检索结果-内蒙古大学图书馆

7th International Conference on Signal Processing and Intelligent Systems, ICSPIS 2021

作者： Shahbakhsh, Mostafa Balouchzehi Hassanpour, Hamid Shahrood University of Technology Faculty of Computer Engineering IT Shahrood Iran

ISBN: (纸本)9781665409384

Face super-resolution, known as face hallucination, is a domain-specific image super-resolution problem, which refers to generating high resolution face images from their low resolution. State-of-The-Art face super-resolution methods used deep convolutional neural networks. However, due to significant pose changes and difficulty in recovering high-frequency details in facial areas, most of these methods do not deploy facial structures and identity information well, and it is tough for them to reconstruct super-resolved face images. According to previous researches, proper use of low-resolution image edges can be a solution for these problems. EIPNet (Edge and Identity Preserving Network) is one of the newest methods to achieve outstanding results in this area. In the EIPNet method, the authors used a lightweight edge extraction block in the proposed GAN structure. In this research, we intend to improve the performance of the EIPNet method by presenting a simple but efficient technique. Our proposed technique divides the face images into upper and lower parts. We train a separate network for each area. This technique reduces the number of face components to train from each area, and the networks can better be trained from their components. The results show that this technique can have an excellent effect on visual quality and quantitative measurements in face super-resolution. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Application of VR technology in the process of training engineers 36

Application of VR technology in the process of training engi...

引用

36th Information Systems Education Conference, ISECON 2023

作者： Salach, Mateusz Dzierwa, Andrzej Belzo, Artur Bolanowski, Marek Paszkiewicz, Andrzej Department of Complex Systems The Faculty of Electrical and Computer Engineering Rzeszow University of Technology Al. Powstańców Warszawy 12 Rzeszów35-959 Poland Department of Manufacturing Processes and Production Engineering The Faculty of Mechanical Engineering and Aeronautics Rzeszow University of Technology Al. Powstańców Warszawy 12 Rzeszów35-959 Poland

The paper presents a didactic application created in virtual reality to visualize a processes of milling and turning inside CNC machines with pre-modeled raw materials. The paper focuses on preparing and working with 3D models and configuring the VR app. The virtual reality application and classes are part of the idea of Education 4.0 – the new and future method of learning in schools. As a result of the work carried out, the possibilities of using VR tools in the process of training engineers were identified, as well as the areas that should be taken into account in the preparation of this class of solutions. The developed solution was tested in a group of students in order to assess the usefulness of the proposed solution and determine the directions for further work. © 2023 Proceedings of the Information Systems Education Conference, ISECON. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Brand Visibility in Packaging: A Deep Learning Approach for Logo Detection, Saliency-Map Prediction, and Logo Placement Analysis

arXiv

引用

arXiv 2024年

作者： Hosseini, Alireza Hooshanfar, Kiana Omrani, Pouria Toosi, Reza Toosi, Ramin Ebrahimian, Zahra Akhaee, Mohammad Ali School of Electrical and Computer Engineering University of Tehran College of Engineering Tehran Iran Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran Department of Computer Engineering Faculty of Engineering Golestan University Gorgan Iran

In the highly competitive area of product marketing, the visibility of brand logos on packaging plays a crucial role in shaping consumer perception, directly influencing the success of the product. This paper introduces a comprehensive framework to measure the brand logo’s attention on a packaging design. The proposed method consists of three steps. The first step leverages YOLOv8 for precise logo detection across prominent datasets, FoodLogoDet-1500 and LogoDet-3K. The second step involves modeling the user’s visual attention with a novel saliency prediction model tailored for the packaging context. The proposed saliency model combines the visual elements with text maps employing a transformers-based architecture to predict user attention maps. In the third step, by integrating logo detection with a saliency map generation, the framework provides a comprehensive brand attention score. The effectiveness of the proposed method is assessed module by module, ensuring a thorough evaluation of each component. Comparing logo detection and saliency map prediction with state-of-the-art models shows the superiority of the proposed methods. To investigate the robustness of the proposed brand attention score, we collected a unique dataset to examine previous psychophysical hypotheses related to brand visibility. the results show that the brand attention score is in line with all previous studies. Also, we introduced seven new hypotheses to check the impact of position, orientation, presence of person, and other visual elements on brand attention. This research marks a significant stride in the intersection of cognitive psychology, computer vision, and marketing, paving the way for advanced, consumer-centric packaging designs.∗ © 2024, CC BY-NC-SA.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on long and short-term social recommendation based on convolutional and gated recurrent units 29

