检索结果-内蒙古大学图书馆

Relay-Assisted Communications Over Multi-Cluster Fluctuating Two-Ray Faded Channels

IET Communications 2025年第1期19卷

作者： Mehdi, Haider Hussain, Zakir Saleem, Syed Muhammad Atif Ahmed, Syed Areeb Department of Electrical Engineering National University of Computer and Emerging Sciences Karachi Pakistan

In this paper, a decode-and-forward relay-assisted device-to-device (D2D) network is examined over novel multi-cluster fluctuating two-ray (MFTR) fading channels. All communication links are functioning in terahertz (THz) conditions. Co-channel interference (CCI) is considered as well. We assume an eavesdropper is also present near the receiver and overhears the relay's signal. With the help of characteristic functions, expressions of outage, success probability, capacity with outage, secrecy outage, probability of strictly positive secrecy capacity and intercept probability are presented. These expressions are functions of MFTR fading conditions, THz channel parameters and distances between various nodes in the system. Numerical results based on the derived expressions are discussed under various scenarios. © 2025 The Author(s). IET Communications published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

RESIDENTIAL electrical STORAGE: FEASIBILITY STUDY FOR HYBRID RESIDENTIAL PV/BATTERY SYSTEMS IN CYPRUS 14

RESIDENTIAL ELECTRICAL STORAGE: FEASIBILITY STUDY FOR HYBRID...

引用

14th Mediterranean Conference on Power Generation Transmission, Distribution and Energy Conversion, MEDPOWER 2024

作者： Tillyros, Kypros Komodromos, Michael Lestas, Marios Christofides, Nicholas Department of Electrical Engineering Computer Engineering and Informatics Frederick University Nicosia Cyprus Frederick Research Centre Nicosia Cyprus

ISBN: (纸本)9781837242689

This paper presents a simulation study on integrating grid-connected photovoltaic (PV) systems with a potential to implement battery storage in residential settings. It analyses the performance and feasibility of such systems in enhancing self-consumption and energy export. The simulation model considers factors like household energy demand profiles, and PV output profiles. Through this analysis, it is anticipated to offer insights for homeowners, policymakers, and industry stakeholders on achieving greater energy independence and resilience. Finally, findings show that the attempt to effectively utilise battery storage in a residence while aiming for the most economically feasible system heavily depends on the load demand. It was observed that no matter the profile of the building or the energy utilisation, there is no significant change in energy costs. However, the results manifested an upcoming trend for utilising energy that will prove beneficial for costumers. © The Institution of engineering & Technology 2024.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Wireless Mouse EEG Device: Novel Design for Easy Operation 46

Wireless Mouse EEG Device: Novel Design for Easy Operation

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Benomar, Mohamed Xia, Xing Zhang, Hai Huang, Mao-Hsiang Vishwanath, Manoj Xu, Xiangmin Cao, Hung University of California Irvine Department of Electrical Engineering and Computer Science IrvineCA92697 United States University of California Irvine Department of Anatomy and Neurobiology IrvineCA92697 United States University of California Irvine Department of Computer Science IrvineCA92697 United States University of California Irvine Department of Electrical Engineering and Computer Science Department of Computer Science Department of Biomedical Engineering IrvineCA92697 United States

ISBN: (纸本)9798350371499

Electroencephalogram (EEG) has been widely used in studies using rodent models to understand brain functions and neurological disorders. However, conventional EEG setups have limits as recording devices are bulky and tethered, causing discomfort and deviating from natural habitat conditions. To address these, we develop an innovative wireless EEG device for mice with a compact size, wireless recording via Bluetooth, and minimal invasiveness through screw mounting. The device enhances experimental setups while ensuring the well-being of the mice in a more realistic environment facilitating easier translation to human studies. In an experimental setting involving induced seizures, EEG signals were recorded and analyzed to discern differences across epilepsy phases in both anesthetized and awake stages. This device holds promise to revolutionize EEG research using mice, bridging the gap between laboratory conditions and real-world scenarios, thus advancing our understanding of neurological phenomena. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Quantizing YOLOv7: A Comprehensive Study 28

Quantizing YOLOv7: A Comprehensive Study

引用

28th International computer Conference, computer Society of Iran, CSICC 2023

作者： Baghbanbashi, Mohammadamin Raji, Mohsen Ghavami, Behnam School of Electrical and Computer Engineering Shiraz University Shiraz Iran Shahid Bahonar University of Kerman Department of Computer Engineering Kerman Iran

