检索结果-内蒙古大学图书馆

Eye State Classification Using Ensemble Machine Learning Models and SMOTE on EEG Data 9

Eye State Classification Using Ensemble Machine Learning Mod...

9th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2024

作者： Trigka, Maria Dritsas, Elias Mylonas, Phivos Athena Research and Innovation Center Industrial Systems Institute Patras26504 Greece University of West Attica Department of Informatics and Computer Engineering Egaleo12243 Greece

ISBN: (纸本)9798350342482

Electroencephalography (EEG) data presents complex and high-dimensional signals, offering great potential for applications in various fields such as neurofeedback, clinical diagnostics, cognitive neuroscience, human-computer interaction (HCI), and beyond. Analyzing EEG signals requires expertise not only from neuroscience, but also from signal processing, machine learning (ML), and statistics to extract meaningful information from brain activity recordings. Specifically, the combination of EEG and ML can provide an advantage in addressing challenging classification tasks in these fields. The present study focuses on the classification of eye state (open or closed) using Ensemble ML models such as Random Forest (RF), Gradient Boosting (GB), AdaBoost, XGBoost, and LightGBM on EEG data. We apply the Synthetic Minority Over-sampling Technique (SMOTE) to address the class imbalance and conduct a comparative analysis of the models' performance with and without SMOTE using 10-fold cross-validation across several metrics namely, Accuracy, Precision, Recall, F1-score, and the Area Under the Curve (AUC). The experimental results highlight the importance of addressing the class imbalance in EEG data to improve model performance. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Hybridization Model of Frame Semantics and deep learning for text semantic similarity calculation 6

Hybridization Model of Frame Semantics and deep learning for...

引用

6th International Conference on computer Information Science and Application Technology, CISAT 2023

作者： Haijing, Liu Department of Computer Engineering Taiyuan Institute of Technology Taiyuan China College of computing informatics and media University Technology Mara Malaysia

ISBN: (纸本)9781510668546

Text semantic similarity computation is a fundamental problem in the field of natural language processing. In recent years, text semantic similarity algorithms based on deep learning have become the mainstream research paradigm, but they suffer from the problem of insufficient understanding of text semantics and thus unclear interpretation of computational results. In this paper, we propose a text semantic encoding model combining Frame semantic theory and deep learning, which enriches the semantic representation within sentences by making full use of the Frame, Frame Elements, lexical units, and inter-Frame relations in the Frame semantic knowledge base and combining them with the Bert model, and interacts with the semantics between sentences through Siamese Transformer encoders. The experiments are validated on MSRParaphraseCorpus and quora-question-pairs, and the results show that the model proposed in this paper outperforms similar models in terms of F1 values. © 2023 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

On the Optimization of User Allocation in Heterogeneous 5G Networks Using DUDe Techniques 14

On the Optimization of User Allocation in Heterogeneous 5G N...

引用

14th International Conference on Ubiquitous and Future Networks, ICUFN 2023

作者： Tsachrelias, Konstantinos Gkamas, Apostolos Katsigiannis, Chrysostomos-Athanasios Bouras, Christos Kokkinos, Vasileios Pouyioutas, Philippos University of Patras Computer Engineering and Informatics Department Patras Greece University Ecclesiastical Academy of Athens Athens Greece University of Nicosia Computer Science Department Nicosia Cyprus

ISBN: (纸本)9798350335385

In previous years, 3G and 4G cellular homogeneous networks configured with macro Base Stations (BSs) relied only on the downlink signal, even though transmission power and interference levels differ significantly between uplink and downlink. In 5G Heterogeneous Networks (HetNet), a new generation which have multiple BSs of different types such as Femto BS and Macro BS, there is the possibility of choosing to receive the data from one BS and transmit them to a different BS, and therefore decoupling the uplink and downlink. Especially, the increasing demand for faster, more reliable, and efficient connectivity has made the optimization of User Equipment (UE) allocation in 5G networks a crucial task. To tackle the challenges posed by heterogeneous 5G networks, this study compares and evaluates the performance of Downlink/Uplink Decoupling (DUDe) and traditional Downlink/Uplink Coupled (DUCo) user allocation approaches. Simulation results show that DUDe UE allocation outperforms DUCo by providing improved network performance and more efficient utilization of network resources in diverse network conditions. These findings have important implications for the design and optimization of 5G networks and provide valuable insights for researchers and practitioners in the field. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

A Highly Interpretable Deep Equilibrium Network for Hyperspectral Image Deconvolution 48

A Highly Interpretable Deep Equilibrium Network for Hyperspe...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Gkillas, Alexandros Ampeliotis, Dimitris Berberidis, Kostas University of Patras Dept. of Computer Engineering & Informatics Greece Ionian University Dept. of Digital Media and Communication Greece

ISBN: (纸本)9781728163277

In this paper, a novel technique for the hyperspectral image deconvolution problem is developed. First, considering the highly ill-posed nature of the examined problem, it is imperative to incorporate proper priors (regularizers) to capture the strong spectral and spatial dependencies of the hyperspectral images. Then, in light of this, a novel optimization problem is proposed by employing a convolutional neural network to act as a regularizer, which is learnt to reflect the properties of the signals of interest. To solve the proposed optimization problem, we use the half quadratic splitting methodology, thus designing an efficient iterative solver (iteration map). Based on the Deep Equilibrium (DEQ) modeling, which aims to express the proposed iterative solver as an equilibrium (fixed-point) computation, a highly interpretable deep learning-based network is derived, which can be trained endto-end. Extensive numerical results using two publicly available datasets illustrate that the proposed method markedly outperforms other state-of-the-art approaches. © 2023 IEEE.

