检索结果-内蒙古大学图书馆

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md. Farhan Shakib Md. Shahid Uz Zaman Md. Al Mamun Azmain Yakin Srizon A. F. M. Minhazur Rahman Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Bushfire detection is a critical task for environmental monitoring, early warning systems and disaster management. State-of-the-art methods utilize deep learning, particularly Convolutional Neural Networks (CNN), for detecting bushfires or mapping burned areas from satellite imagery. Satellite images often contain more than 10 channels, making the selection of appropriate channels a significant challenge. Traditional methods for channel selection in remote sensing often depend on intuition, domain-specific knowledge or trial and error. In contrast, we argue that Deep Learning models can identify previously unseen patterns in the data that may not align with human intuition. These conventional methods tend to use more than three channels, which can significantly increase the computational resources required. There is a clear need for a mathematical automated approach to select the most relevant channels for bushfire classification. This study proposes a novel gradient-based method for identifying the most appropriate channels for bushfire classification using satellite imagery. Unlike traditional approaches, the proposed method leverages gradient information to automatically rank channels based on their contribution to classification accuracy. The method was applied to a combined EuroSAT and Landsat 8 Active Fire Dataset. Based on the results, the NIR, Red, and Blue channels were selected, achieving an accuracy of 96.63%. This approach reduced the number of parameters trained and minimized computational resource usage. Furthermore, the selected channels and resulting classification performance were compared with other state-of-the-art methods. The results demonstrate that the gradient-based method enables optimal channel selection, significantly improving efficiency while maintaining high accuracy. This approach advances the field of remote sensing by offering a scalable and interpretable solution for bushfire monitoring and decision-making.

关键词： Deep learning Accuracy Supervised learning Redundancy Landsat Vectors Mathematical models Satellite images Convolutional neural networks Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Butterfly Optimization and Deep Learning to Classify Heart Sound Signal

Butterfly Optimization and Deep Learning to Classify Heart S...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Faika Fairuj Preotee Md Sabbir Hossain Shuvashis Sarker Farliha Binte Faisal Nawrin Tabassum Shamim Akhter Department of Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

Heart sound signals, or PCG recordings, provide a valuable non-invasive alternative to traditional diagnostic methods like CXR and blood tests for detecting cardiovascular disease. In this study, PCG data are collected, and features such as MFCC and WST are extracted to capture both time and frequency information. These features are used to classify the signals into normal and abnormal categories using DL models, including CNN, Bi-LSTM, and Bi-RNN. The study conducts extensive experiments using individual and combined features, showing that combining features enhances classification accuracy. The proposed CNN model, optimized with the Butterfly Optimization Algorithm, achieves an impressive classification accuracy of 99.07%, outperforming other models. This result highlights the effectiveness of using PCG signals and advanced DL techniques for accurate cardiovascular disease detection, offering a noninvasive and efficient alternative for early diagnosis.

关键词： Heart Deep learning Wavelet transforms Accuracy Feature extraction Classification algorithms Cardiovascular diseases Mel frequency cepstral coefficient Phonocardiography Optimization

来源：评论

学校读者我要写书评

暂无评论

An Interpretable Machine Learning Approach for Bengali Toxic Comments Detection

An Interpretable Machine Learning Approach for Bengali Toxic...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md. Zobayer Ibna Kabir Department of Computer Science and Engineering Ahsanullah University of Science & Technology Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Toxic comment detection is critical for providing a positive online environment and to detect this type of comment is very important for people’s mental health. In this research, a machine learning based pipeline was created to detect if a comment is toxic or not. For prediction purposes, two datasets were *** first dataset, which is publicly available, contains a total of 16,073 comments. Out of 16,073, 8,488 comments are classified as toxic, and 7,585 comments are classified as not *** second dataset, also publicly available and collected from Mendeley Data, contains 44,001 comments. Among these, 28,661 comments are classified as toxic or bully, while 15,340 comments are classified as not toxic or not bully. Preprocessing was completed, and features were extracted using TF-IDF, before training the models on the datasets. Then we evaluated the results using a confusion matrix and performance metrics like precision, f1 score, recall, accuracy. For Dataset-1, the Stochastic Gradient Descent (SGD) classifier achieved the best performance among the implemented models, with a weighted F1 score of 0.91 and an accuracy of 91.44%.For Dataset-2, the Stochastic Gradient Descent (SGD) classifier demonstrated the highest performance among the implemented models, achieving a weighted F1 score of 0.88 and an accuracy of 88.42%..To explain the model’s prediction, LIME framework was implemented. With the use of explainable artificial intelligence, the decision-making process of our models becomes more transparent. Source Code: https://***/ZobayerAkib/An-Interpretable-Machine-Learning-Approach-for-Bengali-Toxic-Comments-Detection-IEEE2025

