检索结果-内蒙古大学图书馆

2nd International Conference on Big Data, IoT and Machine Learning, BIM 2023

作者： Mormo, Samver Jahan RakibulHaque, Md. Department of Computer Science and Engineering Rajshahi University of Engineering and Technology Rajshahi Bangladesh

ISBN: (纸本)9789819989362

Bangla is the sixth most widely spoken language worldwide, making the recognition of handwritten characters in this language an important task. However, recognizing Bangla characters is challenging due to the large number of characters in this language, which is around 400. Furthermore, with the increase in number of characters to recognize, the accuracy decreases. In this research, we propose a transfer learning architecture that branches pretrained convolutional neural network models VGG-16 and DenseNet-121, along with Nadam optimizer. The model is evaluated on Ekush dataset which contains 3,68,776 images over 122 characters or classes. Our proposed model achieved 96.94% accuracy on training data and 96.14% accuracy on test data. A comparison of the various state-of-the-art benchmarks for classifying Bangla Handwritten Characters demonstrates that the proposed model has outperformed previous studies. Our efforts will contribute to the development of an effective tool for automatically recognizing handwritten characters in Bangla. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Integration of Voice Assistance System for Visually Challenged Person

Integration of Voice Assistance System for Visually Challeng...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Jasmine Gilda, A. Jeba Sheela, A. Mary Dayana, A. Gowthami, M. Department of Computer Science and Engineering R.M.K. Engineering College India Department of Computer Science and Engineering Easwari Engineering College India Department of Computer Science Nesamony Memorial Christian College India

ISBN: (纸本)9798350305708

The internet has been of great use in assisting users with various services like information access and communication. Normal people adapt quickly to the internet age without much difficulties, but persons with visual impairments find it difficult to use the internet and its services. Communication and information access are some of the important use cases of communication. Therefore, the availability of opportunities will significantly increase with the creation of voice accessible applications assisting the visually challenged people. This work aims to provide the development of a voice assistance system to visually challenged people facilitating speech recognition to access Email. Additionally, this work facilitates detection of users documents. The suggested method integrates a voice-assist system to find critical documents and access the mail system. It uses the best aspects of the given dataset and outputs the results using webcam. Its primary foundation is interactive voice response, which might make it simple to operate. Mail system provides information on the voicemail system architecture that a blind person can utilize to send emails. The deployment of voice assistance to a system allows easy access for the visually challenged. © 2023 IEEE.

关键词： Object Detection Speech-to-Text (STT) Text-to-Speech (TTS) Visually challenged You Only Look Once (YOLO)

来源：评论

学校读者我要写书评

暂无评论

Human-Centered Coordination for Robot-Assisted Equipment Transport

引用

ASME Letters in Dynamic Systems and Control 2025年第2期5卷 021002页

作者： Fernandez, Joshua Cosby, Austin Mazumdar, Anirban Department of Mechanical Engineering Georgia Institute of Technology AtlantaGA30363 United States Department of Computer Science Mississippi State University MS39762 United States

This work explores how to use an unmanned ground vehicle (UGV) to offload the physical burdens of equipment from humans. This work formulates dynamic alignment following and compares it to position-based following techniques. We describe the control strategies of both following methods and implement them in a dynamic simulation and a physical prototype. We test the performance of the two following methods and show that dynamic alignment following can reduce robot positional error and interaction force between the human and the robot. We then analyze the energetics and the performance of the human-UGV team for candidate transportation tasks. The presence of the robot can make some tasks take longer to perform. Nonetheless, the results show that for the candidate tasks, the robot can reduce human average metabolic power and average overall task energy. © 2024 by ASME.

关键词： Ground vehicles

来源：评论

学校读者我要写书评

暂无评论

VEye-AI Vision Assistant 10

VEye-AI Vision Assistant

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Joy, Alen Nazeer, Naja Abdul Gregory, Neha Maria Davis, Jasmy Sahrdaya College of Engineering and Technology Department of Computer Science and Engineering Thrissur India

ISBN: (纸本)9798350384369

This paper aims to deal with the difficulties faced by blind while interacting with their surroundings. The proposed system introduces VEye - An AI Vision Assistant, a wearable device with an integrated camera and an ear-piece, using AI algorithms to convert real-time visual input from camera to audio description. It includes other features such as obstacle detection, text recognition, face recognition for authorized individuals, object identification, GPS integration and an emergency button. This device assists the visually challenged people in their day- to-day activities and develop a feeling of independence in them. © 2024 IEEE.

