检索结果-内蒙古大学图书馆

Development of a Lightweight Model for Handwritten Dataset Recognition: Bangladeshi City Names in Bangla Script

computers, Materials & Continua 2024年第8期80卷 2633-2656页

作者： MdMahbubur Rahman Tusher Fahmid Al Farid MdAl-Hasan Abu Saleh Musa Miah Susmita Roy Rinky Mehedi Hasan Jim Sarina Mansor MdAbdur Rahim Hezerul Abdul Karim Department of Computer Science and Engineering Bangladesh Army University of Science and Technology(BAUST)Saidpur5310Bangladesh Faculty of Engineering Multimedia UniversityCyberjaya63100Malaysia Pabna University of Science and Technology Pabna6600Bangladesh

The context of recognizing handwritten city names,this research addresses the challenges posed by the manual inscription of Bangladeshi city names in the Bangla *** today’s technology-driven era,where precise tools for reading handwritten text are essential,this study focuses on leveraging deep learning to understand the intricacies of Bangla *** existing dearth of dedicated datasets has impeded the progress of Bangla handwritten city name recognition systems,particularly in critical areas such as postal automation and document ***,no prior research has specifically targeted the unique needs of Bangla handwritten city name *** bridge this gap,the study collects real-world images from diverse sources to construct a comprehensive dataset for Bangla Hand Written City name *** emphasis on practical data for system training enhances *** research further conducts a comparative analysis,pitting state-of-the-art(SOTA)deep learning models,including EfficientNetB0,VGG16,ResNet50,DenseNet201,InceptionV3,and Xception,against a custom Convolutional Neural Networks(CNN)model named“Our CNN.”The results showcase the superior performance of“Our CNN,”with a test accuracy of 99.97% and an outstanding F1 score of 99.95%.These metrics underscore its potential for automating city name recognition,particularly in postal *** study concludes by highlighting the significance of meticulous dataset curation and the promising outlook for custom CNN *** encourages future research avenues,including dataset expansion,algorithm refinement,exploration of recurrent neural networks and attention mechanisms,real-world deployment of models,and extension to other regional languages and *** recommendations offer exciting possibilities for advancing the field of handwritten recognition technology and hold practical implications for enhancing global postal services.

关键词： Handwritten recognition Bangladeshi city names Bangla handwritten city name automated postal services

来源：评论

学校读者我要写书评

暂无评论

A Review on Role of IoT and Machine Learning in Agriculture 7

A Review on Role of IoT and Machine Learning in Agriculture

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Kumar, Gulshan Choudhary, Vishal Kumar Kumar, Shravan Kumar, Rajan Kumar, Mukesh Gourshettiwar, Palash M. Faculty of Engineering And Technology Department of Computer Science And Design Maharashtra Wardha India Faculty of Engineering And Technology Department of Computer Science And Medical Engineering Maharashtra Wardha India

ISBN: (纸本)9798350359299

The agricultural area has undergone a significant transformation owing to the progress made in IoT. It is imperative to have a dependable remote monitoring solution right now. This study aims to accomplish two goals. First, a solution based on an app is offered, which effectively assists in remotely administering the field by displaying the current sensor values. In an Internet of Things based prototype surveillance system, a multi-class categorization method utilizing machine learning and deep learning is incorporated to classify labels such as clear farm, cow, horse, wild boar, and wild elephant. The analysis involved Support Vector Machines and Convolutional Neural Networks, with the accuracy measure being employed to determine the optimal model. The advancements in the Internet of Things (IoT) have significantly transformed the daily lives of individuals. A comprehensive understanding of soil properties gives a variety of soil-related information that can be used to improve crop yields. Machine learning is a cutting-edge technology that aids with agricultural precision and provides answers to crop yield issues. Significant informative advances and Machine Learning (ML) open up new opportunities for deciphering, quantifying, and comprehending data-intensive prediction in agricultural settings. This study thoroughly examines a number of machine learning topics for Internet of Things-based smart agriculture systems. © 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

Identifying Video Tampering through Optical Flow Analysis: A Focus on Frame Manipulations 5

Identifying Video Tampering through Optical Flow Analysis: A...

