检索结果-内蒙古大学图书馆

3rd international conference on Control and Intelligent robotics, ICCIR 2023

作者： Zongkui, Chang Mechanical and Materials Engineering College North China University of Technology Beijing100144 China

ISBN: (纸本)9781510671867

Oil-air lubrication ECT differential electrode sensor is established;the influence of isolated electrode and differential electrode on ECT sensor is analyzed;the range of The range of three structural parameters for measured electrode and differential electrode spacing, electrode length and electrode thickness is determined, and optimization is performed using Design-Expert. The results showed that the image relative error decreased by 18.4% and the image correlation coefficient increased by 36%. © 2023 SPIE.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

MangoLeafXNet: An Explainable Deep Learning Model for Accurate Mango Leaf Disease Classification

引用

IEEE Access 2025年 13卷 93977-94008页

作者： Rayed, Md Eshmam Jim, Jamin Rahman Islam, Md Juniadul Mridha, M.F. Kabir, Md Mohsin Hossen, Md. Jakir American International University-Bangladesh Department of Computer Science and Engineering Dhaka1229 Bangladesh Mälardalens University Division of Computer Science and Software Engineering Västerås722 20 Sweden Multimedia University Faculty of Engineering and Technology Department of Robotics and Automation Melaka Malaysia

Addressing the global challenge of ensuring a consistent and abundant supply of fresh fruit, particularly in the context of fruit crops, is hindered by the prevalence of plant diseases. These diseases directly impact the quality of fruits, leading to a decline in overall agricultural production. Mango leaf diseases pose significant threats to global mango production, necessitating accurate and efficient classification techniques for timely disease management. Our study focuses on introducing MangoLeafXNet, a customized Convolutional Neural Network (CNN) architecture specifically tailored for the classification of mango leaf diseases, along with a healthy class. Our proposed model comprises six layers optimized to capture intricate disease patterns, demonstrating superior performance compared with prevalent pre-trained models. The model is trained and evaluated on three publicly available datasets: MangoLeafBD (4000 images across 8 classes), MangoPest (16 pest classes including healthy leaves), and MLDID (3000 high-resolution images across 5 classes). Our model demonstrated exceptional classification performance, attaining 99.8% accuracy, 99.62% recall, 99.5% precision, and an F1-score of 99.56%. Further validation on the MangoPest dataset and the Mango Leaf Disease Identification Dataset (MLDID) resulted in accuracies of 96.31% and 96.33%, respectively, confirming the robustness and adaptability of MangoLeafXNet across different datasets. Additionally, we incorporate Explainable AI techniques, including GRAD-CAM, Saliency Map, and LIME to enhance the interpretability of our model. We deployed Gradio web interface to create an interactive interface that allows users to upload images of mango leaves and get real-time classification and validation results along with confidence scores. This contribution not only advances the state-of-the-art in mango leaf disease classification but also offers promising prospects for real-time disease diagnosis and precision agriculture

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

A Forefront System for Sugarcane Leaf Disease Classification Using Deep Learning 4

A Forefront System for Sugarcane Leaf Disease Classification...

引用

4th international conference on robotics, Electrical and Signal Processing Techniques, ICREST 2025

作者： Sakib, Abu Noman Md Partha, Sajal Basak Shojib, Mohammad Anik Islam Hasan, Md Mahamudul Shuvo, Badiuzzaman Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh Computer Science and Engineering Chittagong University of Engineering & Technology Chittagong Bangladesh Computer Science and Engineering East West University Dhaka Bangladesh

ISBN: (纸本)9798331530938

The agriculture sector has already seen a favorable advancement because of the involvement of machine learning (ML) methods. Sugarcane industry faces a gruesome drawback because of several types of leaf diseases. Nowadays, ML methods have come handy also to detect the diseases at the very early stage. Our work represents a cutting-edge deep learning method with a goal to classify five popular sugarcane leaf diseases: Bacterial Blight, Mosaic, RedRot, Rust, Yellow, and can also identify which one is Healthy. This study also conducts a comparative analysis of various state-of-the-art models, evaluating their training time, parameters, accuracy and model size using the same dataset. Based on this evaluation, the optimal model was selected for final evaluation. Several pre-trained models were modified to enhance speed and reduce storage requirements. The system can identify the disease category for every given sugarcane leaf image using the EfficientNetB0 model, which demonstrated the best performance, and also provides the probability of correct identification. Several preprocessing steps are involved such as removing noise, addressing missing data, and standardizing images to ensure maximum accuracy. The models were trained, validated, and tested on a dataset of 4,800 sugarcane leaf images from the Sugarcane Leaf Disease Dataset. Among all the models, EfficienNetB0, InceptionV3 and ResNet50 achieved high accuracy (98.75%, 98.54% and 98.54%, respectively). However, EfficienNetB0 was ultimately chosen due to its faster training, smaller size, and fewer parameters, making it ideal for this study. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Multiple Impedance Control of a Space Free-Flying Robot 12

Machine Learning Based Multiple Impedance Control of a Space...

