检索结果-内蒙古大学图书馆

Low-cost Smart Glasses for People with Visual Impairments 1

Low-cost Smart Glasses for People with Visual Impairments

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Nayana, B.R. Raju N R, Yogesh Velidi, Abhav S M S Ramaiah Univesrity of Applied Sciences Dept. of Computer Science Engineering Karnataka Bangalore India Sir M Visvesvaraya Institute of Technology Dept. of Electrical and Electronics Engineering Karnataka Bangalore India National Institute of Technology Dept. of Electronics and Commuincation Engineering Suratkal Karnataka India

ISBN: (纸本)9798350348057

An efficient visual aid is essential for visually impaired candidate. At the same instance it has to be simple, robust and cost effective. However, regardless of being expensive, it is challenging to incorporate high end artificial intelligence into a compact device to serve the purpose. This paper presents a prototype of low-cost smart glasses for visually impaired individuals. Also, a brief survey on the cost and features of the goggles available in the market are included. In this work a prototype is developed integrating Raspberry Pi module, camera, sensors and a goggles. The captured images are processed using object recognition models and its corresponding text is read aloud using google text to translator. Subsequently, a comparative analysis of object recognition model is explored and discussed. Essential experimental results are incorporated along with cost involved for the prototype development. © 2023 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Messenger Phishing Detection Using Heterogeneous Phishing Data

Improving Messenger Phishing Detection Using Heterogeneous P...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Seokjin Oh Keonwoong Noh Sunyub Kim Dohyung An Woohwan Jung Dept. of Applied Artificial Intelligence Hanyang University Seoul Republic of Korea Dept. of Computer Science Hanyang University Ansan Republic of Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

Recently, as messenger phishing has been occurring more frequently, the need for its detection has increased; however, datasets for messenger phishing detection are publicly unavailable. In this paper, we address the data scarcity problem of the newly collected messenger phishing dataset by leveraging various types of pre-existing auxiliary phishing data. Experimental results demonstrate that the error rate decreased by up to 1.81 % and the F1 score improved by 7.35% when smishing and voice phishing data are used. These findings confirm that integrating heterogeneous phishing data can mitigate the data scarcity problem and enhance messenger phishing detection performance.

关键词： Error analysis Phishing Message services Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Messenger Phishing Detection Using Large Language Models

Data Augmentation for Messenger Phishing Detection Using Lar...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Keonwoong Noh Seokjin Oh Sunyub Kim Dohyung An Woohwan Jung Dept. of Applied Artificial Intelligence Hanyang University Seoul Republic of Korea Dept. of Computer Science Hanyang University Ansan Republic of Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

In this study, we introduce a new dataset specifically designed for detecting messenger phishing, an increasingly significant issue in cybercrime. To overcome the scarcity of labeled phishing data, we employ large language models (LLMs) to generate synthetic data, thereby expanding the dataset and improving detection capabilities. Our experimental results show that a model trained exclusively on synthetic data performs comparably to those trained with labeled data. Furthermore, combining synthetic data with labeled data achieves superior F1 and accuracy scores compared to using labeled data only while reducing misclassification errors.

关键词： Training Accuracy Phishing Large language models Data augmentation Data models computer crime Synthetic data

来源：评论

学校读者我要写书评

暂无评论

On Securing Sensitive Data Using Deep Convolutional Autoencoders

On Securing Sensitive Data Using Deep Convolutional Autoenco...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Abib Sy Fehmi Jaafar Kevin Bouchard Dept. of Math and Computer Science Université du Québec à Chicoutimi Quebec Canada

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

There are various traditional methods used for securing sensitive data, such as cryptography algorithms like AES-HMAC-SHA256, Twofish, and Chacha20. However, several studies showed that these cryptography algorithms suffer from security vulnerabilities. In this paper, we explore the use of a cryptography model based on a Deep Convolutional Autoencoder and we compare its performances to the cryptography algorithms. We report the results of a comparative study based on several metrics. We incorporate more nuanced metrics such as cosine similarity, entropy, Kendall and Spearman rate, and Mean Squared Error (MSE) for a comprehensive assessment of model performance and security, in addition to encryption and decryption time *** results obtained are very promising. Our model performs the best on two essential metrics, entropy and MSE. We obtain a decrypted file entropy of 8.01, compared to 7.99 for the three other standard models, with a very low MSE of 0.003, compared to 105.43 for AES, which remains the most efficient compared to the other algorithms.

