检索结果-内蒙古大学图书馆

2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023

作者： Setiawan, Aji Adi, Kusworo Widodo, Catur Edi Diponegoro University Doctoral Program of Information Systems School of Postgraduate Studies Semarang Indonesia Faculty of Engineering Darma Persada University Department of Information Technology Jakarta Indonesia Diponegoro University School of Postgraduate Studies Semarang Indonesia Diponegoro University Faculty of Science and Mathematics Department of Physics Semarang Indonesia

ISBN: (纸本)9798350339215

This research proposes a methodology for identifying the optimal feature combination using Support Vector Machine (SVM) based on edge and texture features. Canny, Sobel, and Prewitt for edge detection and GLCM, Gabor, and LBP for texture analysis are popular feature extraction techniques widely employed in various cases. The approach combines edge and texture features with SVM to classify rice types into five categories: Ipsala, Jasmine, Karacadag, Arborio, and Basmati. Experimental results demonstrate that SVM using Canny, Sobel, and Prewitt combined Gabor texture features outperforms the comparative methods. A comparative analysis based on accuracy scores using confusion matrices is conducted. Combining all feature edge methods, Canny, Sobel, and Prewitt with Gabor on SVM classification is the best model for rice object classification, achieving an accuracy of 96%. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Bacterial Cellulose Membranes Incorporated with Lipase for Oil Degradation

引用

Macromolecular Symposia 2024年第6期413卷

作者： Silveira, Victória Fonseca da Silva, Victória Mendes Junior, Sandro Rogério Kumineck Garcia, Michele Cristina Formolo Pezzin, Ana Paula Testa de Oliveira, Therezinha Maria Novais Schneider, Andrea Lima dos Santos Postgraduate Program in Health and Environment University of Joinville Region – UNIVILLE Santa Catarina Joinville89219-710 Brazil Department of Chemical Engineering University of Joinville Region – UNIVILLE Santa Catarina Joinville89219-710 Brazil Postgraduate Program in Process Engineering University of Joinville Region – UNIVILLE Santa Catarina Joinville89219-710 Brazil

The immobilization of enzymes increases their stability and allows their reuse, and bacterial cellulose (BC) is a material that can be used in this technique. This work aims to produce an enzymatic product to degrade oils and fats using BC as a matrix. Komagataeibacter hansenii bacteria produce BC membranes, and lipase is immobilized on the membranes by ex situ method. Then, the surface of the membranes is modified with zein, a hydrophobic corn protein. The membranes are characterized by TGA, FTIR, scanning electron microscopy (SEM) analysis and oil degradation test. TGA demonstrates higher stability for the membranes with lipase and zein. The FTIR spectrum of pure BC membrane and zein-modified membrane are very similar because of the high zein coating. SEM analysis shows that zein-modified membranes with lipase present smaller amounts of pores. Finally, using soy oil, lipase degrades oil even after immobilization during the degradation test. © 2024 Wiley-VCH GmbH.

关键词： Nafion membranes

来源：评论

学校读者我要写书评

暂无评论

Hand Motor Imagery Identification Using Machine Learning Approaches in a Protocol Based on Visual Stimuli and Passive Movement

Hand Motor Imagery Identification Using Machine Learning App...

引用

Colombian Caribbean Conference (C3), IEEE

作者： Aura X. González-Cely Cristian F. Blanco-Díaz Cristian D. Guerrero-Mendez Teodiano F. Bastos-Filho Postgraduate Program in Electrical Engineering Federal University of Espírito Santo Vitoria Brazil

In recent years, advancements in rehabilitation techniques have been made to leverage biosignals and passive movement as integral components of physical interventions to restore upper limb mobility in people with disabilities. This study introduces a novel Motor Imagery (MI) protocol based on Action Observation (AO) using static visual cues and a robotic glove used in the right hand. To address this, Machine Learning (ML) techniques were assessed using features based on Power Spectral Density (PSD) in the mu (μ, 8–13 Hz) and beta (β, 13–30 Hz) frequency bands. Four distinct classifiers were explored: Kernel Naive Bayes (NB), Quadratic Support Vector Machine (QSVM), Fine k-nearest neighbors (KNN), and Logistic Regression (LR). These classifiers were employed to discriminate between open- and closed-hand MI tasks. Based on the evaluated metrics, it was concluded that the implemented methodology is feasible for classifying MI tasks from the same limb, where the QSVM classifier showed the most promising results, with a mean accuracy of approximately 75%. Future work will focus on implementing the system to control the robotic glove in the context of post-stroke rehabilitation, underscoring its potential clinical utility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effects on Cortical Rhythms Produced by Robotic Glove Assistance During Motor Imagery

Effects on Cortical Rhythms Produced by Robotic Glove Assist...

