检索结果-内蒙古大学图书馆

A Novel Evaluation of Cryptocurrency Future Price Prediction to Manage Fluctuations in Market by using Hybrid Learning Methodology

A Novel Evaluation of Cryptocurrency Future Price Prediction...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Pradeep, D. Divya, G. Rajeshwari, R. Deepa, R. Satyanarayana, T.V.V. M.Kumarasamy College of Engineering Department of CSE Karur India SRM Institute of Science and Technology Kattankulathur Faculty of Engineering and Technology Department of Networking and Communications Chennai India S.A. Engineering College Dept of MCA Chennai India R.M.K. Engineering College Department of Computer Science Engineering Chennai India Department of ECE AP Tirupati India

ISBN: (纸本)9798350319200

In recognition of its optimistic vision on the probable future of cryptocurrencies, the value of cryptocurrency has risen dramatically during the previous eight decades. Cryptocurrency offers significant benefits over the established financial system, and investors have taken notice. Cryptocurrency is unique in that it facilitates decentralized financial services, making it immune to control by large financial institutions. With the rise of electronic currencies like Ethereum (ETH) and BTT, business may be conducted entirely online. One illustration of the distributed structure of physical currencies is the reality that all consumers who use virtual money have utilization of operations without the need for a third-party they can depend on. Like the market fluctuations of traditional stocks, cryptocurrencies fluctuations in price are extremely volatile and non stationary. Traders and academics alike have given increased focus to predictions of bitcoin prices due to the asset class' rising popularity. The use of deep learning in projecting the price of cryptocurrencies has become increasingly important. This research presented a new algorithm for predicting cryptocurrency prices called Hybrid Learning for Crypto Prediction (HLCP), and results from these models demonstrated that the proposed HLCP algorithm outperformed all other methods in this area. The HLCP model offered encouraging and precise predictions for all cryptocurrencies;hence it can be considered the most successful algorithm. The model was used to forecast the 6 month ending prices of cryptocurrency. To measure how well predictions match targets during training and testing, we used the HLCP correlation metric. The proposed method efficiency is evaluated with respect to the following metrics such as training and testing accuracy levels, training and testing loss ratio as well as different cryptocurrencies (ETH, BitCoin and BTT) prediction and actual price comparisons. These metrics clearly shows the effici

关键词： Cryptocurrency Deep Learning HLCP Hybrid Learning for Crypto Prediction Price Prediction Trading

来源：评论

学校读者我要写书评

暂无评论

Design and development of a Synergistic Educational Tool with Hiligaynon-English Recurrent Neural Network Model 12

Design and development of a Synergistic Educational Tool wit...

引用

2023 12th International Conference on Information and Electronics engineering, ICIEE 2023

作者： Siosan, Rosie Jane P. De Castro, Joel T. Byun, Y.C. School of Information and Communications Technology West Visayas State University-Pototan Campus Philippines College of Information and Communications Technology West Visayas State University-Main Campus Philippines Department of Computer Engineering Major of Electronic Engineering Jeju National University Institute of Information Science Technology Jeju63243 Korea Republic of

This project aimed to develop a mobile app tool to teach the Hiligaynon language to elementary pupils, designed with Machine Learning features using the Hiligaynon-Filipino-English Translation RNN Model. The app included games as a pedagogical tool, background music, and incentives to engage learners. The RNN model was developed using Data Science Methodology, while Rapid Agile Development Methodology was used to develop the mobile app for Android operating systems. To assess the app's effectiveness, elementary teachers and IT professionals evaluated its compliance with standards for acceptability. The app was found to be very acceptable, recommended for use in a gamified classroom setting and by parents. Overall, this project promotes technology in language learning to make it more accessible and enjoyable for elementary pupils. © Published under licence by IOP Publishing Ltd.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Unlocking Over-the-Air Efficiency Potential: Epoch-making Approach for Convex Optimization Algorithm-based Microwave Power Transmission Empowered by 256 Elements Antenna Arrays

Unlocking Over-the-Air Efficiency Potential: Epoch-making Ap...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Sanghun Lee Sangwook Nam Jungsuek Oh Department of Electrical and Computer Engineering Institute of New Media and Communications (INMC) Seoul National University Seoul Republic of Korea

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

This paper introduces a Microwave Power Transmission (MPT) system that employs a convex optimization technique for efficient power transfer in a large array antenna. The MPT system, operating at 5.64 GHz, has been fabricated. We designed a 16×16 transmit array antenna, a 5×7 receive array antenna, and a microstrip series power divider. Transmitting circuits are integrated with each antenna element for adjusting phase and amplitude. Additionally, convex optimization is employed to transfer power effectively, maximizing Power Transfer Efficiency (PTE). The received RF power is measured for all antenna elements at various distances, achieving a total RF power of approximately 8.1 W received at a distance of 0.7 meters. The results experimentally validate the proposed MPT system, indicating its coverage in the radiative near-field region and emphasizing its potential for high-power charging in wireless applications.

