检索结果-内蒙古大学图书馆

2023 International Conference on Electrical and Information Technology, IEIT 2023

作者： Hidayat, Wahyu Nur Dwi Prasetyo, Wiji Zahiroh, Ayu Najmatus Maydi Syahri, Esa Pramudheva Afdloly, Mochammad Mu'iz Sari, Rahajeng Kartika Universitas Negeri Malang Department of Electrical Engineering and Informatics Malang Indonesia Smk Negeri 10 Malang Departement of Computer Network Engineering and Telecommunications Malang Indonesia

ISBN: (纸本)9798350327298

The current utilization of e-learning has not been able to increase participation and learning experience and motivate students to achieve educational goals. This research focuses on developing gamification-based learning media in Object-Oriented Programming (OOP) subjects to increase student learning motivation, determine the feasibility level of learning media, and determine the increase in student learning motivation. The method of the research is design thinking It is used to identify and better understand users in the use of applications, find problems faced by users, and can explore new ideas in the creation of appropriate application features in accordance with user needs. The results of expert media validation from the teacher, lecturer, and programmer amounted to 89.78% in the good category, for the material validation results of 91.33% in the very good category. Media use was implemented by 23 students of class XI RPL SMKN 12 Malang. The user trial results showed a percentage of 83.48% with good criteria. The student learning motivation test results showed a percentage of 81.26% with very high criteria. This shows the effect of gamification implementation in fostering student learning motivation. Gamification-based media has been tested for feasibility by media experts, material experts, and students. Therefore, the media is feasible and can be used as a learning support media in object-oriented programming subjects in Vocational High School. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Chaotic Electromagnetic Field Optimization Algorithms

引用

International Journal Bioautomation 2024年第4期28卷 245-265页

作者： Roeva, Olympia Zoteva, Dafina Department of Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Acad. G. Bonchev Str. bl. 105 Sofia1113 Bulgaria Department of Computer Informatics Faculty of Mathematics and Informatics Sofia University "St. Kliment Ohridski" 5 James Bourchier Blvd. Sofia1164 Bulgaria

This paper investigates the performance of various Electromagnetic Field Optimization (EFO) algorithms. Chaos maps are proposed to improve the performance of EFO algorithms. Ten chaotic maps are incorporated in EFO – Chebyshev, Circle, Gauss, Iterative, Logistic, Piecewise, Sine, Singer, Sinusoidal and Tent. To compare the performance of the constructed EFO algorithms, a case study of the identification of the model parameters of a cultivation process model is studied. An experimental data set from E. coli BL21(DE3)pPhyt109 fed-batch cultivation process is used. Based on the results of 30 runs of each EFO, some statistical and InterCriteria analyzes are performed. As a result, the best performing EFO algorithms are iterative EFO and tent chaotic map EFO. These algorithms gave the best objective value (best and mean value) and had a good distribution of results. © 2024 by the authors.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Classification of Alzheimer’s Disease Using the Convolutional Neural Network (CNN) with Transfer Learning and Weighted Loss

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2023年第3期50卷

作者： Oktavian, Muhammad Wildan Yudistira, Novanto Ridok, Achmad Informatics Engineering Faculty of Computer Science Brawijaya University 65145 Indonesia Informatics Engineering Faculty of Computer Science Brawijaya University 65145 Indonesia

Alzheimer’s disease is a progressive neurodegenerative disorder that gradually deprives the patient of cognitive function and can end in death. With the advancement of technology today, it is possible to detect Alzheimer’s disease through Magnetic Resonance Imaging (MRI) scans. With MRI technology and image recognition, early diagnosis of Alzheimer’s disease can be performed automatically using machine learning. Although machine learning has many advantages, currently, deep learning is more widely applied because it has more robust learning capabilities and is suitable for solving image recognition problems. However, several challenges must be faced to implement deep learning, such as the need for large datasets, computing resources, and careful parameter setting to prevent overfitting or underfitting. In responding to the challenge of classifying Alzheimer’s disease using deep learning, this study proposes the Convolutional Neural Network (CNN) with the Residual Layer (ResNet-18) architecture. Transfer learning from ImageNet and weighting the loss function are then applied so that each class has a weight depending on its size. It is proposed to overcome the need for a large and balanced dataset. Furthermore, this study experimented with changing the network activation function to a Mish activation function. From the results of the tests, the model’s accuracy of 88.30% is produced using transfer learning, weighted loss, and the Mish activation function. This accuracy is better than the baseline model, which only gets an accuracy of 69.10%. © (2023), (International Association of Engineers). All Rights Reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Evaluating Machine Learning Techniques for Enhanced Prediction of Building Energy Consumption

Evaluating Machine Learning Techniques for Enhanced Predicti...