引用

Colombian Caribbean Conference (C3), IEEE

作者： Cristian F. Blanco-Díaz Aura X. González-Cely Cristian D. Guerrero-Mendez Fernanda Souza Diego Andrade Teodiano F. Bastos-Filho Postgraduate Program in Electrical Engineering Federal University of Espírito Santo Vitoria Brazil

In recent years, advances in Brain-Computer Interfaces (BCIs) have gained recognition for the design of rehabilitation and/or assistance strategies for populations with neuromotor disabilities. In BCIs, the study of EEG phenomena during hand Motor Imagery (MI) tasks is still challenging. Therefore, to deepen the field, a novel protocol based on MI tasks is proposed in this study, which is compared to the classical MI protocol based on static Action Observation (AO). The proposed protocol is based on a combination of visual stimulation by AO and passive movements generated by a robotic glove. To address cortical effects, Electroencephalography (EEG) analysis was performed to examine the differences in cortical rhythms in the frequency domain. The results allow concluding that the use of the robotic glove generated a greater decrease in power (desynchronization) in the central parietal cortex of the brain, especially for electrode C3. These findings allow further neuroscience studies and will be used to deepen the analysis and detection of MI patterns towards a BCI-controlled upper limb assistance device.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computational modeling of a 119 kWp photovoltaic system

Computational modeling of a 119 kWp photovoltaic system

引用

Power Electronics and Control (SEPOC), Seminar on

作者： Leandro Maciel da Silva Daniel Caldas Soares Ferreira Carlos Torturella Valadão Flávio Barcelos Braz da Silva Postgraduate Program in Control and Automation Engineering Federal Institute of Espirito Santo Serra Brasil

An important aspect of medium and large photovoltaic systems is the ability to predict future electricity generation based on predicted meteorological data as well as the technical and structural characteristics of the system. This prediction can be enabled by applying mathematical models or artificial intelligence. This study aims to develop a reliable and valid computational model using measurements from a real 119 kWp photovoltaic plant at the Federal Institute of Espirito Santo. The model considers meteorological data from a solarimetric station located in the same area, as well as system losses in both AC and DC components. The results indicate that the simulated generation closely aligned with the actual figures, achieving an acceptable low percentage error, less than 0.5%, during the period from September to December 2022.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi Task Classification Using Deep Learning Approaches for Big Five Personality Traits Prediction: A Review 11

Multi Task Classification Using Deep Learning Approaches for...

引用

11th International Conference on Information Technology, Computer and Electrical engineering, ICITACEE 2024

作者： Nudin, Salamun Rohman Gernowo, Rahmat Somantri, Maman Wibowo, Adi Doctoral Program of Information System School of Postgraduate Studies Diponegoro University Semarang Indonesia Diponegoro University Faculty of Science and Mathematics Department of Physics Semarang Indonesia Diponegoro University Faculty of Engineering Department of Electrical Engineering Semarang Indonesia Diponegoro University Faculty of Science and Mathematics Department of Informatics Semarang Indonesia

ISBN: (纸本)9798350389289

This paper presents a comprehensive review of deep learning methods for the Big Five personality traits prediction using multi-task classification. The purpose of the review is to determine the performance of models developed in previous research to describe research opportunities and challenges in the future. The Big Five model is a framework in psychology that categorizes human personality into five dimensions: openness, conscientiousness, extraversion, agreeableness, and neuroticism. The review begins by analyzing 22 articles from the Science Direct, IEEE Xplore, and Scopus databases by applying screening using the Big Five Personality keywords. Then study the concepts of deep learning for model development such as: input, architecture, method, dataset, and performance to identify the strengths and limitations of each approach. The review results of the highest average accuracy by modality such as unimodal text with essay dataset (80.98%), unimodal image with ImageNet dataset (95.36%), unimodal audio with SSPNet dataset (79.48%), bimodal image and audio with Chalearn Video First Impression dataset (91.67%), multimodal text, image, and audio with Chalearn Video First Impression dataset (91.88%). The average accuracy of the Big Five Personality traits was highest (95.36%) and lowest (59%). This highlights the need for standard benchmarks, interpretable models and interdisciplinary collaboration to improve the accuracy, reliability and ethical implications of personality prediction. Future research is expected to pave the way for advancements in understanding human personality through deep learning approaches using other modalities such as EEG, GSR, and PPG. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-based Lane Line Detection System for Visual Path Following Control