Research on long and short-term social recommendation based ...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Jia, Zihe Xue, Peng Dai, Zhiqiang Gao, Qian Zhang, Xiaomeng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China

ISBN: (纸本)9798350330717

The development of the Internet has made people more closely related and has put forward higher requirements for recommendation models. Most recommendation models are studied only for the long-term interests of users. In this paper, the interaction time between the user and the item is introduced as auxiliary information in the model construction. Interaction time is used to determine users' long-term preferences and short-term preferences. In this paper, temporal features are extracted by building a convolutional gated recurrent unit with attention neural network (CNN-GRU-Attention). Firstly, for the problem of accurate feature extraction, CNN are constructed to extract higher-level and more abstract features of themselves and transform high-dimensional data into low-dimensional data;secondly, for the problem of social temporality, GRU are used to not only extract temporal information, but also effectively reduce gradient dispersion, making model convergence and training easier;finally, Graph Attention networks are used to aggregate the social relationship information of users and items respectively, which constitute the final feature representation of users and items respectively. In particular, a modified cosine similarity is used to reduce the error caused by data insensitivity when constructing the social information of the item. In this study, simulation experiments are conducted on two publicly available datasets (Epinions and Ciao), and the experimental results show that the proposed recommended model performs better than other social recommendation models, improving the evaluation metrics of MAE and RMSE by 1.06%-1.33% and 1.19%-1.37%, respectively. The effectiveness of the model innovation is proved. © 2023 IEEE.

关键词： convolutional gated recurrent unit graph attention networks neighborhood recommendation systems social networks

来源：评论

学校读者我要写书评

暂无评论

Power Allocation Strategy for Secret Key Generation Method in Wireless Communications

引用

computers, Materials & Continua 2021年第8期68卷 2179-2188页

作者： Bin Zhang Muhammad Waqas Shanshan Tu Syed Mudassir Hussain Sadaqat Ur Rehman School of Electronics and Information Engineering Hunan University of Science and EngineeringYongzhou425199China Engineering Research Center of Intelligent Perception and Autonomous Control Faculty of Information TechnologyBeijing University of TechnologyBeijing100124China Faculty of Computer Science and Engineering Ghulam Ishaq Khan(GIK)Institute of Engineering Sciences and TechnologyTopi23460Pakistan Department of Electronics Engineering FICTBalochistan University of Information TechnologyEngineering and Management SciencesQuetta87300Pakistan Department of Computer Science Namal InstituteMianwali42200Pakistan

Secret key generation(SKG)is an emerging technology to secure wireless communication from ***,the SKG at the physical layer is an alternate solution over traditional cryptographic methods due to wireless channels’***,the physical layer secret key generation(PHY-SKG)depends on two fundamental parameters,i.e.,coherence time and power *** coherence time for PHY-SKG is not applicable to secure wireless *** is because coherence time is for a certain period of ***,legitimate users generate the secret keys(SKs)with a shorter key length in ***,an attacker can quickly get information about the ***,the attacker can easily get valuable information from authentic ***,we considered the scheme of power allocation to enhance the secret key generation rate(SKGR)between legitimate ***,we propose an alternative method,i.e.,a power allocation,to improve the *** results show 72%higher SKGR in bits/sec by increasing power *** addition,the power transmission is based on two important parameters,i.e.,epsilon and power loss factor,as given in power transmission *** found out that a higher value of epsilon impacts power transmission and subsequently impacts the *** SKGR is approximately 40.7%greater at 250 from 50 mW at epsilon=*** value of SKGR is reduced to 18.5%at 250 mW when epsilonis ***,the transmission power is also measured against the different power loss factor values,i.e.,3.5,3,and 2.5,respectively,at epsilon=***,it is concluded that the value of epsilon and power loss factor impacts power transmission and,consequently,impacts the SKGR.

