检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Freirich, Dror Weinberger, Nir Meir, Ron Viterbi Faculty of Electrical and Computer Engineering Technion - Israel Institute of Technology

Whenever inspected by humans, reconstructed signals should not be distinguished from real ones. Typically, such a high perceptual quality comes at the price of high reconstruction error, and vice versa. We study this distortion-perception (DP) tradeoff over finite-alphabet channels, for the Wasserstein-1 distance induced by a general metric as the perception index, and an arbitrary distortion matrix. Under this setting, we show that computing the DP function and the optimal reconstructions is equivalent to solving a set of linear programming problems. We provide a structural characterization of the DP tradeoff, where the DP function is piecewise linear in the perception index. We further derive a closed-form expression for the case of binary sources. Copyright © 2024, The Authors. All rights reserved.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Keylogger Detection Systems Using Recurrent Neural Networks Enabled with Feature Selection Model 7th

An Enhanced Keylogger Detection Systems Using Recurrent Neur...

引用

7th International Conference on Communication, Device and Networking, ICCDN 2024

作者： Awotunde, Joseph Bamidele Sur, Samarendra Nath Imoize, Agbotiname Lucky Rodríguez, Demóstenes Zegarra Akanji, Boluwatife Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara State Ilorin240003 Nigeria Department of Electronics and Communication Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos 100213 Nigeria Department of Electrical Engineering and Information Technology Institute of Digital Communication Ruhr University Bochum44801 Germany Department of Computer Science Federal University of Lavras Minas Gerais Lavras Brazil

ISBN: (纸本)9789819764648

Keyloggers are malicious software programs that record keystrokes of users without their consent or knowledge. They can steal sensitive information like credit card numbers and passwords. They pose a significant threat to users’ privacy and security since they capture keystroke data. Keylogger detection systems play a vital role in safeguarding users from cyberattacks and mitigating the potential harm caused by keyloggers. Keylogger detection systems employing deep learning have been widely used for identifying and mitigating cyber threats associated with keyloggers. However, they struggle to identify new or unfamiliar keylogger samples. This study aims to explore deep learning techniques with feature selection model to detect keylogger. This study employs Recurrent Neural Networks (RNNs) using a collection of known keylogger dataset. Furthermore, a correlation-based feature extraction method was applied to identify the most relevant features for the model, highlighting the importance of specific features, such as URG flag Count, ACK flag count, and Idle Mean, in differentiating between benign and keylog classes. The proposed model demonstrates superior accuracy of 0.8763 and precision of 0.8569 compared to a baseline model using Logistic Regression (LR) 0.7721 and 0.7407, respectively, indicating a better balance between accurate classification and minimizing false negatives and false positives. The findings from this study help to improve keylogger detection methods, making them more powerful and efficient. These results suggest that a keylogger-based detection system employing a deep learning approach can be a valuable tool for addressing the complex and evolving landscape of cyber threats related to keylogging. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Feature Extraction Approach for Ethiopian Coffee Beans Variant Identification

An Ensemble Feature Extraction Approach for Ethiopian Coffee...

引用

2024 International Conference on Information and Communication technology for Development for Africa, ICT4DA 2024

作者： Tesfaye, Wakjira Fikirie, Tenagne Assosa University Assosa Ethiopia Bahir Dar University Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology P.O.Box 26 Bahir Dar Ethiopia

ISBN: (纸本)9798331527792

Ethiopia's primary export is coffee, which contributes significantly to the country's foreign exchange earnings. In Ethiopia, there are numerous types of coffee beans. Based on their respective geographic origins, these beans differ from one another in terms of quality, color, shape, and other characteristics. These coffee beans are categorized based on where they were grown. However, visual inspection, which is subjective, time-consuming, and prone to error, is used to categorize coffee beans. The goal of this research is to create a suitable system that categorizes various Ethiopian coffee varietals according to the location where they were grown. Six coffee-growing regions provided sample coffees (Harar, Jimma, Limu, Sidama, Yirgachafe, and Wombera). To reduce environmental influences and eliminate variance, an Epson L360 scanner was used to capture input images. 100 images were taken from each region. The total number of images taken was 600, which contained 12604 coffee beans. Out of the total data sets, 75% were used for training and 25% for testing to assess the classification accuracy. Morphological operations and marker-based watershed algorithms were used to segment coffee beans even if they were mutually touched. This research extracted sixty-four Convolutional neural network (CNN) features, five morphological features and five Gray-Level Co-occurrence Matrix (GLCM) features from each coffee bean for the classification process. K-nearest neighbor (KNN) and Support Vector Machine (SVM) classifiers have been evaluated on the extracted feature. The experimental result showed that SVM gave (90.16%) better classification accuracy. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Geometrical Bounds on the Capacity of the Binary Bipolar Input AWGN Channel