引用

South Eastern European Design Automation, computer engineering, computer Networks and Social Media Conference (SEEDA-CECNSM)

作者： Gerasimos Vonitsanos Andreas Kanavos Phivos Mylonas Computer Engineering and Informatics Department University of Patras Patras Greece Department of Informatics Ionian University Corfu Greece Department of Informatics and Computer Engineering University of West Attica Athens Greece

ISBN: (数字)9798331504489

ISBN: (纸本)9798331504496

Accurate prediction of energy usage is crucial for optimizing resource allocation, enhancing energy efficiency, and reducing environmental impact, pivotal for sustainable development. This study examines electricity consumption in three Cornell University buildings, utilizing advanced machine learning techniques to tackle the challenges of sustainable energy management effectively. We specifically evaluated the performance of Support Vector Machine (SVM), Random Forest, Decision Tree, and K-Nearest Neighbors (KNN) in forecasting electricity usage. Our findings reveal that SVM consistently outperforms the other models across various performance metrics, including accuracy and efficiency. These results provide vital insights into the efficacy of these algorithms in predicting energy consumption, thereby supporting strategic energy management decisions in educational institutions and potentially other similar settings.

关键词： Support vector machines Energy consumption Machine learning algorithms Accuracy Social networking (online) Electricity Buildings Nearest neighbor methods Prediction algorithms Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Calibration Approaches for Single-Beam and Multiple-Beam Distance Sensors

引用

IEEE Sensors Journal 2024年第1期24卷 975-983页

作者： Syu, Jia-Hao Lin, Jerry Chun-Wei Biernacki, Piotr Ziebinski, Adam National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and Informatics Devices Gliwice44-100 Poland Silesian University of Technology Department of Distributed Systems and Informatic Devices Gliwice44-100 Poland

Sensors are the foundation to facilitate smart cities, smart grids, and smart transportation, and distance sensors are especially important for sensing the environment and gathering information. Researchers have developed various methods to calibrate distance sensors;however, they mainly focus on using external information for calibration, which is inefficient and computationally expensive. To alleviate the above problems, we propose machine learning (ML)-based calibration approaches for distance sensors. We develop two calibration mechanisms, where the naive mechanism directly predicts the true distance, while the residual mechanism predicts the residual for calibration. The conventional ML regression algorithms are then adopted to predict the true distance or calibration residual. Experimental results show that the designed residual calibration mechanism outperforms the naive mechanism by reducing the root mean square error (RMSE) by 92.2% and mean absolute error (MAE) by 93.3% in the fitting task. In prediction, the proposed 2-D-residual mechanism achieves an improvement of 78.6% and 65.7% compared to the state-of-the-art method. The experimental results show the effectiveness and generalization of the proposed ML-based calibration method, especially for the 2-D mechanism, which achieves the highest robustness in all fitting and prediction tasks. © 2001-2012 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Distribution Matching for Multi-Task Learning of Classification Tasks: A Large-Scale Study on Faces & Beyond 38

Distribution Matching for Multi-Task Learning of Classificat...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Kollias, Dimitrios Sharmanska, Viktoriia Zafeiriou, Stefanos School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom School of Engineering and Informatics University of Sussex United Kingdom Department of Computing Imperial College London United Kingdom

ISBN: (纸本)1577358872

Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer. To provide sufficient learning support, modern MTL uses annotated data with full, or sufficiently large overlap across tasks, i.e., each input sample is annotated for all, or most of the tasks. However, collecting such annotations is prohibitive in many real applications, and cannot benefit from datasets available for individual tasks. In this work, we challenge this setup and show that MTL can be successful with classification tasks with little, or non-overlapping annotations, or when there is big discrepancy in the size of labeled data per task. We explore task-relatedness for co-annotation and co-training, and propose a novel approach, where knowledge exchange is enabled between the tasks via distribution matching. To demonstrate the general applicability of our method, we conducted diverse case studies in the domains of affective computing, face recognition, species recognition, and shopping item classification using nine datasets. Our large-scale study of affective tasks for basic expression recognition and facial action unit detection illustrates that our approach is network agnostic and brings large performance improvements compared to the state-of-the-art in both tasks and across all studied databases. In all case studies, we show that co-training via task-relatedness is advantageous and prevents negative transfer (which occurs when MT model's performance is worse than that of at least one single-task model). Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Channel Estimation Method for Modified Walsh-Hadamard Code Division Multiplexing in Helicopter Satellite Communications and Its Application to Initial Acquisition 16

A Channel Estimation Method for Modified Walsh-Hadamard Code...

引用

16th International Conference on Advanced Technologies for Communications, ATC 2023

作者： Yoshinaka, Yuto Kojima, Toshiharu The University of Electro-Communications Graduate School of Informatics and Engineering Department of Computer and Network Engineering 1-5-1 Chofugaoka Chofu Tokyo182-8585 Japan

ISBN: (纸本)9798350301328

Modified Walsh-Hadamard code division multiplexing (MWHCDM) is a promising solution for the degradation of bit error rate (BER) performance due to the periodic blockage (PB) of the channel caused by rotor blades in helicopter satellite communications. While zero-forcing (ZF) enhances the anti-PB capability of MWHCDM, it requires channel information. This paper proposes a channel estimation method for MWHCDM, discussing its application to initial acquisition. The proposed channel estimation method reproduces the transmitted signal from the received signal by utilizing the structure of MWHCDM signals. It estimates the channel information based on the cross-correlation coefficient between the reproduced transmitted signal and the received signal. computer simulation shows that introducing ZF combined with the proposed channel estimation method to initial acquisition significantly improves the acquisition performance in the PB channel, similar to the BER performance. © 2023 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Interactive Multimodal Learning: Towards Using Pedagogical Agents for Inclusive Education

Interactive Multimodal Learning: Towards Using Pedagogical A...

