检索结果-内蒙古大学图书馆

23rd International Electronics Symposium, IES 2021

作者： Lado, Anita Jaquiline Sooai, Adri Gabriel Mamulak, Natalia Magdalena Rafu Nani, Paskalis Andrianus Bria, Yulianti Paula Batarius, Patrisius Aliandu, Paulina Ngaga, Emerensiana Sinlae, Alfry Aristo Jansen Mau, Sisilia Daeng Bakka Tedy, Frengky Meolbatak, Emiliana Metan Siki, Yovinia Carmeneja Hoar Gumelar, Agustinus Bimo Fanani, Nurul Zainal Yuhana, Umi Laili Universitas Katolik Widya Mandira Dept. of Computer Science Kupang85225 Indonesia Universitas Narotama Faculty of Computer Science Surabaya60117 Indonesia Dept. of Engineering Politeknik Negeri Jember Indonesia Institut Teknologi Sepuluh Nopember Dept. of Informatics Engineering Surabaya60117 Indonesia

ISBN: (纸本)9781665443463

Measuring the performance of several classifiers in the modeling process, based on datasets with certain criteria, becomes important. It used to determine which classifier is more reliable for a particular task. Neural network will be compared its performance against Random Forest using dragon fruit datasets. Consisting of 41 images of healthy and sick fruit and leaf, it is divided into four classes, both classifiers were used in two comparing experiments. The validation used is 10-fold cross-validation. The results obtained are not much different from the prediction accuracy in the range of 70% to 82.9% for both classifiers. © 2021 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Plastic Waste Detection: State-of-the-art, Challenges, and Solutions 3

Machine Learning for Plastic Waste Detection: State-of-the-a...

引用

3rd International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2022

作者： Tamin, Owen Moung, Ervin Gubin Ahmad Dargham, Jamal Yahya, Farashazillah Omatu, Sigeru Angeline, Lorita Universiti Malaysia Sabah Faculty of Computing And Informatics Kota Kinabalu Malaysia Universiti Malaysia Sabah Faculty of Engineering Kota Kinabalu Malaysia Education Research Centre Higashi-Hiroshima739-0046 Japan Taylor's University School of Computer Science Faculty of Innovation And Technology Selangor Malaysia

ISBN: (数字)9781665491495

ISBN: (纸本)9781665491495

Machine learning has advanced rapidly in recent technologies of artificial intelligence. The abundant and cheap computation in machine learning has created more knowledge and reliability of this method. Therefore, more researchers have relied on machine learning to solve plastic waste pollution, which contributes to global greenhouse gas emissions. Datasets are fundamental requirements to build the foundation of the plastic waste detection system. This paper provides an overview of several state-of-the-art deep learning models, focusing on the dataset used for waste classification and identification. The performance of each deep learning model in classification accuracy is also discussed. The challenges of implementing deep learning in plastic waste detection are identified;(i) Data deficiency for training, (ii) Quality of the existing plastic waste dataset, and (iii) Color spaces. Lastly, the proposed solution to each challenge is presented. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Enabled Power Scheduling in IoT-Based Smart Cities

引用

computers, Materials & Continua 2021年第5期67卷 2449-2462页

作者： Nabeela Awan Salman Khan Mohammad Khalid Imam Rahmani Muhammad Tahir Nur Alam MD Ryan Alturki Ihsan Ullah Department of Computer Science Government Girls Degree College MardanKPK23200Pakistan Department of Electrical Energy System UETPeshawar25000Pakistan Department of Computer Science College of Computing and InformaticsSaudi Electronic UniversityKSA Department of Smart Computing Kyungdong UniversityGlobal CampusGosung24764South Korea Department of Information Sciences College of Computer and Information SystemsUmm Al-Qura UniversityMakkahSaudi Arabia Robotics Engineering Daegu Gyeongbuk Institute of Science and TechnologySouth Korea

Recent advancements in hardware and communication technologies have enabled worldwide interconnection using the internet of things(IoT).The IoT is the backbone of smart city applications such as smart grids and green energy *** smart cities,the IoT devices are used for linking power,price,energy,and demand information for smart homes and home energy management(HEM)in the smart *** complex smart gridconnected systems,power scheduling and secure dispatch of information are the main research *** challenges can be resolved through various machine learning techniques and data *** this paper,we have proposed a particle swarm optimization based machine learning algorithm known as a collaborative execute-before-after dependency-based requirement,for the smart *** proposed collaborative execute-before-after dependencybased requirement algorithm works in two phases,analysis and assessment of the requirements of end-users and power distribution *** the rst phases,a xed load is adjusted over a period of 24 h,and in the second phase,a randomly produced population load for 90 days is evaluated using particle swarm *** simulation results demonstrate that the proposed algorithm performed better in terms of percentage cost reduction,peak to average ratio,and power variance mean ratio than particle swarm optimization and inclined block rate.