Geometrical Bounds on the Capacity of the Binary Bipolar Inp...

引用

IEEE International Conference on Microwaves, Communications, Antennas and Electronic Systems, COMCAS

作者： Michael Peleg Shlomo Shamai Viterbi Faculty of Electrical and Computer Engineering Technion-Israel Institute of Technology

ISBN: (数字)9798350348187

ISBN: (纸本)9798350348194

We study power-effective communication systems over band-limited Additive White Gaussian Noise channels in which the transmitter's output is constrained to be symmetric binary (bipolar) or peak-limited. New geometrical analysis is introduced, and the admissible band-limited signals are shown to form a convex set. We improved the previous upper and lower bounds on capacity, the gap between the upper and lower bounds on capacity at high SNR is reduced to 1.7dB. New attributes of the optimal signals are derived, mainly the central role of binary signals with sign transition rate not exceeding the Nyquist rate of the channel. The results rely on an extensive numerical evaluation and would benefit from further analytical progress.

关键词： Microwave antennas AWGN channels Upper bound Microwave communication Signal to noise ratio Biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of Praseodymium Doped Fiber Amplifiers

引用

computers, Materials & Continua 2022年第12期73卷 5411-5422页

作者： Abdullah G.Alharbi Jawad Mirza Mehak Raza Salman Ghafoor Department of Electrical Engineering Faculty of EngineeringJouf UniversitySakaka42421Saudi Arabia SEECS Photonics Research Group Islamabad44000Pakistan Institute of Space Technology Islamabad44000Pakistan School of Electrical Engineering and Computer Science(SEECS) National University of Sciences and Technology(NUST)Islamabad44000Pakistan

In this paper,we report a simulation study on the performance enhancement of Praseodymium doped silica fiber amplifiers(PDFAs)in O-band(1270-1350 nm)in terms of small signal gain,power conversion efficiency(PCE),and output optical power by employing bidirectional *** PDFA performance is examined by optimizing the length of Praseodymium doped silica fiber(PDF),its mode-field diameter(MFD)and the concentration of Pr^(3+).A small-signal peak gain of 56.4 dB,power conversion efficiency(PCE)of 47%,and output optical power of around 1.6 W(32 dBm)is observed at optimized parameters for input signal wavelength of 1310 *** noise figure(NF)of 4.1 dB is observed at input signal wavelength of 1310 ***,the effect of varying the pump wavelength and pump power on output optical power of the amplifier and amplified spontaneous emission(ASE)noise is also investigated,***,the impact of ion-ion interaction(up-conversion effect)on small-signal gain of the amplifier is also studied by considering different values of up-conversion coefficient.

关键词： Praseodymium-doped fiber doped fiber amplifiers optical amplification mode field diameter noise figure

来源：评论

学校读者我要写书评

暂无评论

Coding-Based Hybrid Post-Quantum Cryptosystem for Non-Uniform Information

Coding-Based Hybrid Post-Quantum Cryptosystem for Non-Unifor...

