检索结果-内蒙古大学图书馆

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

作者： Nosin Ibna Mahbub Feroza Naznin Md Imran Hasan Syed Mahfuzur Rahman Shifat Md. Alamgir Hossain Md Zahidul Islam Dept. of Information and Communication Technology Islamic University Kushtia Bangladesh Dept. of Computer Science and Engineering Green University Dhaka Bangladesh Dept. of Computer Science and Engineering Islamic University Kushtia Bangladesh Dept. of Computer Science and Engineering University of Global Village Barishal Bangladesh

This research concentrates on the diagnosis of common mango leaf diseases in Bangladesh using image processing via deep learning. Mango production could be raised by at least 28% globally if the crop could be safeguarded from a variety of diseases. However, without the assistance of an expert, it is challenging for the farmer to detect the disease at the appropriate time. Few studies have been conducted to identify the mango leaf disease present in Bangladesh. So far, no study has been done to identify the seven distinct mango leaf diseases reported in Bangladesh. We proposed a lightweight convolutional neural network (LCNN) in this paper to accurately classify seven distinct mango leaf diseases as well as normal mango leaf. To assess the proposed LCNN model, performance is compared to several pre-trained models such as VGG16, Resnet50, Resnet101, and Xception, and it is found that LCNN achieves the highest testing accuracy (98%).

关键词： Deep learning Computational modeling Image processing Crops Production Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

Automatic Vehicle Detection using DETR: A Transformer-Based Approach for Navigating Treacherous Roads

arXiv

引用

arXiv 2025年

作者： Fahad, Istiaq Ahmed Arean, Abdullah Ibne Hanif Ahmed, Nazmus Sakib Hasan, Mahmudul Institute of Information Technology University of Dhaka Dhaka Bangladesh Dept. of Computer Science and Engineering University of Dhaka Dhaka Bangladesh

Automatic Vehicle Detection (AVD) in diverse driving environments presents unique challenges due to varying lighting conditions, road types, and vehicle types. Traditional methods, such as YOLO and Faster R-CNN, often struggle to cope with these complexities. As computer vision evolves, combining Convolutional Neural Networks (CNNs) with Transformer-based approaches offers promising opportunities for improving detection accuracy and efficiency. This study is the first to experiment with Detection Transformer (DETR) for automatic vehicle detection in complex and varied settings. We employ a Collaborative Hybrid Assignments Training scheme, Co-DETR, to enhance feature learning and attention mechanisms in DETR. By leveraging versatile label assignment strategies and introducing multiple parallel auxiliary heads, we provide more effective supervision during training and extract positive coordinates to boost training efficiency. Through extensive experiments on DETR variants and YOLO models, conducted using the BadODD dataset, we demonstrate the advantages of our approach. Our method achieves superior results, and improved accuracy in diverse conditions, making it practical for real-world deployment. This work significantly advances autonomous navigation technology and opens new research avenues in object detection for autonomous vehicles. By integrating the strengths of CNNs and Transformers, we highlight the potential of DETR for robust and efficient vehicle detection in challenging driving environments. © 2025, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Multi-Component System Clustering with Time-Varying Kernel Density

Remaining Useful Life Prediction of Multi-Component System C...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Ke Fan, Xingle Shi, Hui Zhang, Xiaohong Sun, Chaoli Wang, Jianan Taiyuan University of Science and Technology Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Dept. of Electronic and Information Engineering Taiyuan China Taiyuan University of Science and Technology Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Dept. of Economics and Management Taiyuan China Taiyuan University of Science and Technology Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Dept. of Computer Science and Technology Taiyuan China

ISBN: (纸本)9798350303759

Aiming at the uncertainty of the degradation procedure of a complex multi-component system in a time-varying environment and the influence of the random dependence between different components, a remaining useful life prediction model for time-varying adaptive kernel density estimation based on the dependence between multiple components is established. First, the random dependence between multi-component systems is clustered. Considering that different components in the same cluster are affected by the random dependence, the components between different clusters do not affect each other. Judge the dependence characteristics between components, and use the dependence characteristics of different components to conduct clustering degradation modelling. Secondly, the parameters of the system change with time. Considering that monitoring data near the current time has a greater impact on the remaining useful life prediction compared with historical data, data in the vicinity of the current time is accorded a more significant weight, and a time-varying kernel density estimation prediction method is designed, in which the nearest-neighbour adaptive window-width selection method is used. Finally, give an example to demonstrate the effectiveness by the proposed method. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Customer Feedback and Reviews in E-Commerce Systems

Sentiment Analysis of Customer Feedback and Reviews in E-Com...