关键词： PSO IBR machine learning IoT smart cities CDBR

来源：评论

学校读者我要写书评

暂无评论

Analyzing gaze behavior for text-embellished narrative visualizations under different task scenarios

引用

Visual informatics 2020年第3期4卷 41-50页

作者： Chris Bryan Aditi Mishra Hidekazu Shidara Kwan-Liu Ma School of Computing Informaticsand Decision Systems EngineeringArizona State UniversityUnited States Department of Computer Science University of CaliforniaDavisUnited States

We conduct an eye tracking study to investigate perception text-embellished narrative visualizations under different task *** stimuli are data visualizations embellished with text-based elements:annotations,captions,labels,and descriptive *** consider three common viewing tasks that occur when these types of graphics are viewed:(1)simple observation,(2)active search to answer a query,and(3)information memorization for later *** overarching goal is to understand,at a perceptual level,if and how task affects how these visualizations are interacted *** analyzing collected gaze data and conducting advanced semantic scanpath analysis,we find,at a high level,diverse patterns of gaze behavior:simple observation and information memorization lead to similar optical viewing strategies,while active search significantly diverges,both in regards to which areas of the visualization are focused upon and how often embellishments are interacted *** discuss study outcomes in the context of embellishing visualizations with text for various usage scenarios.

关键词： Eye tracking Perception User study

来源：评论

学校读者我要写书评

暂无评论

Surgical Instrument Detection for Laparoscopic Surgery using Deep Learning 19

Surgical Instrument Detection for Laparoscopic Surgery using...

引用

19th International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON 2022

作者： Boonkong, Apiwat Hormdee, Daranee Sonsilphong, Suphachoke Khampitak, Kovit Khon Kaen University Embedded System RandD Group Computer Engineering Khon Kaen Thailand Khon Kaen University Data Science and Health Informatics Program Academic Affairs Khon Kaen Thailand Khon Kaen University Faculty of Medicine Department of Obstetrics and Gynecology Khon Kaen Thailand

ISBN: (纸本)9781665485845

Laparoscopic surgery has transformed conventional open surgery. Robot-Assisted laparoscopic surgery which is minimally invasive is effective for operations in limited space. Nevertheless, the robotic system which is utilized in such surgery can inflict impair to the surgical instruments, organs, or tissues as a consequence of the narrow field of view and space available to operate, and insufficient tactile response. In laparoscopy, the surgeon observes what he operates via digital images which are displayed on a monitor. In addition to the surgeon's expertise, the image-guided surgery system could offer him significant support if that system is capable of understanding those images. computer Vision has been able to proceed due to the emergence of Machine Learning, and especially Deep Learning. This paper applies Deep Learning for surgical instrument detection for laparoscopic surgery. The fastest model, based on results trained on the COCO 2017 Dataset on TensorFlow Framework, for each of 4 algorithms-Faster-RCNN, SSD, CenterNet and EfficientDet-from Model Zoo, along with YOLOv4 on Darknet Framework, have been investigated in this work. The evaluation metrics used are Precision, Recall and F1-score. The results reveal that each model plays its part well;however, YOLOv4 seemed to breakthrough this statement by offering grate result for all three accuracy metrics. © 2022 IEEE.