引用

IEEE International Symposium on Information Theory

作者： Saar Tarnopolsky Alejandro Cohen Faculty of Electrical and Computer Engineering Technion - Institute of Technology Haifa Israel

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

We introduce for non-uniform messages a novel hybrid universal network coding cryptosystem (NU-HUNCC) in the finite blocklength regime that provides Post-Quantum (PQ) security at high communication rates. Recently, hybrid cryptosystems offered PQ security by premixing the data using secure coding schemes and encrypting only a small portion of it, assuming the data is uniformly distributed. An assumption that is often challenging to enforce. Standard fixed-length lossless source coding and compression schemes guarantee a uniform output in normalized divergence. Yet, this is not sufficient to guarantee security. We consider an efficient almost uniform compression scheme in non-normalized variational distance for the proposed hybrid cryptosystem, that by utilizing a uniform sub-linear shared seed, guarantees PQ security. Specifically, for the proposed PQ cryptosystem, first, we provide an end-to-end coding scheme, NU-HUNCC, for non-uniform messages. Second, we show that NU-HUNCC is information-theoretic individually secured (IS) against an eavesdropper with access to any subset of the links. Third, we introduce a modified security definition, individually semantically secure under a chosen ciphertext attack (ISS-CCA1), and show that against an all-observing eavesdrop-per, NU-HUNCC satisfies its conditions. Finally, we provide an analysis that shows the high communication rate of NU-HUNCC and the negligibility of the shared seed size.

关键词： Source coding Distributed databases Network coding Cryptography Standards

来源：评论

学校读者我要写书评

暂无评论

Underwater visible light communication: recent advancements and channel modeling

引用

Optical and Quantum Electronics 2024年第10期56卷 1-45页

作者： Elfikky, Abdelrahman Boghdady, Ayman I. Mumtaz, Sajid Elsayed, Ebrahim E. Singh, Mehtab Abd El-Mottaleb, Somia A. Mohsan, Syed Agha Hassnain Aly, Moustafa H. Electrical and Computer Engineering Department Baskin School of Engineering University of California Santa Cruz United States Arab Academy for Science Technology and Maritime Transport Alexandria1029 Egypt Institute of Nano Optoelectronics Research and Technology Universiti Sains Malaysia Pulau Malaysia Department of Electronics and Communications Engineering Faculty of Engineering Mansoura University Mansoura Egypt Department of Electronics and Communication Engineering University Institute of Engineering Chandigarh University Punjab Mohali India Alexandria Higher Institute of Engineering and Technology Alexandria Egypt Ocean College Zhejiang University Hangzhou China

Underwater Visible Light Communication (UVLC) is a promising technology for high-speed data transmission in aquatic environments. However, the performance and reliability of UVLC systems are often challenged by factors such as absorption, scattering, and oceanic turbulence. In this paper, we explore various UVLC modulation techniques, analyzing both Single Carrier Modulation and Multi-Carrier Modulation schemes, including their respective advantages and limitations. Through simulations and experimental evaluations, we investigate the effectiveness of modulation strategies such as Non-Return-to-Zero On-Off Keying, Pulse Position Modulation, and Quadrature Amplitude Modulation-Carrierless Amplitude Phase Modulation in addressing the inherent challenges of UVLC. Additionally, we examine advanced techniques like Orthogonal Frequency Division Multiplexing and space-domain index modulation, highlighting their potential to achieve higher data rates and improved reliability in UVLC systems. Our findings underscore the importance of selecting optimal modulation schemes to enhance spectral efficiency, reduce interference, and improve Bit Error Rate performance. Recent experimental advancements have showcased remarkable achievements, such as data rates exceeding 30 Gbps over distances up to 21 m, demonstrating significant progress in system reliability and transmission quality. This paper also identifies potential challenges and open research directions in UVLC, such as the need for efficient channel estimation and system configuration algorithms, contributing to the design and optimization of robust and scalable underwater communication systems. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network

arXiv

引用

arXiv 2024年

作者： Dissen, Yehoshua Yonash, Shiry Cohen, Israel Keshet, Joseph Faculty of Electrical and Computer Engineering Technion – Israel Institute of Technology Israel

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced. This study is focused on recovering from packet loss to improve the word error rate (WER) of ASR models. We propose using a front-end adaptation network connected to a frozen ASR model. The adaptation network is trained to modify the corrupted input spectrum by minimizing the criteria of the ASR model in addition to an enhancement loss function. Our experiments demonstrate that the adaptation network, trained on Whisper’s criteria, notably reduces word error rates across domains and languages in packet-loss scenarios. This improvement is achieved with minimal affect to Whisper model’s foundational performance, underscoring our method’s practicality and potential in enhancing ASR models in challenging acoustic environments. © 2024, CC BY.