关键词： Obstacle detectors

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Image Classification Models for Terrain Recognition 3

A Comparative Study of Image Classification Models for Terra...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Krishna Kumar, V. Karthika, V. Mohana, T. Mugebur Rahman, A. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798350369083

ISBN: (纸本)9798350369083

Terrain recognition is vital for various applications such as autonomous navigation, environmental monitoring, military operations, and urban planning. It enables safe navigation for autonomous vehicles, aids in environmental surveillance, assists in military reconnaissance, and supports urban infrastructure development. Recent years have witnessed the augmentation of machine learning models with online feature extraction techniques and self-supervised learning frameworks. However, a notable challenge lies in managing the complexity inherent in processing extensive datasets or numerous features. In this study, this problem is addressed by employing transfer learning for classifying terrains using images. The effectiveness of three widely used pre-trained convolutional neural network models - ResNet50, VGG16, and InceptionV3 - was compared. The findings demonstrate the strong performance of the models, emphasizing the effectiveness of transfer learning in tasks focused on terrain recognition. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Ensuring Security and Efficiency in Digital Payments using Blockchain with NFC

Ensuring Security and Efficiency in Digital Payments using B...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Mandal, Shovon Shill, Pintu Chandra Khulna University of Engineering & Technology Department of Computer Science and Engineering Khulna Bangladesh

ISBN: (纸本)9798350359688

Bangladesh has recently adopted the worldwide trend of digitalization, namely in the area of financial activities. In Bangladesh, the centralized nature of digital payment systems poses notable obstacles, such as lengthy transaction procedures, vulnerability to fraudulent activities, and the potential for financial theft, despite their increasing popularity. In light of these concerns, our study presents an innovative remedy that utilizes the potential of blockchain technology, in conjunction with Near Field Communication (NFC) technology, to transform the field of electronic transactions. Our adoption of the proof-of-stake technique sets us apart from traditional hand-cash systems as well as the current centralized digital payment systems, providing enhanced efficiency and security. This connection facilitates fast, safe, and user-friendly transactions across several platforms, such as online and mobile applications, thereby greatly improving the digital wallet experience. Our decentralized system guarantees the integrity and immutability of every transaction while significantly decreasing transaction and maintenance expenses. This technique functions independently without any external intervention, fostering trust among users and strengthening the system against fraudulent activity. Our system is specifically designed for the high-volume transaction environment of Bangladesh's digital economy. It has the capability to efficiently handle large transaction volumes while ensuring full security. This article elucidates the revolutionary capacity of our blockchain-powered system to promote a secure, streamlined, and inclusive digital payment ecosystem in Bangladesh, representing a crucial stride towards a technologically progressive financial landscape. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Image Classification: Leveraging Deep Learning and Large Language Models for Semantic Integration 2

Breast Cancer Image Classification: Leveraging Deep Learning...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Harini, K.K. Nandhini, R. Rajeswari, A.M. Deepalakshmi, R. Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India

ISBN: (纸本)9798350383652

Breast cancer, a significant global health problem that is mainly affecting women, demonstrates the importance of early detection to enhance survival rates. Medical image classification is a significant field that utilizes deep learning methods such as Convolutional Neural Networks (CNNs), Region-Based CNNs (R-CNNs), and Deep Neural Networks (DNNs). Despite this, challenges such as over fitting persist, particularly with limited data or complex models. Although these models learn hierarchical features, interpreting them in intricate image structures is still challenging and complicates decision rationale. To address this, we propose a comprehensive approach for breast cancer image classification. The initial process involves image segmentation using CNN to identify regions of interest, followed by precise object detection with OpenCV. Data quality and diversity are ensured by preprocessing and augmentation with ImageDataGenerator, while informative features are extracted using the InceptionV3model. Our analysis of textual descriptions and embeddings is done by integrating Sentence Transformers and CLIP from the Large Language Model (LLM) framework. Achieving robust decision-making is ensured by setting a threshold of 0.7 for image classification based on predicted malignancy probability. Finally, improving the computations of similarity scores can improve prediction accuracy for reliable diagnostic interpretations. An accuracy of 0.92 in breast cancer diagnosis is guaranteed by integrating LLM and CNN for classification. © 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

Comparison of Distributed Key and Access Management for Wireless Ad Hoc Network 18