关键词： Measurement Surveillance Data protection Entropy Data models Encryption Protection Information technology Standards Smart spaces

来源：评论

学校读者我要写书评

暂无评论

Efficient Trajectory Inference in Wasserstein Space Using Consecutive Averaging

arXiv

引用

arXiv 2024年

作者： Banerjee, Amartya Lee, Harlin Sharon, Nir Moosmüller, Caroline Dept. of Computer Science UNC Chapel Hill United States SDSS UNC Chapel Hill United States Dept. of Applied Math Tel Aviv University Dept. of Mathematics UNC Chapel Hill United States

Capturing data from dynamic processes through cross-sectional measurements is seen in many fields, such as computational biology. Trajectory inference deals with the challenge of reconstructing continuous processes from such observations. In this work, we propose methods for B-spline approximation and interpolation of point clouds through consecutive averaging that is intrinsic to the Wasserstein space. Combining subdivision schemes with optimal transport-based geodesic, our methods carry out trajectory inference at a chosen level of precision and smoothness, and can automatically handle scenarios where particles undergo division over time. We prove linear convergence rates and rigorously evaluate our method on cell data characterized by bifurcations, merges, and trajectory splitting scenarios like supercells, comparing its performance against state-of-the-art trajectory inference and interpolation methods. The results not only underscore the effectiveness of our method in inferring trajectories but also highlight the benefit of performing interpolation and approximation that respect the inherent geometric properties of the data. © 2024, CC BY.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

BERT Goes to SQL School: Improving Automatic Grading of SQL Statements

BERT Goes to SQL School: Improving Automatic Grading of SQL ...

引用

computer science, computer Engineering, & applied Computing (CSCE), Congress in

作者： Pablo Rivas Donald R. Schwartz Ernesto Quevedo Dept. of Computer Science School of Eng. & Computer Science Baylor University Dept. of Computing Technology School of Computer Science & Math. Marist College

Automated grading of SQL queries is a challenging task due to the complexity of the language and the variety of acceptable solutions for a given problem. In this paper, we propose a novel approach that leverages deep learning with a BERT model to understand the syntax and semantics of SQL statements. By training BERT on a dataset of SQL queries and their corresponding grades, we create a model that can automatically grade new questions accurately. Our experiments demonstrate that the proposed methodology achieves high accuracy and consistency in grading SQL queries, outperforming existing state-of-the-art models. Furthermore, we provide an analysis of the model's explainability, revealing a new capability that can be extremely beneficial for understanding the decision-making process. Overall, our work demonstrates the potential of deep learning with BERT for improving the efficiency and accuracy of SQL query grading.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Isolation Dual Port MIMO Antenna for Vehicle-to-Vehicle Communication

High Isolation Dual Port MIMO Antenna for Vehicle-to-Vehicle...

引用

2023 IEEE International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2023

作者： Sharma, Preeti Singh, Prabhakar Tiwari, Rakesh N. Kumar, Pradeep Galgotias University Physics Division School of Basic Sciences Greater Noida India Greater Noida Institute of Technology Dept. of Applied Science Greater Noida India Madanapalle Institute of Technology & Science Dept. of Electronics and Communication Engineering Madanapalle India University of KwaZulu-Natal Dept. of Electrical Electronic and Computer Engineering Durban South Africa

ISBN: (纸本)9798350336917

This research paper reports a very thin 2-port multiple-input multiple-output (MIMO) antenna with a small footprint of 14× 10× 0.58mm3. The proposed design works between the frequencies of 8.73 to 15.86 GHz. A modified hexagonal patch is used along with the defected ground plane to obtain wide bandwidth. A conventional decoupling strip technique is utilized to improve the isolation between the ports and it is found >19dB across the whole operating band. In addition to that, 'H'-shaped slot has been incorporated into the grounding plane to enhance impedance matching. The realized gain and radiation patterns of the designed antenna are calculated and found quite acceptable. Furthermore, the diversity parameters of the antenna are computed with envelope correlation coefficient (ECC) 9.97dB across the entire operating frequency range. Finally, the results of MIMO antenna are compared with the calculated data for the purpose of practical validation. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

An adaptive Particle Swarm Optimization to Solve Modern Security System

An adaptive Particle Swarm Optimization to Solve Modern Secu...