关键词： deconvolution deep equilibrium models deep unrolling Hyperspectral images learnable regularizers

来源：评论

学校读者我要写书评

暂无评论

ERSOW Robot's Orientation Data Estimation Based on Landmark L-shape Recognition 24

ERSOW Robot's Orientation Data Estimation Based on Landmark ...

引用

24th International Electronics Symposium, IES 2022

作者： Nurrohmah, Erna Alfi Wibowo, Iwan Kurnianto Bachtiar, Mochamad Mobed Politeknik Elektronika Negeri Surabaya Departement of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

In this paper, the Robot's Orientation Data Estimation System was created based on Landmark L-shape Recognition to reduce the error value in the robot's orientation data. The estimation system is carried out based on the recognition of unique landmarks on the soccer field in the form of "L"-shaped lines to get the reference distance between the landmarks and the robot. The reference distance is used to get the orientation of the robot above the field according to the perception of the omnidirectional camera. In the orientation of the robot between the angle of-135° to-180°, the largest error value from the orientation of the robot produced by vision is 5.5° and the average error is 1.99°. In the robot orientation between the angles of 135° to 180° it has the largest error value from the robot orientation generated by vision is 4.6° with an average error of 1.77°. © 2022 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Exploring computer engineering Students' Perceptions When Introduced to Low-Code Platforms: A Study Using Inquiry Methods and Eye-Tracking Data

Exploring Computer Engineering Students' Perceptions When In...

引用

IEEE Education engineering (EDUCON)

作者： Semira Maria Evangelou Angelos Fotopoulos Dimosthenis Minas Michalis Xenos Computer Engineering and Informatics University of Patras Patras Greece

ISBN: (数字)9798350394023

ISBN: (纸本)9798350394030

This work explores the initial interactions and perceptions of computer engineering students who have no prior experience with low-code platforms. Specifically, undergraduate computer engineering students participated in a comprehensive experiment at the Human-computer Interaction Laboratory at the University of Patras, adhering to a structured experimental protocol encompassing questionnaire completion, exposure to an introductory video on low-code concepts, eye-tracking analysis, interaction with the platform, and interview. The investigation aims to uncover the perspectives of computer engineering students as they encounter a low-code platform for the first time, leveraging concurrent eye-tracking data to gain insights into their focal areas, the patterns that emerged in their approaches to tasks, and the elements that captured their attention. The findings suggest that students demonstrated efficient and swift recognition skills, showcasing various patterns in their task approaches, unveiling a spectrum of strategies and preferences. Interviews conducted post-interaction unveiled positive sentiments, with the majority acknowledging the low-code platform's effectiveness in minimizing application development time. Notably, ease of use emerged as a prominent aspect, with a substantial number finding the platform exceptionally user-friendly.

关键词： Protocols Terminology Navigation Databases Gaze tracking Pattern recognition engineering students

来源：评论

学校读者我要写书评

暂无评论

Streamlit Application for Helmet Detection Based on YOLOS: Case Study Indonesia

Streamlit Application for Helmet Detection Based on YOLOS: C...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Habib, Habib Muchtar, Kahlil Bahri, Al Yuliar Arif, Teuku Arnia, Fitri Safrizal, Safrizal Fuadi Abidin, Taufik Universitas Syiah Kuala Department of Electrical and Computer Engineering Aceh Indonesia Universitas Syiah Kuala Faculty of Mathematics and Natural Sciences Department of Informatics Aceh Indonesia

ISBN: (纸本)9798350369106

Traffic violations are still the biggest problem in the development of traffic in Indonesia. The three biggest violations are (1) running a red light, accounting for 42% of violations, (2) not wearing a helmet, accounting for 23% of violations, and (3) violating traffic signs, accounting for 9% of violations. The violation of not wearing a helmet is the second largest violation in Indonesia, which is due to the lack of awareness of safety while driving. Additionally, the supervision carried out by the security forces is also somewhat inadequate. Supervision is only conducted in certain areas, leading to a high number of violations. To address these issues, the YOLOS (You Only Look at Once Sequence) model, using Vision Transformer and Pytorch, was developed with the assistance of the AI City Challenge 2023 dataset. This model, trained for 200 epochs, is capable of detecting riders who wear helmets and those who do not. It achieves average precision and average recall values for objects with large area coverage in the precision and recall curves (large area), namely 38.8% and 57.2%, and on average precision with an IoU parameter of 0.5, obtaining a value of 63.5%. The implementation of the model in the Streamlit framework to create a system that can be used for detection was successfully completed. The system is capable of performing detection on a single image, webcam video, and video from RTSP CCTV. © 2024 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Plugged-in electric vehicle-assisted demand response strategy for residential energy management

