检索结果-内蒙古大学图书馆

FetchAid: Making Parcel Lockers More Accessible to Blind and Low Vision People With Deep-learning Enhanced Touchscreen Guidance, Error-Recovery Mechanism, and AR-based Search Support

arXiv

引用

arXiv 2024年

作者： Guan, Zhitong Xiong, Zeyu Fan, Mingming Computational Media and Arts Thrust The Hong Kong University of Science and Technology Guangzhou China Division of Integrative Systems and Design Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Parcel lockers have become an increasingly prevalent last-mile delivery method. Yet, a recent study revealed its accessibility challenges to blind and low-vision people (BLV). Informed by the study, we designed FetchAid, a standalone intelligent mobile app assisting BLV in using a parcel locker in real-time by integrating computer vision and augmented reality (AR) technologies. FetchAid first uses a deep network to detect the user's fingertip and relevant buttons on the touch screen of the parcel locker to guide the user to reveal and scan the QR code to open the target compartment door and then guide the user to reach the door safely with AR-based context-aware audio feedback. Moreover, FetchAid provides an error-recovery mechanism and real-time feedback to keep the user on track. We show that FetchAid substantially improved task accomplishment and efficiency, and reduced frustration and overall effort in a study with 12 BLV participants, regardless of their vision conditions and previous experience. © 2024, CC BY-NC-ND.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Beyond Imagination: Leveraging Generative AI to Enhance Learning Through Story World Analogies

Beyond Imagination: Leveraging Generative AI to Enhance Lear...

引用

Frontiers in Education (FIE) Conference

作者： Dünya Baradari Harry Han Julia Xia Carey Ann Strelecki MIT Media Lab Massachusetts Institute of Technology Cambridge MA Graduate School of Education Harvard University Cambridge MA Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This innovative practice full paper describes ConceptualTales, a conversational AI that explains STEM and social science concepts using analogies from popular story worlds and Socratic reasoning. The disconnect between conventional teaching strategies and student engagement is a persistent challenge in educational systems, particularly STEM fields. Traditional methods often fail to resonate with students, rendering the learning process monotonous and detached from their personal interests. Concurrently, students are enthusiastic about and dedicated to fictional worlds such as Marvel, Harry Potter, and Disney. This observation forms the basis for our innovative practice: integrating these beloved narratives into educational content through generative AI. ConceptualTales was tried with middle and high school students in the USA and China and received overwhelmingly positive feedback. Our system combines fiction-inspired learning, analogical reasoning, and Socratic questions, to make educational content personal and interesting to students.

关键词： Conversational artificial intelligence Generative AI Social sciences Education Rendering (computer graphics) Cognition STEM

来源：评论

学校读者我要写书评

暂无评论

Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study

arXiv

引用

arXiv 2022年

作者： Choi, Hongjun Jeon, Eun Som Shukla, Ankita Turaga, Pavan Geometric Media Lab School of Arts Media and Engineering Arizona State University School of Electrical Computer and Energy Engineering Arizona State University United States

Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model. Knowledge distillation (KD), on the other hand, is widely used for model compression and transfer learning, which involves using a larger network’s implicit knowledge to guide the learning of a smaller network. At first glance, these two techniques seem very different, however, we found that "smoothness" is the connecting link between the two and is also a crucial attribute in understanding KD’s interplay with mixup. Although many mixup variants and distillation methods have been proposed, much remains to be understood regarding the role of a mixup in knowledge distillation. In this paper, we present a detailed empirical study on various important dimensions of compatibility between mixup and knowledge distillation. We also scrutinize the behavior of the networks trained with a mixup in the light of knowledge distillation through extensive analysis, visualizations, and comprehensive experiments on image classification. Finally, based on our findings, we suggest improved strategies to guide the student network to enhance its effectiveness. Additionally, the findings of this study provide insightful suggestions to researchers and practitioners that commonly use techniques from KD. Our code is available at https://***/hchoi71/MIX-KD. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Secured Entry Control: An IoT and Deep Learning based Mask Detection System for COVID-19 Suspected Patient Screening and Access Regulation

Secured Entry Control: An IoT and Deep Learning based Mask D...

