检索结果-内蒙古大学图书馆

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Mueed, Iqra Arshad, Usama Ali, Raja Hashim Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany

ISBN: (纸本)9798350328172

For newcomers and tourists, navigating university campuses can be difficult, resulting in aggravation and lost time. We respond by introducing 'GikiLenS', an object identification application driven by deep learning that revolutionizes campus exploration by accurately identifying buildings and landmarks while enhancing user experience. GikiLenS is a comprehensive and user-friendly smartphone application that precisely caters to the demands of newcomers and visitors, unlike previous studies in campus navigation. Our study intends to close this gap and develop a reliable method for identifying campus buildings, optimizing navigation, and enhancing user experience. Through rigorous testing, GikiLenS has proven to have remarkable real-time building detection accuracy, highlighting its potential as an important tool for campus exploration. The app's outcomes and conclusions demonstrate how well it works to give users specific building information, promoting a more knowledgeable and enjoyable campus experience. The importance of our findings lies in the development of a unique, user-centered app that offers a cutting-edge method of campus mobility. Our contribution consists of a game-changing method for building detection that improves campus exploration and user pleasure. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Streamlining software Release Process and Resource Management for Microservice-based Architecture on multi-cloud 25

Streamlining Software Release Process and Resource Managemen...

引用

25th International Multi Topic Conference, INMIC 2023

作者： Herath, Isuru Pathum Jayawardena, Samuditha Fadhil, Ahamed Kodagoda, Nuwan Arachchillage, Udara Srimath S.Samaratunge Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science Sri Lanka

ISBN: (纸本)9798350317701

The software development process is more flexible with the concept of containerization in the microservice platform. This research is on three key components to resolve problems faced by the developers and DevOps teams in the IT industry. First, the development phase expects a fully automated software release process from to the deployment phase and then optimize processes tailored to Docker, and Kubernetes, in microservice-based applications. Then streamline the process and leverage the container orchestration technologies to monitor the main aspect of the development lifecycle through the multi-cloud deployment on demand of the growth of day-today releases on multi-regions. A centralized monitoring platform is developed to monitor the deployed applications and that provides comprehensive visibility regarding performance and health of microservices. At the stage of scalarization in microservices, Vertical Pod Autoscaling (VPA) and Horizontal Pod Autoscaling (HPA) are available approaches for resource allocation, and they require measuring the minimum and maximum resource limits. As a result, an intelligent resource allocation system is proposed using a combination of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) algorithms to cater to dynamic resource allocation, optimizing scalability, and improving cost-efficiency. This research aims to achieve practical insights into the IT industry's automated deployment, managing, scaling, and monitoring of microservice-based applications through the mentioned components. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

The research of human interaction recognition based on fusion features of key frame feature library

引用

International Journal of Information and Communication technology 2021年第1期18卷 57-69页

作者： Zhang, Haiyan Gao, Shangbing Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai'an China Nanjing Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing Xiaozhuang University Nanjing China

Some issues such as computational complexity and low recognition accuracy still exist in human interaction recognition. In order to solve the problem, the paper has proposed innovative and effective method based on fixed features of key frame feature library. Firstly, GIST feature and HOG feature were extracted from the pre-processed videos. Secondly, training videos with different kinds of actions were clustered by the K-means algorithm respectively to get key frame feature of each action for constructing key frame feature library. And similarity measure was utilised to calculate the frequency of different key frames in every interactive video, and statistical histogram representation of interactive videos were obtained. Finally, the decision level fusion was achieved by using SVM classifier based on histogram intersection kernel to obtain impressive results on UT-interaction dataset. The correct recognition rate of the proposed algorithm is 85%, which indicates that the proposed algorithm is simple and effective than others. © 2021 Inderscience Enterprises Ltd.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Practical Secure Heterogeneous Communication for Internet of Things

SSRN

引用

SSRN 2022年

作者： Jin, Chunhua Zhu, Huihui Qin, Wenyu Chen, Zhiwei Jin, Ying Shan, Jinsong Faculty of Computer & Software Engineering Huaiyin Institute of Technology Huai’an233003 China

