检索结果-内蒙古大学图书馆

International Electronics Symposium (IES)

作者： Muhajirin Ida Ilyas Idris Winarno Dadet Pramadihanto Dept. of Information and Computer Politeknik Elektronika Negeri Surabaya Surabaya Indonesia Dept. of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Surabaya Indonesia

This paper presents an algorithm for detecting collisions in flight traffic management for drones. The algorithm is simple to implement and can be used to effectively manage the flow of drones in a safe and efficient manner. The algorithm has been tested in simulation and has been shown to be effective in detecting collisions between drones. The algorithm is also simple to implement and can be used with existing drone traffic management systems. As the number of drones in the sky continues to grow, this algorithm will become increasingly important for ensuring the safety of drone operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Twitter (X) Users Towards the Boycott of Pro-Israel Brand Using Support Vector Machine Method with SMOTE Approach

Sentiment Analysis Twitter (X) Users Towards the Boycott of ...

引用

Control & Automation, Electronics, Robotics, Internet of Things, and Artificial Intelligence (CERIA), IEEE International Conference on

作者： Hana Patricia Mawarnie Widodo Murien Nugraheni Dept. of Informatics and Computer Engineering Education Universitas Negeri Jakarta Jakarta Indonesia Dept. of Information System and Technology Universitas Negeri Jakarta Jakarta Indonesia

ISBN: (数字)9798331511166

ISBN: (纸本)9798331511173

The Israel-Palestine conflict that occurred on October 7, 2023, resulted in a boycott of brands known to be pro-Israel. Twitter or X, as one of the largest social media platforms in the world, became a platform for people to voice their opinions regarding the boycott. This study aims to analyze the sentiment of Twitter or X users towards the boycott of pro-Israel brands using the Support Vector Machine (SVM) method with the SMOTE (Synthetic Minority Oversampling Technique) approach. The Support Vector Machine (SVM) method is a machine learning method used for classification and regression. SMOTE is a technique used to overcome data imbalance. The data used in this study is Indonesian language tweet data from October 7, 2023, to April 7, 2024. The data was collected using data crawling techniques. The results of the study from the 80:20 data split, show that the Support Vector Machine (SVM) polynomial kernel model with the SMOTE technique has better performance in analyzing the sentiment of Twitter or X users towards the boycott of pro-Israel brands, with an accuracy value of 98,47%.

关键词： Support vector machines Sentiment analysis Accuracy Social networking (online) Blogs Machine learning Polynomials Internet of Things Kernel Robots

来源：评论

学校读者我要写书评

暂无评论

PhishGuard: A Convolutional Neural Network-Based Model for Detecting Phishing URLs with Explainability Analysis

arXiv

引用

arXiv 2024年

作者： Islam, Md Robiul Islam, Md Mahamodul Afrin, Suraiya Antara, Anika Tabassum, Nujhat Amin, Al Dept. of Computer Science and Engineering Uttara University Dhaka Bangladesh Dept. of Informatics University of Oslo Oslo Norway Khulna Bangladesh Dept. of Electrical and Electronics Engineering BRAC University Dhaka Bangladesh Dept. of Electrical and Computer Engineering North South University Dhaka Bangladesh Dhaka Bangladesh

Cybersecurity is one of the global issues because of the extensive dependence on cyber systems of individuals, industries, and organizations. Among the cyber attacks, phishing is increasing tremendously and affecting the global economy. Therefore, this phenomenon highlights the vital need for enhancing user awareness and robust support at both individual and organizational levels. Phishing URL identification is the best way to address the problem. Various machine learning and deep learning methods have been proposed to automate the detection of phishing URLs. However, these approaches often need more convincing accuracy and rely on datasets consisting of limited samples. Furthermore, these black-box intelligent models' decision to detect Suspicious URLs needs proper explanation to understand the features affecting the output. To address the issues, we propose a 1D Convolutional Neural Network (CNN) and trained the model with extensive features and a substantial amount of data. The proposed model outperforms existing works by attaining an accuracy of 99.85%. Additionally, our explainability analysis highlights certain features that significantly contribute to identifying the phishing URL. © 2024, CC BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Quantum Data Reduction with Application to Video Classification

arXiv

引用

arXiv 2022年

作者： Blekos, Kostas Kosmopoulos, Dimitrios Computer Engineering & Informatics Dept. University of Patras Rio Greece

We investigate a quantum video classification method using a hybrid algorithm. A quantum-classical step performs a data reduction on the video dataset and a quantum step—which only has access to the reduced dataset—classifies the video to one of k classes. We verify the method using sign videos and demonstrate that the reduced dataset contains enough information to successfully classify the data, using a quantum classification process. The proposed data reduction method showcases a way to alleviate the "data loading" problem of quantum computers for the problem of video classification. Data loading is a huge bottleneck, as there are no known efficient techniques to perform that task without sacrificing many of the benefits of quantum computing. © 2022, CC BY.

