检索结果-内蒙古大学图书馆

Wireless modulation classification based on Radon transform and convolutional neural networks

Journal of Ambient Intelligence and Humanized Computing 2023年第5期14卷 6263-6272页

作者： Ghanem, Hanan S. Al-Makhlasawy, Rasha M. El-Shafai, Walid Elsabrouty, Maha Hamed, Hesham F. A. Salama, Gerges M. El-Samie, Fathi E. Abd Department of Electrical Engineering Faculty of Engineering Minia University Minia61111 Egypt Department of Computers and Systems Electronics Research Institute Cairo Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Electronics and Communications Engineering Egypt-Japan University of Science and Technology Alexandria Egypt Faculty of Engineering Egyptian-Russian University Cairo Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Convolutional Neural Networks (CNNs) are efficient tools for pattern recognition applications. They have found applications in wireless communication systems such as modulation classification from constellation diagrams. Unfortunately, noisy channels may render the constellation points deformed and scattered, which makes the classification a difficult task. This paper presents an efficient modulation classification algorithm based on CNNs. Constellation diagrams are generated for each modulation type and used for training and testing of the CNNs. The proposed work depends on the application of Radon Transform (RT) to generate more representative patterns for the constellation diagrams to be used for training and testing. The RT has a good ability to represent discrete points in the spatial domain as curved lines. Several pre-trained networks including AlexNet, VGG-16, and VGG-19 are used as classifiers for modulation type from the spatial-domain constellation diagrams or their RTs. Several simulation experiments are presented in this paper to compare different scenarios for modulation classification at different Signal-to-Noise Ratios (SNRs) and fading channel conditions. © 2022, The Author(s).

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

EfficientViT: An Efficient Vision Transformer for Fire and Smoke Image Classification 1

引用

4th International Conference on Smart Systems: Innovations in Computing, SSIC 2023

作者： Gourisaria, Mahendra Kumar Patel, Ayush V. Chatterjee, Rajdeep Singh, Vijander School of Computer Engineering KIIT Deemed to Be University Odisha Bhubaneswar751024 India Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur302034 India Department of ICT and Natural Science Faculty of Information Technology and Electrical Engineering NTNU—Norwegian University of Science and Technology Aalesund Norway

ISBN: (数字)9789819736904

ISBN: (纸本)9789819736898

Given the variety of fire and smoke, which are distinguished by variances in texture and color, it is extremely difficult to detect fire and smoke from visual imagery. A significant amount of economic and environmental harm has resulted from fire and smoke incidents around the world. In order to prevent property damage and save lives, fires must be detected as soon as possible, for example, forest fires, which frequently occur in the summer yet are easily avoidable. Using cutting-edge deep learning models including Convolutional Neural Network (CNN), VGG16, Vision Transformer (ViT), and MobileViT, we offer a thorough method for classifying fire and smoke in this study. We also provide an innovative model dubbed EfficientViT, which combines the advantages of the MobileViT and Inverted Residual layers. The correct classification of visual images into the categories of fire and smoke is our main goal. We show that EfficientViT beats the other developed models, obtaining an amazing accuracy of 0.92, through a thorough experimentation and evaluation. This demonstrates how well our suggested model works at correctly differentiating between incidents of fire and smoke. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of an Artificial Intelligence of Things-Based Autonomous Mobile Robot System for Cleaning Garbage

Design and Implementation of an Artificial Intelligence of T...

引用

作者： Chen, Liang-Bi Huang, Xiang-Rui Chen, Wei-Han Pai, Wen-Yu Huang, Guan-Zhi Wang, Wei-Chien National Penghu University of Science and Technology Department of Computer Science and Information Engineering Magong Penghu880011 Taiwan The University of Sydney Faculty of Engineering and Information Technologies SydneyNSW2006 Australia

This article proposes an autonomous mobile robot (AMR) system based on the artificial intelligence of things (AIoT) for collecting garbage. The proposed system consists of an AMR subsystem, a robot operating system (ROS) robot subsystem, an artificial intelligence (AI) garbage recognition subsystem, a solar power supply subsystem, and a smart trash can subsystem. The AMR subsystem uses a motor drive, which is built on an aluminum alloy metal base and is connected to an AI edge computing module via an app, to control the robot. The ROS subsystem is built on an edge computing module, which is coupled with the motor drive module to control the robot arm and the robot gripper and is connected to the AI edge computing module to control the robot arm through the app. The AI garbage recognition subsystem recognizes the types of waste in real time through an image sensor (camera). This subsystem adopts multiple sensors that can monitor the level of waste in the trash can. Moreover, a map on a web platform locates all trash cans. Servomotors enable automatic opening and closing of the lid to prevent the unpleasant smell of garbage from wafting. A user connects to the AI edge computing module through an app to monitor the robot and control the movement of the robot to any location on the map. © 2001-2012 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Improving text detection by generating images with curved text instances

