检索结果-内蒙古大学图书馆

International Journal of Interactive Mobile Technologies 2023年第23期17卷 4-19页

作者： Chi, Jing On, Chin Kim Zhang, Haopeng Chai, Soo See Faculty of Computing and Informatics University Malaysia Sabah Sabah Malaysia School Information and Electrical Engineering Hebei University of Engineering Hebei China Faculty of Computer Science and Information Technology Universiti Malaysia Sarawak Sarawak Malaysia

With the emergence of deep learning, Convolutional Neural Network (CNN) models have been proposed to advance the progress of various applications, including face recognition, object detection, pattern recognition, and number plate recognition. The utilization of CNNs in these areas has considerably improved security and surveillance capabilities by providing automated recognition solutions, such as traffic surveillance, access control devices, biometric security systems, and attendance systems. However, there is still room for improvement in this field. This paper discusses several classic CNN models, such as LeNet-5, AlexNet, VGGNet, GoogLeNet, and ResNet, as well as lightweight models for mobile-based applications, such as MobileNet, ShuffleNet, and EfficientNet. Additionally, deep CNN-based face recognition models, such as DeepFace, DeepID, FaceNet, and SphereFace, are explored, along with their architectural characteristics, advantages, disadvantages, and recognition accuracy. The results indicate that many scholars are researching lightweight face recognition, but applying it to mobile devices is impractical due to high computational costs. Furthermore, noise label learning is not robust in actual scenarios, and unlabeled face learning is expensive in manual labeling. Finally, this paper concludes with a discussion of the current problems faced by face recognition technology and its potential future directions for development. © 2023 by the authors of this article. Published under CC-BY. All Rights Reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Real-Clinical MRI and BraTS Datasets for Brain Tumor Segmentation 26

Comparative Analysis of Real-Clinical MRI and BraTS Datasets...

引用

26th Irish Machine Vision and Image Processing Conference, IMVIP 2024

作者： Ranjbarzadeh, Ramin Keles, Ayse Crane, Martin Bendechache, Malika Department of Artificial Intelligence Engineering Faculty of Engineering and Natural Sciences Ankara Medipol University Ankara Turkey School of Computing Faculty of Engineering and Computing Dublin City University Ireland ADAPT Research Centre School of Computer Science University of Galway Ireland

ISBN: (纸本)9781837242672

This study compares the BraTS 2020 dataset with a Real-Clinical dataset from Ankara Bilkent City Hospital for brain tumor segmentation. We analyzed histogram attributes and image dimensions, revealing that the Real-Clinical dataset has a more diverse and skewed intensity distribution compared to the uniformity of the BraTS dataset. This inconsistency suggests potential challenges for algorithms trained on BraTS data when applied in clinical settings, which exhibit greater image variation. Additionally, the higher resolution and inclusion of the entire skull in the clinical dataset complicate processing and segmentation, necessitating more robust algorithms. Our research underscores the importance of developing advanced machine-learning tools that can handle the complexity and variability of clinical MRI scans, enhancing diagnostic accuracy and clinical applicability. This study lays the groundwork for improving medical imaging algorithms to ensure their effectiveness in real-world clinical environments. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Multi-objective Optimization of Vision Transformer 8

An Evolutionary Multi-objective Optimization of Vision Trans...

引用

8th International Conference on Information Technology, InCIT 2024

作者： Sacheewapasuk, Suvipa Jewajinda, Yutana Praditwong, Kata Silpakorn University Faculty of Engineering and Industrial Technology Department of Electrical Engineering Nakhon Pathom Thailand Silpakorn University Faculty of Science Department of Computing Nakhon Pathom Thailand

ISBN: (纸本)9798350366303

This paper presents an evolutionary multi-objective optimization of vision transformer architecture and the effect of two genetic crossover operators, two-point and uniform crossover, on the quality of the solutions. The proposed method employs the multi-objective genetic algorithm (NSGA-II) and uses a block-based encoding for visual transformer models. By adopting configurable blocks, the encoding method allows the search for various ViT architectures. The paper comprehensively analyzes the effect of genetic operators on the quality of the solution, providing practical insights for future research. The experimental results, which are reported on the Cifar-10 dataset, demonstrate a trade-off between model size and accuracy and are compared to the state-of-the-art models, providing solid evidence of the findings. © 2024 IEEE.

