检索结果-内蒙古大学图书馆

2022 International Conference on Information and Communication Technology for Development for Africa, ICT4DA 2022

作者： Kassahun, Ermias Hailu, Zelalem Jember, Kehali A. Chali, Diriba University of Gondar Department of Electrical and Computer Engineering Gondar Ethiopia Mettu University Department of Electrical and Computer Engineering Metu Ethiopia Addis Ababa Science and Technology University Department of Electrical and Computer Engineering Addis Ababa Ethiopia

ISBN: (数字)9781665455879

ISBN: (纸本)9781665455879

Recently, different emerging technologies have been introduced due to the massive demand of mobile users. As it is difficult to accommodate only by RF technology, Light fidelity has become in to the picture. Li-Fi uses light-emitting diode to convey high-speed data rate in a short coverage area. In this paper non-orthogonal, multiple access technology is implemented to investigate the performance of proposed approach. Comparative analysis is done with orthogonal multiple access scheme taking different performance metrics in to consideration. Extensive simulation is carried out using MATLAB. The simulation result shows that the non-orthogonal multiple access is better resource allocation approach over the orthogonal frequency division multiple access. © 2022 IEEE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Cutting-Edge Climate Analysis: Combining MLP-GRU and Remote Sensing Technologies

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 348-363页

作者： Shaik, Reddi Khasim Priya, S. Shanmuga Saranya, N. R, Kotteeswaran Ramya, S. Thiagarajan, R. Department of Electrical and Electronics Engineering Vishnu Institute of Technology Bhimavaram India SRM Institute of Science and Technology Tiruchirappalli India Department of EIE St. Joseph’s College of Engineering Chennai India Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu Perundurai Erode India Department of Information Technology Prathyusha Engineering College Chennai India

Climate change poses significant challenges to societies worldwide, necessitating accurate and reliable climate prediction models to inform mitigation and adaptation strategies. The ability to forecast climate variables such as temperature, precipitation, and soil moisture is crucial for a wide range of applications, including agriculture, water resource management, and disaster preparedness. Traditional models have often struggled to capture the complex, nonlinear relationships and temporal dependencies inherent in climate data. In this study, we present a novel Hybrid MLP-GRU Network for climate prediction, leveraging the combined strengths of Multi-Layer Perceptron (MLP) and Gated Recurrent Unit (GRU) models. This hybrid approach aims to capture both complex, nonlinear relationships and temporal dependencies in climate data, enhancing the accuracy and reliability of predictions. We utilized comprehensive datasets from the Copernicus Climate Change Service (C3S), focusing on essential variables such as temperature, precipitation, soil moisture, and vegetation indices. The data underwent rigorous preprocessing, including normalization, temporal alignment, and feature extraction, to ensure high-quality inputs for the model. The model was trained and validated on extensive climate datasets, demonstrating superior performance metrics with an accuracy of 97.77%, RMSE of 0.140, and MAE of 0.120 on validation data. Comparative analysis with other models, including Linear Regression, Random Forest, LSTM, and CNN, highlights the efficacy of our hybrid approach. The Hybrid MLP-GRU Network consistently outperformed these models in terms of RMSE, MAE, and accuracy. Additionally, hyperparameter tuning, cross-validation, and deployment assessments were conducted to optimize the model’s performance and ensure robust predictions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Climate data Climate prediction Data preprocessing Feature extraction Gated Recurrent Unit Hybrid MLP-GRU Network Machine learning Multi-Layer Perceptron Nonlinear relationships Temporal dependencies

来源：评论

学校读者我要写书评

暂无评论

How to Find a Large Solution Set to Cover the Entire Pareto Front in Evolutionary Multi-Objective Optimization

How to Find a Large Solution Set to Cover the Entire Pareto ...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Pang, Lie Meng Nan, Yang Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China

ISBN: (纸本)9798350337020

Recently, it has been pointed out in many studies that the performance of evolutionary multi-objective optimization (EMO) algorithms can be improved by selecting solutions from all examined solutions stored in an unbounded external archive. This is because in general the final population is not the best subset of the examined solutions. To obtain a good final solution set in such a solution selection framework, subset selection from a large candidate set (i.e., all examined solutions) has been studied. However, since good subsets cannot be obtained from poor candidate sets, a more important issue is how to find a good candidate set, which is the focus of this paper. In this paper, we first visually demonstrate that the entire Pareto front is not covered by the examined solutions through computational experiments using MOEA/D, NSGA-III and SMS-EMOA on DTLZ test problems. That is, the examined solution set stored in the unbounded archive has some large holes (i.e., some uncovered area of the Pareto front). Next, to evaluate the quality of the examined solution set (i.e., to measure the size of the largest hole), we propose the use of a variant of the inverted generational distance (IGD) indicator. Then, we propose a simple modification of EMO algorithms to improve the quality of the examined solution set. Finally, we demonstrate the effectiveness of the proposed modification through computational experiments. © 2023 IEEE.

