检索结果-内蒙古大学图书馆

Frontiers of Information technology (FIT)

作者： Danyaal Mahmood Usama Arshad Raja Hashim Ali Zain Ul Abideen Muhammad Huzaifa Shah Talha Ali Khan Ali Zeeshan Ijaz Nisar Ali Abu Bakar Siddique Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain Faculty of Electronic Systems Engineering University of Regina Regina Canada

The advent of deep Q-learning has opened up new possibilities in training autonomous agents to perform intelligently in intricate settings. This research work examines the potential of deep Q-learning in the paradigmatic Snake game, which requires an agent to navigate a grid, ingest food items, and avoid collisions. We incorporated a partially observable game state, introducing a novel level of difficulty to the task. Our proposed approach utilizes a straightforward feed-forward neural network to estimate Q-values of potential actions, given the current state. The agent progressively learns to balance between exploration and exploitation, allowing it to navigate optimally in the game scenario. Most existing studies in deep Q-learning for the Snake game overlook the complexities posed by partial observability, focusing mainly on fully observable state representations. Furthermore, the majority of the investigations delve into the efficacy of complex neural network architectures, leaving a gap in the understanding of the performance of more simplistic feed-forward networks. Our study fills this gap by offering an in-depth exploration and analysis of deep Q-learning strategies, especially when applied to partially observable game states and simple neural networks. Simulations and results reveal that adopting simpler state representations can significantly boost the agent’s performance in the Snake game. A more detailed and intricate reward function is also observed to enhance the agent’s decision-making skills and overall proficiency in the game. These observations underscore the significance of optimizing state representations and reward functions for maximizing the performance of deep Q-learning agents in the Snake game.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bipolar Operation Scheme of Modular Multilevel DC-DC Converter (MMDC) for Resilient MVDC Distribution Systems 1

Bipolar Operation Scheme of Modular Multilevel DC-DC Convert...

引用

1st IEEE International Power electronics and Application Symposium, PEAS 2021

作者： Zhao, Shanshan Cui, Shenghui Hu, Jingxin Chen, Yu Huazhong University of Science And Technology School of Electrical And Electronic Engineering Wuhan China Seoul National University Department of Electrical And Computer Engineering Seoul Korea Republic of RWTH Aachen University Faculty of Electrical Engineering And Information Technology Aachen Germany

ISBN: (纸本)9781665413596

The modular multilevel DC-DC converter (MMDC) is a promising solution for the interconnection of MVDC distribution systems with LVDC ports. Due to the symmetric structure and operation scheme, the MMDC is normally only capable of operating with monopole MVDC distribution systems. This paper proposes a bipolar operation scheme of the MMDC. Based on the concept of the flux dc-bias cancellation, a center-tapped high-frequency interface transformer is employed on the MV side of the MMDC. A dedicated operation method is proposed, whereby the power flows of the two MVDC poles can be manipulated independently with a simple control scheme. Compared to the conventional MMDC with monopole operation, no additional component is required and no penalty of increased current rating is imposed on the semiconductor devices or the interface transformer. Moreover, a single-pole operation is also possible with the proposed operation scheme. If the valves of one pole are faulty, it can be isolated from the main converter for maintenance while the MMDC can continue operation without interruption and deliver at least 50% of the rated power capacity. Hence, the reliability and availability of the power delivery can be significantly enhanced. The validity of the proposed bipolar operation scheme of the MMDC has been verified by both simulations and experiments with a down-scale prototype. © 2021 IEEE.

关键词： Poles

来源：评论

学校读者我要写书评

暂无评论

A 60 GHz and 2.08 mW Active Quasi-Circulator in 22 nm FDSOI technology

A 60 GHz and 2.08 mW Active Quasi-Circulator in 22 nm FDSOI ...

引用

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： Sujan Chowdhury Arindom Chakraborty Upal barna Joy Abrar Fahim Muhtasim Alam Chowdhury Mehedi Hasan Faculty of Electrical and Computer Engineering Technical University of Dresden Dresden Germany Depertment of Electrical and Electronic Engineering University of Science and Technology Chittagong Chattogram Bangladesh Depertment of Electrical and Computer Engineering New York University New York USA Depertment of Electrical and Computer Engineering University of Arizona Arizona USA Depertment of Electrical and Computer Engineering University of Maryland College Park Maryland USA