Internet of things (IoT) is a promising network that combines various information sensing devices with the Internet to realize the interconnection of pervasive things. Security is a pivotal issue to ensure widespread adoption of the IoT. To ensure the security of data transmission, in this paper, we construct a heterogeneous online and offline signcryption from a wireless sensor network (WSN) to an Internet server. In our construction, the WSN is in certificateless cryptosystem (CLC) which does not involve public key certificate management problem in public key infrastructure (PKI) and key escrow problem in identity based cryptosystem (IBC), while the server is in IBC which avoids public key certificate management problem. For signcryption process, the proposed scheme is split into two steps: offline step and online step. In the former step, the time-consuming calculations are completed, but do not involve the transmitted message. In the latter step, only some lightweight calculations are involved, but message must be available. Confidentiality, authentication, non-repudiation, and integrity can be achieved in a logical single step. In addition, an elaborate performance analysis demonstrates that our proposed scheme has advantages in terms of computational cost and private key size, offline storage, as well as communication overhead. © 2022, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Enhancing students' learning achievements, self-efficacy, and motivation using mobile augmented reality

引用

Journal of computer Assisted Learning 2024年第4期40卷 1823-1837页

作者： Aldeeb, Fatimah H. Sallabi, Omar M. Elaish, Monther M. Hwang, Gwo-Jen Computer Network College of Computer Technology Benghazi Libya Computer Science The Libyan Academy Benghazi Libya Software Engineering Information Technology Faculty University of Benghazi Benghazi Libya Computer Science Information Technology Faculty University of Benghazi Benghazi Libya Graduate Institute of Educational Information and Measurement National Taichung University of Education Taichung City Taiwan Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology Taipei City Taiwan Yuan Ze University Taoyuan City Taiwan

Background: This paper examines the use of augmented reality (AR) as a concept-association tool in schools, with the aim of enhancing primary school students' learning outcomes and engagement. Conflicting findings exist in previous studies regarding the cognitive load of AR-enriched learning, with some reporting reduced load and others indicating increased demand and poorer performance. Understanding these implications is essential for effectively leveraging AR in education. The study offers a fresh perspective on the potential of AR technology in improving educational experiences. Objectives: The primary goal of this research was to evaluate the effectiveness of an AR-assisted concept-association strategy for improving essential knowledge acquisition and skills outcomes, increasing cognitive load, and increasing self-efficacy and learning motivation among primary school students. Methods: A quasi-experimental design with a control group was employed to investigate the effectiveness of the intervention. Results and Conclusions: The results demonstrate that the implementation of the AR-assisted concept-association strategy effectively enhanced essential knowledge acquisition and skills outcomes, increased cognitive load, and increased self-efficacy and learning motivation among primary school students. These findings highlight the potential of AR technology to improve the learning experience and engagement of primary school students. The study contributes to the existing literature on the effectiveness of AR technology in education, suggesting future research directions. Ultimately, it offers a practical solution for improving the learning experience by presenting a new approach for teaching using AR technology. © 2024 John Wiley & Sons Ltd.

关键词： augmented reality biology education cognitive load learning motivation mobile learning self-efficacy

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Matching for Noisy and Distorted Patterns Using a Siamese Network With ResNet50 and Multihead Attention

引用

IEEE Access 2025年 13卷 88047-88064页

作者： Sawhney, Tinny Sharma, Ashu Abrol, Pawanesh Kumar Lehana, Parveen Chaahat Yadav, Vaishali Scherer, Rafal Kulakov, Oleksii Ali Alzubi, Ahmad University of Jammu DSP Laboratory Department of Electronics Jammu180006 India University of Jammu Department of Computer Science and IT Jammu180006 India Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science and Engineering Punjab Rajpura140401 India Manipal University Jaipur Department of Computer Science & Communication Engineering Jaipur303007 India Czestochowa University of Technology Department of Artificial Intelligence Częstochowa42-200 Poland Faculty of Informatics and Software Engineering National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" Kyiv03056 Ukraine King Saud University Community College Department of Computer Science Riyadh11451 Saudi Arabia