引用

12th RSI international conference on robotics and Mechatronics, ICRoM 2024

作者： Safdari, Amirhossein Zarafshan, Payam Alipour, Khalil Tarvirdizadeh, Bahram Fang, Gu School of Intelligent Systems Engineering College of Interdisciplinary Science and Technology University of Tehran Department of Mechatronics Engineering Tehran Iran School of Engineering Design and Built Environment Western Sydney University Sydney Australia

ISBN: (纸本)9798331529734

This study investigates the application of Machine Learning (ML) to reduce the inherent computational burden in Multiple Impedance Control (MIC) for robotic systems. Impedance Control (IC) is a powerful method for robots to interact with their environment by simultaneously controlling position and force. However, the increasing complexity of control methods such as MIC requires more and more complex computations, which can lead to problems such as increased response time and reduced efficiency in the control system, making implementation on the controller impractical. To address this challenge, this paper proposes a new ML-based method called ML-MIC. This method aims to reduce the computational complexity associated with MIC using ML techniques, thereby improving the efficiency and speed of robotic control systems. The development of ML-MIC not only leads to improved control system performance but also enables more effective implementation of robotic and mechatronic systems. © 2024 IEEE.

关键词： Robot learning

来源：评论

学校读者我要写书评

暂无评论

Roopkotha: A Companion Robot for Enhancing Interactive Storytelling with Natural Interaction 3

Roopkotha: A Companion Robot for Enhancing Interactive Story...

引用

3rd international conference on Image Processing and robotics, ICIPRoB 2024

作者： Mehzabin, Kazi Mayesha Islam, Md. Zahidul Nur, Md. Ashaduzzaman Shidujaman, Mohammad Samani, Hooman Mi, Haipeng Independent University Bangladesh RIoT Center and Department of Computer Science and Engineering Dhaka Bangladesh Creative Computing Institute University of the Arts London London United Kingdom Tsinghua University Media and Interaction Lab Academy of Arts and Design Beijing China

ISBN: (纸本)9798350374766

Roopkotha is a storytelling robot that seamlessly combines traditional storytelling methods and technology, creating a captivating robot storyteller. We are creating a special prototype in the world of robots that tells stories in a way that is easy to understand and enjoy. In this era of technological advancement, Roopkotha combines voice recognition with Bangla Language processing, emotion recognition, human behavior detection. Roopkotha aims to revolutionize the way stories are told and engage with users on a deep emotional level. Furthermore, Roopkotha is equipped with advanced facial expressions and emotion recognition technology. The emotion recognition feature helps the robot to have a profound connection with the users. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based on TensorFlow for the Recognition of Handwritten Digits in the Odia

Convolutional Neural Network Based on TensorFlow for the Rec...

引用

2024 international conference on advances in Computing Research on science engineering and technology, ACROSET 2024

作者： Bajaj, Karan Bordoloi, Dibyahash Tripathy, Ramamani Mohapatra, Srikanta Kumar Sarangi, Pradeepta Kumar Sharma, Parth School of Computer Science and Engineering Lovely Professional University Department of Cse Jalandhar India Graphic Era Hill University Department of Cse Dehradun India School of Engineering and Technology Chitkara University Department of Cse Solan India Institute of Engineering and Technology Chitkara University Department of Cse Rajpura India

ISBN: (纸本)9798350388800

Odia, which is recognized as the official language of the Indian State of Odisha, is one of the many regional languages that people in India use to communicate with one another. Over fifty million people worldwide communicate in the Odia language, which has a history that dates back more than a millennium and a half. Odia digits' complexity arises from each character's intricate design, which features numerous curves. Handwritten scripts exhibit increased complexity due to the unrestricted nature of freeform writing. Odia script is used to write a great deal of historical texts, some of which date back more than a thousand years. A suitable automation technology that makes it simple to convert old paper documents into digital data protects these irreplaceable records. This article investigates the recognition performance of a Convolutional Neural Network model for handwritten Odia numbers. By entering the numerical numbers into Microsoft Paint, we were able to generate data using software. For the CNN model's implementation, we used Python programming. Following the CNN model's training and testing of the dataset, 80% accuracy was noted. © 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

Twitter Scraping and Sentiment Analysis on Stock Price

Twitter Scraping and Sentiment Analysis on Stock Price

引用

2024 international conference on advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Iniyan, S. Thangakumar, J. Rajendran, P. Selvi Hindustan Institute Of Science And Technology Dept. Of Computer Science And Engineering Chennai603103 India

