检索结果-内蒙古大学图书馆

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Bharti, Ayush Sinha, Vishal Kumar Peter, J. Selvin Paul Priya Esther, B. Srmist Department of Computer Science and Engineering Chennai India Srmist Department of Mechatronics Chennai India

ISBN: (纸本)9798350309140

The rise of deepfake videos presents substantial obstacles in guaranteeing the genuineness and reliability of visual media material. This study focuses on the crucial problem of identifying deepfake content by introducing a sophisticated method that combines ResNext CNNs along with LSTM models, utilizing transfer learning approaches. Employed a comprehensive approach by using a wide array of datasets such as FaceForensics++, Celeb-DF, and the Deepfake Detection Challenge. Utilizing transfer learning, a ResNext CNN that has been pre-trained is employed to extract complex features from video frames. This enables the subsequent training of an LSTM layer to identify temporal patterns and distinctive cues that are exclusive to modified videos. The effectiveness of fusion model has been demonstrated through extensive experimentation and validation on these rich datasets. It demonstrates a strong ability to reliably distinguish between authentic and manipulated movies, regardless of the different facial alteration techniques, environmental variables, and complex situations seen in real-life situations. The integration of ResNext-based feature extraction with LSTM-based temporal modeling shows substantial progress in the detection of deepfake videos. The efficacy of approach is highly promising, since it provides both dependability and scalability. This study makes a significant contribution to the field of deepfake identification by offering a powerful collection of techniques to tackle the growing concerns surrounding disinformation and manipulation in visual media. © 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

A Framework for Industrial Inspection System using Deep Learning

引用

Annals of Data Science 2024年第2期11卷 445-478页

作者： Hridoy, Monowar Wadud Rahman, Mohammad Mizanur Sakib, Saadman Department of Mechatronics & amp Industrial Engineering Chittagong University of Engineering & ampTechnology Chattogram Bangladesh Department of Mechanical Engineering Chittagong University of Engineering & ampTechnology Chattogram Bangladesh Department of Computer Science & amp Engineering Chittagong University of Engineering & ampTechnology Chattogram Bangladesh

Industrial Inspection systems are an essential part of Industry 4.0. An automated inspection system can significantly improve product quality and reduce human labor while making their life easier. However, a deep learning-based camera inspection system requires a large amount of data to classify the defective products accurately. In this paper, a framework is proposed for an industrial inspection system with the help of deep learning. Additionally, A new dataset of hex-nut products is proposed containing 4000 images, i.e., 2000 defective and 2000 non-defective. Moreover, different CNN architectures, i.e., Custom CNN, Inception ResNet v2, Xception, ResNet 101 v2, ResNet 152 v2, are experimented with the concept of transfer learning on the new hex-nut dataset. Fine-tuning the CNN architectures is performed by freezing the last 14 layers, which provided the optimal architecture, i.e., Xception (last 14 layers trainable, excluding the fully connected layer). The proposed framework can efficiently separate the defective products from the non-defective products with 100% accuracy on the hex nut dataset. Furthermore, the proposed optimal Xception architecture has experimented on a publicly available casting material dataset which produced 99.72% accuracy, outperforming existing methods. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s);author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

i-Glove: An Intelligent Glove System Based on Deep Learning to Support Deaf-blind Individuals in Recognizing Banknotes 3

i-Glove: An Intelligent Glove System Based on Deep Learning ...

引用

3rd IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Hossain, Fahad Mohammad Alavi, Rafit Safat, Yeamin Sarker, Gobinda Chandra Noor, Nafisa Hossain, Ekram Mymensingh Engineering College Department of Computer Science and Engineering Mymensingh Bangladesh University of Dhaka Department of Robotics and Mechatronics Engineering Dhaka Bangladesh

