检索结果-南通市图书馆

A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification

Journal of Computer and Communications 2024年第2期12卷 173-200页

作者： Adama Dembele ronald waweru mwangi Ananda Omutokoh Kube Department of Mathematics Pan African University Institute for Basic Sciences Technology and Innovation Nairobi Kenya Department of Computing School of Computing and Information Technology Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya Department of Mathematics and Actuarial Sciences Kenyatta University Nairobi Kenya

Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.

关键词： MobileNet Image Classification Lightweight Convolutional Neural Network Depthwise Dilated Separable Convolution Hierarchical Multi-Scale Feature Fusion

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advancing Type II Diabetes Predictions with a Hybrid LSTM-XGBoost Approach

引用

Journal of Data Analysis and Information Processing 2024年第2期12卷 163-188页

作者： Ayoub Djama Waberi ronald waweru mwangi Richard Maina Rimiru Department of Mathematics Pan African University Institute for Basic Sciences Technology and Innovation (PAUSTI) Nairobi Kenya Department of Computing Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya School of Computing and Information Technology (SCIT) Jomo Kenyatta University of Agriculture and Technology (JKUAT) Nairobi Kenya

In this paper, we explore the ability of a hybrid model integrating Long Short-Term Memory (LSTM) networks and eXtreme Gradient Boosting (XGBoost) to enhance the prediction accuracy of Type II Diabetes Mellitus, which is caused by a combination of genetic, behavioral, and environmental factors. Utilizing comprehensive datasets from the Women in Data Science (WiDS) Datathon for the years 2020 and 2021, which provide a wide range of patient information required for reliable prediction. The research employs a novel approach by combining LSTM’s ability to analyze sequential data with XGBoost’s strength in handling structured datasets. To prepare this data for analysis, the methodology includes preparing it and implementing the hybrid model. The LSTM model, which excels at processing sequential data, detects temporal patterns and trends in patient history, while XGBoost, known for its classification effectiveness, converts these patterns into predictive insights. Our results demonstrate that the LSTM-XGBoost model can operate effectively with a prediction accuracy achieving 0.99. This study not only shows the usefulness of the hybrid LSTM-XGBoost model in predicting diabetes but it also provides the path for future research. This progress in machine learning applications represents a significant step forward in healthcare, with the potential to alter the treatment of chronic diseases such as diabetes and lead to better patient outcomes.

关键词： LSTM XGBoost Hybrid Models Machine Learning. Deep Learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Enhancing Pneumonia Detection in Pediatric Chest X-Rays Using CGAN-Augmented Datasets and Lightweight Deep Transfer Learning Models

引用

Journal of Data Analysis and Information Processing 2024年第1期12卷 1-23页

作者： Coulibaly Mohamed ronald waweru mwangi John M. Kihoro Department of Mathematics Pan African University Institute for Basic Sciences Technology and Innovation (PAUSTI) Nairobi Kenya Department of Computing Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya School of Computing and Mathematics The Cooperative University of Kenya Nairobi Kenya

Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.

关键词： Pneumonia Detection Pediatric Radiology CGAN (Conditional Generative Adversarial Networks) Deep Transfer Learning Medical Image Analysis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Stacking-Based Ensemble Approach with Embeddings from Language Models for Depression Detection from Social Media Text

引用

Journal of Data Analysis and Information Processing 2023年第4期11卷 420-453页

作者： Akwa Gaius ronald waweru mwangi Antony Ngunyi Department of Mathematics Pan African University Institute for Basic Sciences Technology and Innovation (PAUSTI) Nairobi Kenya Department of Computing Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya Department of Statistics and Actuarial Sciences Dedan Kimathi University of Technology Nairobi Kenya

Depression is a major public health problem around the world and contributes significantly to poor health and poverty. The rate of the number of people being affected is very high compared to the rate of medical treatment of the disease. Thus, the disease often remains untreated and suffering continues. Machine learning has been widely used in many studies in detecting depressive individuals from their contents on online social networks. From the related reviews, it is apparent that the application of stacking for diagnosing depression has been minimal. The study implements stacking based on Extra Tree, Extreme Gradient Boosting, Light Gradient Boosting and Multi-layer perceptron and compares its performance to state of the art bagging and boosting ensemble learners. To better evaluate the effectiveness of the proposed stacking approach, three pretrain word embeddings techniques including: Word2vec, Global Vectors and Embeddings from language models were employed with two datasets. Also, a corrected resampled paired t-test was applied to test the significance of the stacked accuracy against the baseline accuracy. The experimental results shows that the stacking approach yields favourable results with a best accuracy of 99.54%.

