检索结果-内蒙古大学图书馆

Visualization, informatics and Technology Conference (IVIT), International

作者： Rini Hafzah Abdul Rahim Dinna Nina Mohd Nizam Nur Faraha Mohd Naim Aslina Baharum User Experience Group Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Sabah Malaysia Computing and Information System School of Engineering and Technology Sunway University Selangor Malaysia

ISBN: (数字)9798350354447

ISBN: (纸本)9798350354454

The advent of advanced educational technologies, and immersive learning utilizing virtual reality (VR), augmented reality (AR), and mixed reality (MR) have emerged as a powerful tool to enhance learning experiences. However, traditional approaches often lack the ability to address the unique needs of Deaf and Hard of Hearing (DHH) students, particularly in practical skill development. The usage of immersive learning for the purpose of DHH students is still limited, especially in Malaysia. This study explores critical elements of immersive learning environments designed to facilitate practical skill acquisition for DHH students. Using the systematic literature review (SLR) determines immersive practical skill learning elements from selected 34 papers to help DHH students learn more effectively. 30 constructs are highlighted in the SLR results as recommendations for creating immersive learning for DHH practical skills. It is thus intended that the highlighted features would contribute to both the process of teaching and learning as well as the enhancement of student performance.

关键词： Visualization Prototypes Mixed reality Auditory system Educational technology Object recognition informatics Augmented reality Immersive learning

来源：评论

学校读者我要写书评

暂无评论

Technology Usage For Education: Polytechnic Deaf or Hard-of-Hearing Student

Technology Usage For Education: Polytechnic Deaf or Hard-of-...

引用

IEEE Symposium on Computers & informatics (ISCI)

ISBN: (数字)9798350353853

ISBN: (纸本)9798350353860

This article investigates the application of technology to enhance education for polytechnic deaf or hard-of-hearing (DHH) students. Polytechnic institutions play a crucial role in preparing students for diverse careers through hands-on, practical education. However, DHH students face unique challenges in accessing and fully participating in polytechnic programs. To provide a diverse approach, the technology focusing on visual technology, such as Augmented Reality and Virtual Reality, incorporates crucial components suitable for DHH visual learning modalities. The study uses a mixed-method approach, integrating questionnaires, interviews, and observational data to discover more about DHH lecturers’ and students’ preferred learning methods. 77 DHH Sijil Khas Operasi Katering student from selected three Polytechnic and Community Colleges gave their feedback from questionnaires, and five lecturers were interviewed to get a clearer picture of the current usage of technology among DHH students at polytechnic and community college. Results of the lecturer’s interview suggest that DHH students need visual aids, communication tools, and focus-enhancing resources to help them learn effectively, especially in cooking classes where understanding kitchen equipment and safety is crucial to prevent injuries. Meanwhile, results from DHH students’ questionnaires show students’ interest and prefer to use technology, with 88% agreeing to use technology such as Games, AR, VR and AR Games for their teaching and learning process and to make their learning process more interesting, fun and enjoyable. Integrating the use of technology and information technology as part of the approach of teaching aids to deaf students is hoped to help them to understand better, focus and have more fun in learning.

关键词： Learning systems Visualization Education Focusing Games Safety Interviews

来源：评论

学校读者我要写书评

暂无评论

FlexiFed: Personalized Federated Learning for Edge Clients with Heterogeneous Model Architectures 23

FlexiFed: Personalized Federated Learning for Edge Clients w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wang, Kaibin He, Qiang Chen, Feifei Chen, Chunyang Huang, Faliang Jin, Hai Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia Faculty of Information Technology Monash University Australia Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world's web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed;and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×. © 2023 ACM.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

DECENTRALIZED ATTRIBUTION OF GENERATIVE MODELS 9

DECENTRALIZED ATTRIBUTION OF GENERATIVE MODELS

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Kim, Changhoon Ren, Yi Yang, Yezhou School of Computing Informatics and Decision Systems Engineering Arizona State University United States School for Engineering of Matter Transport and Energy Arizona State University United States

Growing applications of generative models have led to new threats such as malicious personation and digital copyright infringement. One solution to these threats is model attribution, i.e., the identification of user-end models where the contents under question are generated from. Existing studies showed empirical feasibility of attribution through a centralized classifier trained on all user-end models. However, this approach is not scalable in reality as the number of models ever grows. Neither does it provide an attributability guarantee. To this end, this paper studies decentralized attribution, which relies on binary classifiers associated with each user-end model. Each binary classifier is parameterized by a user-specific key and distinguishes its associated model distribution from the authentic data distribution. We develop sufficient conditions of the keys that guarantee an attributability lower bound. Our method is validated on MNIST, CelebA, and FFHQ datasets. We also examine the trade-off between generation quality and robustness of attribution against adversarial post-processes. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Validating trustworthy service composition through VIPLE and pi-calculus