ISBN: (纸本)9798331534400

The deaf-blind community faces significant challenges in identifying banknotes due to simultaneous hearing and vision impairments, which complicate their ability to conduct daily financial transactions. Recent advances in Artificial Intelligence (AI)-based assistive technologies offer promising potential to address these challenges. This study presents the "i-Glove,"a wearable device specifically developed to assist the deaf-blind community in Bangladesh with accurate banknote identification. The i-Glove is designed to recognize nine common Bangladeshi banknotes (e.g., BDT 20, 50, 100) through a camera module integrated on the palmar side of the glove, which captures real-time images of the banknotes. These images are then processed by a convolutional neural network (CNN) model to accurately classify each banknote. Identified notes are translated into unique vibration patterns that are delivered to the user through a shaftless vibration motor embedded in the glove, providing intuitive, non-visual communication. Compared to previous approaches, our model demonstrates superior performance even with a compact dataset, achieving an overall F1-score accuracy of 96.55%, with class-specific precision, recall, and F1-score metrics ranging from 90% to 100%. Additionally, a dedicated application is developed which supports real-time banknote detection and interfaces seamlessly with the glove. The proposed system represents a significant step forward in assistive technology for the deaf-blind community, empowering the users with greater autonomy in financial transactions. © 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

juktoMala: A Handwritten Bengali Consonant Conjuncts Dataset for Optical Character Recognition Using BiT-based M-ResNet-101x3 Architecture 3

juktoMala: A Handwritten Bengali Consonant Conjuncts Dataset...

引用

3rd International Conference on Electrical, computer and Communication engineering, ECCE 2023

作者： Hasan, Md. Mehedi Hossain, Md. Ali Srizon, Azmain Yakin Sayeed, Abu Rajshahi University of Engineering & Technology Department of Computer Science & Engineering Department of Mechatronics Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350345360

Bengali, the seventh most spoken language in the world by the number of speakers, doesn't have a well-established Optical Character Recognition (OCR) system for handwritten texts. One of the major reasons behind this lacking is contributed to having no complete conjuncts database. No dataset available today covers all the conjunct characters that are used by authors around the globe. In this research, we prepared a complete dataset consisting of 292 consonant conjunct characters, which is the biggest consonant conjunct character dataset to date by the number of classes available in the literature to our knowledge. We applied Big Transfer-based M-ResNet-101x3 Deep Convolutional Neural Network (DCNN) which achieves 91.32% accuracy that outperforms the baseline EfficientNetB7 approach which obtained 81.05% accuracy. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Underground Sewer Defect Classification Using a Modified RegNet

引用

computers, Materials & Continua 2023年第6期75卷 5451-5469页

作者： Yu Chen Sagar A.S.M.Sharifuzzaman Hangxiang Wang Yanfen Li L.Minh Dang Hyoung-Kyu Song Hyeonjoon Moon Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Intelligent Mechatronics Engineering Sejong UniversitySeoul05006Korea Department of Information of Communication Engineering and Convergence Engineering for Intelligent DroneSejong UniversitySeoul05006Korea

The sewer system plays an important role in protecting rainfall and treating urban *** to the harsh internal environment and complex structure of the sewer,it is difficult to monitor the sewer *** are developing different methods,such as the Internet of Things and Artificial Intelligence,to monitor and detect the faults in the sewer *** learning is a promising artificial intelligence technology that can effectively identify and classify different sewer system ***,the existing deep learning based solution does not provide high accuracy prediction and the defect class considered for classification is very small,which can affect the robustness of the model in the constraint *** a result,this paper proposes a sewer condition monitoring framework based on deep learning,which can effectively detect and evaluate defects in sewer pipelines with high *** also introduce a large dataset of sewer defects with 20 different defect classes found in the sewer *** study modified the original RegNet model by modifying the squeeze excitation(SE)block and adding the dropout layer and Leaky Rectified Linear Units(LeakyReLU)activation function in the Block structure of RegNet *** study explored different deep learning methods such as RegNet,ResNet50,very deep convolutional networks(VGG),and GoogleNet to train on the sewer defect *** experimental results indicate that the proposed system framework based on the modified-RegNet(RegNet+)model achieves the highest accuracy of 99.5 compared with the commonly used deep learning *** proposed model provides a robust deep learning model that can effectively classify 20 different sewer defects and be utilized in real-world sewer condition monitoring applications.

关键词： Deep learning defect classification underground sewer computer vision convolutional neural network RegNet

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Phonocardiogram Signals Analysis for Cardiovascular Abnormalities Detection

Deep Learning Based Phonocardiogram Signals Analysis for Car...