引用

International Conference on Advancement in electrical and Electronic engineering (ICAEEE)

作者： Abida Sultana Hasibul Islam Peyal Md. Injamul Islam Md. Nazmul Abdal Shafiun Miraz Md. Mahin Rahaman Kontho Zannatul Mawa Leion Abdul Al Mamun Dept. of Electrical & Computer Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh Dept. of Computer Science & Engineering Uttara University Dhaka Bangladesh Dept. of Computer Science and Engineering University of Liberal Arts Bangladesh Dhaka Bangladesh Dept. of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh Dept. of Computer Science and Engineering Tejgaon College Dhaka Bangladesh

ISBN: (数字)9798350388282

ISBN: (纸本)9798350388299

The new coronavirus SARS-CoV-2, which triggered the COVID-19 pandemic, has had an unparalleled effect on economies, cultures, and world health. In response to the critical need for strict COVID-19 screening systems in public areas, this study presents a creative Secured Entry Control system. Detecting and controlling possible COVID-19 carriers attempting to enter the country is made possible by this system, which makes use of deep learning algorithms and IoT technology. The mask detection algorithm, MobileNetV2 model, has an exceptional validation accuracy of $98.96 \%$. The model’s reliability is supported by performance evaluations using ROC curves, confusion matrix analysis, and an AUC value of $98.96 \%$, which is close to the optimal AUC score of $100 \%$. Because MobileNetV2 is well-suited for low-processing devices, it is easy to deploy it on Raspberry Pi, which helps to create an affordable system. Furthermore, by spotting increased body temperatures, a contactless temperature sensor improves the system’s ability to identify possible COVID-19 carriers. The functioning of the system is confirmed by the working prototype that is presented in the Experimental Results section. The main goal of this research is to create an autonomous system that is affordable and selectively allows access to people who are less likely to transmit COVID-19 in public areas. To achieve the overall objective of reducing the spread of COVID-19 in public spaces, this research highlights the successful integration of mask identification algorithms and IoT.

关键词： COVID-19 Temperature sensors Deep learning Workability Accuracy Autonomous systems Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Locating Microalgae in Image Captured by Smartphone and Digital Microscope Camera 8

A Deep Learning Approach for Locating Microalgae in Image Ca...

引用

Joint 8th International Conference on Digital arts, media and technology and 6th ECTI Northern Section Conference on electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2023

作者： Kaewman, Nitiphong Charoenkwan, Phasit Yana, Jinnapat Suanoi, Phon-Ubon Duangjan, Kritsana Pekkoh, Jeeraporn Pumas, Chayakorn Chiang Mai University Faculty of Science Department of Biology Chaing Mai Thailand College of Arts Media and Technology Chaing Mai University Chaing Mai Thailand Chulalongkorn University Faculty of Engineering Department of Computer Engineering Bangkok Thailand Science and Technology Research Institute Chiang Mai University Chaing Mai Thailand Chiang Mai University Faculty of Science Department of Biology Chiang Mai Thailand

ISBN: (纸本)9798350396546

The utilization of microalgae as a bioindicator for water quality assessment has traditionally relied on the expertise of morphological identification. With the advent of technological advancements, particularly the smartphone camera, there has been increasing interest in using it as a tool for various fields of microbiological and medical diagnostics, including image analysis of microalgae. Despite the growing popularity of smartphone-based image analysis, the image quality of smartphone cameras for detecting microalgae has yet to be thoroughly evaluated. Therefore, the purpose of this study was to investigate the suitability of smartphone-based camera for collecting microalgae images and compare it to that of a digital microscope camera. Additionally, the effect of different microscopic magnifications at 100x and 400x on model performance was thoroughly studied. Four models, YOLOv5, RetinaNet, EfficientDet, and Faster-RCNN, were trained on microalgae image datasets taken by both a smartphone camera (SC) and a digital microscope camera (DMC) under 100x and 400x magnification. A total of 11,608 images were divided into three parts: train (70%), validation (10%), and test (20%), with the test dataset separated into four parts for each device and magnification. The results of the study indicated that Faster-RCNN was the best model for microalgae detection, with the highest average precision (AP0.5) values of 0.60, 0.84, 0.91, and 0.96 at 100x magnification of SC and DMC and 400x magnification of SC and DMC, respectively. The comparison between the image quality of SC and DMC at each magnification revealed that the SC was less suitable for microalgae identification, particularly at 100x magnification. Conversely, the 400x magnification of SC had the potential to identify microalgae through the use of smartphone-based photography, as well as digital microscope camera. © 2023 IEEE.