引用

International Conference on New Trends in Computing sciences (ICTCS)

作者： Olla Bulkrock Abdallah Qusef Ahmed BaniMustafa Software Engineering Dept. Princess Sumaya University for Technology Amman Jordan Computer Information Science Dept. Higher Colleges of Technology Abu Dhabi UAE

ISBN: (数字)9798331523411

ISBN: (纸本)9798331523428

Natural Language Processing (NLP) is an effective tool for analyzing consumer satisfaction with products and services typically sold by e-businesses. This study explores the use of sentiment analysis to understand customer feedback and ratings using a dataset acquired by Amazon. That dataset covers online purchases over a period of eight years. The study aims to examine the factors that impact sentiment polarity throughout different periods and understand changes in consumer feelings and reviews towards online products and services. The applied method comprehensively studies sentiment, extracting features using the Term Frequency-Inverse Document Frequency (TF-IDF) and other text analysis and data processing procedures. Visualization is also applied to illustrate the trends, patterns, and changes in customer satisfaction over time and per product and line of products. The findings underscore the importance of sentimental research in discerning customer sentiments on online e-commerce platforms and offer practical recommendations for enhancing online and improving customer satisfaction.

关键词： Sentiment analysis Text analysis Reviews Social networking (online) Mood Customer satisfaction Market research Feature extraction Multilingual Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Determining Key Points of the Dynamometer Chart of a Sucker Rod Pump

Algorithm for Determining Key Points of the Dynamometer Char...

引用

International Conference on Industrial engineering, Applications and Manufacturing (ICIEAM)

作者： Klara Tagirova Alexey Vulfin Sergey Klinovenko Dept. of Technical Cybernetics Ufa University of Science and Technology Ufa Russia Dept. of Computer Engineering and Information Security Ufa University of Science and Technology Ufa Russia Dept. of Complex Information Security Omsk State Technical University Omsk Russia

ISBN: (数字)9798331512194

ISBN: (纸本)9798331512200

The oil production industry is a consumer of the most modern means of automation of measurements, control, diagnostics, and management. The specified functions are performed with high metrological characteristics (indicators) and allow for the regulation of the parameters of technical devices, for example, the parameters of the operating modes of pumping equipment, according to technical indicators. The paper proposes an algorithm for searching for characteristic points of a dynamometer chart based on time series analysis in combination with the derivative method, which allows identifying characteristic points of a dynamometer chart and thereby expanding the diagnostic capabilities of a sucker rod pump. The novelty of the proposed solution lies in the ensemble of methods that take into account both the geometric features of the analyzed dynamometer chart and the physical characteristics of the processes occurring in the sucker rod pump. The metrics achieved during the computational experiments show that the localization of the found key points coincides with the expert marking with F1 = 0.73.

关键词： Location awareness Performance evaluation Industries Oils Time series analysis Production Industrial engineering Dynamometers Regulation Intelligent control

来源：评论

学校读者我要写书评

暂无评论

Enhancing Network Intrusion Detection in a Limited Labeled Data Scenario: An Active Learning Approach

Enhancing Network Intrusion Detection in a Limited Labeled D...

引用

Computing, Applications and Systems (COMPAS), IEEE International Conference on

作者： Md Sharafat Hossain Md Al Amin Hossain Md Shahin Sikdar Md Saiful Islam Institute of Information and Communication Technology Bangladesh University of Engineering and Technology Dhaka Bangladesh Dept. of Information Technology Engineering Selcuk University Konya Turkiye Dept. of Computer Science and Engineering Prime University Dhaka Bangladesh

ISBN: (数字)9798331529765

ISBN: (纸本)9798331529772

The Internet was originally developed to facilitate easier communication through digital devices. It has made our lives easier by providing means for communication and delivering digital resources anywhere and at any time in the world. However, the internet also exposes users to the risk of criminals exploiting various vulnerabilities in the internet system, launching sophisticated attacks to gain valuable information and hamper users’ lives. Henceforth, an effective intrusion detection system (IDS) is imperative for safeguarding the data and resources of users in the cyber world. This research aims to enhance semi-supervised IDS models by leveraging limited labeled data and unlabeled data and exploring innovative approaches to improve adaptability and accuracy in detecting known and emerging threats, particularly in scenarios with limited labeled data available. Our study uses the UNSW-NB15 dataset, and the results show that our suggested active learning-based semi-supervised model, which was created with 2000 labeled data, is better than the supervised model that uses the same number of labeled data. The proposed model achieved an accuracy score of 97.67% while existing studies achieved an accuracy score of 94.61%.

关键词： Adaptation models Accuracy Computational modeling Active learning Personal digital devices Network intrusion detection Benchmark testing Data models Internet computer crime

来源：评论

学校读者我要写书评

暂无评论

Smart Assistive 3D Tool to Remedy Children's Learning Difficulties for Distance Education 23

Smart Assistive 3D Tool to Remedy Children's Learning Diffic...

