检索结果-内蒙古大学图书馆

Electrical, Electronic and Information Sciences (eStream), Open Conference of

作者： Dalius Navakauskas Ćarūnas Paulikas Tomyslav Sledevič Dainius Udris Department of Electronic Systems Vilnius Lithuania Department of Computer Science and Communications Technologies Vilnius Lithuania Department of Electrical Engineering Vilnius Lithuania

ISBN: (数字)9798350352412

ISBN: (纸本)9798350352429

We are very glad to welcome our colleagues - young scientists, researchers and practitioners to the 11-th IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream‘ 2024), held in Vilnius Gediminas Technical University (VILNIUS TECH), Vilnius, Lithuania, on 25 April 2024. The eStream conferences aim to disseminate the research achievements between worldwide groups of scientists and engineers working in different areas of science to reach more tight relationships and generate new ideas for joint projects or other means of collaboration.

关键词： Collaboration

来源：评论

学校读者我要写书评

暂无评论

Stock Market Trading Based on Market Sentiments and Reinforcement Learning

引用

computers, Materials & Continua 2022年第1期70卷 935-950页

作者： K.M.Ameen Suhail Syam Sankar Ashok S.Kumar Tsafack Nestor Naglaa F.Soliman Abeer D.Algarni Walid El-Shafai Fathi E.Abd El-Samie Department of Computer Science&Engineering NSS College of EngineeringPalakkad678008KeralaIndia Department of Electronics and Communication Engineering NSS College of EngineeringPalakkad678008KeralaIndia Unitéde Recherche de Matière Condensée D’Electronique et de Traitement du Signal(URAMACETS)Department of PhysicsUniversity of DschangP.O.Box 67DschangCameroon Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia Department Electronics and Electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt

Stock market is a place,where shares of different companies are *** is a collection of buyers’and sellers’*** this digital era,analysis and prediction in the stock market have gained an essential role in shaping today’s *** market analysis can be either fundamental or *** analysis can be performed either with technical indicators or through machine learning *** this paper,we report a system that uses a Reinforcement Learning(RL)network and market sentiments to make decisions about stock market *** system uses sentiment analysis on daily market news to spot trends in stock *** sentiment analysis module generates a unified score as a measure of the daily news about *** score is then fed into the RL module as one of its *** RL section gives decisions in the form of three actions:buy,sell,or *** objective is to maximize long-term future *** have used stock data of Apple from 2006 to 2016 to interpret how sentiments affect *** stock price of any company rises,when significant positive news become available in the public *** results reveal the influence of market sentiments on forecasting of stock prices.

关键词： Deep learning machine learning daily market news reinforcement learning stock market

来源：评论

学校读者我要写书评

暂无评论

Statistical Device Simulation and Machine Learning of Process Variation Effects of Vertically Stacked Gate-All-Around Si Nanosheet CFETs

引用

IEEE Transactions on Nanotechnology 2024年 23卷 386-392页

作者： Kola, Sekhar Reddy Li, Yiming Butola, Rajat National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Department of Electronics and Electrical Engineering Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Biomedical Engineering Institute of Pioneer Semiconductor Innovation Institute of Artificial Intelligence Innovation Hsinchu300093 Taiwan

In this study, we report the process variation effect (PVE) including the work function fluctuation (WKF) on the DC/AC characteristic fluctuation of stacked gate-all-around silicon complementary field-effect transistors (CFETs). The PVE affects characteristic fluctuation significantly;in particular, for the variability of off-state current. Owing to the bottom channel of a fin-type, the P-FET suffers from the worst off-state current fluctuation (more than 200% variation) compared to the N-FET. The device variability induced by the WKF is marginal because of amorphous-type metal grains. As input features to an artificial neural network (ANN) model, low and high work function values, as well as parameters of PVE that have prevalent effects on CEFT transfer characteristics are further considered and modeled. The estimated values of R2-score prove that the ANN model properly grasps information from the dataset successfully;thus, it can be used to model emerging CFETs for circuit simulation. © 2002-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Sentiment Analysis: A GRU Approach for Improved Accuracy