引用

2023 International Conference on Robotics and Automation in Industry, ICRAI 2023

作者： Hussain, Sayed Shahid Ashfaq, Muniba Khan, Muhammad Salman Anwar, Shahzad Department of Computer Systems Engineering Peshawar Pakistan Department of Mechatronics Systems Engineering Peshawar Pakistan

ISBN: (纸本)9781665464727

Cardiovascular diseases are among the vital causes of mortality worldwide which need early detection with the use of auscultation examination. Heart diseases could be diagnosed in a convenient way of heartbeat sound analysis. Manual auscultation is time-consuming and problematic to differentiate heart sounds related to different kinds of heart abnormalities. Also, as it requires an expert in the field, it becomes costly and quite prone to human error. Due to all these issues, there is a high demand for an automatic diagnostic system, an alternative way to human examination. This research focuses on developing Artificial Intelligence (AI) based system of the latest computational algorithms for detecting heart abnormalities from heart sounds. Heart sounds are classified as to be normal or abnormal from Phonocardiogram (PCG) signals. One of the recent techniques introduced in deep learning algorithms for audio classification is 1-Dimensional Convolutional Neural Network (1D-CNN). This research work includes a 1D-CNN as a classification algorithm. A widely used publicly available dataset of heart sounds from PhysioNet/CinC (2016) challenge is utilized. The method acquires accuracy, sensitivity, specificity, F1 score, and precision of 95.45%, 97.44%, 93.6%, 95.45%, and 95.54% respectively. The proposed approach uses a less-complicated customized 1D-CNN algorithm, outshining most of the previous competitive methods by securing high performance that makes it appropriate for diagnosing heart diseases from PCG data. © 2023 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost Robotic Arm Manipulator Model for Enhancing Student Learning in an Industrial Robots Course 53

A Low-Cost Robotic Arm Manipulator Model for Enhancing Stude...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Mashagbeh, Mohammad Ai-Khawaldeh, Mustafa Hussein, Sanad Alabdellat, Husam Swidan, Andraws The University of Jordan The Department of Mechatronics Engineering Amman Jordan Philadelphia University The Department of Mechatronics Engineering Amman Jordan The University of Jordan The Department of Computer Engineering Amman Jordan

ISBN: (纸本)9798350336429

Recent years have seen a rise in the importance of the field of robotics, therefore students need to understand its basic concepts. Forward and inverse kinematics, which are essential components of robotic arm control, must be understood in order to design and program a robotic arm manipulator. To help students understand these concepts, this study proposes a low-cost robotic arm model. The robotic arm model is simple to build, inexpensive, and flexible, allowing students to experiment with various configurations and test various kinematic concepts. The model consists of a 3 DOF RRR (3 revolute joints) robot, pro-viding students with a 3D view of the D- H (Denavit-Hartenberg) parameters. As the robot moves, students can observe and visualize parameters such as the twist of the link a and the angle of the joint (). This improves students' understanding of the concept of D-H parameters. The proposed robotic arm model can be used to teach students about the basics of robotic arm manipulators while also serving as a less expensive substitute for more expensive commercial models. The D-H parameters, forward and inverse kinematic analysis can be explained using the model, which can also help students comprehend these fundamental mathematical concepts. In general, this inexpensive robotic arm model gives students a practical and convenient approach to advance their robotic knowledge and abilities. According to the results of our study, the use of the proposed model in an industrial robots course can greatly enhance students' learning outcomes. The model gives students practical experience and enables them to apply theoretical ideas in a reality, which improves their comprehension of the subject. Also, it was discovered that the model was a useful tool for involving students in the learning process and boosting their motivation to study. Our research implies that, especially in situations where access to expensive equipment is restricted, using a low-cost robotic arm manipu

关键词： D-H parameters Forward Kinematics Inverse Kinematics RRR Robot

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of MEMS Tuning Fork Gyroscope Designs with Microlever Amplification Mechanism for Enhanced Sensitivity and Robustness 6

Comparative Analysis of MEMS Tuning Fork Gyroscope Designs w...