Dermatoglyphics, the study of unique ridge patterns on fingertips, plays a crucial role in fingerprint-based identification. However, skin conditions such as psoriasis, eczema, and verruca vulgaris can distort these patterns. This distortion creates challenges for fingerprint matching systems in forensic science and biometric authentication. This paper proposes a Siamese network with a modified ResNet50 architecture and multihead attention mechanisms to improve fingerprint matching under such distortions. The Siamese network enables the system to compare fingerprint pairs effectively, even under distortions. The modified ResNet50 architecture captures intricate ridge patterns, while the multihead attention mechanisms focus on critical fingerprint regions. Overall, the proposed approach enhances the system’s ability to learn discriminative features. As a result, it can effectively differentiate between matched and unmatched fingerprint pairs, even in the presence of moderate to extreme noise. The proposed system was trained on the Sokoto coventry fingerprint dataset (SOCOFing) and a custom dataset. Experimental results demonstrate high accuracy, with the system achieving 99.47% accuracy under low noise conditions and 90% under moderate noise. However, performance declined to 55.56% under extreme distortions. A comparative analysis highlighted the superiority of the proposed system over widely used minutiae-based methods. The latter exhibited a significant drop in matching scores, falling below 15% for highly distorted fingerprints. These findings underscore the limitations of traditional fingerprint recognition techniques and highlight the effectiveness of proposed approach in handling dermatoglyphic distortions. © 2013 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

PolyLite: A Lightweight Transformer With Multi-Scale Attention for Colorectal Polyp Segmentation 15

PolyLite: A Lightweight Transformer With Multi-Scale Attenti...

引用

15th International Conference on software, Knowledge, Information Management and Applications, SKIMA 2023

作者： Elkarazle, Khaled Raman, Valliappan Chua, Caslon Then, Patrick Faculty of Engineering Sarawak Malaysia Coimbatore Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu India University of Technology Department of Computer Science and Software Engineering Swinburne Melbourne Australia

ISBN: (纸本)9798350316551

The urgent need for early detection and intervention in colorectal cancer highlights the importance of automating colorectal polyp detection. Despite the use of deep learning techniques for polyp detection from medical images, these methods often struggle with issues such as skewed data distribution and class imbalances. In this study, we introduce PolyLite, a lightweight transformer-based model designed to balance performance and efficiency. PolyLite features a custom SegFormer encoder that takes advantage of its lightweight design, and a decoder that uses a multi-scale attention network (MA-NET) to achieve an optimal balance between accuracy and efficiency. To improve accuracy and reduce false negatives, we incorporate a reverse attention layer that effectively counteracts input mask attention during training. This refocuses the model's efforts to better learn non-polyp regions. PolyLite undergoes a two-stage training process, beginning with pre-training on the ImageNet dataset and then fine-tuning on the Kvasir-SEG dataset. We conduct rigorous evaluations on three complex datasets: CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB. Empirical results demonstrate PolyLite's superiority over existing techniques, as evidenced by its performance in terms of Intersection over Union and Dice scores. This validates its effectiveness and scalability in polyp segmentation, making complex and computationally intensive architectures unnecessary. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with a Novel Concoction Loss Function for Identification of Ophthalmic Disease

引用

computers, Materials & Continua 2023年第9期76卷 3763-3781页

作者： Sayyid Kamran Hussain Ali Haider Khan Malek Alrashidi Sajid Iqbal Qazi Mudassar Ilyas Kamran Shah Department of Computer Science TIMES InstituteMultan60000Pakistan Department of Software Engineering Faculty of Computer ScienceLahore Garrison UniversityLahore54000Pakistan Department of Computer Science Applied CollegeUniversity of TabukTabukSaudi Arabia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl Hofuf31982Saudi Arabia Department of Mechanical Engineering College of EngineeringKing Faisal UniversityAl HofufSaudi Arabia