引用

5th International Conference on Advanced information Technologies, ICAIT 2024

作者： Linn, Nay Htet Mar Win, Zin University of Computer Studies Mandalay Department of Information Technology Support and Maintenance Mandalay Myanmar University of Computer Studies Mandalay Faculty of Computer Science Mandalay Myanmar

ISBN: (纸本)9798331510046

This research addresses the critical problem of video tampering detection, focusing on frame deletions, insertions, and duplications. An unconventional approach is proposed, utilizing Farneback optical flow to detect inconsistencies in motion patterns indicative of tampering. To enhance the accuracy of optical flow computation, Contrast-Limited Adaptive Histogram Equalization (CLAHE) is applied to manage artifacts resulting from compression, lighting changes, and occlusions. Additionally, temporal filtering techniques are employed to reduce noise sensitivity. Our methodology includes evaluating motion consistency across frames, extracting texture features from the flow field, and applying thresholding techniques to identify abnormal motion characteristics. Temporal consistency checks are performed to ensure the persistence of detected forged regions over multiple frames. Experimental results on publicly available datasets demonstrate the effectiveness of our approach, achieving a TPR of 93.15% and a FAR of 6.65%, highlighting its high accuracy and robustness in identifying video tampering. © 2024 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Intelligent biomedical image classification in a big data architecture using metaheuristic optimization and gradient approximation

引用

Wireless Networks 2024年第8期30卷 7087-7108页

作者： Almutairi, Laila Abugabah, Ahed Alhumyani, Hesham Mohamed, Ahmed A. Department of Computer Engineering College of Computer and Information Sciences Majmaah University Majmaah11952 Saudi Arabia College of Technological Innovation Zayed University Abu Dhabi Campus Abu Dhabi United Arab Emirates Department of Computer Engineering College of Computers and Information Technology Taif University P.O. Box 11099 Taif21944 Saudi Arabia Department of Information Technology Faculty of Computer and Information Assiut University Assiut71515 Egypt

Medical imaging has experienced significant development in contemporary medicine and can now record a variety of biomedical pictures from patients to test and analyze the illness and its severity. computer vision and artificial intelligence may outperform human diagnostic ability and uncover hidden information in biomedical images. In healthcare applications, fast prediction and reliability are of the utmost importance parameters to assure the timely detection of disease. The existing systems have poor classification accuracy, and higher computation time and the system complexity is higher. Low-quality images might impact the processing method, leading to subpar results. Furthermore, extensive preprocessing techniques are necessary for achieving accurate outcomes. Image contrast is one of the most essential visual parameters. Insufficient contrast may present many challenges for computer vision techniques. Traditional contrast adjustment techniques may not be adequate for many applications. Occasionally, these technologies create photos that lack crucial information. The primary contribution of this work is designing a Big Data Architecture (BDA) to improve the dependability of medical systems by producing real-time warnings and making precise forecasts about patient health conditions. A BDA-based Bio-Medical Image Classification (BDA-BMIC) system is designed to detect the illness of patients using Metaheuristic Optimization (Genetic Algorithm) and Gradient Approximation to improve the biomedical image classification process. Extensive tests are conducted on publicly accessible datasets to demonstrate that the suggested retrieval and categorization methods are superior to the current methods. The suggested BDA-BMIC system has average detection accuracy of 94.6% and a sensitivity of 97.3% in the simulation analysis. © The Author(s) 2023.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Carbon Dioxide Emission Forecasting using Machine Learning and Time Series Statistical Models 25

Carbon Dioxide Emission Forecasting using Machine Learning a...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Hassan, Tahir Mansour, Khalid Waseemullah, Waseemullah Memon, Muhammad Qasim Ned University of Engineering and Technology Department of Computer Science & Information Technology Karachi Pakistan Arab Open University Faculty of Computer Studies Bahrain Sindh Bhitshah Pakistan