In recent years, circuit design of high-frequency active quasi-circulator for full-duplex wireless systems have attracted wide attention in the area of Microwave and Radio Frequency (RF) circuits. This paper presents the design of an active quasi-circulator intended for operation in the 60 GHz Industrial, Scientific, and Medical (ISM) radio band, employing 22nm FD-SOI technology. The goal is to achieve a low noise figure, superior isolation, and a high-power handling capability, as measured by the 1 dB compression point. The quasi-circulator design incorporates a Wilkinson power divider and low noise amplifier, yielding a noise figure of 7 dB, 18 dBm power handling, 20 dB isolation, and 2.08 mW power consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Region Feature Reformer with Semantic Preservation for Adversarial Android Malware Detection

SSRN

引用

SSRN 2023年

作者： Li, Qian Hu, Qingyuan Wu, Di Qi, Saiyu Qi, Yong Wei, Wei Xiong, Naixue Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an China School of Computer Science and Engineering Xi’an University of Technology Xi’an China Department of Computer Science Georgia State University AtlantaGA30302 United States Wuhan China

With the widespread use of smartphones, Android malware has posed serious threats to their security, making its detection of utmost concern. To combat the evolving Android malware attacks, deep learning-based methods have been successfully developed in practical applications due to their strong generalization and unparalleled flexibility in automatic malware detection. However, recent studies have shown that the highly complex transformations of machine learning models, the general unverifiability caused by compound structures, and the unexplainability of predictions have enabled the attackers to carry out inference of the models, which has led to the creation of adversarial samples. Therefore, recent research has concentrated on the key areas of defense against adversarial attacks such as malicious detection. This paper introduces NetAED, a framework for reactive defenses against malware attacks based on adversarial examples, which neither modifies the deployed classifier nor requires knowledge of the process for crafting adversarial examples. In NetAED, we propose a Random Cross-Region Feature Perturbation mechanism and employ non-linear quantization to alleviate the impact of adversarial examples. We further develop ARNDroid, an Android malware detection system against adversarial examples, which integrates the proposed NetAED. This method is a general training paradigm agnostic to model architecture and data modality. Therefore, it could be applied to any deep learning-based solutions for model reliability and protection in cyber-security domain. Promising experimental results based on real-world datasets demonstrate that ARNDroid typically provides superior classification performance and robustness to white-box attacks compared with state-of-the-art approaches. In all, we do believe that our method is applicable to a wide range of cyber-security scenarios and can provide reliability and robustness in AI-based Cybersecurity Solutions. © 2023, The Authors. All ri

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Glasses Influence on the Eyes Exposed to 2.45 GHz Electromagnetic Radiation 15

Glasses Influence on the Eyes Exposed to 2.45 GHz Electromag...

引用

15th International Conference on Advanced Technologies, Systems and Services in Telecommunications, TELSIKS 2021

作者： Jovanovic, Dragana B. Jovanovic, Dejan B. Stankovic, Vladimir B. Zivaljevic, Dragana U. Cvetkovic, Nenad N. Vuckovic, Dragan D. Hederic, Zeljko D. University of Niš Faculty of Electronic Engineering Aleksandra Medvedeva 14 Niš18000 Serbia University of Niš Faculty of Electronic Engineering Carnojevicá 10a Niš18000 Serbia Faculty of Electrical Engineering Computer Science and Information Technology J.J. Strossmayer University Osijek Kneza Trpimira 2b Osijek31000 Croatia

ISBN: (纸本)9781665444422

The investigation of the influence of the metal frame spectacles on the electric field and Specific Absorption Rate distribution within the user's eyes exposed to the mobile phone electromagnetic field is presented in the paper. Numerical analysis of electric field distribution and Specific Absorption Rate has been performed when user's eye is exposed to radiation of the mobile phone operating at 2.45 GHz. Numerical solutions are obtained solving the equations of electromagnetic wave propagation. Accordingly, the obtained results are given for biological tissues within user's eyes. The 3D models of human head and human eye and spectacles have been developed. The results obtained for the models with and without glasses have been compared in order to determine the effects of the presence of described glasses on distributions of values of interest. © 2021 IEEE.

关键词： Electromagnetic fields

来源：评论

学校读者我要写书评

暂无评论

Accelerating supersingular isogeny Diffie-Hellman (SIDH) cryptosystem for the security of resource-constrained IoT devices with FPGA

Accelerating supersingular isogeny Diffie-Hellman (SIDH) cry...