ISBN: (纸本)9798350338195

YOLO is a deep neural network (DNN) model presented for robust real-time object detection following the one-stage inference approach. It outperforms other real-time object detectors in terms of speed and accuracy by a wide margin. Nevertheless, since YOLO is developed upon a DNN backbone with numerous parameters, it will cause excessive memory load, thereby deploying it on memory-constrained devices is a severe challenge in practice. To overcome this limitation, model compression techniques, such as quantizing parameters to lower-precision values, can be adopted. As the most recent version of YOLO, YOLOv7 achieves such state-of-the-art performance in speed and accuracy in the range of 5 FPS to 160 FPS that it surpasses all former versions of YOLO and other existing models in this regard. So far, the robustness of several quantization schemes has been evaluated on older versions of YOLO. These methods may not necessarily yield similar results for YOLOv7 as it utilizes a different architecture. In this paper, we conduct in-depth research on the effectiveness of a variety of quantization schemes on the pre-trained weights of the state-of-the-art YOLOv7 model. Experimental results demonstrate that using 4-bit quantization coupled with the combination of different granularities results in 3.92x and 3.86x memory-saving for uniform and non-uniform quantization, respectively, with only 2.5% and 1% accuracy loss compared to the full-precision baseline model. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Joint Dual Learning With Mutual Information Maximization for Natural Language Understanding and Generation in Dialogues

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 2445-2452页

作者： Su, Shang-Yu Chung, Yung-Sung Chen, Yun-Nung Rakuten Institute of Technology Rakuten Tokyo158-0094 Japan Massachusetts Institute of Technology Electrical Engineering and Computer Science CambridgeMA02139 United States National Taiwan University Department of Computer Science and Information Engineering Taipei106319 Taiwan

Modular conversational systems heavily rely on the performance of their natural language understanding (NLU) and natural language generation (NLG) components. NLU focuses on extracting core semantic concepts from input texts, while NLG constructs coherent sentences based on these extracted semantics. Inspired by information theory in digital communication, we introduce a one-way communication model that mirrors human conversations, comprising two distinct phases: (1) the conversion of thoughts into messages, similar to NLG, and (2) the comprehension of received messages, similar to NLU. This paper presents a novel algorithm that trains NLU and NLG collaboratively by concatenating their models and maximizing mutual information between inputs and outputs. This approach efficiently facilitates the transmission of semantics, leading to enhanced learning performance for both components. Our experimental results, based on three benchmark datasets, consistently demonstrate significant improvements for both NLU and NLG tasks, highlighting the practical promise of our proposed method. © 2014 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Safety-certified Receding-horizon Motion Planning and Containment Control of Autonomous Surface Vehicles via Neurodynamic Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Lyu, Guanghao Peng, Zhouhua Wang, Dan Wang, Jun School of Marine Electrical Engineering Dalian Maritime University Dalian China Department of Computer Science and the School of Data Science City University of Hong Kong Hong Kong

This paper addresses the safety-certified motion planning and containment control of under-actuated autonomous surface vehicles subject to model uncertainties, external disturbances, and input constraints in the presence of stationary and moving obstacles. A three-level modular control architecture is proposed with a trajectory generation module at its planning level, an adaptive guidance module at its guidance level, and a kinetic control module at its control level. Specifically, at the planning level, a safety-certified containment trajectory generator is designed to generate safe trajectories over a rolling time window to achieve containment formation and collision avoidance with neighboring ASVs, stationary obstacles, and moving obstacles via dynamic control barrier functions and twotimescale neurodynamic optimization models. At the guidance level, an adaptive line-of-sight guidance law is developed based on a finite-time predictor to estimate unknown sideslip angles and generate guidance commands. At the control level, an optimal control law is designed based on finite-time neural predictors and control Lyapunov functions for the autonomous surface vehicle with input constraints to follow the desired guidance commands. The effectiveness and characteristics of the proposed method are demonstrated via simulations and hardware-in-theloop experiments for cooperative exploration. IEEE

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Broadband Impedance Matching for Wearable Magnetoinductive Waveguides

Broadband Impedance Matching for Wearable Magnetoinductive W...

引用

2025 United States National Committee of URSI National Radio Science Meeting, USNC-URSI NRSM 2025

作者： Jenkins, Connor Kiourti, Asimina ElectroScience Laboratory Department of Electrical and Computer Engineering The Ohio State University ColumbusOH43212 United States

ISBN: (纸本)9781946815200

Magnetoinductive Waveguides (MIWs) consist of coupled electrically small resonant elements that support the propagation of magnetoinductive waves. By exciting current on an element, a magnetic field is formed, leading to the generation of current on neighboring elements via Faraday's Law. This pattern continues to form a traveling wave. MIWs have been used in wireless power transfer applications, sub-wavelength imaging setups, and as data communication media for applications such as Magnetic Resonance Imaging (MRI) or in challenging Radio-Frequency (RF) environments such as underground, underwater or on the body. In particular, our previous work has focused on their application to wireless body area networks (WBANs) that seamlessly interconnect wearable devices and sensors. © 2025 USNC-URSI.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Learning for Aspect-Based Sentiment Analysis of Urdu Tweets 8

Weakly-Supervised Learning for Aspect-Based Sentiment Analys...