关键词： Evolutionary multi-objective optimization Pareto front solution selection framework unbounded external archive

来源：评论

学校读者我要写书评

暂无评论

Drone Object Detection Using RGB/IR Fusion 20

Drone Object Detection Using RGB/IR Fusion

引用

IS and T International Symposium on Electronic Imaging: 20th Computational Imaging, COIMG 2022

作者： Yang, Lizhi Ma, Ruhang Zakhor, Avideh Department of Electrical Engineering and Computer Science University of California Berkeley United States

Object detection using aerial drone imagery has received a great deal of attention in recent years. While visible light images are adequate for detecting objects in most scenarios, thermal cameras can extend the capabilities of object detection to nighttime or occluded objects. As such, RGB and Infrared (IR) fusion methods for object detection are useful and important. One of the biggest challenges in applying deep learning methods to RGB/IR object detection is the lack of available training data for drone IR imagery, especially at night. In this paper, we develop several strategies for creating synthetic IR images using the AIRSim simulation engine and CycleGAN. Furthermore, we utilize an illumination-aware fusion framework to fuse RGB and IR images for object detection on the ground. We characterize and test our methods for both simulated and actual data. Our solution is implemented on an NVIDIA Jetson Xavier running on an actual drone, requiring about 28 milliseconds of processing per RGB/IR image pair. © 2022, Society for Imaging science and Technology.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Artisan: Automated Operational Amplifier Design via Domain-specific Large Language Model 24

Artisan: Automated Operational Amplifier Design via Domain-s...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Chen, Zihao Huang, Jiangli Liu, Yiting Yang, Fan Shang, Li Zhou, Dian Zeng, Xuan State Key Laboratory of Integrated Chips and Systems School of Microelectronics Fudan University Shanghai China China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Department of Electrical Engineering University of Texas at Dallas RichardsonTX United States

ISBN: (纸本)9798400706011

This paper presents Artisan, an automated operational amplifier design framework using large language models (LLMs). We develop a bidirectional representation to align abstract circuit topologies with their structural and functional semantics. We further employ Tree-of-Thoughts and Chain-of-Thoughts approaches to model the design process as a hierarchical question-answer sequence, implemented by a mechanism of multi-agent interaction. A high-quality opamp dataset is developed to enhance the design proficiency of the Artisan-LLM. Experimental results demonstrate that Artisan outperforms state-of-the-art optimization-based methods and benchmark LLMs, in success rate, circuit performance metrics, and interpretability, while accelerating the design process by up to 50.1X. Artisan will be released for public access. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

HiRISE: High-Resolution Image Scaling for Edge ML via In-Sensor Compression and Selective ROI 24

HiRISE: High-Resolution Image Scaling for Edge ML via In-Sen...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Reidy, Brendan Tabrizchi, Sepehr Mohammadi, Mohammadreza Angizi, Shaahin Roohi, Arman Zand, Ramtin Department of Computer Science and Engineering University of South Carolina ColumbiaSC United States School of Computing University of Nebraska-Lincoln LincolnNE United States Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ United States

ISBN: (纸本)9798400706011

With the rise of tiny IoT devices powered by machine learning (ML), many researchers have directed their focus toward compressing models to fit on tiny edge devices. Recent works have achieved remarkable success in compressing ML models for object detection and image classification on microcontrollers with small memory, e.g., 512kB SRAM. However, there remain many challenges prohibiting the deployment of ML systems that require high-resolution images. Due to fundamental limits in memory capacity for tiny IoT devices, it may be physically impossible to store large images without external hardware. To this end, we propose a high-resolution image scaling system for edge ML, called HiRISE, which is equipped with selective region-of-interest (ROI) capability leveraging analog in-sensor image scaling. Our methodology not only significantly reduces the peak memory requirements, but also achieves up to 17.7× reduction in data transfer and energy consumption. © 2024 Copyright held by the owner/author(s).

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Prediction of miRNA family based on class-incremental learning

Prediction of miRNA family based on class-incremental learni...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Yajun Qiu, Lulu Li, Aimin Fei, Rong Li, Junhuai Wu, Fang-Xiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China Division of Biomedical Engineering Department of Mechanical Engineering Department of Computer Science Saskatoon Canada

ISBN: (纸本)9798350386226

With the development of deep sequencing, recent studies indicate that a miRNA precursor can generate multiple miRNA isoforms (isomiRs). The family prediction of canonical miRNAs and isomiRs could provide a basis for miRNA functional research. In this study, we propose a novel method for family identification of canonical miRNA and isomiRs based on incremental learning. First, a benchmark dataset is constructed by processing data based on miRNA sequences and their family annotation. Moreover, sequence embedding and RNN are used for capturing essential features and inherent dependencies within a sequence. Finally, incremental learning is applied to accommodate the continuous influx of miRNA sequencing data, enabling RNN to stay relevant and effective over time. Comparative experiments and ablation studies illustrate the effectiveness of our model, which can help to comprehensively understand miRNA's function. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of DPS in NOMA for Different MIMO Antenna Configurations 9

Performance Comparison of DPS in NOMA for Different MIMO Ant...