引用

International Journal of Simulation and Process Modelling 2020年第1-2期15卷 76-88页

作者： Zhao, Shenghui Li, Yuemin Wang, Yang Chen, Yinong College of Computer Information and Engineering Chuzhou University Chuzhou Anhui China School of Computing Informatics and Decision System Engineering Arizona State University TempeAZ85287 United States

The current formal verification practice focuses on functionality and does not consider verification of the non-functional attributes. In this study, we propose a method in which non-functional attributes are incorporated into the logic rules of inference in terms of composition of the linear logic and pi-calculus. Giving the credibility to non-functional attributes is important, especially in the cloud computing platform and IoT environments, where trust and security are ultra-important. Such studies have not been paid much attention by researchers and practitioners. In our approach, the evolvement of the non-functional attributes is included in the process of formal verification of the service composition scheme. In addition to theoretical analysis, we applied a tool named Visual IoT/robotics Programming Language Environment (VIPLE) to execute and verify the validity of the service composition model's function. We translate the proving process of the linear logic into the corresponding pi-calculus expressions. VIPLE can translate visual work flow into pi-calculus and can verify the correctness of pi-calculus expressions. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Identification of the K-most Vulnerable Entities in a Smart Grid system 3

Identification of the K-most Vulnerable Entities in a Smart ...

引用

3rd International Conference on Advanced Communication Technologies and Networking, CommNet 2020

作者： Roy, Sohini Sen, Arunabha Arizona State University School of Computing Informatics and Decision System Engineering TempeAZ85281 United States

ISBN: (纸本)9781728187044

A smart grid system can be considered as a multi-layered network with power network in one layer and communication network in the other. The entities in both the layers exhibit complex intra-and-interdependencies between them. A reliable decision making by the smart grid operator is contingent upon correct analysis of such dependencies between its entities and also on accurate identification of the most critical entities in the system. The Modified Implicative Interdependency Model (MIIM) [1] successfully captures such dependencies using multi-valued Boolean Logic based equations called Interdependency Relations (IDRs) after most of the existing models made failed attempts in doing that. In this paper, for any given integer K, this model is used to identify the K-most vulnerable entities in a smart grid, failure of which can maximize the network damage. Owing to the problem being NP complete, an Integer Linear Programming (ILP) based solution is given here. Validation of the model [1] and the results of the ILP based solution is done by simulating a smart grid system of IEEE 14-Bus using MATPOWER and Java Network Simulator (JNS). Simulation results prove that not only the model MIIM [1] is correct but also it can predict the network damage for failure of K-most vulnerable entities more accurately than its predecessor Implicative Interdependency Model (IIM) [2]. © 2020 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

A Restful Persistent Devs-Based Interaction Model for the Componentized Weap and Leap Restful Frameworks

A Restful Persistent Devs-Based Interaction Model for the Co...

引用

2021 Winter Simulation Conference, WSC 2021

作者： Fard, Mostafa D. Sarjoughian, Hessam S. Arizona Center for Integrative Modeling Simulation School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

ISBN: (纸本)9781665433112

Modeling the interactions between separate models contributes to building flexible hybrid simulation frameworks. In earlier work, an Algorithmic Interaction Model was proposed and developed to integrate the componentized WEAP and LEAP RESTful frameworks for modeling and simulating water and energy systems. However, this approach does not separate modeling and simulation protocol from each other. It also does not support flexible, structured model hierarchies. To overcome these limitations, the parallel DEVS formalism is used to develop an Interaction Model for use with the DEVS-Suite simulator. The resulting DEVS Interaction Model (DEVS-IM) is supported with a RESTful framework and MongoDB for storing the interaction models for the coupled water and energy models. The DEVS-IM, grounded in system theory and component-based modeling, offers strong support for the model reusability, flexibility, and maintainability traits essential for developing realistic simulations of coupled energy and water systems. © 2021 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

A Self-Updating K-Contingency List for Smart Grid system

A Self-Updating K-Contingency List for Smart Grid System

引用

IEEE Annual computing and Communication Workshop and Conference (CCWC)

作者： Sohini Roy Arunabha Sen School of Computing Informatics and Decision System Engineering Arizona State University Tempe Arizona USA

ISBN: (数字)9781665414906

ISBN: (纸本)9781665430586

A reliable decision making by the operator in a smart grid is contingent upon correct analysis of intra-and-interdependencies between its entities and also on accurate identification of the most critical entities at a given point of time. A measurement based self-updating contingency list can provide real-time information to the operator about current system condition which can help the operator to take the required action. In this paper, the underlying intra-and-interdependencies between entities for a given power-communication network is captured using a dependency model called Modified Implicative Interdependency Model (MIIM) [1]. Given an integer K, the event-driven self-updating contingency list problem gives the list of K-most critical entities, failure of which maximizes the network damage at the current time. Owing to the problem being NP complete, a fast heuristic method to generate a real-time contingency list using system measurements is provided here. The validation of the work is done by comparing the contingency list obtained for different K values using the MIIM model on a smart grid of IEEE 14-Bus system with that obtained by simulating the smart grid using a co-simulation system formed by MATPOWER and Java Network Simulator (JNS). The results also indicate that the network damage predicted by both the ILP based solution [2] and the proposed heuristic solution using MIIM are more realistic compared to that obtained using another dependency model called Implicative Interdependency Model (IIM) [3].