关键词： Microalgae

来源：评论

学校读者我要写书评

暂无评论

An Automatic Reflective Clothing Detection Algorithm Based on YOLOv5 for Work Type Recognition 11

An Automatic Reflective Clothing Detection Algorithm Based o...

引用

11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022

作者： He, Xinyi Ma, Ping Chen, Yiyang Liu, Yuan School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu Key Laboratory of Media Design and Software Technology Wuxi214122 China School of Mechanical and Electrical Engineering Soochow University Suzhou215137 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

At present, traditional manual methods are still utilized for the inspection of reflective clothing on a wide range of construction sites. Using this manual inspection methods wastes much human resource. In this paper, the YOLOv5 model is used as the network framework to automatically detects whether the workers wear reflective clothing, and determines types of work by examining reflective clothing of different colors. By identifying the color difference of the reflective clothing, the network is capable of distinguish whether the target work type can enter relevant construction areas with different danger levels. In this paper, by constructing the labeled data set and training on the basis of YOLOv5 model framework, a target model is obtained. Its detection speed can adapt to real-time monitoring. The accuracy and recall rates can meet the requirements on the training set and verification set. It has a desired effect on the testing set of real website captured images, and can realize the intelligent recognition of reflective clothing on construction sites. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Patient Satisfaction Surveys and Feedback with Cloud Computing and NLP Techniques 8

Optimizing Patient Satisfaction Surveys and Feedback with Cl...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Jayanthi, L.N. Shanmugam, Kannan Suma, Challapalli Sagar, B.S. Maniraj, S.P. Ganeshbabu, T.R. Saveetha College of Liberal Arts and Sciences Department of Commerce Tamil Nadu Chennai India Vit Bhopal University School of Computing Science and Engineering Department of Gaming Technology Madhapradesh Bhopal India Department of Computer Science and Engineering Andhra Pradesh Bhimavaram India Reva University Department of Electrical and Electronics Engineering Karnataka Bengaluru India Faculty of Engineering & Technology Department of Data Science and Business Systems Chennai Tamil Nadu Kattankulathur India Department of Electronics and Communication Tamil Nadu Namakkal India

ISBN: (纸本)9798350376425

Healthcare quality assessment and identification of opportunities for improvement are crucially facilitated by patient satisfaction surveys. Traditional approaches sometimes face difficulties in handling substantial amounts of written comments and obtaining real useful data. It presents a new method that combines cloud computing with Natural Language Processing (NLP) approaches to enhance the analysis of patient satisfaction data. By using cloud platforms, it can effectively manage large datasets and provide scalable, cost-efficient processing. The use of NLP methods, such as text mining and sentiment analysis, enables the conversion of unstructured input into structured insights, thereby uncovering the fundamental patient feelings and patterns. This connection enables the analysis of data in real-time also improving the accuracy of interpreting feedback and facilitating fast enhancements in healthcare services. Future research will prioritise the improvement of NLP algorithms and the investigation of supplementary cloud-based technologies to enhance the accuracy and efficiency of patient satisfaction analysis to improved patient care and experience. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Model for Software Defect Prediction 2

An Ensemble Model for Software Defect Prediction

引用

2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022

作者： Ali, Amad Rizwan Ur Rehman, Attique Nawaz, Ali Ali, Tahir Muhammad Abbas, Muhammad UserMaven Inc United States University of Sialkot Department of Software Engineering Sialkot Pakistan College of Electrical and Mechanical Engineering National University of Science and Technology Rawapindi Pakistan Gulf University for Science and Technology Department of Computer Science College of Science and Arts Kuwait