关键词： Secret key generation rate power allocation physical layer wireless communication

来源：评论

学校读者我要写书评

暂无评论

Exploiting Deep Learning Architectures for Effective Real-Time Data Analysis in Machine Learning 3

Exploiting Deep Learning Architectures for Effective Real-Ti...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Shreenidhi, H.S. Rajarajeswari, S. Bhagwat, Suvarna R. Sharma, Khushboo Seth, Kanika Yadav, Rakesh Kumar Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

This paper seeks to discover how deep state-of-the-art architectures can be leveraged for robust actual-time information evaluation in device studying packages. The paper begins by supplying a comprehensive assessment of contemporary the modern-day in deep brand new-based totally facts evaluation technology. It then examines case research state-of-the-art real-time records analysis programs to illustrate the viability and blessings of modern-day existing deep latest architectures. Programs encompass self-driving vehicle generation, laptop vision, natural language processing, and time-collection evaluation. This targeted evaluation is supplemented by assessing ultra-modern capability shortcomings and demanding situations associated with using these architectures in actual-time scenarios. Subsequently, the paper provides a set of modern-day pointers and first-rate practices to help practitioners efficiently leverage deep trendy architectures for actual-time information evaluation. With the aid of combining a comprehensive review of current deep-gaining knowledge state modern-based records evaluation technology, a detailed dialogue present day its utility guiding ideas, and a summary of the latest potential shortcomings and demanding situations, this paper offers a practical manual to the effective of deep learning architectures for real-time data analysis. © 2023 IEEE.

关键词： architectures challenges combining recommendations shortcomings

来源：评论

学校读者我要写书评

暂无评论

Boosting Cybersecurity Effectiveness through Machine Learning for Proactive Detection and Mitigation of New Threats 2

Boosting Cybersecurity Effectiveness through Machine Learnin...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Duraimutharasan, N. Rao, N. Venkatesvara Poongavanam, N. Kanimozhi, K.V. Manikandan, S.P. Faculty of Advanced Computing Sciences AMET UNIVERSITY Tamil Nadu Chennai India Department of Computer Science and Engineering J.N.N.INSTITUTE OF ENGINEERING Ushaa GardenKannigaipair Periyapalayam Highway Chennai India Saveetha University Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India School of Engineering and Technology CMR UNIVERSITY Karnataka Bengaluru India

ISBN: (纸本)9798350383867

Cybersecurity still remains an all-time issue before the technological age as the enterprises continue to deal with the evolving nature of the threats arising every day. Traditional cybersecurity approaches are becoming deficient in the situation of constantly improving, swiftly mutating threats, which leads to the revision and refocus of the current approaches to the preventative reactivity type. For that, machine learning (ML) has come into the arena as a strong tool for improving cybersecurity capacity through the ¨p roactivë recognition and the ¨mitigatioñ̈ of unknown threats. The focus of this paper is the function of ML in cyber security. Here is considered anomaly detection, malware classification, threat intelligence analysis, and security form adversarial attacks. We conduct literature search, detail a novel research methodology embracing data acquisition, preprocessing, ML model training, and deployment. We present experiments versus conventional security approaches from different ML domains used confirming the superiority in cybersecurity of the presented models. Moreover, resistance to chicanery such as adversarial attacks and the models understandability are discussed. Next, research vector and innovation directions in the ML cybersecurity are highlighted. As a whole, this study provides the example of how ML can strengthen previous alliance strategies to cybersecurity and prevent the risks associated with interchanging cyber threats. ©2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Performance of SBC Clusters for HPC Workloads 5

Evaluating Performance of SBC Clusters for HPC Workloads

引用

5th IEEE International Conference on Smart Systems and Technologies, SST 2022

作者： Krpić, Zdravko Loina, Luka Galba, Tomislav Faculty of Electrical Engineering Computer Science and Information Technology J. J. Strossmayer University Of Osijek Osijek Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

Clusters of modern Single Board computers (SBCs) pack significant computing power thanks to the new generation of low-power CPUs. So far, such clusters have mainly been used for educational and hobbyist projects but since their computing power grew, they are increasingly recognized as a disruptive technology, especially in fog and edge computing. This is also due to their low cost and low power consumption, as well as their expendability. In this paper we will investigate how do such clusters cope with compute-bound applications. To do so we will use High Performance Linpack (HPL) benchmark, a well-established tool for evaluating performance of High Performance Computing systems, to compare processing power of two 4-node clusters using different generations of SBCs: Odroid U3 and Odroid MC1. The results show that clusters of SBCs are indeed small-scale HPCs capable of running moderate computing workloads that could be generated at the computing edge. © 2022 IEEE.