关键词： Data reduction

来源：评论

学校读者我要写书评

暂无评论

Enhance Object Tracking on Augmented Reality Markerless using FAST Corner Detection 5

Enhance Object Tracking on Augmented Reality Markerless usin...

引用

5th IEEE International Conference on Information Technology, Information Systems and Electrical engineering, ICITISEE 2021

作者： Nurhadi Winanto, Eko Arip Saparudin Dinamika Bangsa University Faculty Of Engineering Sriwijaya University Dept. Of Informatics Engineering Indonesia University Of Technology Malaysia School Of Computing Malaysia Telkom University Faculty Of Computer Science Dept. Of Informatics Engineering Indonesia

ISBN: (纸本)9781665401968

Markerless-based is the method in Augmented Reality (AR) to augmentation 3D objects in the frame. One of the challenges in markerless AR is to extract features as input data training on markerless AR. One of algorithm for feature extraction of object target is FAST corner detection in image processing. This paper uses FAST corner detection for feature extraction on Augmented Reality Markerless based with the aim to improve performance of augmentation objects in AR. The User Defined Target and Extended Tracking are to improve convenience and reliability of the AR. The aim is can trace 3D objects even the 3D object invisible. The results show that maximum environment for the best augmentation is intensity in of 80-190 cd. © 2021 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

On the Quantization of Recurrent Neural Networks for Smiles Generation

On the Quantization of Recurrent Neural Networks for Smiles ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Adriano Durao Joel P. Arrais Bernardete Ribeiro Gabriel Falcao Instituto de Telecomunicações Dept. of Electrical and Computer Engineering University of Coimbra Portugal CISUC Dept. of Informatics Engineering University of Coimbra Portugal

This paper focuses on the effects of applying quantization during training to Recurrent Neural Networks (RNNs) used in Simplified Molecular-Input Line-Entry System (SMILES) generation, a form of line notation for molecular information used in the development of pharmaceutical drugs, from the PubChem database. It offers the flexibility to choose the precision used by the model, by defining the number of bits at each layer. The RNNs are the focus of the current study, by comparing the performance of three of the most used algorithms, Simple RNN, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The models were trained on a selection of SMILES. By exploiting the QK-eras library, quantization performance was compared to their floating-point equivalent for several combinations of parameters. The goal of the testing program developed is to generate a large number of novel SMILES, facilitating the process of Drug Discovery which is traditionally long, and thus very expensive and difficult. By understanding how the behavior of quantized networks deviates from the regular model, in relation to the parameters used, we are able to control the process of choosing whether to quantize a model and to which degree it becomes more or less efficient. In this study, we observed good performance even for 4-bit models making use of LSTM and GRU layers, the same way we concluded that Simple RNN quantization does not compensate the effort.

关键词： Training Drugs Quantization (signal) Recurrent neural networks Process control Logic gates Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Chaotic American zebra search optimization algorithm for benchmark challenges 15

Chaotic American zebra search optimization algorithm for ben...

引用

15th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2023

作者： Kamboj, Vikram Kumar Krishna, Ardhala Bala Verma, Chaman Raboaca, Maria Simona Filote, Constantin Stepanova, Maria Schulich School of Engineering University of Calgary AB Canada Malla Reddy Engineering College for Women Dept. of Electrcical and Electronics Engineering Hyderabad India Eötvös Loránd University Faculty of Informatics Dept. of Media and Edu. Informatics Budapest Hungary National Research and Development Institute for Cryogenics and Isotopic Technologies Icsi Energy Department Ramnicu Valcea240050 Romania Stefan Cel Mare University of Suceava Faculty of Electrical Engineering and Computer Science Suceava720229 Romania Bauman Moscow State Technical University Engineering Business and Management Faculty Russia

ISBN: (纸本)9798350321388

In this research, we presented a modification to the recently developed swarm premised American zebra search optimization algorithm (AZOA) using chaos. The particular Singer mapping was proposed by the so-called chaotic AZOA and was already known to perform better in optimization. Twelve uni, multi modal benchmark functions, three-bar truss and ten bar truss optimal structural designs were tested. The chaotic AZOA with Singer map would perform more effectively, more consistently, and quicker than the classical AZOA and other recent metaheuristics in optimization, according to the results, which also supported the viability of the modifications. It was discussed if the chaotic AZAO could be optimized with the original AZOA, and the chaotic AZOA was suggested for use in applications for actual engineering challenges. © 2023 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Comparison of Fast Frequency Response Methods in the Low-Inertia Grid of Cyprus

Comparison of Fast Frequency Response Methods in the Low-Ine...