Transfer Learning-based Lane Line Detection System for Visua...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Allan S. Almeida Tiago T. Ribeiro Andre G. S. Conceicao Postgraduate Program in Electrical Engineering Federal University of Bahia Salvador Brazil Department of Electrical and Computer Engineering Federal University of Bahia Salvador Brazil

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

One of the most important tasks in autonomous driving and autonomous vehicle navigation is detecting a path or trajectory that the vehicle should follow. Over the past few years, some learning-based works have stood out more than traditional computer vision techniques in detecting such lanes. In this paper we present an approach to solve the lane line detection problem in the context of visual path following by using a residual factorized convolutional neural network. Experimental results show a promising model that can detect lane lines even under severe lighting conditions and in the presence of occlusions and shadows. The path detection system was tested along with a visual path following formulation based on Nonlinear Model Predictive Control. Still, it can be used for any controller in the context of visual navigation for autonomous vehicles. Nonetheless, the proposed model architecture strikes a remarkable balance between accuracy and efficiency, making the system suitable for real-time applications.

关键词： Measurement Visualization Accuracy Navigation Computational modeling Lighting Computer architecture Trajectory Convolutional neural networks Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

The Internet of Things (IoT) as an Emerging Technological Solution for the Covid-19 Pandemic Mitigation: An Overview 3

The Internet of Things (IoT) as an Emerging Technological So...

引用

3rd International Conference on Electrical, Electronics, Informatics, and Vocational Education, ICE-ELINVO 2020

作者： Abubakari, M.S. Mashoedah Department of Electronics Engineering Education Postgraduate Program Universitas Negeri Yogyakarta Indonesia

Currently, the whole world is facing the critical economy crash and enormous casualties as the ongoing coronavirus continues its intensive attack across the planet. Sadly, individuals in billions of numbers continue to face a constant threat from this contagious disease, with the condition unlikely to getting any improvement soon. In this paper, the aim is to provide an overview study of the current situation concerning the COVID-19 outbreak and the potential role of Internet of Things (IoT) as well as the associated technologies acting as technological solution in mitigating the outbreak. Thus, some potential literatures have been briefly reviewed for this paper as a research method. The review results indicate that, several technological solutions are innovated to deal with the COVID-19 pandemic effects. Digital technologies play a major role in the reformation of public health response towards the COVID-19 pandemic. Among digital technologies which have been at the front line include the IoT. Some examples and potential applications of IoT are discussed. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning with Obstacle Avoidance using APF and COLREGS for USVs

Trajectory Planning with Obstacle Avoidance using APF and CO...

引用

IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

作者： Kelvin K. C. F. Nunes Tiago T. Ribeiro Andre G. S. Conceicao Postgraduate Program in Electrical Engineering Federal University of Bahia Salvador Brazil Department of Electrical and Computer Engineering Federal University of Bahia Salvador Brazil

ISBN: (数字)9798350352344

ISBN: (纸本)9798350352351

This paper presents a trajectory planning and obstacle avoidance system for Unmanned Surface Vehicles (USV) in complex and dynamic navigation environments. The developed system employs a modified Artificial Potential Field (APF) algorithm and the International Regulations for Preventing Collisions at Sea (COLREGS) to ensure safe and efficient navigation. Modifications were implemented to the original algorithm to deal with obstacles approaching the autonomous vehicle, including adding vectors to determine the direction of deviation based on the cross-product. The proposed system was validated in the Gazebo simulation environment within a dynamic scenario featuring static and moving obstacles.

关键词： Trajectory planning Navigation Heuristic algorithms Vectors Regulation Safety Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Kano Model Analysis of Android Apps Quality from End User's Preferences 3

Kano Model Analysis of Android Apps Quality from End User's ...

引用

3rd International Conference on Electrical, Electronics, Informatics, and Vocational Education, ICE-ELINVO 2020

作者： Putra, R.A.S. Priyanto Electronics and Informatics Engineering Education Postgraduate Program Yogyakarta State University Indonesia

This study aimed to explore the end user's preferences regarding the features of an android app by classifying them with the Kano Model. The list of features was based on ISO/IEC 25010 combined with Android Core App Quality Guidelines. This expert system android app which is named 'Pilih Media' is used to help teachers selecting learning media based on Anderson's theory of learning media selection. Respondents in this study were 50 teachers. Kano model was used in this study as a guideline in making questionnaires and also analyzing the data. From the study, it can be concluded that there are 17 features classified as the Attractive requirement category, six features classified as One-dimensional category, one feature classified as Must-be category, and five features classified as the Indifferent category. Overall, it seems that a lot of features have the potential to increase the end user's satisfaction. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Expert systems

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：