引用

Innovative Approaches in Smart Technologies (ISAS), International Symposium on

作者： Mohammed H. Ahmed Asaad Noori Hashim Khalid A. Hussein dept. Computer Science College of Education Mustansiriyah University Baghdad Iraq dept. Computer Science College of Computer Science and Math University of Kufa Najaf Iraq

Nonlinear stream ciphers hold a vital position in ensuring confidentiality within contemporary cryptographic systems. In this context, we interduce a new approach known as the Adaptive Three Sub-Swarm PSO based on Regrouping Strategy (ATSPSO-RG) to enhance the effectiveness of deciphering nonlinear stream ciphers, particularly those based on the Bruer generator system. Our method significantly reduces the complexity of cipher-only attacks, making the extraction of the correct secret key more efficient. The proposed system dividing the population size into three distinct subswarm, each incorporating its evolving strategies, namely the single score, four score, and nine score strategies. In the single score strategy, we employed, the traditional PSO evolving process. In the four scores strategy, we used three additional scores in addition to the single score of the traditional PSO to update the velocity and position of particles. lastly, the nine score strategy employed five scores to update the velocity and position, as well as the four scores of the previous score. To counteract the issue of premature convergence, we employ a regrouping strategy that periodically reinitializes the population. Experimental results vividly demonstrate the success of the ATSPSO-RG method in deciphering the Bruer cipher, even when dealing with a varying number of Linear Feedback Shift Registers (LFSRs) and polynomial degrees, spanning up to 15, and secret initial values extending up to 39. The method proves its efficiency in cryptanalysis, offering a potent solution for nonlinear stream ciphers with substantial key sizes while ensuring a reasonable timeframe for analysis. The research outcomes underscore the efficacy of ATSPSO-RG, highlighting both its accuracy and time efficiency in deciphering nonlinear stream ciphers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Content Based Classification of Short Messages using Recurrent Neural Networks in NLP

Content Based Classification of Short Messages using Recurre...

引用

Artificial Intelligence, computer, Data sciences and Applications (ACDSA), International Conference on

作者： Deepthi Tabitha Bennet Preethi Samantha Bennet Priya Thiagarajan Sundarakantham. K Dept. of Applied Mathematics and Computational Science Thiagarajar College of Engineering Madurai India Dept. of Computer Science and Business Systems Thiagarajar College of Engineering Madurai India Dept. of Computer Science and Engineering Thiagarajar College of Engineering Madurai India

Short message spam poses a significant threat for all mobile phone users, as it can act as an efficient tool for cyberattacks including spreading malware and phishing. Traditional anti-spam measures are only minimally effective against modern spammers. Intelligent analysis of the content to categorise the messages as Spam (unwanted and unsolicited) or Ham (useful messages) is therefore essential to safeguard the user from such attacks. Various artificial intelligence (AI) techniques are proving to be useful in the analysis of the content of such short messages to classify and filter spam. We have trained, validated and tested seven such AI techniques on the SMS spam collection dataset to identify the best model for designing and developing a content based classification system. Recurrent Neural Networks (RNN) have shown the highest performance metrics (Test Accuracy: 99.28%) and hence our proposed system includes a RNN model for classification. A web app of this system has also been deployed where a single SMS can be input and the designed system can classify it as Spam or Ham. The designed system is compared against existing systems and is found to be significantly better.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection Systems for Distributed Denial-of-Service (DDoS) Attack Based on Time Series: A Review

Detection Systems for Distributed Denial-of-Service (DDoS) A...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Ahmed Adil Nafea Mustafa Maad Hamdi Baraa saad Abdulhakeem Ahmed Thair Shakir Mustafa S. Ibrahim Alsumaidaie Ali Muwafaq Shaban dept. Artificail inteligence College of Computer Science and Information Technology University of Anbar Ramadi Iraq dept. of Computer Science College of Computer Science and IT University of Anbar Ramadi Iraq dept. of Information System College of Computer Science and IT University of Anbar Ramadi Iraq dept. of Biophysics College of Applied Sciences University of Anbar Ramadi Iraq dept. Information System College of Computer Science and Information Technology University of Anbar Ramadi Iraq

ISBN: (数字)9798350374131

ISBN: (纸本)9798350374148

The Distributed Denial-of-Service (DDoS) attacks are one of the most critical threats to the stability and security of the Internet. With the increasing number of devices connected to the Internet, the frequency and severity of DDoS attacks are also increasing. To mitigate the impact of DDoS attacks, intelligent detection systems are becoming increasingly important. This paper reviews the recent literature on intelligent techniques, including machine learning (ML), Deep Learning (DL), and artificial intelligence (AI), for detecting DDoS attacks. We will provide an overview of the existing research in the field and analyse the trends in using time series data analysis for DDoS attack detection. A taxonomy and conceptual framework for DDoS mitigation are presented. This study highlights the use of several intelligent techniques for detecting DDoS attacks and evaluates the performance utilizing real datasets and also discusses future research directions in this field.

关键词： Data analysis Reviews Time series analysis Taxonomy Reinforcement learning Denial-of-service attack Stability analysis

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：