检索结果-内蒙古大学图书馆

Temporal-Spatial Feature Extraction in IoT-Based SCADA System Security: Hybrid CNN-LSTM and Attention-Based Architectures for Malware Classification and Attack Detection

引用

IEEE Access 2025年 13卷 102109-102132页

作者： Onur Polat Ali Ayid Ahmad Saadin Oyucu Enes Algül Ferdi Doäan Ahmet Aksöz Department of Computer Engineering Bingöl University Bingöl Türkiye Department of Electrical Engineering College of Engineering University of Kirkuk Kirkuk Iraq Department of Computer Engineering Faculty of Technology Gazi University Ankara Türkiye Department of Computer Engineering Adıyaman Üniversitesi Adiyaman Türkiye Department of Electrical and Electronics Engineering Kayseri University Kayseri Türkiye

This research presents a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model developed for malware classification from IoT devices in the SCADA system and for detecting anomalies in the network. The developed model identifies complex attacks in the network by taking advantage of the strengths of CNNs that reveal spatial features and LSTMs that detect temporal dependency. CICIoT 2023 is used as the dataset. ADAM optimization algorithm with cross-entropy loss is used to eliminate overfitting and training is performed. Within the scope of the study, the proposed model is compared by applying it with six deep learning architectures (hybrid CNN-LSTM, Non-Local Neural Network (NLNN), Residual Attention Network (RAN), Dual Attention Network (DANet), Transformer-CNN and Attentional CNN). The obtained results show that the proposed CNN-LSTM model outperforms other complex architectures and achieves a high test accuracy of 99.23%. It has demonstrated remarkable performance according to precision, recall and F1 evaluation metrics in detecting distributed denial of service (DDoS) and denial of service (DoS) attacks. The proposed model successfully identifies Mirai botnet variants and fragmentation-based attacks. Although other models, Transformer-CNN (98.81%) and DANet (98.07%), provide high performance, they fall behind the superior temporal modeling capabilities of CNN-LSTM. When the obtained findings are examined, they highlight the relative strengths of various deep learning approaches for IoT security applications. The performances of the implemented deep learning models reached accuracies exceeding 96%, demonstrating the importance of IoT-based SCADA systems against evolving cyber threats. The study revealed the superior successes of deep learning-based approaches for IoT security.

关键词： Security SCADA systems Internet of Things Malware Convolutional neural networks Protocols Long short term memory Feature extraction Access control Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Influence of cavitational and non-cavitational ultrasonic treatment on the structure and electrochemical properties of nanoporous wood activated carbon

引用

Applied Nanoscience (Switzerland) 2023年第11期13卷 7303-7313页

作者： Ptashnyk, Vadym Bordun, Ihor Maksymych, Vitalii Malovanyy, Myroslav Kulyk, Yurij Calus, Dariusz Chabecki, Piotr Szymczykiewicz, Ewelina Faculty of Mechanics Energy and Information Technology Lviv National Environmental University Lviv Region Dubliany80381 Ukraine Faculty of Electronics and Computer Technologies Ivan Franko National University of Lviv Lviv79005 Ukraine Faculty of Electrical Engineering Czestochowa University of Technology Czestochowa42-200 Poland Institute of Sustainable Development Lviv Polytechnic National University Lviv79013 Ukraine Institute of Applied Mathematics and Fundamental Sciences Lviv Polytechnic National University Lviv79013 Ukraine Faculty of Physics Ivan Franko National University of Lviv Lviv79005 Ukraine

The effect of ultrasonic radiation in the cavitational and non-cavitational modes on the properties of wood activated carbon (AC) has been investigated. The AC was synthesized from birch wood by pyrolysis at 800 ºC and activation by water vapor. The duration of the ultrasonic treatment was chosen so that the AC received the same amount of acoustic energy. It has been shown that ultrasonic treatment in the cavitational mode does not cause significant changes in the porous structure of wood activated carbon, with only the redistribution of mesopores in size taking place. The non-cavitational ultrasonic treatment not only redistributes the mesopores in size, but also forms a microporous structure of the AC. Taken together, these factors lead to an increase in the specific surface area to 719 m2/g as against 551 m2/g for the original carbon. It was found that the specific capacity of the AC after ultrasonic exposure increased to 94.8 F/g for carbon after non-cavitational treatment and 142.3 F/g for carbon after cavitational treatment as against 58.3 F/g for the original carbon. The impedance dependences at different bias voltages for supercapacitors made from both the original and treated AC were analyzed. Equivalent electrical circuits modeling impedance hodographs were constructed. To this end, the de Levie model was employed, modified by the connection of a parallel R SC C SC-link. It was established that due to the ultrasonic treatment of carbon in the cavitational mode, the density of energy states of delocalized charge carriers at the Fermi level increases, which results in the redistribution of capacitances that form an electrical double layer, and this increases the specific capacity of carbon. The increase in the specific capacity of AC after ultrasonic treatment in the non-cavitational mode is primarily attributed to the formation of a microporous structure and, consequently, an increase in the specific surface area. © 2023, King Abdulaziz City for Science and

关键词： Wood

来源：评论

学校读者我要写书评

暂无评论

Efficient Usage of Energy in 5G toward Sustainable Development inclined to Industry 4.0 Connectivity

Efficient Usage of Energy in 5G toward Sustainable Developme...