关键词： Training Support vector machines Analytical models Accuracy Explainable AI Pipelines Hate speech Stochastic processes Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

AI Innovations in Heart Disease Prediction using Machine Learning and Risk Stratification using Deep Learning

AI Innovations in Heart Disease Prediction using Machine Lea...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Rubasri S Roshini M S. Hemalatha Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

The goal of the heart disease prediction project is to use machine learning and deep learning techniques to create an accurate and efficient system. To obtain insights into the dataset, the project starts with thorough data preprocessing, which includes data cleansing, addressing missing values, and conducting exploratory data analysis. Data visualisation tools are used to support this research in order to find important patterns and correlations that help with the model-building stage. By combining several decision trees, the method increases the predictive potential of the model. To guarantee robustness and dependability, performance is assessed using important measures like accuracy, precision, recall, and cross-validation. A deep learning algorithm is also included to manage data on heart illness that is based on images. Convolutional neural networks (CNNs) use the Lenet architecture for image classification, and pre-processing and data augmentation approaches improve model performance. In comparison to conventional approaches, this work suggests a sophisticated heart disease prediction model that combines Machine Learning (ML) and Deep Learning (DL) techniques, attaining an accuracy of X% and greatly lowering misclassification rates. By employing oversampling approaches, the suggested system effectively manages unbalanced datasets and enhances prediction robustness through feature selection and ensemble learning.

关键词： Heart Deep learning Technological innovation Accuracy Predictive models Prediction algorithms Robustness Data models Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Feature Loss in Generative Adversarial Network for Satellite Image Resolution Enhancement

Exploring Deep Feature Loss in Generative Adversarial Networ...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md. Sorwar Alam Rafiqul Islam Department of Computer Science and Engineering Dhaka University of Engineering & Technology Gazipur Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Satellite imaging is an essential tool that is commonly utilized for agricultural development, environmental monitoring, urban planning, and many other applications. However, the poor resolution of satellite images makes it difficult to extract fine-grained features and prevents them from being used effectively. Several techniques, including unsupervised and supervised learning models, have been developed to address the challenges. In this paper, an efficient resolution improvement approach is proposed by tweaking the adversarial loss functions of a Generative Adversarial Network using deep neural network features. A lightweight MobileNet model is incorporated as backbone to improve adversarial loss functions for generating a high-resolution (HR) image from a low-resolution (LR) image. The proposed model is trained on pairs of LR and HR image datasets to map the LR image to its corresponding HR image. Then, extensive experiments are carried out to obtain HR images that are compared to some state-of-the-art models. The experimental results also investigated losses, indicating the effectiveness and improvement of the suggested approach for boosting satellite image resolution.

关键词： Training Visualization Satellites Urban planning Transfer learning Superresolution Imaging Generative adversarial networks Feature extraction Satellite images

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of IoT and IoT Security Attacks: Understanding the Threat Landscape 2

A Comprehensive Analysis of IoT and IoT Security Attacks: Un...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Dhayal, Himanshi Siwach, Vikas Sehrawat, Harkesh Dalai, Renu Department of Computer Science and Engineering UIET Maharshi Dayanand University Haryana Rohtak India GGSIPU Guru Gobind Singh Indraprastha University East Delhi Campus Delhi India

ISBN: (纸本)9798331530389

IoT has remarkably changed the internet landscape since its introduction. Today, even an isolated physical device is provided with the internet, which allows it to exchange information with other devices. As much flexibility as these devices offer, they also have numerous security issues, causing threats to its users. Adversaries increasingly exploit the vulnerabilities in Internet of Things devices to execute attacks that can inflict significant harm on individuals, communities, and organizations. Consequently, prioritizing the detection, prevention and mitigation of the attacks is imperative to ensure safety and security. The paper provides an in-depth examination of internet of things (IoT) taxonomy, highlighting the associated challenges and security attacks within the IoT ecosystem, which subsequently gives insights into the vulnerabilities of the IoT ecosystem. Additionally, it includes a comparative analysis of various security attacks along with their impacts. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Usability of Vending Machines through Multi-Method Evaluation Techniques

