检索结果-内蒙古大学图书馆

1st IEEE International Symposium on Consumer Technology, ISCT 2024

作者： Marthana Yusa, I Made Adi Sudi Anggara, I Gede Darma Yasa, Ngakan Putu Novitasari, Dwi Widhi Adnyana, I Nyoman Institut Bisnis Dan Teknologi Indonesia Visual Communication Design Denpasar Indonesia Multimedia Design Subject Institut Bisnis Dan Teknologi Indonesia Study Program of Informatics Technology Denpasar Indonesia

ISBN: (纸本)9798350365191

This paper examines the integration of Artificial Intelligence (AI) in the digital creation of Balinese dance animations, with a specific focus on the Hanoman dance character as the case study. Hanoman dance as a part of Balinese dance, known for its intricate movements, unique costume and cultural significance, presents a unique challenge for digital artists. AI technologies, such as machine learning and computer vision, offer novel approaches to capturing and animating these complex dance forms. This study examines current AI applications in this domain, assesses their effectiveness, and discusses the potential advancements and limitations. Through the use of rotoscoping and motion capture techniques, this study adeptly examines the intricate movements of the Hanoman dance, an integral part of Balinese dance heritage, employing text-to-animation and AI models for video footage motion capture. The thorough processes of data collection, preprocessing, and model training emphasized in the study highlight the necessity of a meticulous methodology. Furthermore, incorporating expert feedback during the validation and refinement phases ensures that the digital representations are both authentic and expressive. The study concludes that AI technologies can play a crucial role in preserving Balinese dance, offering educational tools and digital archives that uphold the cultural integrity of this traditional art form. © 2024 IEEE.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Supervised Machine Learning Approach for Predicting Cardiovascular Complications Risk in Patients with Diabetes Mellitus

Supervised Machine Learning Approach for Predicting Cardiova...

引用

International Conference on Electrical Engineering and informatics, ICEEI

作者： Arief Purnama Muharram Fahmi Sajid Master Program of Informatics School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

Diabetes mellitus, particularly type-2 diabetes, remains a prevalent health issue, raising concerns due to its associated risk of complications. Among these, cardiovascular complications pose a significant threat, exhibiting high morbidity and mortality rates. Health screening plays a pivotal role in stratifying the risk levels of diabetes patients, facilitating proactive measures to prevent the progression of complications. As such, the primary objective of this study is to develop a predictive model system for assessing cardiovascular risk in diabetes patients. Our study used the Cardiovascular Disease dataset and conducts experiments with various supervised machine learning algorithms, such as Naive Bayes, decision tree, random forest, AdaBoost, and XG- Boost. The results reveal that ensemble learning algorithms based on boosting, particularly AdaBoost and XGBoost, outperform other supervised machine learning methods. However, even with the best performance achieved using the dataset, the accuracy stands at 0.71, and the F -1 score is 0.69, which is still acceptable for screening purposes. Although these results provide valuable insights, indicating individuals at higher risk for cardiovascular complications in diabetes, further improvements are needed to enhance early prevention strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bibliometric Analysis: Research Trends in Leaf Image Segmentation and Classification

Bibliometric Analysis: Research Trends in Leaf Image Segment...

引用

2024 International Conference on Artificial Intelligence and Mechatronics System, AIMS 2024

作者： Agustini, Eka Puji Gernowo, Rahmad Kurnianingsih Wibowo, Adi Warsito, Budi Doctoral Program of Information System School of Postgraduated Studies Diponegoro University Semarang Indonesia Doctoral Program of Information System Diponegoro University Semarang Indonesia Master of Applied Science Program Polytechnic Semarang Indonesia Diponegoro University Faculty of Science and Mathematics Department of Informatics Semarang Indonesia Faculty of Science and Mathematics Diponegoro Universitty Department of Statistics Semarang Indonesia

ISBN: (纸本)9798350350524

Exploring various phenomena and issues related to leaf images is paramount, particularly in segmentation and classification of such images. This study employs bibliometric analysis to delve into two overarching themes: The trends in publication and the evolution of publications, along with a keyword-based analysis. The research methodology unfolds in two stages: (1) data collection and (2) analysis. The dataset comprises 1,248 articles sourced from the Scopus database, covering the period from 1988 to 2023. The research findings unveil a noteworthy surge in publication trends, peaking at 231 documents in 2023. An in-depth examination of journal names demonstrates that studies on the segmentation and classification of leaf images are predominantly featured in computer science journals, exemplified by the publication of 589 documents. Furthermore, an analysis of frequently used keywords highlights 'Extraction' as the predominant term, employed a total of 364 times. This underscores that the research focus on leaf image segmentation and classification presents ample opportunities for researchers to delve more profoundly into the subject. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Analyzing Political Figures in Real-Time: Leveraging YouTube Metadata for Sentiment Analysis

arXiv

引用

arXiv 2023年

作者： Putra, Danendra Athallariq Harya Muharram, Arief Purnama Master Program of Informatics School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