引用

2022 IEEE Region 10 Symposium, TENSYMP 2022

作者： Pradhan, Devasis Tun, Hla Myo Wah, Naw Khu Say Oo, Thandar Priyanka, K.C. Dash, Ajit Acharya Institute of Technology Department of Electronics & Communication Engineering Bangalore India Yangon Technical University Faculty of Computer & Electrical Engineering Yangon Myanmar Bijiu Pattnaik University of Technology Global Research Consultant Bhubaneswar India

ISBN: (数字)9781665466585

ISBN: (纸本)9781665466585

As traffic requests keep on flooding, conveying 5G similarly as its past ages become dynamically far-fetched. In addition to the fact that it would mean a sensational expansion in energy utilization of portable organizations, it would likewise contrarily affect the climate. An imaginative and feasible methodology is expected to break the energy bend. With the appearance of the fifth era of wireless networks, with a huge number of more base stations and billions of associated gadgets, the requirement for an energy-productive framework plan and activity will be significantly really convincing. With the revolution of Industry 4.0 systems rely on antenna technology to connect various sensors and actuators which enables the higher mobility of robots and drones through wireless communication. © 2022 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 Novel Phase Shifter for 5G Base Station Antenna 7

A Novel Phase Shifter for 5G Base Station Antenna

引用

7th World Conference on Computing and Communication Technologies, WCCCT 2024

作者： Du, Lin Feng, Botao Ding, Xiao Gu, Wenzhe Sun, Sanshan Deng, Li Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China Macau University of Science and Technology Faculty of Humanities and Arts 999078 China Huizhou University School of Computer Science and Engineering Huizhou516007 China Sichuan Normal University College of Physics and Electronic Engineering Sichuan China Beijing University of Posts and Telecommunications College of Information and Communication Engineering Beijing China

ISBN: (纸本)9798350372328

In this paper, a phase shifter for the base station antenna with low cost, ease of manufacturing and good performance on phase shift is presented. The phase shifter consists of a metal shell, a substrate, two dielectric plates, and two conductor lines. The phase shift is realized by moving the dielectric plates longitudinally, which cover the conductor lines. With the slots in dielectric materials, the slotted part of dielectric plates can function similarly to a quarter-wavelength impedance matching. Therefore, the function of this phase shifter is that the voltage standing wave ratio (VSWR) and power distribution ratio can be guaranteed when the dielectric plate is moved. The phase shifter exhibits a bandwidth of 1.7-2.1 GHz and the corresponding phase shift is 86.88° when the dielectric plate moves by 90 mm. Moreover, its good physical features including light weight, low cost, and easy fabrication make it well suitable for base station antenna applications. © 2024 IEEE.

关键词： Phase shifters

来源：评论

学校读者我要写书评

暂无评论

Bird species recognition using spiking neural network along with distance based fuzzy co-clustering

引用

International Journal of Speech technology 2023年第3期26卷 681-694页

作者： Mohanty, Ricky Bhuyan, Hemanta Kumar Pani, Subhendu Kumar Ravi, Vinayakumar Krichen, Moez Department of Electronics & Communication Orissa Engineering College Odisha Bhubaneswar India Deemed to be University Andhra Pradesh Guntur India Krupajal Computer Academy Biju Patnaik University of Technology Odisha Rourkela India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar34754 Saudi Arabia Faculty of Computer Science and Information Technology Al-Baha University Al-Baha65528 Saudi Arabia ReDCAD Laboratory University of Sfax Sfax3029 Tunisia

This paper has emphasized several sounds for Bird Species Recognition based on their vocalization. Although various techniques have been designed with good equipment for identifying different birds’ sounds, still it has limitations to classify or recognize different birds’ sounds at dissimilar moments of traveling. Thus, this paper presents the model for recognizing the bird’s sound in several situations using Spiking Neural Network (SNN). In this model, Permutation Pair Frequency Matrix Coefficients are considered for the features representing the bird sound frames, after the application of pre-processing method on the moment of recordings. These features are applied as input to the three-layered SNN and subsequently to the hidden layer, which performs the work of spiking if there is any change in the feature. The spikes activate any one of the neuron’s outputs, that produces a higher probability class. Further, the SNN along with the Distance Fuzzy Co-clustering algorithm technique used on these bird sounds to achieve optimum results. The performance of this model achieved more than 94% accuracy and a computation time of 4.16 ms better than other existing approaches. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A CH9 Low-Profile Circularly-Polarized Antenna for Indoor Positioning 7

A CH9 Low-Profile Circularly-Polarized Antenna for Indoor Po...