引用

2023 IEEE International Humanitarian Technology Conference, IHTC 2023

作者： Al Omoush, Muhammad H. Salih, Sumaia E. Kishore, Sameer Mehigan, Tracey Dublin City University Faculty of Engineering and Computing Dublin Ireland Dublin Ireland Middlesex University Department of Computer Engineering and Informatics Dubai United Arab Emirates

ISBN: (纸本)9798350314311

A pedagogical agent is an animated interface in an interactive online learning environment. Its role involves guiding users through instructions and participating in direct discussions. Numerous research studies underline the advantages of pedagogical agents in delivering instruction, tailoring learning experiences, and promoting inclusivity. The authors utilize machine learning techniques to develop an interactive multimodal application (combining visuals and audio) designed as a pedagogical agent. This application is intended to assist in teaching primary school students (aged 6 to 8) the recognition of colors and letters. Additionally, it incorporates voice interaction to assess their learning progress. The overarching objective of this pedagogical agent is to seamlessly integrate artificial intelligence (AI) into educational settings, thereby amplifying student engagement and motivation during the learning process. This paper will explore the journey of creating a machine learning-based application and its potential utility in supporting educators. Furthermore, the authors will investigate potential augmentations that could render the application more adept at aiding students with dyslexia. The paper will emphasize the significance of human-computer interaction (HCI), as it significantly shapes pedagogical agents' design and operational aspects. © 2023 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

KDTL: knowledge-distilled transfer learning framework for diagnosing mental disorders using EEG spectrograms

引用

Neural Computing and Applications 2024年第30期36卷 18919-18934页

作者： Singh, Shreyash Jadli, Harshit Padma Priya, R. Surya Prasath, V.B. Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Vellore India Division of Biomedical Informatics Cincinnati Children’s Hospital Medical Center CincinnatiOH45229 United States Department of Pediatrics University of Cincinnati College of Medicine CincinnatiOH45257 United States Department of Biomedical Informatics College of Medicine University of Cincinnati CincinnatiOH45267 United States Department of Computer Science University of Cincinnati CincinnatiOH45221 United States

Electroencephalography (EEG) is a well-known modality in neuroscience and is widely used in identifying and classifying neurological disorders. This paper investigates how EEG data can be used along with knowledge distillation-based deep learning models to detect mental disorders like epilepsy and sleep disorders. The EEG signals are converted into time–frequency plots using short-time Fourier transforms. Further, we propose a novel methodology for using knowledge distillation-based transfer learning (KDTL). Knowledge distillation is becoming quite prevalent in the machine learning field and is associated with various applications in our work;we propose its use in the detection of mental disorders from EEG spectrograms. We convert the EEGs using short-term Fourier transform to obtain time–frequency representation and apply teacher-student by first training a large teacher model and use knowledge distillation to train a student model. In our experiments, we found that ConvNext teacher and MobileNet student combination obtained better results. Our proposed KDTL approach is tested on two datasets with multiple cases, namely the Bonn and ISRUC datasets and obtain 98% and 95% accuracies, respectively. Further experimental results show that the overall KDTL methodology can obtain high classification accuracy across both datasets in binary and multiclass classifications and proves to be better than multiple prior works. Further, our KDTL approach provides a way to train lightweight models which have a smaller number of trainable parameters and thereby constitute lower training time overall. Our proposed KDTL-based approach obtained accurate results in diagnosing mental disorders from EEG spectrograms. Compared to other related methods, KDTL outperformed across tasks with obtained good results in both binary and multiclass classifications. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Edge Energy Orchestration 20th

Edge Energy Orchestration

引用

20th International Conference on the Economics of Grids, Clouds, Systems, and Services, GECON 2024

作者： Kumar, Vijay Valizadeh, Nima Petri, Ioan Rana, Omer Nag, Ambarish Zisman, Sagi Tripp, Charles Paul, Shuva School of Computer Science and Informatics Cardiff University Cardiff United Kingdom School of Engineering Cardiff University Cardiff United Kingdom Colorado United States Colorado United States

ISBN: (纸本)9783031812255

Edge computing devices have increased in number and capability over recent years. The ability to process data and execute machine learning in proximity to data generation and collection sources provides several advantages over using cloud- based data centers. We describe an orchestration mechanism that enables edge devices to make more effective use of energy resources in their proximity – a technique we refer to as "edge energy orchestration". A software "orchestrator" can take account of renewable generation to alter how task execution on edge devices is carried out. An application scenario is used to illustrate the use of the orchestrator in practice, followed by a discussion about how this approach can be generalized to a broader set of applications © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Clean energy

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：