ISBN: (纸本)9781665498197

Software testing is one of the important ways to ensure the quality of software. It is found that testing cost more than 50% of overall project cost. Effective and efficient software testing utilizes the minimum resources of software. Therefore, it is important to construct the procedure which is not only able to perform the efficient testing but also minimizes the utilization of project resources. The goal of software testing is to find maximum defects in the software system. As world is continuously moving toward data driven approach for making important decision. Therefore, in this research paper we performed the machine learning analysis on the publicly available datasets and tried to achieve the maximum accuracy. The major focus of the paper is to apply different machine learning techniques on the datasets and find out which technique produce efficient result. Particularly, we proposed an ensemble learning models and perform comparative analysis among KNN, Decision tree, SVM and Naïve Bayes on different datasets and it is demonstrated that performance of Ensemble method is more than other methods in term of accuracy, precision, recall and F1-score. The classification accuracy of ensemble model trained on CM1 is 98.56%, classification accuracy of ensemble model trained on KM2 is 98.18% similarly, the classification accuracy of ensemble learning model trained on PC1 is 99.27%. This reveals that ensemble learning is more efficient method for making the defect prediction as compared other techniques. © 2022 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Integrated Product-Process Design: Conceptual Framework for Data Driven Manufacturing Resource Selection 2

Integrated Product-Process Design: Conceptual Framework for ...

引用

2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022

作者： Uz Zaman, Uzair Khaleeq Ghoto, Mujtaba Rafique Siadat, Ali Baqai, Aamer Ahmed Aqeel, Anas Bin Qamar, Usman College of Electrical & Mechanical Engineering National University of Science and Technology Department of Mechatronics Engineering Islamabad44000 Pakistan Arts et Métiers ParisTech - Campus de Metz Laboratoire Conception Fabrication Commande Metz57070 France College of Electrical & Mechanical Engineering National University of Science and Technology Department of Computer & Software Engineering Islamabad44000 Pakistan

ISBN: (纸本)9781665498197

With the extensive development of new technologies and the application of information in the manufacturing industry, immense volumes of distinct data are being generated and collected daily. However, this data is largely unusable as its not meticulously cleaned and processed. The effective utilization of such complex data is the cornerstone of data analytics, as successful analysis leads to useful, relevant, and actionable knowledge, which in the long run can prove to be revolutionary for any field and open new avenues. Although the application of data analytics in areas such as sales & marketing, healthcare, cybersecurity, and climate change is largely prevalent, the implementation of data analysis and its tools for efficient product & process design is an unexplored opportunity with large volumes of data generated by major stakeholders throughout the manufacturing and product-process design activity remaining underutilized. This paper, therefore, defines a novel conceptual framework that applies data analysis to integrated product-process design (IPPD) for weighted data-driven IPPD that amalgamates data generated from multiple streams. Primarily from the user perspective, supply chain network, current & upcoming technological processes, and competitor process and product designs, will be utilized. The proposed framework can be further used to create new products better aligned with customer requirements, enhance the overall quality of the product, improve production efficiency through new technological advancements, support the supply chain network, and give the applicant industry a competitive advantage against its competitors. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Machine Vision Based Local Hyacinth Bean Breed Recognition Using Convolutional Neural Network

Machine Vision Based Local Hyacinth Bean Breed Recognition U...

引用

Advances in Computing,Communication, electrical, and Smart Systems (iCACCESS), International Conference on

作者： Md. Abbas Ali Khan Md. Ataur Rahman Md Liton Hossain Md. Tarek Habib Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Bachelor of Science in Electrical and Electronic Engineering Center for Innovation and Technology University of Liberal Arts Bangladesh Dhaka Bangladesh

The classification is a significant one. This paper proposes a CNN-based Local Hyacinth Bean Breed Recognition (CNN-LHBR) approach along with a machine vision approach. Among the 52 breeds, we have taken only eight categories, namely Bashpaki Faridpur, Chaina Sada Patla Chela, Gochi, Kajoli, Katla, Lati, Noldub, and Pudi Aishna. There are many works done before about breed detection of different fruits as well as disease recognition. But no research has done such a work as LHBR, especially in Bangladesh. The interest of this research is the reason for the high protein and vitamin B complex; besides, each bean has a separate test, yield, seed, and nutrition level. More importantly, we have implemented 3 CNN models for the experiment of the breed recognition of 8 Hyacinth Bean specimens. For model accuracy, we have considered training, validation, and testing accuracy. As for performance evaluation, the confusion matrix has bean applied. Among the models, the customized CNN model gives the best accuracy. The customized CNN model's accuracy is 97.50%.

关键词：

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：