Multimodal Sentiment Analysis: A GRU Approach for Improved A...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Manogaran, Nalini Annamalai, Suresh Anbarasu, V. Nair, Resmi R Balusamy, Balamurugan Veluval, Parimala Sushamass, Sushamass Arunprasath, S. Department of CSE Tamil Nadu Chennai600077 India SRM Institute of Science and Technology School of Computing College of Engineering and Technology Department of Networking and Communications Kattankulathur603203 India Department of Electronics and Communication Engineering Tamil Nadu Chennai602105 India Uttar Pradesh 201314 India Pune India Manipal University Jaipur Department of Computer Science and Engineering Rajasthan Jaipur303007 India

ISBN: (纸本)9798350378092

In the real world, data often comes in different forms, such as text, audio, and video, making it multi-modal. This poses a challenge for machine learning models, which need to be able to process and understand this type of data. One way to address this challenge is to use models that can handle multiple data types in a single model. This enables the model to learn from the diverse information offered by the various data types. This research explores various methods for sentiment analysis in a multi-modal context, incorporating text, images, and potentially audio data. The methods evaluated include lexicon-based methods, machine learning with text features, convolutional neural networks (CNNs) for text, and a proposed multi-modal GRU model. The objective of the multi-modal GRU model is to surpass existing methods by efficiently capturing and integrating sentiment information from various modalities. The evaluation of the model's capabilities and constraints encompasses multiple performance indicators, including accuracy, precision, recall, and F1-score. Our Multi-modal GRUs model achieved an accuracy rate of 85%, precision of 82%, recall of 80%, and an F1-score of 81%. These metrics indicate that the model adeptly captures the underlying patterns within the multimodal data. © 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

Ultra-low-thickness, highly sensitive, and perfect-absorption THz refractive index and temperature sensors based on Tamm plasmon polaritons and Fabry-Perot resonators

引用

Optik 2024年 315卷

作者： Mostafavi Ghahfarokhi, Zahrasadat Pakray, Farzaneh Rezaei, Mir Hamid Singh, Hari Shankar School of Electrical and Computer Engineering University of Missouri Columbia United States Department of Electrical Engineering Faculty of Engineering Shahid Chamran University of Ahvaz Ahvaz Iran Department of Communications and Electronics School of Electrical and Computer Engineering Shiraz University Shiraz Iran Department of Electronics and Communication Engineering Thapar Institute of Engineering and Technology Punjab Patiala147004 India

In this paper, an ultra-low thickness with high sensitivity and perfect absorption based on the excitation of Tamm plasmon polaritons and Fabry-Perot resonance for sensing applications is presented. The sensor comprises a graphene sheet, a spacer layer, an analyte region, and a one-dimensional periodic stack of the dielectric and metal layers. The sensor's performance is evaluated using the transfer matrix method under different conditions, including the presence of the graphene sheet and metallic layers of the periodic stack, a change in the chemical potential of the graphene sheet, the thickness of the layers, as well as the incident polarization and angle. The simulation results show that the presence of the graphene sheet causes stimulation of Tamm plasmon polaritons, and the presence of metal layers simultaneously increases the absorption and decreases the thickness of the sensor. The sensitivity of the sensor is 0.9667 THz/RIU (equivalent to 305 μm/RIU) with an absorption peak of 99.99 %. The use of silicon as the analyte allows the proposed structure to perform as a temperature sensor in the range of 1 THz, which results in a temperature sensitivity of 0.055 THz/°C (equivalent to 16.45 nm/°C). The proposed sensor has the advantages of extremely thin thickness, perfect absorption, high sensitivity, tunability, and fabrication-friendly structure. The proposed sensor has high potential for use in various sensing applications. © 2024 Elsevier GmbH