关键词： Crossover Genetic algorithm Multiobjective optimization Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Fake Social Media Profile Identification and Report Using Machine Learning

Fake Social Media Profile Identification and Report Using Ma...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Chinnasamy, P. Ayyasamy, Ramesh Kumar Subramaniam, Suthashini Sangodiah, Anbuselvan Iftikhar, Aqsa Kiran, Ajmeera Kalsalingam Academy of Research and Education Department of Computer Science and Engineering School of Computing TamilNadu Srivilliputtur India Kampar Malaysia School of Computing Faculty of Computing and Engineering Quest International University Perak Ipoh30250 Malaysia MLR Institute of Technology Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331540685

In the digital age, Online Social Networking platforms are integral to daily life, but they also attract malicious bots that mimic human behaviour and pose cybersecurity threats. This literature review focuses on recent Machine Learning-based techniques for detecting and classifying bots on major social media platforms. It covers supervised, semi-supervised, and unsupervised methods, dataset details, and feature categories. While the technology is advancing, an ongoing challenge lies in the creation of ever- evolving bots to evade detection. The study offers insights into the evolving landscape of cybersecurity and the need for continual research in this field, but potential drawbacks may include data privacy concerns, The pervasive influence of the internet and social media as platforms for real-time information dissemination and their potential to shape perceptions and lives. It highlights the concern that unverified and malicious content can significantly impact users' perceptions. The paper offers a taxonomy for classifying malicious information at various stages and presents technologies to combat the issue from content generation to containment. The results illustrate the efficacy of machine learning in improving the dependability and safety of social media platforms, offering a scalable approach to address the increasing problem of online deception. © 2024 IEEE.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Comparison of CNN-based deep learning architectures for rice diseases classification

引用

Artificial Intelligence in Agriculture 2023年第3期9卷 22-35页

作者： Md Taimur Ahad Yan Li Bo Song Touhid Bhuiyan Department of Computer Science and Engineering Daffodil International UniversitySavarBangladesh School of Mathematics Physics and Computing University of Southern QueenslandToowoombaAustralia School of Engineering University of Southern Queensland ToowoombaAustralia Department of Computer Science and Engineering Faculty of Science and Information TechnologyDaffodil International UniversityBangladesh

Although convolutional neural network(CNN)paradigms have expanded to transfer learning and ensemble models from original individual CNN architectures,few studies have focused on the performance comparison of the applicability of these techniques in detecting and localizing rice ***,most CNN-based rice disease detection studies only considered a small number of diseases in their *** these shortcomings were addressed in this *** this study,a rice disease classification comparison of six CNN-based deep-learning architectures(DenseNet121,Inceptionv3,MobileNetV2,resNext101,Resnet152V,and Seresnext101)was conducted using a database of nine of the most epidemic rice diseases in *** addition,we applied a transfer learning approach to DenseNet121,MobileNetV2,Resnet152V,Seresnext101,and an ensemble model called DEX(Densenet121,EfficientNetB7,and Xception)to compare the six individual CNN networks,transfer learning,and ensemble *** results suggest that the ensemble framework provides the best accuracy of 98%,and transfer learning can increase the accuracy by 17%from the results obtained by Seresnext101 in detecting and localizing rice leaf *** high accuracy in detecting and categorisation rice leaf diseases using CNN suggests that the deep CNN model is promising in the plant disease detection domain and can significantly impact the detection of diseases in real-time agricultural *** research is significant for farmers in rice-growing countries,as like many other plant diseases,rice diseases require timely and early identification of infected diseases and this research develops a rice leaf detection system based on CNN that is expected to help farmers to make fast decisions to protect their agricultural yields and quality.

关键词： Deep learning Convolutional neural networks(CNNs) Transfer learning Plant leaf disease detection

来源：评论

学校读者我要写书评

暂无评论

Implementation of Power Meter System Security in Smart Grids with QRNG Method 5

Implementation of Power Meter System Security in Smart Grids...

引用

5th IEEE International Conference on computing, Power, and Communication Technologies, IC2PCT 2024

作者： Patel, Aum Shrivastava, Simran Sujatha, G. Srm Institute of Science and Technology School of Computing College of Engineering and Technology Faculty of Engineering and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798350383522

Smart grids face emerging threats as connectivity expands attack surfaces. To strengthen smart meter data encryption through optimized integration of a cloud-based quantum random number generator (QRNG) service. QRNGs leverage intrinsic quantum properties to produce true randomness for cryptographic keys. An architecture is presented utilizing a QRNG service on the IBM quantum computing platform. Quantum entropy is remotely sampled and delivered on-demand via APIs to generate quantum random AES encryption keys for smart meter communications. Homomorphic encryption secures credential transmission. Compared to mathematical pseudorandom number generators, the quantum origin provides stronger security against brute force attacks and future quantum computing decryption. Tailoring QRNG generation and integration focuses on the performance, cost, and deployment constraints of grid-wide encryption hardening. The optimized approach aims to maximize randomness while minimizing complexity. By hardening cryptography via readily available quantum key generation, the QRNG integration delivers indispensable security enhancement. © 2024 IEEE.

