检索结果-内蒙古大学图书馆

16th IEEE International Conference on computer Science and Education, ICCSE 2021

作者： Saniei, Namdar Ontario Tech University Dept. of Electrical Computer and Software Engineering Oshawa Canada

ISBN: (纸本)9781665414685

Thanks to computers and the internet, since the rise of COVID-19, different methods of online teaching have replaced the face-to-face teaching;however there has not been a viable method of assessment that is fully capable of replacing in class assessments. It is hard, if not impossible, to maintain the integrity of the exams, when conducted remotely. Even prior to the COVID attack, arranging and conducting exams for students, who depend on Students Accessibility Services (SAS), were becoming cumbersome and a burden for universities and instructors. If there were no exams required, as an assessment tool, both the abovementioned issues, would not be a problem. In this paper a few theoretical common solutions to both the issues mentioned above is theorized, proposing elimination or reduction of the exams, as major assessment tool for undergraduate students. The model in which all the exams are eliminated is referred to as Stress-free, and the one with reduced exams is called Stress-less model. Implementing the models discussed in this paper, demand an overhaul of the entire higher education system. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

EdgStr: Automating Client-Cloud to Client-Edge-Cloud Transformation

EdgStr: Automating Client-Cloud to Client-Edge-Cloud Transfo...

引用

International Conference on Distributed Computing Systems

作者： Kijin An Eli Tilevich Software Engineering Team Samsung Research Seoul South Korea Dept. of Computer Science Software Innovations Lab Virginia Tech Blacksburg VA United States

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

To harness the potential of edge resources, two-tier client-cloud applications require transformation into three-tier client-edge-cloud applications. Such transformations are hard for programmers to perform correctly by hand. Many cloud services maintain a runtime state that needs to be replicated at the edge. Once replicated, this state must then be synchronized efficiently and correctly. To facilitate the transition to edge computing, we present a framework that automatically transforms client-cloud apps to their client-edge-cloud versions. Our framework, EdgStr, automatically replicates cloud-based services at the edge. EdgStr synchronizes the replicated service state by relying on a third-party Conflict-Free Replicated Data Type (CRDT). It generates code that connects service state changes to CRDT update operations, thus ensuring that the state changes at each replica eventually converge to the same replicated state. As an evaluation, we applied EdgStr to transform representative distributed mobile apps for deployment in dissimilar network and device setups. EdgStr correctly replicates cloud services (targeting the important domain of ***), deploying the resulting replicas on an ad-hoc edge cluster, hosted by Raspberry PI devices. As long as eventual consistency is congruent with the functionality of a cloud service, EdgStr can automatically replicate this service and deploy the replicas at the edge, thus offering the performance benefits of edge-based execution, without the high costs of manual program transformation.

关键词： Performance evaluation Costs Runtime Codes Transforms Manuals Mobile applications

来源：评论

学校读者我要写书评

暂无评论

Robust texture features for emphysema classification in CT images 28

Robust texture features for emphysema classification in CT i...

引用

28th European Signal Processing Conference, EUSIPCO 2020

作者： Li, Haipeng Mukundan, Ramakrishnan Dept. of Computer Science and Software Engineering University of Canterbury Christchurch New Zealand

ISBN: (纸本)9789082797053

In this paper, we propose a novel feature extraction method based on local quinary patterns (LQP), multifractal features and intensity histograms for classifying emphysema into three subtypes in computed tomography images. Compared to local binary patterns, LQP method computes more image local patterns to represent texture features. Multifractal features which enhancing local textures are combined with other features to constitute a feature vector for this classification task. An autoencoder network and principal components analysis are used to reduce the dimensionality of the feature vector before using an SVM classifier. The proposed method is tested on an emphysema database containing 168 annotated regions of interest of three different subtypes. The experimental results demonstrate that our method outperforms most other state-of-the-art approaches with the best classification accuracy of 92.3% using the least dimensionality (15) of the feature vector. © 2021 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Enhancing Autism Education: Exploring Interactive Videos and AI Integration for Effective Teaching

Enhancing Autism Education: Exploring Interactive Videos and...