关键词： Radio frequency Microstrip antenna arrays Wireless networks Transmitting antennas Receiving antennas Power transmission Microwave theory and techniques

来源：评论

学校读者我要写书评

暂无评论

Enhancing Student Performance Prediction with Greylag Goose Optimization Algorithm

Enhancing Student Performance Prediction with Greylag Goose ...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Rizk, Faris H. Mohamed, Mahmoud Elshabrawy Sameh, Basant Zaki, Ahmed Mohamed Eid, Marwa M. El-Kenawy, El-Sayed M. Computer Science and Intelligent Systems Research Center BlacksburgVA24060 United States Delta Higher Institute of Engineering and Technology Department of Communications and Electronics Mansoura35111 Egypt Delta University for Science and Technology Faculty of Artificial Intelligence Mansoura35111 Egypt

ISBN: (纸本)9798350351408

The current paper addresses the central role of hyperparameter optimization in improving the predictive power of the MLP Regressor for forecasting student performance in Portuguese secondary schools. The uniqueness of this research lies in its exploration of metaheuristic optimization algorithms, specifically highlighting GGO (Greylag Goose Optimization) for enhancement. The study utilized a dataset crucial for understanding and predicting student performance, with a special focus on its distinctive features. By comprehensively tuning the MLP Regressor, the paper demonstrates remarkable improvements in various performance measures, as evident in the enclosed tables. Specifically, the MSE values calculated for the MLP Regressor both before and after GGO optimization are compared. Without optimization, the MLP Regressor had an MSE of 0.0103. After GGO optimization, the MSE significantly improved to 0.0060, indicating enhanced accuracy with GGO in the model. These findings emphasize that hyperparameter optimization, particularly the GGO technique, is crucial for refining the MLP Regressor in predicting student performance. The paper not only delves into the technical aspects but also concludes by highlighting the broader consequences of these outcomes. The potential educational applications are substantial, as improved models can provide more accurate predictions, empowering educators and policymakers to make informed decisions in education. This paper establishes a foundation for future research directions, contributing to the pool of ideas for educational predictive modeling. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Leveraging Reinforcement Learning for a Novel Traffic-Aware Scheduler in 5G NR IIoT Networks

Leveraging Reinforcement Learning for a Novel Traffic-Aware ...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio communications (PIMRC)

作者： Luciano Miuccio Salvatore Riolo Giampaolo Cuozzo Riccardo Marini Department of Electrical Electronic and Computer Engineering University of Catania Italy National Laboratory of Wireless Communications (WiLab) CNIT Italy

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

The integration of 5G New Radio (NR) into the manufacturing industry stands as a pivotal aspect of the Industrial Internet of Things (IIoT) paradigm, mitigating constraints posed by traditional wired communication technologies in terms of flexibility, mobility, and adaptability. However, ensuring comparable performance levels presents challenges in the scheduling design of 5G NR networks, particularly due to the emphasis on uplink transmissions within industrial applications. Indeed, current uplink schedulers proposed by the 3rd Generation Partnership Project (3GPP) exhibit performance trade-offs, forcing the network to acquire knowledge of uplink traffic and faltering in the presence of heterogeneous traffic sources, commonplace in industrial environments. In this paper, we thus propose a Reinforcement Learning (RL)-based approach that dynamically assigns users to the most suitable uplink scheduler without prior or acquired knowledge of the different traffic patterns. Through 3GPP-compliant network simulations, we demonstrate the effectiveness of our approach in optimizing network performance while addressing the complexities of heterogeneous IIoT environments and maintaining standard compliance.

关键词： Hands Job shop scheduling Reinforcement learning Traffic control Production facilities 3GPP Uplink Standards Optimization Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Denoising Techniques in Healthcare Data for Improving Accuracy in Medical Applications - A Survey 7

Denoising Techniques in Healthcare Data for Improving Accura...

引用

7th International Conference on Communication and Electronics Systems, ICCES 2022

作者： Karthikram, A. Saravanan, M. Srm Institute of Science and Technology Department of Computer Science and Engineering Chennai Kattankulathur India Srm Institute of Science and Technology Department of Networking and Communications Chennai Kattankulathur India

ISBN: (数字)9781665496346

ISBN: (纸本)9781665496346

Bigdata alludes to a huge assortment of information that keeps on expanding dramatically over the long run. Big data sources in health care incorporate patient medical records, clinic records, clinical test results, and data gathered by medical services testing machines. The main challenge associated with the health care data is the lack of accuracy, medical errors. This can be overcome by using big data so that the health care data can be denoised and accurate data can be obtained. This helps to enhance the efficiency of diagnosis of diseases. This review paper deals with various algorithms and denoising techniques which are used to enhance the accuracy of obtained health care data. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Portuguese Student Performance: Comparative Machine Learning Analysis

Predictive Modeling of Portuguese Student Performance: Compa...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