关键词： Machine Learning Natural Language Processing Depression

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Hybrid Ensemble Learning Approach Utilizing Light Gradient Boosting Machine and Category Boosting Model for Lifestyle-Based Prediction of Type-II Diabetes Mellitus

引用

Journal of Data Analysis and Information Processing 2023年第4期11卷 480-511页

作者： Mahadi Nagassou ronald waweru mwangi Euna Nyarige Institute for Basic Sciences Technology and Innovation Department of Mathematics Pan African University Nairobi Kenya School of Computing and Information Technology Department of Computing Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya Department of Mathematics Statistics and Actuarial Sciences Machakos University Nairobi Kenya

Addressing classification and prediction challenges, tree ensemble models have gained significant importance. Boosting ensemble techniques are commonly employed for forecasting Type-II diabetes mellitus. Light Gradient Boosting Machine (LightGBM) is a widely used algorithm known for its leaf growth strategy, loss reduction, and enhanced training precision. However, LightGBM is prone to overfitting. In contrast, CatBoost utilizes balanced base predictors known as decision tables, which mitigate overfitting risks and significantly improve testing time efficiency. CatBoost’s algorithm structure counteracts gradient boosting biases and incorporates an overfitting detector to stop training early. This study focuses on developing a hybrid model that combines LightGBM and CatBoost to minimize overfitting and improve accuracy by reducing variance. For the purpose of finding the best hyperparameters to use with the underlying learners, the Bayesian hyperparameter optimization method is used. By fine-tuning the regularization parameter values, the hybrid model effectively reduces variance (overfitting). Comparative evaluation against LightGBM, CatBoost, XGBoost, Decision Tree, Random Forest, AdaBoost, and GBM algorithms demonstrates that the hybrid model has the best F1-score (99.37%), recall (99.25%), and accuracy (99.37%). Consequently, the proposed framework holds promise for early diabetes prediction in the healthcare industry and exhibits potential applicability to other datasets sharing similarities with diabetes.

关键词： Boosting Ensemble Learning Category Boosting Light Gradient Boosting Machine

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Isolation and Characterization of SARS-CoV-2 in Kenya

引用

American Journal of Molecular Biology 2024年第2期14卷 66-83页

作者： Albina Makio Robinson Mugasiali Irekwa Matthew Mutinda Munyao Caroline Wangui Njoroge Peter Kipkemboi Rotich Tonny Teya Nyandwaro Joanne Jepkemei Yego Anne Wanjiru mwangi James Hungo Kimotho ronald Tanui Vincent Rutto Samson Muuo Nzou Center for Traditional Medicine and Drug Research Kenya Medical Research Institute Nairobi Kenya Center for Microbiology Research Kenya Medical Research Institute Nairobi Kenya Production Department Kenya Medical Research Institute Nairobi Kenya Department of Biochemistry and Microbiology Rhodes University Grahamstown South Africa Center for Virus Research Kenya Medical Research Institute Nairobi Kenya

The discovery of Severe Acute Respiratory Syndrome-Coronavirus-2 (SARS-CoV-2) in Wuhan, Hubei province, China, in December 2019 raised global health warnings. Quickly, in 2020, the virus crossed borders and infected individuals across the world, evolving into the COVID-19 pandemic. Notably, early signs of the virus’s existence were observed in various countries before the initial outbreak in Wuhan. As of 12th of April, the respiratory disease had infected over 762 million people worldwide, with over 6.8 million deaths recorded. This has led scientists to focus their efforts on understanding the virus to develop effective means to diagnose, treat, prevent, and control this pandemic. One of the areas of focus is the isolation of this virus, which plays a crucial role in understanding the viral dynamics in the laboratory. In this study, we report the isolation and detection of locally circulating SARS-CoV-2 in Kenya. The isolates were cultured on Vero Cercopithecus cell line (CCL-81) cells, RNA extraction was conducted from the supernatants, and reverse transcriptase-polymerase chain reaction (RT-PCR). Genome sequencing was done to profile the strains phylogenetically and identify novel and previously reported mutations. Vero CCL-81 cells were able to support the growth of SARS-CoV-2 in vitro, and mutations were detected from the two isolates sequenced (001 and 002). Genome sequencing revealed the circulation of two isolates that share a close relationship with the Benin isolate with the D614G common mutation identified along the S protein. These virus isolates will be expanded and made available to the Kenya Ministry of Health and other research institutions to advance SARS-CoV-2 research in Kenya and the region.

关键词： SARS-CoV-2 COVID-19 Whole Genome Sequencing Phylogenetic Analysis Nucleotide Substitutions Amino Acid Changes

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Re-Testing in Batch Testing Model Based on Quality Control Process for Proportion Estimation

引用

Open Journal of Statistics 2021年第1期11卷 123-136页

作者： ronald Waliaula Wanyonyi Olivia Wanjeri mwangi Charles Wambugu mwangi Department of Mathematics Egerton University Njoro Kenya Data Science Institute University of Delaware Newark DE USA Department of Mathematics and Actuarial Kabarak University Kabarak Kenya

The quality of products manufactured or procured by organizations is an important aspect of their survival in the global market. The quality control processes put in place by organizations can be resource-intensive but substantial savings can be realized by using acceptance sampling in conjunction with batch testing. This paper considers the batch testing model based on the quality control process where batches that test positive are re-tested. The results show that re-testing greatly improves the efficiency over one stage batch testing based on quality control. This is observed using Asymptotic Relative Efficiency (ARE), where for values of p computed ARE > 1 implying that our estimator has a smaller variance than the one-stage batch testing. Also, it was found that the model is more efficient than the classical two-stage batch testing for relatively high values of proportion.

关键词： Quality Control Batch Testing Cut Off Value Proportion Re-Testing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：