ISBN: (纸本)9798350364828

social media is useful in the community for sharing and discussing various events with others. The study's main objective is to predict the sign of the stock by sentimental analysis regarding the Hindenburg report on Adani group stocks by obtaining tweets from Twitter. The study's findings will aid in understanding the effect of the Hindenburg report on the stocks of the Adani group. Excel files are downloaded from Twitter containing tweets from social media users. Tweets are cleaned up by eliminating noise data after extraction. Machine learning algorithms, such as Logistic Regression (LR), Linear support classification (SVC), Random Forest (RF), and voting, were used to classify the data into positive, Neutral, and negative groups. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Novel Complete Coverage Path Planning of a Biped Wall-Climbing Robot for Window Cleaning

Novel Complete Coverage Path Planning of a Biped Wall-Climbi...

引用

2024 IEEE international conference on robotics and Biomimetics, ROBIO 2024

作者： Zhang, Weijian Li, Zikang Tam, Lap Mou Xu, Qingsong University of Macau Faculty of Science and Technology Department of Electromechanical Engineering Taipa China

ISBN: (纸本)9781665481090

Cleaning exterior walls of high-altitude buildings is a critical task typically performed by human workers. However, manual maintenance exhibits several disadvantages. To address these issues, this paper presents a biped wall-cleaning robotic system (BWCRS) dedicated to the maintenance of multi-isolate areas on exoskeleton-structured windows. To tackle the complete coverage cleaning path planning (CCCPP) problem, an innovative approach is proposed by integrating a deep Qnetwork (DQN)-based method with the BWCRS. The proposed method enhances the cleaning process by optimizing the robot's travel path using DQN, ensuring stable navigation on walls with obstacles through advanced biped loco-manipulation. The effectiveness of the reported approach is validated by conducting extensive simulation and experimental investigations. Comparative studies reveal that the reported approach outperforms the existing method. The results demonstrate the BWCRS's capability to efficiently and safely clean exoskeleton-structured windows. Moreover, the proposed framework can be extended to path planning of other types of climbing robots. © 2024 IEEE.

关键词： Exoskeleton (robotics)

来源：评论

学校读者我要写书评

暂无评论

Thickness Measurement of Alloy Steel Carburizing Layer Based on Laser Ultrasonic

Thickness Measurement of Alloy Steel Carburizing Layer Based...

引用

2024 lEEE international conference on Advanced Information, Mechanical engineering, robotics and Automation, AIMERA 2024

作者： Mao, Xing Xu, Dong Zhang, Shaotong Wang, Xiaocheng Yang, Quan Wang, Ruixiao Sun, Wei Yu, Rengfei University of Science and Technology Beijing Institute of Engineering Technology Beijing China Northeastern University School of Mechanical Engineering and Automation Shenyang China Capital Engineering & Research Incorporation Limited Beijing China Hot Rolling Workshop Angang Steel Company Limited Anshan China

ISBN: (纸本)9798350343335

Carburizing is one of the most widely used chemical heat treatment processes in the machinery manufacturing industry. The surface hardness, wear resistance and flexural fatigue strength of the workpiece after carburization is greatly improved. The thickness of the carburized layer is one of the main technical indicators to measure the quality of carburized parts. However, at present, the carburized shaft carburized layer thickness inspection is generally a contact method. In this paper, the thickness of the carburized layer of alloy steel was detected using Laser Ultrasonic (LU) non-destructive testing technology. First of all, using simulation signals to verify the effectiveness of sparse decomposition reconstruction and wavelet threshold denoising algorithm, and then the use of sparse decomposition and reconstruction combined with wavelet threshold denoising algorithm on the experimental LU signal denoising to extract the weak signal, obtained carburized layer thickness of alloy steel, accuracy of test results up to more than 95%. This study provides theoretical and data support for the development and application of on-line inspection equipment for carburized layers. © 2024 IEEE.

关键词： Inspection equipment

来源：评论

学校读者我要写书评

暂无评论

Enhancing Object Detection in Remote Sensing Images with GFA and ADS Modules Based on InternAware Model 6

Enhancing Object Detection in Remote Sensing Images with GFA...

引用

6th international conference on robotics and Computer Vision, ICRCV 2024

作者： Zhou, Xue Zhang, Bin School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331527426

To improve object detection accuracy and resolve large variations in object size in remote sensing images, this paper proposes the InternAware model based on InternImage-T. The GFA (Global Feature Aware) module is used to eliminate significant background information, enhancing the model's global perception of object regions and reducing complex background interference. Additionally, the ADS (Attention Down Sampling) module refines the feature map and transmits effective semantic information, boosting the model's encoding ability within the deep network. The model's detection performance is evaluated on the public UCAS AOD dataset. Experimental results show that the proposed model outperforms the baseline model, with an APL increase of 4.1% on the UCAS AOD dataset, confirming the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Image enhancement

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：