ISBN: (纸本)9798350351408

Such an analysis of different machine learning methods for predicting the achievement levels of students in Portuguese secondary education makes this essay. The research highlights the importance of accurate expectations of learners' results for education system administrations and respective policymakers. The current study makes use of the 'Student Performance in Portuguese Secondary education' dataset and employs machine learning algorithms, namely MLPRegressor, XGBoost, DecisionTreeRegressor, CatBoost, and KNeighborsRe-gressor, to the corpus. Performance metrics such as mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), etc., are used to judge every model's performance. The conclusion that can be drawn from the data is that the MLPRegressor model leads among the competitors, having an MSE equivalent of 0.0103, which is superior to others. The findings of this study are of great significance for educational institutions and policymakers as they work to make appropriate contact with students' performance prediction. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Multi-Carrier Deep Learning CSK Communication System

引用

IEEE communications Letters 2025年第6期29卷 1191-1195页

作者： Mobini, Majid Kaddoum, Georges Herceg, Marijan Babol Noshirvani University of Technology Department of ECE Babol Iran University of Québec École de technologie supérieure Département de génie électrique MontréalQC Canada Lebanese American University Cyber Security Systems and Applied AI Research Center Beirut Lebanon University of Osijek Faculty of Electrical EngineeringComputer Science and Information Technology Department of Communications Croatia

A new Multi-Carrier Deep Learning Chaos Shift Keying (MC-DLCSK) modulation is designed in this paper. The proposed receiver includes a Neural Network (NN)-based classifier that recovers MC-DLCSK signals. The results demonstrate that the MC-DLCSK system achieves a considerable Bit Error Rate (BER) gain compared to all existing similar systems under both Additive White Gaussian Noise (AWGN) and Rayleigh fading channels. © 1997-2012 IEEE.

关键词： White noise

来源：评论

学校读者我要写书评

暂无评论

Compressed space quantum approximate optimization algorithm for constrained combinatorial optimization

arXiv

引用

arXiv 2024年

作者： Shirai, Tatsuhiko Togawa, Nozomu Waseda Institute for Advanced Study Waseda University Japan Department of Computer Science and Communications Engineering Waseda University Japan

Combinatorial optimization is a promising area for achieving quantum speedup. Quantum approximate optimization algorithm (QAOA) is designed to search for low-energy states of the Ising model, which correspond to near-optimal solutions of combinatorial optimization problems (COPs). However, effectively dealing with constraints of COPs remains a significant challenge. Existing methods, such as tailoring mixing operators, are typically limited to specific constraint types, like one-hot constraints. To address these limitations, we introduce a method for engineering a compressed space that represents the feasible solution space with fewer qubits than the original. Our approach includes a scalable technique for determining the unitary transformation between the compressed and original spaces on gate-based quantum computers. We then propose compressed space QAOA, which seeks near-optimal solutions within this reduced space, while utilizing the Ising model formulated in the original Hilbert space. Experimental results on a quantum simulator demonstrate the effectiveness of our method in solving various constrained COPs. © 2024, CC BY.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Target Range and Velocity Estimation for Joint Radar and communications with Up and Down Chirps

Target Range and Velocity Estimation for Joint Radar and Com...

引用

IEEE International Conference on Radar

作者： Batu K. Chalise Moeness G. Amin Electrical and Computer Engineering Department New York Institute of Technology NY Center for Advanced Communications Villanova University PA

ISBN: (数字)9798350362381

ISBN: (纸本)9798350362398

This paper proposes joint radar and communications scheme based on chirp waveform diversity. A monostatic radar transmits a sequence of alternating up and down chirps to acquire target related information (TRI), while leveraging such waveform diversity to deliver data to another radar. This data can be TRI acquired in previous coherent pulse interval (CPI) or scheduling data, such as radar signal bandwidth, carrier frequency, and waveform parameters. We propose range and velocity estimation of multiple targets using dechirping and discrete Fourier transform (DFT). Given P chirps and N fast time samples, 2N DFTs, each of length $\frac{P}{2}$, are computed over slow time to locate peaks in the corresponding DFT amplitudes. The most frequently occurring peak locations are utilized for estimating target velocities, which, together with most frequently occurring peak locations in 2P DFTs, each of length $\frac{N}{2}$, computed over fast time, are then used for estimating target ranges. When compared to the standard range-Doppler processing, this method reduces computational complexity, and is motivated for improving robustness against noise. computer simulations are used to show the performance of the proposed method in terms of the range and velocity estimation errors versus signal-to-noise ratio (SNR). Simulations show that the proposed method provides better range estimation than the method that uses only up or down chirps, especially when two targets are closely located. These results suggest that alternating up and down chirp-based transmission not only supports data transmission but also improves radar performance.

关键词： Wireless communication Estimation error Chirp Processor scheduling Discrete Fourier transforms Radar Robustness Computational complexity Standards Signal to noise ratio

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：