引用

Energy informatics 2023年第1期6卷 6页

作者： Alfaverh, Khaldoon Alfaverh, Fayiz Szamel, Laszlo Department of Electric Power Engineering Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics P.O.B. 91 Budapest1521 Hungary School of Engineering and Computer Science University of Hertfordshire HatfieldAL10 9AB United Kingdom

Demand response (DR) management systems are a potentially growing market due to their ability to maximize energy savings by allowing customers to manage their energy consumption at times of peak demand in response to financial incentives from the electricity supplier. Successful execution of a demand response program requires an effective management system where the home energy management system (HEMS) is a promising solution nowadays. HEMS is developed to manage energy use in households and to conduct the management of energy supply, either from the grid or the alternative energy sources like solar or wind power plants. With the increase of vehicle electrification, in order to achieve a more reliable and efficient smart grid (SG), cooperation between electric vehicles (EVs) and residential systems is required. This cooperation could involve not only vehicle to grid (V2G) operation but a vehicle to home (V2H) too. V2H operation is used to transfer the power and relevant data between EVs and residential systems. This paper provides an efficient HEMS enhanced by smart scheduling and an optimally designed charging and discharging strategy for plugged-in electric vehicles (PEVs). The proposed design uses a fuzzy logic controller (FLC) for smart scheduling and to take the charging (from the grid)/discharging (supply the household appliances) decision without compromising the driving needs. Simulations are presented to demonstrate how the proposed strategies can help to reduce electricity costs by 19.28% and 14.27% with 30% and 80% state of charge (SOC) of the PEV respectively compared to the case where G2V operation only used along with the photovoltaic (PV) production, improve energy utilization by smoothing the energy consumption profile and satisfy the user’s needs by ensuring enough EV battery SOC for each planned trip. © 2023, The Author(s).

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Implementation of Design Patterns on Unity Components to Increase Reusability and Game Speed Development 25

Implementation of Design Patterns on Unity Components to Inc...

引用

25th International Electronics Symposium, IES 2023

作者： Yunanto, Andhik Ampuh Jamal, Sabila Sa'Adah, Umi Aziz, Adam Shidqul Permatasari, Desy Intan Nailussa'Ada Hardiansyah, Fadilah Fahrul Politeknik Elektronika Negeri Surabaya Keputih Sukolilo Department of Informatics and Computer Engineering East Java Surabaya City60111 Indonesia

ISBN: (纸本)9798350314731

In the past few years, a few game studios have already developed mid-core games. In this kind of game, U is one of the most crucial and complex parts. Game companies have to develop their products quickly and effectively so they can compete in the industry. Developing games quickly with a good architecture is not easy, especially the products that are developed are products with high complexity. Plus, currently, there is still no special framework or library that helps the development of mid-core games. This research implements design patterns to develop Unity Engine framework to develop game UI components. Validation results showed an increase in the development time by 28% to 91% and in the interaction cost by 10% to 66%. Moreover, the survey result also shows a customer satisfaction rate of 78% using CSAT formula. It is considered an excellent response by CSAT standard, so it could be concluded that according to customer, this framework already has an excellent performance. © 2023 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Neighbor Selecting Cooperation Strategies for Distributed Learning

Neighbor Selecting Cooperation Strategies for Distributed Le...

引用

European Signal Processing Conference (EUSIPCO)

作者： Evangelos Georgatos Christos Mavrokefalidis Kostas Berberidis Computer Engineering and Informatics Department University of Patras Greece

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

In distributed learning, a network of agents co-operate for solving a common task, like training a particular neural network. The devices usually adopt an iterative procedure with two steps, namely, they, first, perform local optimization, using, e.g., stochastic gradient descent, and, then, they exchange information among them in order to achieve consensus on the final solution. In current literature, the proposed distributed algorithms achieve consensus using averaging rules over the received information at each agent. Here, the paper departs from this paradigm and focuses on “single agent” cooperation strategies in which each agent selects a particular neighbor at each iteration and uses only that information during the local optimization step. Three selection rules are designed and it is shown that they inherit the convergence properties of commonly used averaging rules. Moreover, their effectiveness is demonstrated experimentally in classification tasks over other algorithms using well-known datasets for a wide range of scenarios, capturing factors like non-IID datasets, network size, and AI model size.

关键词： Training Performance evaluation computer aided instruction Distance learning Signal processing algorithms Stochastic processes Signal processing Classification algorithms Partitioning algorithms Optimization

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：