引用

6th International Conference on Robotics and Automation in Industry, ICRAI 2024

作者： Bashir, Uzair Javaid, Faraz Ali, Osama Arshad, Adeel Rehman, Masood Ur Department of Electrical and Computer Engineering Islamabad Pakistan Department of Mechatronics Engineering Islamabad Pakistan Superior University Faculty of Engineering and Technology Lahore Pakistan

ISBN: (纸本)9798350355703

This paper presents a comparative analysis of two MEMS Tuning Fork Gyroscope (TFG) designs employing microlever amplification mechanisms for sensitivity amplification in the sense mode. An input frame added in microlever amplification frame to increase the robustness of MEMS gyroscope. Design A incorporates a non-anchored input frame in microlever, while Design B features an anchored input frame in microlever. Frequency response analysis and modal analysis were performed using CoventorMEMS+ to evaluate the impact of input frame of microlever on undesired mode suppression, mechanical sensitivity, and robustness. The results indicate that anchoring the microlever in Design B significantly reduces quadrature displacement arise because of environmental linear acceleration in the sense mode while maintaining comparable amplified sensitivity to Design A. Design B offers enhanced stability and robustness, making it a more suitable candidate for precision applications such as autonomous vehicle navigation systems. © 2024 IEEE.

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Enhanced Prediction of Metamaterial Antenna Parameters Using Advanced Machine Learning Regression Models

引用

Progress In Electromagnetics Research C 2024年 146卷 1-12页

作者： Jain, Prince Sahoo, Prabodh K. Khaleel, Aymen D. Al-Gburi, Ahmed Jamal Abdullah Department of Mechatronics Engineering Parul Institute of Technology Parul University Gujarat Vadodara391760 India Computer Engineering Department College of Engineering Al-Iraqia University Iraq Jalan Hang Tuah Jaya Durian Tunggal Melaka76100 Malaysia

The integration of machine learning (ML) regression models in predicting the parameters of metamaterial antennas significantly reduces the design time required for optimizing antenna performance compared to traditional simulation tools. Metamaterial antennas, known for overcoming the bandwidth constraints of small antennas, benefit greatly from these advanced predictive models. This study applies and evaluates four ML regression models — Extra Trees, Random Forest, XGBoost, and CatBoost — to predict key antenna parameters such as S11, gain, and bandwidth. Each model’s performance is assessed using metrics like Mean Absolute Error (MAE), Mean Squared Error (MSE), R-squared (R2), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Error (RMSE) across different training and testing set configurations (30%, 50%, and 70%). The Extra Trees model achieves the best performance for predicting gain, with an R2 of 0.9990, MAE of 0.0069, MSE of 0.0002, RMSE of 0.0145, and MAPE of 0.3106. Feature importance analysis reveals that specific features, such as pr and p0 for gain and Y a and Xa for bandwidth, are critical in the predictive models. These findings highlight the potential of ML methods to improve the efficiency and accuracy of metamaterial antenna design. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

A non Invasive Brain-computer-Interface for Service Robotics 3

A non Invasive Brain-Computer-Interface for Service Robotics

引用

3rd IEEE International Conference on Artificial Intelligence, ICAI 2023

作者： Ahmed, Fatima Iqbal, Hashim Nouman, Ahmed Maqbool, Hafiz Farhan Zafar, Saqib Saleem, Muhammad Khurram University of Engineering & Technology Mechatronics Engineering Department Lahore Pakistan AASS Computer Science Department Orebro University Örebro Sweden University of Engineering & Technology Mechatronics Engineering Department Taxila Pakistan

ISBN: (纸本)9798350322125

A Brain-computer Interface (BCI) enables individuals to control a system solely through their brain activity, without relying on physical movement. These interfaces have numerous applications, particularly in assisting individuals with paralysis. Our research paper details a BCI interface that can classify and control seven wheelchair movements: forward, backward, left, right, stair climbing upwards, stair climbing downwards, and stop. We collected raw signal data using the electroencephalog-raphy (EEG) technique from healthy volunteers, which we then filter before feeding into the feature extraction and classification stages. We evaluated our approach using three classification algorithms: Convolution Neural Network (CNN), Support Vector Machines (SVM), and Random Forest Classifier, and compared their performance. Our experimental results demonstrate that our proposed approach is highly promising for implementing BCI, with a classification accuracy of 99% using a Random Forest Classifier. © 2023 IEEE.

关键词： Brain computer interface

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：