引用

electronic engineering (ICEEM), International Conference on

作者： Shaimaa Abo Khadra Nabil A. Ismail Gamal M. Attiya Salah Eldin S. E. Abdulrahman Dept. Mechatronics Engineerng High Institute of Engineering and Technology Al-Mahalla-El-Kobra Egypt Dept. Computer Science & Engineering Faculty of Electronic En. Menoufia University Menouf Egypt

It is imperative to note that post-quantum cryptography, such as supersingular isogeny Diffie-Hellman (SIDH), is essential for ensuring that Internet of Things (IoT) devices have a restricted amount of resources. The primary challenges in assuring the security of IoT devices are addressed by this work's analysis of SIDH implementations designed for field programmable gate array (FPGA) architecture. Extensive efforts towards implementing the architecture for a rapid and constant-time FPGA implementation of SIDH. This quantum-resistant cryptographic primitive is a crucial component for adhering to NIST's PQC standardization. Our goal with this paper is to demonstrate how FPGA architectures can enhance the parallelism of SIDH, making it a more practical option for securing resource-limited IoT devices. Our focus is on providing a reliable speed record for SIDH, which is crucial for ensuring the security of IoT devices. The design for isogeny computation was built over p434 in Xilinx Virtex 6 and produced 45ms for public key generation in addition to 35ms for secret key generation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TanhR nonlinear companding scheme for UWA systems

引用

International Journal of electronics Letters 2021年第4期9卷 517-523页

作者： Abd El-galil, Menna S. Soliman, Naglaa F. Abdalla, M.I. Elaskily, Mohamed A. Abd El-Samie, Fathi E. Department of Electronics and Communications Faculty of Engineering Zagazig University 44519 Zagazig Egypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman University Riyadh 84428 Saudi Arabia Electronic Research Institute Cairo Egypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt

The basic idea of this letter is concerned with the large Peak-to-Average Power Ratio (PAPR) problem in multi-carrier Under-Water Acoustic (UWA) communication systems that implement Orthogonal Frequency Division Multiplexing (OFDM). A Tangent Rooting (TanhR) companding technique is presented in this paper to reduce the PAPR in UWA communication systems. This technique achieves a noticeable reduction of the PAPR in UWA systems, while maintaining a good Bit Error Rate (BER) performance. Channel equalisation with Linear Minimum Mean Square Error (LMMSE) and Zero-Forcing (ZF) equalisers is considered in this paper. Simulation results ensure superiority of the proposed technique compared to the Selected Mapping (SLM) and the Partial Transmit Sequence (PTS) techniques from both the PAPR and BER perspectives. © 2020 Informa UK Limited, trading as Taylor & Francis Group.

关键词： equalisation OFDM PAPR Underwater acoustic communication (UWA)

来源：评论

学校读者我要写书评

暂无评论

Compact 2-Way Power Divider for IoT Application 5

Compact 2-Way Power Divider for IoT Application

引用

5th International Conference on electronic Design, ICED 2020

作者： Masrakin, Khuzairi Zulkepli, Muhammad Ikram Ibrahim, Siti Zuraidah Rahim, Hasliza A. Dewani, Aliya A. Karim, M.N.A. School of Computer and Communication Engineering Universiti Malaysia Perlis Perlis Malaysia Centre for Wireless Monitoring and Applications School of Electrical Engineering Griffith University Brisbane Australia Department of Electronic Engineering Technology Faculty of Engineering Technology Universiti Malaysia Perlis Perlis Malaysia

The utilization of power dividers covers a vast range of applications such as the Internet of Things (IoT). For this purpose, the need for having a robust and ergonomic electronic device is crucial. Bulky size could barely integrate onto the human body due to its weight that could be very difficult to implement. Hence, this paper presents the design of a compact power divider for IoT applications. It was designed on a substrate Rogers 4350B, ϵr=3.48, tan δ= 0.0037 and h=0.17mm. The design was meant to be operated at 2.4GHz frequency with the output of equally 3dB power division on the output port. Wilkinson design was implemented to perform the design of power divider which will be simulated using computer Simulation technology (CST) microwave studio simulation tools. Parameter sweep was done to its width of transmission line at 0.21mm and 0.31mm to optimize the performance of the design. The simulated result was then compared against measured results in which S-parameter was evaluated in terms of input return loss, isolation and power division. Simulated and measured results showed that 0.21mm width of the transmission line performs better as compared to 0.31mm width of the transmission line. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Trading Model for Stock Price Forecasting Integrating Forester with Golden Ratio Strategy

Algorithmic Trading Model for Stock Price Forecasting Integr...