Improving text detection by generating images with curved te...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Landeka, Leon Grbic, Ratko Brisinello, Matteo Herceg, Marijan TTTech Auto Central and Eastern Europe Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

ISBN: (纸本)9798350347722

Modern text detection algorithms rely on deep neural networks, which are trained on labeled datasets to achieve high performance. Despite the increasing popularity of text detection, accurate detection of text in natural images remains a challenging problem due to variations in text size, shape, color, and font. In particular, curved text instances present a unique challenge for detection algorithms, yet they are seldom found in existing text detection datasets. In this paper, we present an approach to improve curved text detection performance by generating synthetic images with curved text instances and polygon bounding regions as annotations. We train a deep neural network-based text detector on these synthetic images and evaluate its performance on test sets. Our findings highlight the importance of utilizing diverse and realistic datasets for training robust text detection systems. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Tool for automatic labeling of objects in images obtained from Carla autonomous driving simulator

Tool for automatic labeling of objects in images obtained fr...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Bencevic, Zvonimir Grbic, Ratko Jelic, Borna Vranjes, Mario TTTech Auto Central and Eastern Europe Osijek Croatia Computer Science and Information Technology Osijek Faculty of Electrical Engineering Osijek Croatia

ISBN: (纸本)9798350347722

To successfully train modern object detectors in a supervised manner, a large number of labeled images is usually required. Collecting and annotating images can be an expensive and time-consuming job, especially in the field of autonomous driving. A cheaper and faster alternative can be found in computer simulations of real-world traffic scenes, where the object of interest can be automatically labeled. In this spirit, a tool for automatic labeling of the images obtained from CARLA autonomous driving simulator is proposed. The tool runs in parallel with CARLA simulator and creates a synthetic dataset with annotations in the appropriate format for the following objects of interest: Traffic lights, traffic signs, vehicles, and pedestrians. The tool enables the end-user to generate a synthetic dataset with a desired number of images and with desired parameters such as weather condition, image resolution, and traffic density. In that way, large synthetic datasets can be generated in a short period of time. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Insight into Janus V2COS as anode material of high-performance alkali metal ion battery: Diffusion barrier, recyclability, specific capacity, and open-circuit voltage

引用

Physical Review Materials 2024年第8期8卷 085801-085801页

作者： Fanfan Wang Jun Yuan Zhufeng Zhang Baoan Song Junhua Zhao Jincheng Yue Tian Xu Jun Zhou School of Physical Science and Technology Faculty of Electrical Engineering and Computer Science College of Chemical and Material Engineering School of Electronic Information Engineering

Transition metal carbides, nitrides, and carbonitrides, known as MXenes, exhibit exceptional conductivity, stability, and large specific surface area, rendering them promising candidates for anode materials in rechargeable batteries. Herein, we investigate the electrochemical characteristics of the Janus MXene V2COS monolayer, as an anode material of alkali metal ion batteries by using first-principles calculations. The phonon band structure and ab initio molecular dynamics simulations confirm the stability of the Janus V2COS monolayer. The mechanical and electrical properties of the Janus V2COS monolayer are explored and proved to have good mechanical stability and electrical conductivity. The surface of the Janus V2COS monolayer demonstrates the facile adsorption of alkali metal ions and low diffusion barriers. As an anode material, the recyclability of the Janus V2COS has been verified in the ion intercalation/deintercalation processes. Furthermore, the theoretical specific capacities and the open-circuit voltages of the Janus V2COS monolayer are calculated to be 165.54mAh/g and 2.62 V for Li, 662.18mAh/g and 0.76 V for Na, and 294.43mAh/g and 0.4 V for K, respectively. It presents that the Janus V2COS monolayer is a potential anode material of sodium-ion batteries and potassium-ion batteries.

关键词： Electrochemical properties 2-dimensional systems Density functional theory First-principles calculations

来源：评论

学校读者我要写书评

暂无评论

Analysis of PV and EV Chargers Integration Impact on Radial LV Distribution Network 8

Analysis of PV and EV Chargers Integration Impact on Radial ...