Comparison of Distributed Key and Access Management for Wire...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Nandhini Devi, S. Sathiya Lakshmi, E. Shiny, A. Nithya, M. Sri Sairam Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9789380544519

A remote organization comprises of the many organization geographies that are broadly circulated, associated by moving hubs alluded to as portable hubs. Transfer innovation is utilized to upgrade parcel conveyance and work on the exhibition of remote organizations, tantamount to overall similarity for microwave access and LTE-A. Verification is crucial in an extremely remote geography because of thousands of clients speaking with each other with no recognizable proof. A public-key cryptanalytic rule that works with the Distributed key exchange algorithm is used for these authentications. the strategy for the Disseminated key trade calculation is that 2 clients solidly trade keys that they in the long run use to encode a message. The goal of our research is to reduce the amount of work in the relay network and increase performance in a way that is comparable to the quality factor. These parts. contemplate making a dependable way to decrease idleness and increment data rates, lastly, information move is one of the critical difficulties in remote systems administration, then, at that point, we will generally consider a jump by-bounce plot. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Comparison Data Transmission Delay Performance Wireless Ad-Hoc Networks

来源：评论

学校读者我要写书评

暂无评论

One Day International Cricket Match Score Prediction Using Machine Learning Approaches 1

One Day International Cricket Match Score Prediction Using M...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Hossain, Md. Sabbir Rumpa, Ummay Khadiza Hossain, Md. Shakil Shovon, Sazzadul Islam Huque, Md. Tahmidul Hasan, Mahamudul East West University Department of Computer Science and Engineering Dhaka Bangladesh Central Michigan University Department of Information System MI United States Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350377002

Cricket is the game that binds Bangladeshis to-gether. The datasets were split into different parts based on the time of the cricket matches to experiment with the results. We have used Random Forest Regression and Linear Regression to experiment with the results. We have worked on different sets of independent variables while working with different datasets but runs and wickets were constant features. The linear Regression technique gave 0.58 of r-squared metric and its MAE: 32.857046003557706, MSE: 1793.4360657965133, RMSE: 42.34897951304746 values indicate that the regression model is making predictions that are reasonably close to the actual ob-served values. However, there is still some room for improvement. The r-squared metric of 0.787 was derived from a relatively brief dataset, MAE: 20.48880467759807, MSE: 690.1167559064677, RMSE: 26.270073389818837 metrics indicate that the regression model is making predictions that are very close to the actual observed values. Random Forest Regression's r-squared metric resulted in 0.807 but the learning curve pointed out an overfit model. Thus, linear regression contained the best result. We have applied the regularisation technique to achieve a better result. The dataset was collected from Github and Kaggle, sizes are (350899, 15) and (4037, 9) respectively. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

CPL-SLAM: Centralized Collaborative Multi-Robot Visual-Inertial SLAM Using Point-and-Line Features

引用

IEEE Internet of Things Journal 2025年第12期12卷 21866-21875页

作者： Liu, Xin Wen, Shuhuan Liu, Huaping Richard Yu, F. Yanshan University Engineering Research Center The Ministry of Education for Intelligent Control System and Intelligent Equipment Key Lab of Intelligent Rehabilitation and Neuroregulation in Hebei Province Department of Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao066004 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Shenzhen University College of Computer Science and Software Engineering China Carleton University Canada

Traditional visual-inertial SLAM (Simultaneous Localization and Mapping) systems predominantly rely on feature point matching from a single robot to realize the robot pose estimation and environment map construction. However, in complex scenarios, these traditional systems struggle with issues such as tracking failures due to illumination changes, rapid movements, and low-texture environments, and they perform poorly in terms of mapping efficiency and global consistency. To address these challenges, we propose a centralized collaborative SLAM system that employs both point and line features for tracking in the robot and map fusion in the cloud. The proposed system leverages the fusion of point and line features across all instances in the process, which allows our method to achieve higher localization accuracy in structured, low-texture scenes. With the aid of classifying gravity-aligned vertical lines and spatial parallel lines, the proposed system can deliver faster and more accurate odometry in complex scenes. Furthermore, we developed intra-robot and inter-robot loop closure detection methods based on point and line features, generating a globally consistent sparse point cloud and structured scene map in the cloud. Our method is able to build richer maps while improving accuracy compared to existing methods. Experimental results on public datasets and in real-world environments show that, compared to existing advanced methods, our approach demonstrates better performance. © 2014 IEEE.

关键词： SLAM robotics

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：