引用

IEEE Region 10 Humanitarian technology Conference (R10-HTC)

作者： Niranjana Govindan Bharathi Baskaran Azizul Azizan Fitri Yakub Inge Dhamanti C Dhaya Department of Computing Technologies Faculty of Engineering & Technology SRMIST Kattankulathur Chennai India Cyberphysical Research Group (Embedded AI & ML Science Lab) Faculty of Intelligence UTM Kuala Lumpur Malaysia Electronic System Engineering Department Malaysia-Japan International Institute of Technology UTM Kuala Lumpur Malaysia Department of Health Policy and Administration Faculty of Public Health Universitas Airlangga Surabaya Indonesia Department of Computer Science and Technology Adhiparasakthi Engineering College Melmaruvathur India

ISBN: (数字)9798350340204

ISBN: (纸本)9798350340211

Algorithmic trading has emerged as a powerful tool for making data-driven trading decisions in financial markets. In this paper, we present an innovative algorithmic trading model for stock price forecasting that integrates forest-based machine learning algorithms with the Golden Ratio strategy. Our proposed approach aims to leverage the predictive power of machine learning while incorporating insights from technical analysis to enhance trading performance and profitability. The methodology involves data collection and preprocessing, feature engineering, model development, and performance evaluation. Historical stock price data, financial indicators, and sentiment analysis data are gathered and pre-processed to ensure data quality. Feature engineering techniques are applied to extract relevant features, and forest-based machine learning algorithms are trained on the data to forecast stock prices. The Golden Ratio strategy is integrated into the trading model to identify the entry point and exit point. Empirical validation and performance evaluation demonstrate the effectiveness and robustness of the proposed approach. Through back testing and simulation-based testing, we evaluate the model's accuracy, profitability, and risk-adjusted returns. Our findings contribute to the advancement of algorithmic trading research and practice, offering insights into the potential benefits of combining machine learning algorithms with established trading strategies. The proposed hybrid model incorporates Golden Ratio Strategy, integrating Random Forest (RF). The results of the proposed random forest with Golden Ratio Strategy are compared with the results of individual model. This comparison helps in proving the efficiency of the proposed model.

关键词： Adaptation models Machine learning algorithms Soft sensors Forestry Reinforcement learning Predictive models Feature extraction Data models Forecasting Testing

来源：评论

学校读者我要写书评

暂无评论

Bayesian Optimized Supervised Learning for Short-Term Net Load Forecasting in Distribution Grids with Net-Metering

Bayesian Optimized Supervised Learning for Short-Term Net Lo...

引用

Australasian Universities Power engineering Conference, AUPEC

作者： Abdul Haseeb Shahid Nawaz Khan Naveed Arshad Muhammad Waseem Md. Rabiul Islam Md. Jahangir Hossain Shuvra Prokash Biswas Department of Computer Science Lahore University of Management Sciences Lahore Pakistan Department of Electronic Engineering Maynooth University Kildare Ireland School of Electrical Computer and Telecom Engineering University of Wollongong Keiraville NSW Australia School of Electrical and Data Engineering University of Technology Sydney Ultimo NSW Australia Faculty of Engineering and Information Sciences University of Wollongong Wollongong NSW Australia

ISBN: (数字)9798350377941

ISBN: (纸本)9798350377958

As power systems evolve into more intelligent, flexible, and interactive networks with a higher penetration of Renewable Energy Sources (RES) on the demand side, net load forecasting has become a cost-effective and essential technique for planning, stability, and reliability of modern power grids. This study explores both direct and indirect methodologies for short-term net load forecasting (STNLF) in distribution grids considering solar net-metering using deep learning (DL) and machine learning (ML) techniques. The proposed models begin with feature engineering and filtering using Pearson Correlation and Mutual Information (MI) indices, followed by developing a forecasting models employing a Bayesian Optimized Long Short-Term Memory (BO-LSTM) network and Bayesian Optimized Random Forest (BO-RF). The model’s effectiveness was validated using historical net load data from the Lahore Electric Supply Company (LESCO) spanning January 2022 to January 2024, as LESCO has the highest number of net-metering customers among all Distribution Companies (DISCOS) in Pakistan. Results demonstrate the BO-RF model’s capability to deliver accurate and robust STNLF, achieving a Mean Absolute Percentage Error (MAPE) of $\mathbf{3. 5 6 \%}$ for the test data and $\mathbf{2. 2 1 \%}$ for the train data. This study also compares the efficiency of indirect and direct methods for STNLF, demonstrating that the indirect method generally performs better than direct method in distribution grids.

关键词： Radio frequency Correlation Load forecasting Predictive models Power system stability Data models Bayes methods Forecasting Long short term memory Load modeling

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：