关键词： Fabry-Perot interferometers

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Meets Fluid Antenna: Towards Robust and Scalable Edge Intelligence

arXiv

引用

arXiv 2025年

作者： Park, Sangjun Seo, Hyowoon Department of Electronics and Communications Engineering Kwangwoon University Seoul01897 Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Federated learning (FL) is an emerging machine learning paradigm with immense potential to support advanced services and applications in future industries. However, when deployed over wireless communication systems, FL suffers from significant communication overhead, which can be alleviated by integrating over-the-air computation (AirComp). Despite its advantages, AirComp introduces learning inaccuracies due to the inherent randomness of wireless channels, which can degrade overall learning performance. To address this issue, this paper explores the integration of fluid antenna systems (FAS) into AirComp-based FL to enhance system robustness and efficiency. Fluid antennas offer dynamic spatial diversity by adaptively selecting antenna ports, thereby mitigating channel variations and improving signal aggregation. Specifically, we propose an antenna selection rule for fluid-antenna-equipped devices that optimally enhances learning robustness or training performance. Building on this, we develop a learning algorithm and provide a theoretical convergence analysis. The simulation results validate the effectiveness of fluid antennas in improving FL performance, demonstrating their potential as a key enabler for wireless AI applications. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic-Based Deep Reinforcement Learning Pre-Training: A Case Study in MEC Task Offloading

Fuzzy Logic-Based Deep Reinforcement Learning Pre-Training: ...

引用

Cyber Science and Technology Congress (CyberSciTech), IEEE

作者： Jiujie Zhang Yangfei Lin Zhaoyang Du Wugedele Bao Department of Computer and Network Engineering The University of Electro-Communications Tokyo Japan Department of Information Science and Technology Baotou Teachers' College Baotou China Department of Computer Science and Information Engineering Hohhot Minzu College Hohhot China

ISBN: (数字)9798331532093

ISBN: (纸本)9798331532109

The joint optimization of task offloading in mobile edge computing (MEC) presents significant challenges due to the complex interaction between computation, communication, and resource constraints. Deep reinforcement learning (DRL) algorithms offer promising solutions for optimizing task offloading decisions in dynamic environments. However, these algorithms often face drawbacks, such as arbitrary or random parameter initialization, which lacks semantic and behavioral relevance. Thus, extensive exploration is required to identify optimal policies, particularly at the early learning stages. To address this issue, a pre-training framework for DRL algorithms is proposed, which utilizes fuzzy logic to guide initial policy exploration. The proposed approach incorporates a fuzzy logic-based module for task offloading, enabling the framework to collect valuable experiential data related to task offloading decisions. These experiences are then used to pre-train the DRL algorithm offline, facilitating the rapid acquisition of more meaningful initial parameters. Simulations in an MEC task offloading scenario with multiple mobile devices and edge servers demonstrate that the proposed framework enhances early-stage performance and improves long-term stability of the DRL algorithm by reducing average task processing time and increasing average task completion rates. Additionally, the fuzzy logic-based task offloading module performs effectively even when it is applied independently.

关键词： Fuzzy logic Performance evaluation Multi-access edge computing Heuristic algorithms Semantics Refining Deep reinforcement learning Stability analysis Servers Thermal stability

来源：评论

学校读者我要写书评

暂无评论

An Assessment on Internet of Things

An Assessment on Internet of Things

引用

Multi-disciplinary Conference in Emerging Research Trends (IMCERT), International

作者： Engr. Ali Ahmed Huma Ali Ahmed Computer Engineering Department Bahria University Karachi Campus Karachi Pakistan Department of Computer Science Newports Institute of Communications & Economics Karachi Pakistan

These days we are spending our lives where we are heavily dependent on IT developments. Technology plays a major role in our daily routine as we are relying on these technologies to get maximum comfort and benefits. Among many others, Internet of Things (IoT) also shows a rapid advancement through passage of time. IoT is a huge domain that deals with sensor based gadgets and has a lot of applications all around us. The world is swinging around with sensors and devices which will help humans to communicate with ease. In this research paper, we are going to provide a comprehensive survey of IoT technologies and also enlighten the issues associated with the technologies.