引用

23rd International Arab Conference on information Technology, ACIT 2022

作者： Mustafa, Dheya Mustafa, Intisar Ghazi Zriqat, Samah Althebyan, Qutaibah College of Engineering The Hashemite University Dept. of Computer Engineering Zarqa3113131 Jordan College of Education Qatar University Dept. of Educational Sciences Doha Qatar Yarmouk University Dept. of Information Technology and Computer Science Irbid Jordan College of Engineering Al Ain University Al Ain United Arab Emirates

ISBN: (纸本)9798350320244

COVID-19 has accelerated the shift away from the traditional classroom to online learning around the globe. Despite its advantages, students could not easily adapt to the challenges of transition overnight. To remedy academic difficulties that arise with online education, this paper introduces an assistive 3D educational tool for slow learners in elementary school, mainly for Arabic, English, and Math subjects. The proposed tool can be fully integrated with remedial programs to help students who could not adapt to distance learning during the pandemic, slow learners, or even students who cannot attain school. This tool automatically adapts to students' weaknesses and classifies students based on academic performance rather than age. Furthermore, it provides an easy-to-use interface for teachers to customize it using their own content and game scenarios. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Adaptive Joint Source-Channel Coding using Hypernetworks

Deep Learning-Based Adaptive Joint Source-Channel Coding usi...

引用

Communications and Networking (MeditCom), IEEE International Mediterranean Conference on

作者： Songjie Xie Hengtao He Hongru Li Shenghui Song Jun Zhang Ying-Jun Angela Zhang Khaled B. Letaief Dept. of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Dept. of Information Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (数字)9798350309485

ISBN: (纸本)9798350309492

Deep learning-based joint source-channel coding (DJSCC) is expected to be a key technique for the next-generation wireless networks. However, the existing DJSCC schemes still face the challenge of channel adaptability as they are typically trained under specific channel conditions. In this paper, we propose a generic framework for channel-adaptive DJSCC by utilizing hypernetworks. To tailor the hypernetwork-based framework for communication systems, we propose a memory-efficient hypernetwork parameterization and then develop a channel-adaptive DJSCC network, named Hyper-AJSCC. Compared with existing adaptive DJSCC based on the attention mechanism, Hyper-AJSCC introduces much fewer parameters and can be seamlessly combined with various existing DJSCC networks without any substantial modifications to their neural network architecture. Extensive experiments demonstrate the better adaptability to channel conditions and higher memory efficiency of Hyper-AJSCC compared with state-of-the-art baselines.

关键词： Adaptive systems Wireless networks Soft sensors Image communication Neural networks Memory management Network architecture

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approaches To Predict The Stability of Smart Grid

Research Square

引用

Research Square 2024年

作者： Satu, Shahriare Khan, Imran Dept. of Management Information Systems Noakhali Science and Technology University Noakhali3814 Bangladesh Dept. of Computer Science and Engineering Gono Bishwabidyalay Dhaka1344 Bangladesh

The smart grid is a modern solution to generate, distribute, and use energy effectively and efficiently. Ensuring the stability of the smart grid is critical to guarantee safe and consistent operation. This study proposes a machine learning model to identify smart grid stability more efficiently. To accomplish this, we collected the electrical grid stability dataset from a public machine learning repository and analyzed the correlation of individual features. Different feature selection and transformation techniques were employed to generate subsequent feature sets. Then, various classification techniques were applied to the primary and its subsets to identify the best machine-learning model for predicting smart grid stability more efficiently. The results indicated that MLP showed the highest accuracy (97.06%) for the Z-score transformed data set using Grid Search Optimization. This study demonstrates the potential of using machine learning to predict smart grid stability accurately and efficiently, providing a critical tool for improving the reliability, efficiency, and sustainability of the energy industry. © 2024, CC BY.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Smart Musical Instruments preset sharing: An ontology-based data access approach 7

Smart Musical Instruments preset sharing: An ontology-based ...

引用

7th IEEE World Forum on Internet of Things, WF-IoT 2021

作者： Turchet, Luca Bouquet, Paolo University of Trento Dept. Information Engineering and Computer Science Trento Italy

ISBN: (纸本)9781665444316

Interoperability represents an important aspect in research dealing with the emerging class of smart musical instruments (SMIs). To date, no interoperable file format for the exchange of content produced by heterogeneous SMIs has been defined yet. This paper proposes a solution to the issue of sharing presets among heterogeneous SMIs, which are used to conFigure an SMI. The heterogeneity of SMIs may come from the type, structure and implementation of the SMI's embedded system, its sound engine and sensor interface. The presented solution is based on the 'ontology-based data access' paradigm and leverages the existing Smart Musical Instruments Ontology. This approach allows one to share presets between heterogeneous SMIs by mapping information about the configuration of an instrument to the concepts of the ontology. Thanks to this approach, SMIs developers can implement programs that convert proprietary formats for the configuration of the instrument into a common format for SMIs, and vice versa. We present the general architecture and workflow of this approach, and we describe an implementation for it which involves the sharing of presets among two heterogeneous smart guitars. © 2021 IEEE.

关键词： Ontology

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：