引用

7th World Conference on Computing and Communication Technologies, WCCCT 2024

作者： Zhang, Zhenfeng Feng, Botao Gu, Wenzhe Ding, Xiao Sun, Sanshan Deng, Li Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China Huizhou University School of Computer Science and Engineering Huizhou516007 China Macau University of Science and Technology Faculty of Humanities and Arts 999078 China Sichuan Normal University College of Physics and Electronic Engineering Sichuan China Beijing University of Posts and Telecommunications College of Information and Communication Engineering Beijing China

ISBN: (纸本)9798350372328

This paper presents a low-profile CH9 circularly polarized 3-element multiple input multiple output (MIMO) antenna for precise positioning applications. The feeding structure of the antenna employs a conventional wilkinson power divider to achieve circular polarization, where the feeding structure and the radiating patch are located on the same layer of the dielectric substrate with a grounded backside. The -10-dB bandwidth of each antenna element ranges from 7.04 to 8.55 GHz, with a gain larger than 2.21 dBi within the desired bandwidth. In order to enhance localization accuracy and minimize the impact of spatial correlation, the distance interval between antenna elements is designed to be 12.5 mm. Experimental results show that when ports 1, 2 and 3 are excited with equal amplitude phase differences of 0 °, 90 ° and -90 °, respectively, the frequency bandwidth of the MIMO antenna is ranging from 7.61 to 8.48 GHz, with corresponding gain fluctuating from 5.39 to 8.07 dBi. In addition, the circularly polarized bandwidth is from 7 to 8.89 GHz, which fully covers the CH9 frequency band. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Web-Based Integrated School Management System for Enhanced Student-Teacher and Resource Accessibility

Web-Based Integrated School Management System for Enhanced S...

引用

International Conference on computer Theory and Applications (ICCTA)

作者： Wessam M. Salama Moustafa H. Aly Department of Computer Engineering Faculty of Engineering Pharos University in Alexandria Alexandria Egypt Department of Electronics and Communications Engineering College of Engineering and Technology Arab Academy for Science Technology and Maritime Transport Alexandria Egypt

ISBN: (数字)9798331529680

ISBN: (纸本)9798331529697

In this paper, an integrated school management system is introduced to enhance educational interactions by connecting students and teachers. Moreover, it simplifies the sharing and retrieval of academic resources in pdf format. The primary objectives include creating a user-friendly web-based platform for improved student-teacher connectivity, supporting multiple languages (starting with English and Arabic), and providing introductory videos for new users. In addition, an attendance tracking system for student safety is implemented. Furthermore, key features of the system include user registration and profile management, secure login and authentication, a user-friendly dashboard, messaging tools for direct communication, and scheduling, pdf file upload with effective organization and search options, real-time notifications, and robust data security and privacy measures are introduced. The HTML5, CSS3, JavaScript, Tailwind for the front, *** technology is introduced for the backend, MongoDB for the database, JWT for authentication, and cloud-based storage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost AI-Powered System for Early Detection of Diabetic Retinopathy and Ocular Diseases in Resource Limited Settings

引用

IEEE Access 2025年 13卷 97322-97336页

作者： Harpreet Vohra Mohammad Kamrul Hasan Siti Norul Huda Sheikh Abdullah Shayla Islam Abdul Hadi Abd Rahman Shreya N. Bhojake Dhruv Bobal Awal Kaur Gandhi Muskan Chandramohan Dhasarathan Department of Electronics and Communication Engineering Thapar Institute of Engineering & Technology Patiala Punjab India Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Kuala Lumpur Malaysia Institute of Computer Science and Digital Innovations UCSI University Kuala Lumpur Malaysia

Eye Health is a vital yet often neglected aspect of healthcare, especially in distant and deprived regions that are less accessible to specialized diagnostic tools and professionals. This paper introduces an intelligent diabetic retinopathy detection system to enhance affordability, accessibility, and early diagnosis. The system features a cost-effective imaging setup utilizing a 28D lens and a camera to capture high-quality fundus images. These images are analyzed using advanced Convolutional Neural Networks to determine the cases of people suffering from eye issues: Age-related vascular degeneration (AMD), Diabetic retinopathy (DR), and Glaucoma. A user-friendly web application hosted on AWS facilitates seamless image upload, automated diagnosis, and report generation. Achieving an accuracy of 96.5%, the system ensures reliable diagnostics, enabling timely medical intervention. By integrating AI-driven analysis and cloud-based accessibility, this solution aims to transform eye care in resource-limited settings. Performance evaluation against existing methods highlights its superiority, with an F1 score of 98.2 % for DR, 92.5% for Glaucoma, and 98.8% for AMD, outperforming many previous approaches that either focused on single-disease detection or relied on costly hardware.