引用

International Conference on Innovations in Information Technology

作者： Fatima Al Raeesi Mariam K. Al Kuwaiti Jose Berengueres Dept. of Software Engineering United Arab Emirates University Al Ain UAE Dept. of Computer Science & Software Engineering United Arab Emirates University Al Ain UAE

This research project proposes the use of interactive videos to enhance teachers' training in educating autistic children. Effective teaching methods for students with autism require teachers to comprehend the condition and employ tailored instructional strategies, including adapting assignments, aiding those with language difficulties, and utilizing visual aids for better organization and focus. Traditional teacher training methods can be both expensive and time-consuming. In contrast, interactive videos provide a proactive and flexible way to access training content, empowering teachers to engage with the material dynamically and take control of their learning experiences. Future work will explore the integration of AI-driven ChatGPT to offer personalized support and create a dynamic training program, with the goal of improving inclusivity and educational quality in autism settings while benefiting teachers, students, and the education system at large.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Composite metamorphic relations for integration testing 22

Composite metamorphic relations for integration testing

引用

8th International Conference on computer Technology Applications, ICCTA 2022

作者： Iakusheva, Sofia Khritankov, Anton Phystech School of Applied Mathematics and Informatics Moscow Institute of Physics and Technology Russia Faculty of Computer Science Dept. of Software Engineering Hse University Russia

ISBN: (纸本)9781450396226

Metamorphic testing is a testing method for problems without test oracles. Integration testing allows for detecting errors in complex systems that may not be found during the testing of their components. In this paper, we propose a novel approach that applies metamorphic testing in integration testing. The main idea is to develop a composite metamorphic relation for the system represented as an acyclic graph. This relation is a logical function of metamorphic relations for the parts of the system (vertices of the graph). It takes into account the features of the parts. Also, it can simplify the search for failure by identifying the subsystem with error. In this paper's theoretical part, we describe an algorithm of relation design. Then, we apply our method to a bioinformatics system for comparative genetic analysis of tissues using production tools. This experiment proves our method can be applied to real-life pipelines and find errors in them. © 2022 ACM.

关键词： Integration testing

来源：评论

学校读者我要写书评

暂无评论

An Effective Detection of Brain Tumor Detection Using ResNet-50 Model

An Effective Detection of Brain Tumor Detection Using ResNet...

引用

Advancement in Renewable Energy and Intelligent Systems (AREIS), International Conference on

作者： V. Raji S. Maheswari S. Sree Dharinya P. Chinniah Kavin K. S. Kiruba Thangam Raja Dept. of Information Technology S.K.P. Engineering College Tiruvannamalai India Dept. of CSE(IoT) Nandha Engineering College Erode Tamilnadu India Dept. of Software and Systems Engineering School of Computer Science Engineering and Information Systems VIT University Vellore India Dept. of ECE ST. Joseph College of Engineering Sriperumbudur Tamilnadu India Dept. of EEE Government College of Engineering Tirunelveli Tamil Nadu India Dept. of Software and Systems Engineering School of Computer Science Engineering and Information Systems(SCORE) VIT University Vellore India

ISBN: (数字)9798350387230

ISBN: (纸本)9798350387247

Rapid proliferation of aberrant neurons in brain tumors significantly damages organ function or causes death, endangering adult health. These tumors vary widely in terms of their locations, sizes, and textures. Finding malignant tumors requires the use of Magnetic Resonance Imaging (MRI). However, physically diagnosing brain tumors is a timeconsuming and potentially unpredictable technique. Cropping and resizing to fixed dimensions ensures consistency before submitting brain MRI images for analysis using deep learning models such as modified ResNet-50. This study uses the modified ResNet-50 model, a deep Convolutional Neural Network (CNN) renowned for its accuracy and resilience in image recognition tasks, to provide an efficient method for brain tumor diagnosis. Initially trained on Image Net, the modified ResNet-50 model further improved using transfer learning on many annotated brain MRI scan datasets. By adding variation to the dataset, data augmentation makes the model more robust and helps it to generalize. Deeper networks are trained without sacrificing performance to the model's architecture, which addresses the vanishing gradient problem. This work classification model implemented using Python software, which facilitated the development, training, and evaluation processes, allowing for an analysis of their performance. The optimized model outperformed conventional Machine Learning (ML) techniques, demonstrating over 94% accuracy in tumor identification and classification tests. With the potential to enhance patient outcomes and diagnostic efficiency, the integration of modified ResNet-50 in brain tumor identification offers a significant development towards accurate and dependable automated diagnostic systems. The accuracy of the modified Resnet-50 is 94%, and the specificity comparison of the modified ResNet-50 is 93.5%, respectively.

关键词： Deep learning Analytical models Accuracy Magnetic resonance imaging Transfer learning computer architecture Brain modeling Data augmentation Data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Multi-DNN Inference

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Mul...