ISBN: (纸本)9798331540012

Climate change is considered a global disaster that has wreaked havoc worldwide. Climate change conditions are primarily driven due to emission of carbon dioxide and other greenhouse gases. Around the globe, several countries are facing serious challenges related to global warming and climate change. The adverse effects of global warming and climate change are recently observed in the form heat waves, floods, extreme rainfall events and drought conditions. The escalating CO2 emission level causes threats of food security and water scarcity. To overcome this, timely and accurate CO2 emissions forecasting is essential for developing effective mitigation strategies in such a manner that CO2 emission impacts can be reduced. The aim of this study is to forecast the total CO2 emissions of upcoming years using various statistical, machine learning models such as ARIMA (Auto-Regressive Integrated Moving Average), SARIMA (Seasonal ARIMA), Linear Regression, and Decision tree regressor. We had forecasted CO2 emission on the basis of influencing factors, which highly contributes in CO2 emission. The performance of the models is validated using multiple evaluation metrics such as MAE, MSE RMSE,MAPE and R2 square. The results show that CO2 emission is highly affected by fossil fuel consumption. In particular, Linear regression performs better among all applied models, with R2 value 0.93 and MAE, RMSE and MAPE values 5.52, 6.47 and 0.03, respectively. Our research delineates the results and insights that will assist concerned authorities, policymakers and environmental agencies. The present study also aim to inform authorities, helping them to better understand the future of CO2 emission trajectories and make timely efforts and interventions to tackle the climate change and global warming challenges. © 2024 IEEE.

关键词： Low emission

来源：评论

学校读者我要写书评

暂无评论

Handling Imbalanced Data for Improved Classification Performance: Methods and Challenges 3

Handling Imbalanced Data for Improved Classification Perform...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Abokadr, Somiya Azman, Azreen Hamdan, Hazlina Amelina, Nurul University Putra Malaysia Faculty of Computer Science & Information Technology Department of Intelligent Systems Seri Kembangan43400 Malaysia Al Zintan University Faculty of Science Libya University Putra Malaysia Faculty of Computer Science & Information Technology Seri Kembangan43400 Malaysia University Putra Malaysia Faculty of Computer Science and Information Technology Department of Computer Science Malaysia University Putra Malaysia Faculty of Computer Science and Information Technology Department of Multimedia Selangor Darul Ehsan Serdang Malaysia

ISBN: (纸本)9798350305333

Imbalanced data significantly impacts the efficacy of machine learning models. In cases where one class greatly outweighs the other in terms of sample count, models might develop a bias towards the majority class, thereby undermining the performance of the minority class. Imbalanced data act to increase the risk of overfitting, as the model may memorize the majority of class samples instead of learning underlying patterns. This paper addresses these challenges in the classification field by exploring various solutions, including under-sampling, oversampling, SMOTE, cost-sensitive learning, and ensemble deep learning methods. The evaluate the performance of these methods on different datasets and provide insights into their strengths and limitations. The paper presents a taxonomy of strategies for imbalanced binary and multi-class classification problems, including resampling, algorithmic, and hybrid methods. Ultimately, the paper furnishes guidelines to facilitate the selection of the most pertinent method for mitigating imbalanced data challenges within a specific classification context. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Measurement of ChatGPT Performance in Mapping Natural Language Speficaction into an Entity Relationship Diagram 11

Measurement of ChatGPT Performance in Mapping Natural Langua...

引用

11th IEEE International Conference on systems and Control, ICSC 2023

作者： Omar, Mussa A. University of Ajdabiya Faculty of Information System Computer Science Department Libya

ISBN: (纸本)9798350304886

This paper explores the entity relationship diagram, a popular conceptual model used to depict entities, attributes, and relationships graphically. To help with this, we use ChatGPT, a sophisticated language model based on the GPT architecture, which can translate natural language text into an entity relationship diagram. The paper details the process of evaluating how well ChatGPT can perform compared to other state-of-the-art approaches for entity and relationship extraction. Our experimental findings demonstrate the strong ability of ChatGPT to translate natural language text into entity relationship diagrams, which has potential applications for knowledge graph building, data integration, and database schema design. Moreover, it can aid in automating the extraction and organization of information from unstructured text data, thereby simplifying the study of complex systems. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning for Breast Cancer Image Classification Using Pre-trained CNNs and Random Oversampling Method 5

Ensemble Learning for Breast Cancer Image Classification Usi...