引用

9th International Conference on computer and Communication engineering, ICCCE 2023

作者： Sadid, Md. Shahriar Alavi, Abdullah Rafique, Moontasir Farhad, Md. Aadnan Kawser, Mohammad Tawhid Metropolitan University Department of Electrical and Electronic Engineering Sylhet Bangladesh Metropolitan University Department of Computer Science and Engineering Sylhet Bangladesh Islamic University of Technology Department of Electrical and Electronic Engineering Gazipur Bangladesh

ISBN: (纸本)9798350325218

The demand for an ever-increasing data rate and the growing number of users means that newer multiple-access technologies need to be developed. The paper considers how multiple input and multiple output (MIMO) systems can be implemented with non-orthogonal multiple access (NOMA) to determine the performance shift for dynamic power allocation schemes (DPS). Dynamic power allocation scheme is considered due to the wireless medium's volatile nature. Monte-Carlo simulation has been used in this study and log-normal shadowing has been used as the path loss model. Rayleigh fading channel is considered for non-line of sight communication. The goal is to find the average spectral efficiency and outage probability for this setup for a range of antenna configurations from 2 × 1 to 4 × 4 and observe the variation across different antenna numbers. Both the near and the far users' performance has been investigated. The findings show that although there is a definite pattern in MIMO for the far users, there is no such pattern for the near users. For a single antenna system, the near user performs better in average spectral efficiency up to a designated power level, after which MIMO takes over. For the far user, MIMO always outperforms the single antenna system. Also, several MIMO configurations are simulated to find the best-performing antenna system. The results conclude that as the transmitted power increases, the MIMO systems with the greater number of antennas perform better. However, this is not the case for the lower power level. © 2023 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

LOW-LEVEL CONTROL OF MEMS DRIVEN FEMTO-SCALE SMALL SOLAR SAIL SPACECRAFT FOR EARTH ESCAPE TRAJECTORIES

LOW-LEVEL CONTROL OF MEMS DRIVEN FEMTO-SCALE SMALL SOLAR SAI...

引用

2024 Small Satellites Systems and Services Symposium, 4S 2024

作者： Alvara, Alexander N. Pister, Kristofer S.J. Department of Mechanical Engineering University of California Berkeley PO Box 4629 BerkeleyCA94708 United States Department of Electrical Engineering and Computer Science University of California Berkeley BerkeleyCA United States

ISBN: (纸本)9781510688940

This paper presents a low-level control strategy for femto-scale solar sail spacecraft to achieve Earth escape trajectories. The BLISS spacecraft employs MEMS inchworm motors to manipulate carbon fiber tethers that connect the sail to the spacecraft main body. Adjustments in tether length control the distance between the sail and main body and dictate the spacecraft's pitch and yaw. The study explored variations by parametric search in initial radial position, angular orientation, and lightness number to understand their effects on mission success. Additionally, we examined energy efficiency, power distribution, and pointing accuracy, which showed that the system provides sufficient control authority for successful missions. This approach allowed for Earth escape trajectory simulations with control over maximum cone angles to ensure stability and maintain control authority. A PD controller is used to generate control signals. Results indicate that the selected sail model with a ~10 g spacecraft, 1 m2 solar sail, σβ = 10 g/m2, and β = 0.16 can reach interplanetary space, designated as the Hill Radius for Earth, in approximately 125 days from GEO. © 2025 The Authors.

关键词： Solar sails

来源：评论

学校读者我要写书评

暂无评论

Active and Reactive Power Flow Control of the Dual Active Bridge Converter

Active and Reactive Power Flow Control of the Dual Active Br...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Lauryn Morris Thomas W. Francois Jonathan Saelens Oroghene Oboreh-Snapps Arnold Fernandes Praneeth Uddarraju Sophia A. Strathman Jonathan W. Kimball Department of Electrical and Computer Engineering Missouri University of Science and Technology

ISBN: (数字)9798331516116

ISBN: (纸本)9798331516123

The Dual Active Bridge (DAB) is a reliable and efficient converter capable of providing bi-directional power transfer and galvanic isolation. An ac-ac DAB can control both active and reactive power flow. The present work introduces a combined feedback/feed-forward current control system, utilizing the calculated and measured converter currents translated into the dq reference frame, to control the output power. The system was simulated in PLECS to demonstrate the control algorithm’s ability to track the dq currents and provide the necessary output power.

关键词： Reactive power Power measurement Flow production systems Bridge circuits Bidirectional control Switched reluctance motors Power electronics Reliability Voltage control Power generation

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：