关键词： Cryptography cryptography protocols cybersecurity encryption privacy QKD QRNG quantum entropy quantum key distribution quantum random number generator quantum uncertainty security smart grid smart meter true randomness

来源：评论

学校读者我要写书评

暂无评论

RSSI Estimation for Constrained Indoor Wireless Networks Using ANN 4

RSSI Estimation for Constrained Indoor Wireless Networks Usi...

引用

4th IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2024

作者： Arif, Samrah Khan, M. Arif Rehman, Sabih ur Abbas, Syed Muzahir School of Computing Mathematics and Engineering Charles Sturt University NSW Australia School of Engineering Faculty of Science and Engineering Macquarie University SydneyNSW Australia

ISBN: (纸本)9798350395914

In the expanding field of the Internet of Things (Io'T), wireless channel estimation is a significant challenge. This is specifically true for low-power IoT (LP-IoT) communication, where efficiency and accuracy are extremely important. This research establishes two distinct LP-IoT wireless channel estimation models using Artificial Neural Networks (ANN): a Feature-based ANN model and a Sequence-based ANN model. Both models have been constructed to enhance LP-IoT communication by lowering the estimation error in the LP-IoT wireless channel. The Feature-based model aims to capture complex patterns of measured Received Signal Strength Indicator (RSSI) data using environmental characteristics. The Sequence-based approach utilises predetermined categorisation techniques to estimate the RSSI sequence of specifically selected environment characteristics. The findings demonstrate that our suggested approaches attain remarkable precision in channel estimation, with an improvement in MSE of 88.29% of the Feature-based model and 97.46% of the Sequence-based model over existing research. Additionally, the comparative analysis of these techniques with traditional and other Deep Learning (DL)-based techniques also highlights the superior performance of our developed models and their potential in real-world IoT applications. © 2024 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

YOLO-based Traffic Signal Optimization for Intelligent Traffic Flow Management 8

YOLO-based Traffic Signal Optimization for Intelligent Traff...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Joesam Dinesh, C. Shrinidhi, S. Amaran, Sibi Sree Kumar, K. Karthikeyan, U. Srm Institute of Science and Technology Dept of Computing Technologies Kattankulathur India Dept of Computing Technologies Kattankulathur India Srm Institute of Science and Technology Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology Kattankulathur SRM Nagar Tamilnadu Chennai603203 India

ISBN: (纸本)9798350376425

As cities grow in population and the number of vehicles increases, traffic congestion has become a major problem. Traffic jams lead to delays, driver stress, higher fuel consumption, and increased air pollution. Megacities are particularly affected. To manage traffic effectively, it's essential to calculate road traffic density in real-time. Optimizing traffic control is crucial for this. The system uses live images from traffic cameras and AI-based image processing to measure vehicle density and adjust traffic signals accordingly, reducing congestion, speeding up transit, and lowering pollution. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Refractive Index Measurement Based on Fibre Optics with Multiparameter Sensing Capabilities 19

Refractive Index Measurement Based on Fibre Optics with Mult...

引用

19th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2023

作者： Bong, Paul Cornelius Tan, Alfred Jia Yee Chua, Hong Siang Swinburne University of Technology Sarawak Campus Faculty of Engineering Computing and Science Kuching Malaysia

ISBN: (纸本)9781665476928

Quality control and assurance plays a core in chemical, agrifood, F B and pharmaceutical industries due to quality regulations. Refractometry plays an indispensable part in determining the composition or purity of a sample and conventional solutions can be intrusive and very expensive. In this paper we aim to determine the Refractive Index (RI) sensing and multiparameter sensing capabilities of a triple U-shaped side + center polished macrobent fibre optic sensor prototype. This prototype was tested on controlled glycerol samples ranging from (1.34-1.39) Refractive Index Unit (RIU) and showed a linear trend in RI sensing. It boasts an average percentage error of 0.1318% in refractive index measurements when subjected to 12 randomly prepared test data within the range of(1.33 to 1.40) RIU. Individually, the percentage error is higher for each probe but did not exceed 0.4% when used in tandem. This proves improved performance when using multiple probes with different configurations. The sensor was also able to extrapolate further for 1. 40RIU which was not within the range of the training data thus it is highly scalable. Its temperature sensing (30°C to 45°C) capabilities was also tested. Despite the great performance in RI sensing, the center polished probe was found unsuitable. The 500\mum diagonal polished probe showed great sensitivity and linearity while the 300\mum diagonal polished probe showed low sensitivity and high linearity, thus allowing the system to determine the RIU of the solution at room temperature. This project shows great promise in the field of multiparameter RI sensing. © 2023 IEEE.

关键词： Probes

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：