关键词： Laparoscopy

来源：评论

学校读者我要写书评

暂无评论

Oversampling Multi-Label Data Based on Natural Neighbor and Label Correlation

SSRN

引用

SSRN 2023年

作者： Liu, Bin Zhou, Ao Wang, Jin Tsoumakas, Grigorios Key Laboratory of Data Engineering and Visual Computing School of Computer Science of Technology Chongqing University of Posts and Telecommunications Chongqing400065 China School of Informatics Aristotle University of Thessaloniki Thessaloniki54124 Greece

In multi-label learning, addressing the class imbalance issue is of paramount importance. Oversampling methods are preferred as they offer a more general solution independent of the model choice, i.e., they alleviate the imbalance of datasets by augmenting instances in the pre-processing step. Existing neighbor-based oversampling methods employ an empirical number of neighbors (k=5), to identify the local region for new instances creation. However, a single fixed k value cannot fit all labels, because every label usually has its own distinct distribution and complexity. Furthermore, the label assignment for synthetic instances usually depends on the statistics of individual labels within the corresponding neighborhood, ignoring the informative correlation among labels. To overcome these limitations, we propose an oversampling method called Multi-Label Oversampling with Natural neighbor and label Correlation (MLONC). Our approach offers three main advantages: 1) the adaptive number of neighbors for each label related to the data complexity is obtained via natural neighbor detection;2) it encourages generating more instances proximate to the decision boundary of highly imbalanced labels, and diminishes the impact of outliers;3) exploitation of label correlation in label assignment enhances the quality of the synthetic instances. Experimental results demonstrate the effectiveness of MLONC under various base classifiers. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Identification of Acute Myeloid Leukemia (AML) Subtypes: M1, M2, M3 on White Blood Cells Using Microscopic Images

Identification of Acute Myeloid Leukemia (AML) Subtypes: M1,...

引用

International Electronics Symposium (IES)

作者： Soniya Jasmine Azzahra Riyanto Sigit Heny Yuniarti Yetti Hernaningsih Ade Imannurohma Departemen of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Surabaya Indonesia Departemen of Clinical Pathology Faculty of Medicine Airlangga University Dr. Soetomo General Academic Hospital Surabaya Indonesia

Leukemia is a form of blood cancer characterized by an overproduction of abnormal white blood cells that invade the body’s immune system. Leukemias are divided into four main groups based on cell type and growth rate. Acute Myeloid Leukemia (AML) is one of them, namely leukemia that occurs in the myeloid series. AML itself is divided into several subtypes, according to the French-American-British (FAB), namely M0-M7. AML subtypes M1, M2, and M3 are influenced by the same cell type, namely myeloblast cells, so a more detailed analysis is needed to classify them. Therefore we need a system that can identify the presence of AML in the blood, this identification is done by classifying white blood cells on microscopic images. To detect the presence of AML in microscopic images, multiple processes will be used, including preprocessing, segmentation, feature extraction, and classification stages by applying the K-NN method. This classification procedure will result in a diagnosis of M1, M2, or M3 blood cells. At the end of phase 1 of this final project, pre-processing and segmentation processes and graphical user interface (GUI) designs have been carried out. This final project resulted in an accuracy of 80% for the identification of subtype M1, 70% for the identification of subtype M2, and 80% for the identification of subtype M3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-level biomedical NER through multi-granularity embeddings and enhanced labeling

arXiv

引用

arXiv 2023年

作者： Shahrokh, Fahime Ghadiri, Nasser Samani, Rasoul Moradi, Milad Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan84156-83111 Iran Institute for Artificial Intelligence Center for Medical Statistics Informatics and Intelligent Systems Medical University of Vienna Vienna Austria

Biomedical Named Entity Recognition (NER) is a fundamental task of Biomedical Natural Language Processing for extracting relevant information from biomedical texts, such as clinical records, scientific publications, and electronic health records. The conventional approaches for biomedical NER mainly use traditional machine learning techniques, such as Conditional Random Fields and Support Vector Machines or deep learning-based models like Recurrent Neural Networks and Convolutional Neural Networks. Recently, Transformer-based models, including BERT, have been used in the domain of biomedical NER and have demonstrated remarkable results. However, these models are often based on word-level embeddings, limiting their ability to capture character-level information, which is effective in biomedical NER due to the high variability and complexity of biomedical texts. To address these limitations, this paper proposes a hybrid approach that integrates the strengths of multiple models. In this paper, we proposed an approach that leverages fine-tuned BERT to provide contextualized word embeddings, a pretrained multi-channel CNN for character-level information capture, and following by a BiLSTM + CRF for sequence labelling and modelling dependencies between the words in the text. In addition, also we propose an enhanced labelling method as part of pre-processing to enhance the identification of the entity's beginning word and thus improve the identification of multi-word entities, a common challenge in biomedical NER. By integrating these models and the pre-processing method, our proposed model effectively captures both contextual information and detailed character-level information. We evaluated our model on the benchmark i2b2/2010 dataset, achieving an F1-score of 90.11. These results illustrate the proficiency of our proposed model in performing biomedical Named Entity *** Codes 68T50, 68T07 Copyright © 2023, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Measuring Credibility Level of E-commerce Sellers with Structural Equation Modeling and Naive Bayes on Tweets of Service Quality

Measuring Credibility Level of E-commerce Sellers with Struc...