引用

IEEE Symposium on Real-Time and Embedded Technology and Applications

作者： Woosung Kang Jinkyu Lee Youngmoon Lee Sangeun Oh Kilho Lee Hoon Sung Chwa Dept. of Electrical Engineering and Computer Science DGIST Republic of Korea Dept. of Computer Science and Engineering Sungkyunkwan University (SKKU) Republic of Korea Dept. of Robotics Hanyang University Republic of Korea Department of Software & Computer Engineering Ajou University Republic of Korea School of AI Convergence Soongsil University Republic of Korea

ISBN: (数字)9798350358414

ISBN: (纸本)9798350358421

The increasing complexity and memory demands of Deep Neural Networks (DNNs) for real-time systems pose new significant challenges, one of which is the GPU memory capacity bottleneck, where the limited physical memory inside GPUs impedes the deployment of sophisticated DNN models. This paper presents, to the best of our knowledge, the first study of addressing the GPU memory bottleneck issues, while simultaneously ensuring the timely inference of multiple DNN tasks. We propose RT-Swap, a real-time memory management framework, that enables transparent and efficient swap scheduling of memory objects, employing the relatively larger CPU memory to extend the available GPU memory capacity, without compromising timing guarantees. We have implemented RT-Swap on top of representative machine-learning frameworks, demonstrating its effectiveness in making significantly more DNN task sets schedulable at least 72% over existing approaches even when the task sets demand up to 96.2% more memory than the GPU's physical capacity.

关键词： Scheduling algorithms Memory management Graphics processing units Artificial neural networks Machine learning Drives Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Memory Siamese Network for Video Anomaly Detection

SSRN

引用

SSRN 2023年

作者： Roy, Pankaj Raj Bilodeau, Guillaume-Alexandre Seoud, Lama LITIV Dept. Computer and Software Engineering Polytechnique Montréal Canada Institute of Biomedical Engineering Polytechnique Montréal Canada

Existing machine learning-based video anomaly detection methods are computationally expensive and have limited spatio-temporal modeling capabilities, resulting in overfitting the model for a specific video scene. To tackle this problem, we propose an end-to-end bidirectional Siamese generative framework, trained solely with normal videos that can make future and past predictions using the same subnetworks. With appearance features extracted from an encoder, a multilevel transformer-based fusion network produces the forward features for images from past to current frames or the backward features for images from future to current frames. These features are then quantized through their corresponding learnable embeddings using vector quantization. The appearance predictions are then produced from the quantized features for anomaly detection. Moreover, the self-attention in spatial and temporal domains significantly improves the generalization performance, as shown by the superior zero-shot adaptation while outperforming the existing state-of-the-art on the most challenging datasets. © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

The Design of a Lightweight Inductive Power Coupler for eVTOLs

The Design of a Lightweight Inductive Power Coupler for eVTO...

引用

IEEE Annual Southern Power Electronics Conference (SPEC)

作者： Duleepa J Thrimawithana Kai-Yeung Li Jackman Lin Didier Chassaigne Olivier Crepel Madalina Pascaru Antoine Van der Laan Julien Gosteau Grant Covic Dept. of Electrical Computer Software Engineering The University of Auckland New Zealand Airbus Central R&T France

ISBN: (数字)9798350351156

ISBN: (纸本)9798350351163

Inductive power transfer (IPT) technology can play an important role in achieving the sustainability goals of the aviation industry. However, the power-to-weight ratio of the IPT power pick-up system needs to improve significantly to beyond 10 kW/kg to improve feasibility for applications in the aviation sector. This paper presents a new magnetic coupler design that would help achieve this power-to-weight target in an IPT system with small airgaps. The proposed design introduces an air cavity between the coil and the ferrite structure of the magnetic coupler on the eVTOL/aircraft side. The ferrite structure in this design functions somewhat like a magnetic shield, and the air cavity helps reduce the flux density in the ferrite while also making the flux distribution more uniform. A comparison between traditional and proposed designs is provided to show that a 40% weight reduction can be achieved. Experimental data of a 90 kW prototype is presented to show that it can operate at an efficiency of 97.4% when transferring power over a 10 mm coil-coil air-gap.

关键词： Ferrites Wireless communication Magnetic flux Air gaps Prototypes Couplers Magnetic noise Power electronics Sustainable development Magnetic shielding

来源：评论

学校读者我要写书评

暂无评论

Bluetooth Low Energy-based Adaptive Scheme for IoT Services

Bluetooth Low Energy-based Adaptive Scheme for IoT Services

引用

International Conference on Ubiquitous and Future Networks, ICUFN

作者： Gaoyang Shan Geunkyung Choi Byeong-Hee Roh Dept. of Software and Computer Engineering Ajou University Suwon South Korea Dept. of AI Convergence Nework and Dept. of Computer Engineering Ajou University Suwon South Korea

To adapt to various IoT services, Bluetooth Low Energy (BLE) specification has defined a variety of communication modes, such as advertising, extended advertising, and periodic advertising events. As services’ environments, such as the number of users and QoS requirements, are changed, modes of protocols should be also adjusted to meet those services’ needs. This paper proposes an adaptive BLE scheme to reflect dynamically changing services’ environments. The effectiveness of the proposed scheme is verified through simulation experiments.

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：