引用

8th International Conference on Smart and Sustainable Technologies, SpliTech 2023

作者： Dubravac, Marina Šimić, Zvonimir Topić, Danijel Knežević, Goran Fekete, Krešimir Josip Juraj Strossmayer University of Osijek Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

ISBN: (纸本)9789532901283

Recently, there is more and more integration of photovoltaics (PV) and chargers for electric vehicles (EV) in existing low-voltage (LV) distribution networks. Integration of PVs and EV chargers individually can have a negative effect on the electrical variables of radial distribution networks such as voltages, loading of network elements, losses, etc. However, their simultaneous operation mitigates the negative impact caused by their individual integration. In this paper, different levels of PVs and EV chargers integration are considered and their effect on voltages, loading of cables, losses, as well as power exchange with the external network is studied. Simulation scenarios are implemented in DIgSILENT PowerFactory and power flows are analyzed. According to obtained results, the worst scenarios present two marginal scenarios - without PVs and 100% EV chargers and 100% PVs and without EV chargers. Values of observed parameters in these scenarios have the highest deviations from rated values. In scenario with 50% PV and 25% EV chargers integration, voltage deviation from rated voltage, loading of cables and losses have the lowest value. © 2023 University of Split, FESB.

关键词： Cables

来源：评论

学校读者我要写书评

暂无评论

A novel modular deep fully convolutional network for efficient low resolution facial expression recognition

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第6期14卷 7747-7759页

作者： Aly, Walaa Shahin, Ahmed I. Aly, Saleh Department of Information Technology College of Computer and Information Sciences Majmaah University Al-Majmaah11952 Saudi Arabia Department of Electrical Engineering Faculty of Engineering Aswan University Aswan81542 Egypt Department of Natural and Applied Sciences Community College Majmaah University Al-Majmaah11952 Saudi Arabia

Facial expression is one of the most important and natural way to express human feelings. Although deep convolutional neural networks have improved the performance of facial expression recognition (FER) systems, recognizing facial expressions from low resolution images is still a challenging task for real-time applications. A new modular deep fully convolutional neural network is designed to tackle this problem. The proposed network is composed of four modules namely, feature extraction (FE), residual spatial-channel attention (RSCA), atrous spatial pyramid pooling (ASPP), and classification module. The prominent facial regions relevant to facial expressions are extracted using FE module and then strengthened using RSCA and ASPP modules. Finally, a classification module using convolutional layers with adjusted stride parameter values is employed instead of fully connected layers to significantly reduce the number of learnable parameters. Experimental results using CK+, RAF-DB, and SFEW 2.0 datasets show that our proposed method achieves improved accuracies of 99.9%, 84.96%, and 53.0% at image resolutions of 32 × 32 , 48 × 48 , and 26 × 26 , respectively. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Propagation of Radio Waves in Wine Cellars 30

Propagation of Radio Waves in Wine Cellars

引用

30th International Conference on Systems, Signals and Image Processing, IWSSIP 2023

作者： Rimac-Drlje, Snjezana Rupcic, Slavko Keser, Tomislav Aleksi, Ivan Kovacevic, Ivana Miling, Robert Mandric, Vanja J. J. Strossmayer University of Osijek Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

ISBN: (纸本)9798350337297

Monitoring, control and management of wine production using sensors, IoT and machine learning methods is becoming more and more common. Wireless connection of sensors requires knowledge of losses due to electromagnetic (EM) wave propagation, and wine cellars represent a specific environment due to their architecture and wine vessels that hinder wave propagation. This paper presents the results of measuring EM wave losses in a basement with characteristics similar to wine cellars, and the measurement results are compared with the corresponding theoretical models. Measurements were performed for frequencies 860 MHz and 2.4 GHz, for LOS and NLOS conditions. It was found that at small distances from the transmitting antenna, losses increase according to the Free space model, and then the waveguide mechanism and multimode propagation begin to dominate. The tunnel model in this region gives a rough approximation of the losses. Furthermore, it was shown that in the NLOS region the losses can be modeled with the knife-edge diffraction loss model. © 2023 IEEE.

关键词： Diffraction

来源：评论

学校读者我要写书评

暂无评论

A Study on Eye Tracking for Mobile Devices Using Deep Learning 23

A Study on Eye Tracking for Mobile Devices Using Deep Learni...

引用

24th International Conference on computer Systems and Technologies, CompSysTech 2023

作者： Le Hoang, Nam Porta, Marco Faculty of Information Technology Hanoi University Hanoi Viet Nam Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy

ISBN: (纸本)9798400700477

While eye tracking technology has been around for several years, it has traditionally been implemented on personal computers using specific devices. Eye tracking through smartphones or tablets is much more challenging, because it involves the use of standard cameras and typically significantly fewer computational resources. In this paper, we present a study in which, based on a large dataset of face images acquired via mobile devices, we investigate the influence of some design choices (in particular, related to optimizers, color, and regularization techniques) on a deep learning convolutional architecture. We believe that the results obtained, although preliminary, can provide a useful contribution to a challenging and constantly evolving research field such as that of eye tracking for mobile appliances. © 2023 ACM.

关键词： Eye tracking

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：