引用

IEEE Region 10 International Conference TENCON

作者： Marastika wicaksono aji bawono Diana Purwitasari Mauridhi Hery Purnomo Departement of Technology Management Sepuluh Nopember Institute of Technology Telkom University Bogor West Java Departement of Informatics Engineering Sepuluh Nopember Institute of Technology Surabaya East Java Departement of Electrical Engineering Departement of Computer Engineering Sepuluh Nopember Institute of Technology Surabaya East Java

In digital development 4.0, store brands are very important. The problem in this research is the lack of consumer trust to buy quality goods in e-commerce store accounts so that it affects consumer satisfaction. This study aims to address this question feedback from the problems of the customer, then on the other hand a questionnaire with the PLS-SEM (Partial Least Squares Structural Equation Modeling) model to determine the dimensions of the variables selected according to customer experience. To achieve this aim, both negative and positive customer comments were compiled to assess customer satisfaction, employing a comparative analysis method through Naive Bayes algorithm. The overarching goal was to achieve optimal results and extract valuable insights regarding the determinants that influenced customer satisfaction within the domain of online transactions. This research also has an impact on buyers so they can have an understanding of the factors that support trust in customer satisfaction, so that individuals do not hesitate in making purchasing decisions to shop online. The results showed that the algorithm initially recorded a modest accuracy score of 0.37. Meanwhile, after implementing hyperparameter tuning, the accuracy increased significantly to 0.62. In the aspect of Smart PLS questionnaire analysis, a standardized Normed Fit Index (NFI) of 0.707 was recorded, which was slightly below the established threshold of 0.90. The standardized root mean square residual (SRMR) was measured at 0.071, falling below the specified value of 0.08, indicating a commendable model fit. However, the RMS theta value at 0.240 exceeded the threshold of 0.102.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Guiding the Way: A Systematic Literature Review on Mentoring Practices in Open Source Software Projects

SSRN

引用

SSRN 2023年

作者： Feng, Zixuan Kimura, Katie Trinkenreich, Bianca Sarma, Anita Steinmacher, Igor Oregon State University School of Electrical Engineering and Computer Science CorvallisOR97331 United States Northern Arizona University School of Informatics Computing and Cyber Systems FlagstaffAZ86011 United States

Context: Mentoring in Open Source Software (OSS) is important to its project’s growth and sustainability. Mentoring allows contributors to improve their technical skills and learn about the protocols and cultural norms of the project. However, mentoring has its challenges: mentors sometimes feel unappreciated, and mentees may have mismatched interests or lack interpersonal skills. Existing research has investigated the different challenges of mentoring in different OSS contexts, but we lack a holistic understanding. Objective: A comprehensive understanding of the current practices and challenges of mentoring in OSS is needed to implement appropriate strategies to facilitate mentoring. Method: This study presents a systematic literature review investigating how literature has characterized mentoring practices in OSS, including their challenges and the strategies to mitigate them. We retrieved 232 studies from four digital libraries. Out of these, 21 were primary studies. Using this, we performed backward and author snowballing, adding another 27 studies. We conducted a completeness check by reviewing the references of the 4 most relevant primary studies, which resulted in us adding 1 additional study. We then conducted a full-text review and evaluated the studies using a set of criteria;as a result, 10 papers were excluded. We then employed an open-coding approach to analyze, aggregate, and synthesize the selected studies. Results: We reviewed 39 studies to investigate the different facets of mentoring in OSS, encompassing motivations, goals, channels, and contributor dynamics. We then identified 13 challenges associated with mentoring in OSS, which fall into three categories: social, process, and technical. We also present a quick-reference strategy catalog to map these strategies to challenges for mitigation. Conclusions: Our study serves as a guideline for researchers and practitioners about mentoring challenges and potential strategies to mitigate these challenge

关键词： Open source software

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：