关键词： Performance evaluation Protocols Corporate acquisitions Market research Internet of Things Security Reliability

来源：评论

学校读者我要写书评

暂无评论

Reduction on Model Operations Complexity of Simplified Volterra in Digital Predistortion for Wireless communications

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2024年第7期51卷 801-812页

作者： Choo, Hong Ning Hashim, Shaiful Jahari Latiff, Nurul Adilah Abdul Rokhani, Fakhrul Zaman Yusoff, Zubaida Varahram, Pooria Universiti Putra Malaysia Selangor Seri Kembangan43400 Malaysia Universiti Putra Malaysia Selangor Seri Kembangan43400 Malaysia School of Ocean Engineering Universiti Malaysia Terengganu Terengganu Kuala Terengganu21300 Malaysia Computer and Communications Systems Engineering Department Faculty of Engineering Universiti Putra Malaysia Selangor Seri Kembangan43400 Malaysia Faculty of Engineering Multimedia University Selangor Cyberjaya63100 Malaysia Research and Development Principal Engineer of Benetel Limited DublinD08 Ireland

The evolution of Digital Predistortion (DPD) for Power Amplifier (PA) linearization in wireless communications has seen a natural progression towards increasingly complex DPD models. This complexity directly correlates with improved accuracy in modeling PAs, thereby enhancing the linearization performance of DPD systems. As the demand for bandwidth and PA operation frequencies continues to rise, there is a growing trend towards achieving higher accuracy at the expense of increased complexity. This trend poses challenges for DPD design, necessitating the introduction of more complex algorithms to ensure effective PA linearization. This phenomenon is especially apparent in Volterra Series DPD algorithms, which are widely used for modelling nonlinear systems like PAs. This paper showcases the steps of reducing the modelling operations complexity of the Simplified Volterra (SV) method. The treated SV method presented in this paper is compared against the original SV method through simulation. The DPD model operations complexity is evaluated using the number of required multiplication operations. The DPD PA linearization performance is evaluated with respective model’s Normalized Mean Square Error (NMSE). A 57% reduction on the number of multiplication operations is observed in the treated SV against the original SV. Measured NMSE is similar for both models, indicating the treated SV model achieves this reduction in complexity without sacrificing linearization performance. © (2024) International Association of Engineers. All rights reserved.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Modeling and Assessment of RSSI in LoRa WAN Network Using a Neural Network Approach

Modeling and Assessment of RSSI in LoRa WAN Network Using a ...

引用

International Symposium on Intelligent Systems and Informatics (SISY)

作者： Josip Spišić Matko Zrnić Drago Žagar Krešimir Crgić Department of Communications Faculty of Electrical Engineering Computer Science and Information Technology Osijek Croatia

This study employed a l0-fold cross-validation approach to train and validate neural networks to predict the RSSI (received signal strength indicator) in LoRaWAN communication. The model's performance was accurately estimated by averaging results across multiple validation sets and training sequences, and biased outcomes were mitigated. Implementing data normalization techniques, a simple neural network architecture, regularization approaches, and iteration limits ensured robustness within the limitations of a small dataset. The assessment of three neural network models using different optimization algorithms demonstrated their potential for accurate RSSI predictions, particularly for low-power IoT devices like LoRaWAN end devices, where energy efficiency is crucial. Lightweight neural networks on such devices enable efficient data processing while conserving energy, extending their lifespan, and reducing maintenance needs. Experimentation with deeper structures and unconventional activation functions may be necessary for complex problems, further enhancing performance in specific domains like RSSI assessment for LoRaWAN end devices.

关键词：

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：