引用

5th International Conference on Advanced information Technologies, ICAIT 2024

作者： Thuzar, Win Myat Moe Htay, Moe Uinversity of Computer Studies Mandalay Department of Information Technology Supporting and Maintenance Mandalay Myanmar Uinversity of Computer Studies Mandalay Faculty of Computer Science Mandalay Myanmar

ISBN: (纸本)9798331510046

The classification of breast cancer images presents significant challenges, especially when dealing with imbalanced datasets that underrepresent minority classes. This study tackles the issue by implementing ensemble learning techniques with pre-trained convolutional neural networks (CNNs) such as ResNet50, GoogleNet, and EfficientNet. The random oversampling method was employed to address the imbalance, which effectively increases the representation of minority classes within the dataset. This study performs detailed data analysis after this adjustment to improve the model's ability to identify these minority classes. By combining the predictions of the three models into an ensemble, the approach aims to improve both the accuracy and robustness of the classification process. The ensemble method works much better at finding minority classes, as shown by the results of experiments. This proves that it can handle uneven datasets when classifying breast cancer images. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Using ECLAT Algorithm for Privacy Preserving on Publishing Data 3

Using ECLAT Algorithm for Privacy Preserving on Publishing D...

引用

3rd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer Engineering, MI-STA 2023

作者： Omran, Osama M Ben University of Benghazi Faculty of Information Technology Department of Computer Science Benghazi Libya

ISBN: (纸本)9798350319897

many organizations such as online organizations, hospitals, and universities use massive amounts of customer information and use Database systems to enter their data. Many services and benefits are provided by these organizations to the public. The organizations want to publish the data and information for the purpose of research and analysis to obtain many benefits and advantages to improve their work. On the other hand, the data include individuals' sensitive and private information, therefore, organizations are concerned about the security as well privacy;in fact privacy is an important issue when organizations publish their data. This paper suggests a technique to preserve the privacy of the information. The proposed technique uses the ECLAT algorithm which is efficiently mined using the vertical data format. In addition to the ECLAT algorithm, the proposed technique uses some extra steps to process and manage data and to be prepared and secure for publishing. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Opinion mining for stock trend prediction using deep learning

引用

Multimedia Tools and Applications 2024年 1-24页

作者： Albahli, Saleh Nazir, Tahira Department of Information Technology College of Computer Qassim University Buraydah Saudi Arabia Faculty of Computing Riphah International University Islamabad Pakistan

Stock market prediction by using Machine Learning (ML) models has been a hot topic of research for more than a decade. Combined with the power of sentiment analysis and ML, social media posts like tweets and financial news can have a big impact on how accurately stock market price predictions are made. Our proposed work makes use of social media posts from Twitter and Google Finance data to predict the price of the stock market using DL techniques. To perform this job, we propose a method that first introduces a concept of fake tweets detection and removal using BERT and then we prepare our dataset using preprocessing techniques. The feature extraction is performed using FastText and VADER, after that the prediction is made through the Deep Belief Network. Two datasets (i.e., Sentiment140 and Twitter real-time data) were used in the experiments and attained 89.12% accuracy along with precision, recall, and F1-Score of 90.15%, 89.12%, and 89.67%. This research not only refines stock market prediction accuracy through a sophisticated blend of sentiment analysis and ML but also introduces novel methodologies in fake tweet detection, feature extraction, and prediction models, charting new territories in the pursuit of precision and reliability. Results reveal that the proposed method performs better in terms of overall accuracy than the most recent methods. We intend to expand the functionality of our approach in the future by including additional well-known social media, such as Facebook and Google News, etc. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sentiment analysis

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：