关键词： Accuracy Glaucoma Retina Medical services Diabetic retinopathy Imaging Convolutional neural networks Hardware Costs Blindness

来源：评论

学校读者我要写书评

暂无评论

Detection of Detonators in Baggage Using Deep CNN Architecture: A Comparative Study of Contrast Enhancement and Feature Extraction Methods 8

Detection of Detonators in Baggage Using Deep CNN Architectu...

引用

8th IEEE International Conference on Image and Signal Processing and their Applications, ISPA 2024

作者： Lynda, Oulhissane Mostefa, Merah Moldovanu, Simona Moraru, Luminita LSS Faculty of Science and Technology Abdelhamid Ibn Badis University Laboratory of Signals and Systems Mostaganem Algeria Faculty of Automation Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati Modelling & Simulation Laboratory MSlab Department of Computer Science and Information Technology Galati Romania Faculty of Sciences and Environment Modelling & Simulation Laboratory Dunarea de Jos University of Galati MSlab Department of Chemistry Physics & Environment Galati Romania

ISBN: (纸本)9798350309249

Visual inspection of dual-energy X-ray radiographic images of cabin baggage requires high performance, but is hindered by various challenges such as low target prevalence, variability in target visibility, possible presence of multiple targets, and security personnel fatigue and inattention. Artificial intelligence (AI) techniques, particularly deep convolutional neural networks (CNNs), have shown promise in improving the automatic detection of explosives, even with low-resolution radiographic images, especially in high baggage throughput scenarios. In this paper, we focus on the detection of detonators as components of improvised explosive devices. The proposed approach involves comparing two experiments implemented in a deep CNN architecture using TensorFlow and Keras libraries. In the first experiment, raw dual-energy radiographic images without any enhancement were used. The second experiment includes three methods for contrast enhancement and feature extraction: the Contrast Limited Adaptive Histogram Equalization (CLAHE) method, the wavelet transform-based method, and the mixed CLAHE RGB-Wavelet method. In the latter two methods, Haar, Db2, Coif2, and Sym2 mother wavelet functions at two levels (HH and HL) were employed. The analysis of results focuses on a comparative study of performance measures such as accuracy, precision, recall, and F1 score. It was found that the preprocessing methods used in experiment 2, for the two evaluated classes (detonator and no detonator), achieved higher accuracy compared to the raw radiographic images used in experiment 1 (98.08%). The highest accuracies in experiment 2, with a value of 100%, were obtained with the CLAHE method (green channel in grayscale, blue channel in grayscale, and RGB channels) and the wavelet transform method with Haar mother wavelet at two levels HL © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

ZnO Nanorods Coated Glass Substrate Based on Side Coupling Technique for Lactose Sensing Application

ZnO Nanorods Coated Glass Substrate Based on Side Coupling T...

引用

International Conference on Electrical, Communication, and computer engineering (ICECCE)

作者： Marlina Jahava Mohd Hafiz Jali Md. Ashadi Md Johari Mohd Adili Norashikin Haziezol Helmi Mohd Yusof Aminah Ahmad Faculty of Electrical Technology and Engineering Universiti Teknikal Malaysia Melaka Malacca Malaysia Faculty of Electronics and Computer Technology and Engineering Universiti Teknikal Malaysia Melaka Malacca Malaysia Faculty of Information Technology and Computer Engineering Universiti Teknikal Malaysia Melaka Malacca Malaysia

A study has been conducted to investigate the sensing performance of zinc oxide (ZnO) nanorods coated glass substrate using the side coupling approach for lactose sensing application. The concentration of lactose solution was varied from 0% to 100% in order to examine the performance of the proposed sensor, which is influenced by the scattering and absorption of light. Coated glass substrates with optical side coupling could solve the lower output coupling voltage existed in the recent approach. Experimental results show that the proposed approach improved by a factor of 2.5 as compared to the uncoated glass substrate when exposed to variation concentration of lactose solution. The average sensitivity of the sensor was observed to be 0.0201 V/%Concentration throughout the tested %Concentration levels. The utilization of affordable and uncomplicated sensors allows for the precise identification of alterations in the refractive index solution, hence presenting potential applications in the domains of environmental and optical sensing.

关键词：

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：