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

Comparing Ensemble Learning Techniques on Data Transmission Reduction for IoT Systems 1st

Comparing Ensemble Learning Techniques on Data Transmission...

引用

1st International Conference on Advances in Computing Research, ACR’23

作者： Salah, Ahmad Bekhit, Mahmoud Alkalbani, Asma M. Mohamed, Mohamed A. Lestari, Nur I. Fathalla, Ahmed Computer Science Department Faculty of Computers and Informatics Zagazig University Zagazig Sharkia Egypt Information Technology Department College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Ad Dhahirah516 Oman Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW Australia Kent Institute Australia SydneyNSW Australia 2P Perfect Presentation Riyadh Riyadh Saudi Arabia Computer Science Department Faculty of Computers and Informatics Suez Canal University Ismailia Egypt

ISBN: (纸本)9783031337420

The Internet of Things (IoT) systems include a massive number of connected devices. The communication between these devices requires a huge amount of communication. Thus, it is very crucial for an IoT system to reduce communication volumes by minimizing the amount of data transmission. There are several approaches to achieving the goal of data transmission reduction, such as data compression and dual prediction. Dual prediction schemes received more attention in comparison to data compression. The mainstream techniques for proposing dual prediction schemes in the literature can be classified into two main groups, namely, filter-based and deep learning-based methods. The filter-based methods, such as the 1-D Kalman filter, are lightweight in terms of running time and the model’s memory requirements. On the other hand, deep learning-based methods require more memory space and training time, but deep learning models are more accurate as predictive models in comparison to filter-based methods in dual prediction schemes. There are very limited efforts to utilize machine learning methods in dual prediction schemes as a compromise between the aforementioned mainstream techniques. In this work, we extended one of these limited efforts, which utilizes boosting ensemble learning as a machine learning predictive method in a proposed dual prediction scheme. The current work proposes exploring the performance gap between the three main approaches to ensemble learning, namely, boosting, stacking, and bagging. The three proposed ensemble learning models are evaluated on a real dataset and compared against state-of-the-art methods. The obtained results show that among the ensemble learning models, boosting and bagging models are better than the stacking model, but the three proposed ensemble learning models outperformed the state-of-the-art methods of comparison. For instance, the average numbers of mispredictions for all of the experiments were 580, 551, and 1,106 for boosting, ba

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Utilization Using Vector Databases in Green Internet of Things

Optimizing Resource Utilization Using Vector Databases in Gr...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Kumari, Rani Sah, Dinesh Kumar Cengiz, Korhan Nauman, Ali Ivković, Nikola Mihaljević, Ivan Birla Institutue of Technology Department of Computer Science and Engineering Ranchi India Siksha 'o' Anusandhan Department of Computer Science and Engineering Bhubaneswar India Istinye University Department of Computer Engineering Istanbul Turkey University of Hradec Kralove Faculty of Informatics and Management Department of Information Technologies Kralove50003 Czech Republic Yeungnam University Department of Information and Communication Engineering 280 Daehak-Ro Gyeongsan Gyeongbuk38541 Korea Republic of University of Zagreb Faculty of Organization and Informatics Pavlinska 2 Varaždin42000 Croatia

ISBN: (纸本)9798350370218

With the rapid proliferation of Internet of Things (IoT) devices and the ever-increasing volume of sensor data, optimizing resource utilization has become crucial for building sustainable and efficient IoT systems. In this study, we propose a novel approach for optimizing resource utilization in Green IoT through efficient storage and retrieval in vector databases. Our approach leverages specialized data structures, including k-d trees and ball trees, to achieve improved storage efficiency and accelerated retrieval performance for high-dimensional sensor data. We conducted extensive experiments to evaluate the effectiveness of our proposal, comparing it with traditional database approaches. The results demonstrate significant improvements in storage efficiency, with vector databases requiring considerably less storage space compared to traditional databases. Moreover, our approach enables fast and accurate retrieval of high-dimensional sensor data, reducing query times and enhancing real-time data analysis and decision-making capabilities. The technical achievements of our proposal offer promising prospects for the development of sustainable and efficient IoT systems in various domains, such as environmental monitoring, healthcare, and smart cities. Our work contributes to advancing the field of Green IoT by addressing the challenges of resource utilization and query performance through efficient storage and retrieval in vector databases. © 2023 IEEE.

关键词： Green IoT Indexing Techniques Resource Utilization Specialized Data Structures Vector Databases

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：