As ocular computer-aided diagnostic(CAD)tools become more widely accessible,many researchers are developing deep learning(DL)methods to aid in ocular disease(OHD)*** eye diseases like cataracts(CATR),glaucoma(GLU),and age-related macular degeneration(AMD)are the focus of this study,which uses DL to examine their *** imbalance and outliers are widespread in fundus images,which can make it difficult to apply manyDL algorithms to accomplish this analytical *** creation of efficient and reliable DL algorithms is seen to be the key to further enhancing detection *** the analysis of images of the color of the retinal fundus,this study offers a DL model that is combined with a one-of-a-kind concoction loss function(CLF)for the automated identification of *** study presents a combination of focal loss(FL)and correntropy-induced loss functions(CILF)in the proposed DL model to improve the recognition performance of classifiers for biomedical *** is done because of the good generalization and robustness of these two types of losses in addressing complex datasets with class imbalance and *** classification performance of the DL model with our proposed loss function is compared to that of the baseline models using accuracy(ACU),recall(REC),specificity(SPF),Kappa,and area under the receiver operating characteristic curve(AUC)as the evaluation *** testing shows that the method is reliable and efficient.

关键词： Deep learning multi-classification focal loss CNN eye disease

来源：评论

学校读者我要写书评

暂无评论

A Fault Forecasting Approach Using Two-Dimensional Optimization 10

A Fault Forecasting Approach Using Two-Dimensional Optimizat...

引用

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Tajgardan, Mohsen Khoshkangini, Reza Orand, Abbas Rabbani, Mahdi Qom University of Technology Faculty of Electrical and Computer Engineering Qom Iran Department of Computer Science and Media Technology Malmo Sweden Arriver Software AB Qualcomm Company Linköping Sweden Canadian Institute for Cybersecurity University of New Brunswick NB Canada

ISBN: (纸本)9798350373011

Data preparation is crucial in every machine learning approach, particularly when applied to detecting claims in the automotive industry. The challenge of managing highdimensional feature spaces and imbalanced data becomes even more pronounced with the proliferation of IoT devices, which generate vast amounts of data over time. Machine learning models trained on such imbalanced datasets often yield unreliable and inaccurate predictions. Thus, addressing these issues during the data pre-processing phase is critical. In this paper, we introduce a novel two-dimensional optimization (TDO) strategy to tackle the problem of imbalanced data in fault detection, specifically in the context of IoT-enhanced automotive systems. We leverage a heuristic optimization technique known as the Genetic Algorithm to simultaneously reduce both the number of data point tuples and the feature space. Additionally, we evaluate the effectiveness of two-dimensional reduction using Particle Swarm Optimization (PSO) and Whale Optimization algorithms. Our empirical results, derived from data collected from thousands of IoT-equipped vehicles, demonstrate the promise of our proposed methods. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Collaborative learning-based inter-dependent task dispatching and co-location in an integrated edge computing system

引用

Digital Communications and Networks 2024年第6期10卷 1837-1850页

作者： Uchechukwu Awada Jiankang Zhang Sheng Chen Shuangzhi Li Shouyi Yang School of Software Henan Institute of Science and TechnologyXinxiang 453003China School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou 450001China Department of Computing and Informatics Bournemouth UniversityPoole BH125BBUK School of Electronics and Computer Science University of SouthamptonSouthampton SO171BJUK Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266100China

Recently,several edge deployment types,such as on-premise edge clusters,Unmanned Aerial Vehicles(UAV)-attached edge devices,telecommunication base stations installed with edge clusters,etc.,are being deployed to enable faster response time for latency-sensitive *** fundamental problem is where and how to offload and schedule multi-dependent tasks so as to minimize their collective execution time and to achieve high resource *** approaches randomly dispatch tasks naively to available edge nodes without considering the resource demands of tasks,inter-dependencies of tasks and edge resource *** approaches can result in the longer waiting time for tasks due to insufficient resource availability or dependency support,as well as provider ***,we present Edge Colla,which is based on the integration of edge resources running across multi-edge *** Colla leverages learning techniques to intelligently dispatch multidependent tasks,and a variant bin-packing optimization method to co-locate these tasks firmly on available nodes to optimally utilize *** experiments on real-world datasets from Alibaba on task dependencies show that our approach can achieve optimal performance than the baseline schemes.

关键词： Edge computing Collaborative learning Resource utilization Execution time Edge federation Gang scheduling

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：