results of this study reveal great performances compared to existing works in terms of recall, F1-score, and AUC-score. Moreover, new feature crosses are explored in this research which are found to be impactful in predicting customer churn. Finally, the best models are explained using SHapley Additive exPlanations (SHAP), an explainable AI technique. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Recognition from MRI Using Deep Learning with Data Balancing Methods and Its Explainability with AI 4th

Brain Tumor Recognition from MRI Using Deep Learning with Da...

引用

4th International Conference on Image Processing and Capsule Networks, ICIPCN 2023

作者： Al Noman, Abdullah Arif, Abu Shamim Mohammad Computer Science and Engineering Discipline Khulna University Khulna Bangladesh

ISBN: (纸本)9789819970926

The abnormal growth of brain cells is a disease that can damage human brains and lead to malignant brain cancer. This abnormal growth in the brain is called a brain tumor. In the past few years, the number of brain tumor-related patients has increased at an extraordinary rate, due to which brain tumor is at the tenth position in the list of common tumors. But if a brain tumor is detected very early, it is possible to increase the way to get rid of this disease. Researchers are working tirelessly to develop automatic systems for brain tumor recognition. Hence, this paper proposes an automated system for brain tumor recognition based on deep learning and image processing. The dataset used in this article was collected from Kaggle and was not balanced. The dataset was preprocessed using a high boost filter and non-local means denoising technique, and then augmentation and SMOTE were applied to balance the dataset. Finally, different deep learning architectures were utilized. Among them, the ResNet50 model achieved 99.62% accuracy for 15-class recognition. The experimental result showed the reliability of the proposed model. This research will enable the research community to explore further brain tumor recognition from MRI using deep learning. It will also help the physician to detect brain tumors earlier. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Magnetic resonance imaging

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：