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

Image Acquisition and Deep Convolutional Neural Network Incorporated Cost-Effective Automated Nursery Disease Detection Method for the Tea Industry 10

Image Acquisition and Deep Convolutional Neural Network Inco...

引用

10th International Multidisciplinary engineering Research Conference on Moratuwa engineering Research, MERCon 2024

作者： Weerasekara, Dinithi Bhagya Kahatapitiya, Nipun Shantha Sanjeewa, Nuwan Wathudura, Vimukthi Madushan Prasanna, Nuwan Kalupahana, Deshan Wijenayake, Udaya Silva, Bhagya Nathali Wijethunge, Akila Wijesinghe, Ruchire Eranga University of Sri Jayewardenepura Faculty of Technology Department of Materials and Mechanical Technology Pitipana Sri Lanka University of Sri Jayewardenepura Faculty of Engineering Department of Computer Engineering Nugegoda Sri Lanka IOT Solutions Pvt Ltd Homagama Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Department of Information Technology Malabe Sri Lanka Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Engineering Department of Electrical and Electronic Engineering Malabe Sri Lanka

ISBN: (纸本)9798331529048

Tea cultivation, a globally significant industry across over 60 countries, requires effective management of tea nurseries for robust plant growth and disease control. Implementing automated disease detection in tea nurseries using advanced technologies enhances efficiency, precision, and sustainability compared to manual inspection methods. An image acquisition system incorporating a Deep Convolutional Neural Network (DCNN) was developed as a cost-effective automated solution for nursery disease detection. First, images of Blister Blight (BB) disease in tea plants were collected primarily from various estates. These images were then preprocessed, labeled, and augmented to create a robust dataset. Two models based on the YOLOv5 architecture were trained, with the second model benefiting from dataset augmentation and enhanced labeling. The Improved Model achieved a mean Average Precision (mAP) of 80.6% at a 0.5 threshold, demonstrating its high accuracy in BB detection in tea nurseries. It was integrated with the image acquisition system to enable continuous monitoring of tea leaves in nursery plantations and facilitate the immediate detection of BB diseases. This system holds significant potential for further enhancement in disease management across the tea industry, promoting healthier crops, reducing costs, and minimizing environmental impact. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic-Driven Agentic AI for Autonomous Decision-Making Systems 4

Neuromorphic-Driven Agentic AI for Autonomous Decision-Makin...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Manjunath Kamath, K. Samata Mehta, S. Akshaya, H.L. Shilpashree, N. Jadhav, Girish Mitra, Abhijit Department of Cyber Security Karkala India Bengaluru India Sarada Vilas College Department of Computer Science Mysuru India Parul institute of Engineering and Technology Parul University Faculty of Engineering and Technology Department Of Electrical Engineering Post Limda India Pune India

ISBN: (纸本)9798350352931

Agentic AI represents a paradigm shift in the development of intelligent systems capable of adaptive and proactive interactions in dynamic and complex environments. By integrating reinforcement learning (RL) with cognitive frameworks, Agentic AI goes beyond traditional rule-based and reactive models, enabling autonomous systems to make informed decisions, anticipate future states, and learn from experience. This paper explores the theoretical foundations and practical applications of Agentic AI, highlighting its potential to transform a variety of fields, including robotics, autonomous driving, finance, and healthcare. Through a detailed review of state-of-the-art research, we illustrate how cognitive architectures such as ACT-R and Soar, combined with advanced RL techniques like Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO), contribute to the development of AI agents with human-like reasoning and decision-making capabilities. Experimental results demonstrate that Agentic AI significantly outperforms conventional AI approaches in terms of adaptability, learning efficiency, and decision accuracy. The findings suggest that Agentic AI offers a robust framework for creating intelligent systems capable of complex problem-solving, long-term planning, and proactive behavior, paving the way for the next generation of AI-driven applications. © 2024 IEEE.

关键词： Intelligent systems

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：