Sentiment analysis using big data from YouTube videos metadata can be conducted to analyze public opinions on various political figures who represent political parties. This is possible because YouTube has become one of the platforms for people to express themselves, including their opinions on various political figures. The resulting sentiment analysis can be useful for political executives to gain an understanding of public sentiment and develop appropriate and effective political strategies. This study aimed to build a sentiment analysis system leveraging YouTube videos metadata. The sentiment analysis system was built using Apache Kafka, Apache PySpark, and Hadoop for big data handling;TensorFlow for deep learning handling;and FastAPI for deployment on the server. The YouTube videos metadata used in this study is the video description. The sentiment analysis model was built using LSTM algorithm and produces two types of sentiments: positive and negative sentiments. The sentiment analysis results are then visualized in the form a simple web-based dashboard. © 2023, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

GLCM Feature Extraction and PCA for Tuberculosis Detection with Neural Network

GLCM Feature Extraction and PCA for Tuberculosis Detection w...

引用

2022 International Seminar on Application for Technology of Information and Communication, iSemantic 2022

作者： Alfa Farah, M. Nafis Hayyin Suristiyanti, Wiwiek Ibad, Sholihul Pramunendar, Ricardus Anggi Fajar Shidik, Guruh Dian Nuswantoro University Faculty of Computer Science Postgraduate Program in Informatics Engineering Indonesia Dian Nuswantoro University Faculty of Computer Science College Teacher in Informatics Engineering Indonesia

ISBN: (数字)9781665488396

ISBN: (纸本)9781665488396

Automatic recognition system for medical images is quite a challenging job in the medical image processing field. X-rays, CT, and MRI all provide medical pictures and other modalities which are utilized for diagnostic purposes. As in medical sector, detecting tuberculosis (TB) is a very important stage before further treatment is carried out. Human interpretation of a vast array of X-ray pictures can result in detection mistakes, so an automatic recognition system is needed that can detect TB disease. In this study, we use a dataset with two classes and extract GLCM-based texture features from each class, and apply them to a two-layer feed-forward neural network, which gives a classification rate of 99%. © 2022 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

High school students’ epistemic knowledge profiles and their multifaceted learning engagement in science

引用

Research in Science and Technological Education 2023年第3期41卷 1088-1100页

作者： Lin, Tzung-Jin School of Learning Informatics Program of Learning Sciences National Taiwan Normal University Taipei Taiwan Institute for Research Excellence in Learning Sciences National Taiwan Normal University Taipei Taiwan

Background: The role of students’ epistemic understanding of science in mediating their engagement in learning activities and tasks has been highlighted in the literature. Although researchers recognize epistemic knowledge of science as a multi-faceted framework, the so-called person-centered approach that aims to generate meaningful and distinct profiles has not been widely adopted. Purpose: The purpose of this study was to explore Taiwanese high school students’ epistemic knowledge profiles and learning engagements in science. Sample: 631 high school students from six senior high schools in Taiwan were invited to participate in the study. There were 375 males and 256 females. The age of these students ranged from 15 to 18 years, with an average age of 16.84. Design and methods: The students’ epistemic knowledge profiles were surveyed and categorized in terms of three critical dimensions of epistemic understanding of scientific knowledge (Uncertainty of Knowledge, Development of Knowledge, and Purpose of Knowledge). Besides, five forms of science learning engagement (Cognitive, Behavioral, Emotional, Social, and Agentic engagement) were evaluated and then compared based on the classified epistemic knowledge profiles. Results: Three epistemic profiles, namely Highly uncertain yet low purpose, Informed yet highly certain, and Uninformed, were identified. Furthermore, the students of the Informed yet highly certain profile had the highest scores on all the five forms of engagement. Yet, the students in the Highly uncertain yet low purpose and Uninformed profiles did not show significant differences in terms of Behavioral, Agentic, Emotional, or Social engagement. Conclusion: The findings suggest that none of the students in any profiles demonstrated fully sophisticated epistemic understanding of scientific knowledge, and this had different effects on their multifaceted science learning engagement. Moreover, the students demonstrated highly uncertain orientation toward

关键词： epistemic knowledge high school students learning engagement

来源：评论

学校读者我要写书评

暂无评论

Thread programming for Blockchain Creation 7

Thread Programming for Blockchain Creation

引用

7th International Conference on Information Technology Systems and Innovation, ICITSI 2022

作者： Parjuangan, Sabam Suhardi Nugraha, I Gusti Bagus Baskara Doctoral Program of School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung40132 Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung40132 Indonesia