引用

8th Student Research Workshop, RANLPStud 2023

作者： Zoya Department of Computing School of Electrical Engineering & Computer Science National University of Sciences & Technology IslamabadH-12 Pakistan

Aspect-based sentiment analysis (ABSA) is vital for text comprehension which benefits applications across various domains. This field involves the two main sub-tasks including aspect extraction and sentiment classification. Existing methods to tackle this problem normally address only one sub-task or utilize topic models that may result in overlapping concepts. Moreover, such algorithms often rely on extensive labeled data and external language resources, making their application costly and time-consuming in new domains and especially for resource-poor languages like Urdu. The lack of aspect mining studies in Urdu literature further exacerbates the inapplicability of existing methods for Urdu language. The primary challenge lies in the preprocessing of data to ensure its suitability for language comprehension by the model, as well as the availability of appropriate pre-trained models, domain embeddings, and tools. This paper implements an ABSA model Huang et al. (2020) for unlabeled Urdu tweets with minimal user guidance, utilizing a small set of seed words for each aspect and sentiment class. The model first learns sentiment and aspect joint topic embeddings in the word embedding space with regularization to encourage topic distinctiveness. Afterwards, it employs deep neural models for pre-training with embedding-based predictions and self-training on unlabeled data. Furthermore, we optimize the model for improved performance by substituting the CNN with the BiLSTM classifier for sentence-level sentiment and aspect classification. Our optimized model achieves significant improvements over baselines in aspect and sentiment classification for Urdu tweets with accuracy of 64.8% and 72.8% respectively, demonstrating its effectiveness in generating joint topics and addressing existing limitations in Urdu ABSA. © 2023 Incoma Ltd. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Lightweight Parallel CNN To Classify COVID-19 Associated Pneumonia From Chest X-Ray 20

Lightweight Parallel CNN To Classify COVID-19 Associated Pne...

引用

20th International Conference on electrical engineering, Computing Science and Automatic Control, CCE 2023

作者： Kibria, Hafsa Binte Hossain, Md. Ali Rajshahi University of Engineering & Technology Department of Electrical & Computer Engineering Rajshahi6204 Bangladesh Rajshahi University of Engineering & Technology Department of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798350306767

The global outbreak of the novel Coronavirus disease (COVID-19) has impacted millions of individuals, leading to widespread health, economic, and social consequences. Additionally, the overwhelming number of COVID-19 cases has strained healthcare facilities, underscoring the crucial need for timely and accurate detection of infected individuals to mitigate the pandemic's impact. Inspired by the fact that existing deep learning models often rely on millions of parameters, rendering them unsuitable for resource-constrained devices, we developed a lightweight Parallel Convolutional Neural Network (PCNN) in this research. The model addresses the necessity for efficient COVID-19 pneumonia diagnostics from chest X-ray images by significantly reducing the number of parameters, resulting in a notable accuracy of 99.25% with 313k parameters. To further reduce parameters, separable convolution blocks were introduced, yielding an accuracy of 99.21% with 224k parameters. Despite their lightweight nature, our model demonstrates competitive performance compared to heavyweight models, emphasizing an accuracy rate of 99.21%. By minimizing computational costs and memory requirements, our model offers a cost-effective solution that can be effortlessly deployed on devices with limited resources. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Classification of Duku Fruit Varieties

Deep Learning-Based Classification of Duku Fruit Varieties

引用

2023 International Conference on Artificial Intelligence Robotics, Signal and Image Processing, AIRoSIP 2023

作者： Pratondo, Agus Novianty, Astri Telkom University School of Applied Sciences Department of Multimedia Engineering Bandung Indonesia Telkom University School of Electrical Engineering Department of Computer Engineering Bandung Indonesia

ISBN: (纸本)9798350327472

Classifying duku fruit varieties (Lansium domesticum) is vital for the agricultural industry, market segmentation, and customer satisfaction. This work use the VGG-16 and Inception V3 models to evaluate the usage of deep learning approaches for the classification of duku varieties. Utilizing transfer learning and fine-tuning techniques, this research modifies pre-trained models for the aim of duku fruit categorization. Experiments were conducted utilizing samples of the duku condet, matesih, and palembang variations to evaluate the performance of the models. The results are promising, with Inception V3 achieving an accuracy rate of 79.22 percent and VGG-16 achieving an accuracy rate of 75.92 percent. These accuracy percentages indicate that the models can properly classify different duku fruit kinds based on their external appearance. The paper underlines the significance of transfer learning for enhancing the performance of models by employing the knowledge gained from previously trained models on large datasets. © 2023 IEEE.

关键词： Fruits

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：