引用

International Conference on Energy Transition in the Mediterranean Area (SyNERGY MED)

作者： Andreas Argyrou Savvas Panagi Petros Aristidou Dept. of Electrical & Computer Engineering & Informatics Cyprus University of Technology Limassol Cyprus Distribution System Operator Electricity Authority of Cyprus Nicosia Cyprus

ISBN: (数字)9798350375923

ISBN: (纸本)9798350375930

Modern electric power systems with high levels of penetration of renewable energy sources (RES) often present frequency security problems. The lack of inertia due to the reduced number of synchronous generators in these systems, in combination with the usual inability of RES to provide frequency support, leads to system operators having to curtail RES or rely heavily on Under Frequency Load Shedding schemes to ensure frequency security. Fast Frequency Reserves (FFR) have been proposed as a solution to strengthen the frequency support of the system and alleviate security problems. FFR allows mitigating Rate of Change of Frequency, Nadir, and post-fault frequency steady-state problems after an event. In this paper, we present, analyze, implement and compare five FFR controllers to alleviate frequency security problems in low-inertia grids. The low-inertia, islanded, Cyprus dynamic model is used to quantify the results and exhibit the impact on a real system.

关键词： Renewable energy sources Power system dynamics Load shedding Power system stability Synchronous generators Stability analysis Steady-state Security Frequency synchronization Frequency control

来源：评论

学校读者我要写书评

暂无评论

An alternative Design Approach for the Design of Wideband Bandpass Filters Based on Cascaded Building Blocks

An alternative Design Approach for the Design of Wideband Ba...

引用

European Conference on Microwave

作者： Adnan Nadeem Symeon Nikolaou Dimitra Psychogiou Photos Vryonides Frederick Research Center Cyprus Dept. of Electrical and Computer Engineering and Informatics Frederick University Cyprus School of Engineering University College Cork Ireland Tyndall National Institute Ireland

ISBN: (数字)9782874870774

ISBN: (纸本)9798350385892

This paper introduces a novel design approach for the realization of wideband bandpass filters (BPFs). The technique is based on a conventional filter topology consisting of shunt short-circuited stubs connected by transmission lines where its λ g /4 interconnecting lines and its λ g /4 short-circuited stubs are replaced by a building block consisting of λ g /8 lines separated by λ g /8 short-circuited coupled-line sections. Guidelines on the design formulas through ABCD analysis in practical filter implementations are provided. Additionally, the manuscript presents a design example and its practical validation through the manufacturing and testing of a fourth-order microstrip-type BPF.

关键词： Band-pass filters Microwave measurement Power transmission lines Prototypes Transmission line measurements Microwave theory and techniques Topology Microwave filters Wideband Testing

来源：评论

学校读者我要写书评

暂无评论

Photonic Neuromorphic Accelerator Combined with an Event-Based Neuromorphic Camera for High-Speed Object Classification

Photonic Neuromorphic Accelerator Combined with an Event-Bas...

引用

2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

作者： Tsirigotis, Aris Tsilikas, Ioannis Sozos, Kostas Bogris, Adonis Mesaritakis, Charis University of the Aegean Dept. Information and Communication Systems Engineering Palama 2 str. Karlovasi Samos83200 Greece National Technical University of Athens Dept. Applied Physics and Mathematics Iroon Polytechniou 9 Zografou Athens15772 Greece University of West Attica Dept. Informatics and Computer Engineering Ag. Spiridonos Egaleo12243 Greece

ISBN: (纸本)9798350345995

In this work, we demonstrate the impact of an unconventional convolutional photonic accelerator, based on an optical spectrum slicing (OSS) [1], on the classification accuracy of objects, generated through a high-frame rate neuromorphic event-based camera [2]. The experimental setup is depicted in Fig.1a. Ιt consists of a 5 mW-632 nm-LED source, two objective lenses with NA=0.65 that concentrate the light beam into a 100 μmX100 μm channel. In our experiments, the targeted objects consist of test spheres, of different diameters (12, 16, and 20 μm), used in aqua solutions. A pump regulated the sphere's speed to 0.8 m/s. The objects were recorded by a 10 kframe/s capable neuromorphic camera, with a temporal resolution of 1 μs. The camera detects pixel's contrast changes (events), similar to biological systems [2]. The recorded events were exported into 1 kframes/sec videos through a synthetic frame generator software, resulting to 2988 images per particle [2]. Images were post-processed using only noise reduction by frame subtraction and image cropping so as to reduce data volume to 100 x 100 pixels. © 2023 IEEE.

关键词： Cameras

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：