ISBN: (数字)9781665465557

ISBN: (纸本)9781665465557

The process of finding a block hash is a complex problem. One of the problems is making the hash from a generator algorithm that uses the existing string and the transaction data in the block. So far, the idea that has been used is to make it one step at a time using high-powered machines (supercomputing). Developing blockchain applications is hard because supercomputing is expensive. To solve this problem, developers need to use a different method, called parallel programming. This article talks about a parallel way to make block hashes, which are used to make new blocks. We use the SHA256 algorithm to process the hash. When creating a unique character string to be used as a block hash from a set of characters, thread division is done as part of the algorithmic skeleton process. Our experiments show that using threads to split work in parallel has speeded up the build process by 1.56 seconds compared to when blocks are hashed sequentially. In addition, it was also found that the threads that contributed the most to increasing speedup were 3 threads with an average processing time of 111,638 seconds. On average, the parallel hash generation process takes 707,853 seconds, while the sequential one takes 1756,56 seconds. We conclude the solution to building blockchain using the thread programming method with the number of threads is 3 for the computer specifications used to be the same or smaller than the computer specifications we use. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Exact Solution of the Full RMSA Problem in Elastic Optical Networks

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第1期6卷 55-59页

作者： David, Fabio Rezende, Jose F. De Barbosa, Valmir C. Federal University of Rio de Janeiro Informatics and Computer Science Department Rio de Janeiro21941-914 Brazil Federal University of Rio de Janeiro Systems Engineering and Computer Science Program Centro de Tecnologia Rio de Janeiro21941-914 Brazil

Exact solutions of the Routing, Modulation, and Spectrum Allocation (RMSA) problem in Elastic Optical Networks (EONs), so that the number of admitted demands is maximized while those of regenerators and frequency slots used are minimized, require a complex ILP formulation taking into account frequency-slot continuity and contiguity. We introduce the first such formulation, ending a hiatus of some years since the last ILP formulation for a much simpler RMSA variation was introduced. By exploiting a number of problem and solver specificities, we use the NSFNET topology to illustrate the practicality and importance of obtaining exact solutions. © 2019 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Car Detection over Network using Yolov8 in Forza Horizon 4 17

Car Detection over Network using Yolov8 in Forza Horizon 4

引用

17th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2023

作者： Pratama, Vitradisa Sukoco, Agus Pebriadi, Pebi Kusumastuti, Dyah Paramarta, Vip Prihatmanto, Ary Setijadi Institut Teknologi Bandung Doctoral Program of School of Electrical Engineering and Infomatics Bandung Indonesia Universitas Bandar Lampung Departement of Informatics Lampung Indonesia Uniersitas Sangga Buana Bandung Indonesia Institut Teknologi Bandung School of Electical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350309164

In the realm of autonomous vehicles, object detection holds a pivotal role in enabling accurate perception and safe navigation within complex environments. This study incorporates these domains by proposing a vehicle detection system employing YOLO v8 within the popular game Forza Horizon 4. YOLO v8's real-time, accurate object detection prowess aligns seamlessly with the game's dynamics, enriching the user experience through improved vehicle tracking. The research encompasses YOLO v8 model training on an expansive vehicle dataset, adaptation for Forza Horizon 4, and rigorous evaluation, comparing accuracy, speed, and efficiency against existing methods. The methodology entails dataset preparation, YOLO v8 configuration, object detection, result evaluation, optional fine-tuning, and iterative testing and optimization. By scrutinizing two data transmission protocols, RTMP and HTTPS, the research accentuates RTMP's superiority in real-time image data transmission for object detection, surpassing HTTPS in processing speed. While RTMP excels in low-latency scenarios, HTTPS augments security through encrypted data transmission. The findings prove RTMP's speed in image data transmission for real-time object detection, whereas HTTPS's secure communication advantages. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

What does functional connectivity tell us about the behaviorally-functional connectivity of a multifunctional neural circuit?

What does functional connectivity tell us about the behavior...

引用

2022 Conference on Artificial Life, ALIFE 2022

作者： Izquierdo, Eduardo J. Candadai, Madhavun Cognitive Science Program Indiana University Luddy School of Informatics Computing and Engineering Indiana University United States

What insights can statistical analysis of the time series recordings of neurons and brain regions during behavior give about the neural basis of behavior? With the increasing amount of whole-brain imaging data becoming available, the importance of addressing this unanswered theoretical challenge has become increasingly urgent. We propose a computational neuroethology approach to begin to address this challenge. We evolve dynamical recurrent neural networks to be capable of performing multiple tasks. We then analyze the neural activity using popular network neuroscience tools, specifically functional connectivity using Pearson’s correlation, mutual information, and transfer entropy. We compare the results from these tools against a series of informational lesions, as a way to reveal their degree of approximation to the ground-truth. Our initial analysis reveals an overwhelming large gap between the insights gained from statistical inference of the functionality of the circuits based on neural activity and the actual functionality of the circuits as revealed by mechanistic interventions. © Artificial Life Conference Proceedings 2022.

关键词： Recurrent neural networks

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：