Exploring the Usability of Vending Machines through Multi-Me...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Arnab Sircar Bijoya Ghosh Jamal Uddin Tanvin M N Alam Siddiqui Sazia Tabasum Mim Muhammad Nazrul Islam Department of Computer Science and Engineering Military Institute of Science and Technology Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Usability is a key quality attribute to ensure accessibility and high user acceptance of any embedded system. While several studies have examined the usability of embedded systems, only a few have specifically addressed the usability assessment and intuitive design of systems like vending machines. Therefore, the objectives of this research are to explore the usability of existing vending machines and to propose design solutions for enhancing the usability of such embedded systems. To achieve these objectives, three unique vending machines (Your Shop, SnacKeeper, and SPN Convenience) were evaluated using both Heuristic Evaluation (HE) and Cognitive Walkthrough (CW) methods; and revealed a wide range of usability problems. A comparative analysis was performed between the findings of both methods and then the identified usability issues were categorized into interface accessibility, transactional design, instructional layout, and visibility & clarity. Based on the findings, a set of design recommendations was developed to address these challenges. Additionally, as an example a prototypical design was created based on the proposed recommendations. As such, the findings of this study will make a substantial contribution to the fields of embedded system design and human-computer interaction (HCI) to offer valuable insights for designing more usable and intuitive vending machines.

关键词： Human computer interaction Surveys Embedded systems Layout User experience Usability Testing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Agricultural Output to Predict the Best Possible Productivity and Crop Suitable on the Very Particular Land using Machine Learning Techniques

Optimizing Agricultural Output to Predict the Best Possible ...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： P. Kabitha G. Ramu Dharani V K. Gowtham sai surya V.Asha Judi Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Increased worldwide agricultural output needs require farmers to use high yield farming practices and evaluate suitable land utilization for crop production. Advanced ML algorithms function in this research to predict suitable yields alongside crop suitability assessments for different land areas. The research adds value to supervised and unsupervised learning principles to establish a ML system which deals effectively with diverse data types including soil chemistry features and climate elements and historical harvest volumes. Investigative efforts reveal modern separated commodities such as ensemble methods and deep learning and hybrid models to boost agricultural field yield outputs. This study adopts frame literature methodologies in feature selection and enhanced predictive models for better crop yield prediction along with advisory functions. The research outcomes create adaptable agricultural information that helps farmers and stakeholders boost their efficient and sustainable modern farming practices.

关键词： Deep learning Productivity Soil properties Feature extraction Stakeholders Sustainable development Crop yield Optimization Unsupervised learning Farming

来源：评论

学校读者我要写书评

暂无评论

End-to-End Bangla AI for Solving Math Olympiad Problem Benchmark: Leveraging Large Language Model Using Integrated Approach

arXiv

引用

arXiv 2025年

作者： Tabib, H.M. Shadman Deedar, Jaber Ahmed Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh

This work introduces systematic approach for enhancing large language models (LLMs) to address Bangla AI mathematical challenges. Through the assessment of diverse LLM configurations, fine-tuning with specific datasets, and the implementation of Retrieval-Augmented Generation (RAG), we enhanced the model's reasoning precision in a multilingual setting. Crucial discoveries indicate that customized prompting, dataset augmentation, and iterative reasoning improve the model's efficiency regarding Olympiad-level mathematical challenges. © 2025, CC BY.

关键词： Problem solving

来源：评论

学校读者我要写书评

暂无评论

Targeted Image Manipulation 1st

Targeted Image Manipulation

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Sanjay Sen, S. Patel, Sameer Dushyant Bedict, A. Dilip, Golda Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9783031823824

This paper addresses the problem of customization of an image at an object-level, where the aim is to enable users to customize images containing objects unseen during training without explicit supervision. Our approach utilizes a self-supervised method coupled with a semantic embedding space to facilitate object-level manipulation without the need for paired data. Through extensive experiments on various datasets, we demonstrate the effectiveness of our method in accurately customizing images with unseen objects while preserving visual coherence. Our results showcase the potential of targeted image manipulation in diverse applications such as content creation and image editing. In conclusion, this work presents a promising avenue for enabling users to seamlessly customize images containing unseen objects, opening up new possibilities for creative expression and content manipulation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： content manipulation novel image customization object-level customization self-supervised method semantic embedding space

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：