关键词： Current measurement Conferences Predictive models Real-time systems Smart grids Velocity measurement Time factors

来源：评论

学校读者我要写书评

暂无评论

Mining Road Traffic Accident Data for Prediction of Accident Severity

Mining Road Traffic Accident Data for Prediction of Accident...

引用

2023 International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2023

作者： Bahiru, Tadesse Kebede Manjula, V.S. Akele, Tadesse Birara Tesfaw, Engdaw Ayalew Belay, Tadesse Destaw Kombolcha Institute of Technology Wollo University College of Informatics Dept. of Information Technology Amhara Kombolcha Ethiopia Kombolcha Institute of Technology Wollo University College of Informatics Pg Dept of Computer Science Amhara Kombolcha Ethiopia Kombolcha Institute of Technology Wollo University College of Informatics Dept. of Information System Amhara Kombolcha Ethiopia Wachamo University School of Computing and Informatics College of Engineering and Technology Dept. of Information Technology SSNPR Hosaena Ethiopia

ISBN: (纸本)9781665474511

As World Health Organization reports show more than 1.3 million people die each year from traffic accidents and more than twenty to fifty million people are harmed by non-fatal accidents. Understanding and identifying the major factors of road traffic accidents can help the stakeholders to take appropriate measures to minimize the accidents. Support Vector Machine (SVM), J48, and Naïve Bayes (NB) classification techniques are implemented to build a model that predicts accident severities and to identify road traffic accident factors. As experimental findings showed weather conditions, number of lanes, road lighting conditions, and speed limit are the determinant factors that cause more accident severity. Finally, the classification and prediction performance of the models are compared using various performance evaluation techniques. J48 classifier has better classification performance than Support Vector Machine and Naïve Bayes classifiers. Naïve Bayes is the classifier that showed the lowest performance than others, but it has good performance in classifying fatal accident severities rather than serious and slight accident severities. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

KartalOl: a new deep neural network framework based on transfer learning for iris segmentation and localization task—new dataset for iris segmentation

引用

Iran Journal of Computer Science 2023年第4期6卷 307-319页

作者： Khiarak, Jalil Nourmohammadi Oskouei, Amin Golzari Nasab, Samaneh Salehi Jaryani, Farhang Moafinejad, Seyed Naeim Pourmohamad, Rana Amini, Yasin Noshad, Morteza Institute of Control and Computation Engineering Warsaw University of Technology Ul. Nowowiejska 15/19 Warsaw 00-665 Poland Department of Computer Engineering Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran School of Engineering Lorestan University Aleshtar Campus Aleshtar Iran Faculty of Engineering Arak University Arak Iran Department of Physics Shahid Beheshti University Tehran Iran School of Computing Informatics and Decision Systems Engineering Arizona State University AZ United States Faculty of Electrical and Computer Engineering University of Kharazmi Tehran Iran Stanford University Stanford United States

Iris segmentation and localization in unconstrained environments are challenging due to long distances, illumination variations, limited user cooperation, and moving subjects. Some existing methods in the literature have somehow mitigated some of the above-mentioned issues. In this paper, motivated by these weaknesses, we propose a framework that employs a deep neural network-based approach to iris segmentation and localization. The proposed framework is based on a U-Net architecture initialized with a pre-trained MobileNetV2 model. In addition, to better study the detectors in iris recognition scenarios, we have collected 1000 images. The provided dataset (KartalOl) is made publicly available for the research community. In the proposed framework, to have better generalization, we fine-tuned the MobileNetV2 model on the provided data for NIR-ISL 2021 from the CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa and our dataset. Likewise, data augmentation techniques are applied on images. We chose the binarization threshold for the binary masks by iterating over the images in the provided dataset. The proposed framework is trained and tested in CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa, along with the KartalOl dataset. The experimental results highlight that our method surpasses state-of-the-art methods on mobile-based benchmarks. The implementation source code of KartalOl is made publicly available at https://***/Jalilnkh/KartalOl-NIR-ISL2021031301. © The Author(s) 2023.

关键词： Iris segmentation Localization MobileNetV2 model Unconstrained environment

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：