检索结果-内蒙古大学图书馆

Improved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction

Journal of Open Innovation: Technology, Market, and Complexity 2025年第1期11卷

作者： Wahyuddin, Eko Putra Caraka, Rezzy Eko Kurniawan, Robert Caesarendra, Wahyu Gio, Prana Ugiana Pardamean, Bens Department of Statistical Computing Politeknik Statistika STIS Jakarta 13330 Indonesia Statistics Indonesia (BPS) Jl. Dr Sutomo 6-8 Jakarta Indonesia School of Economics and Business Telkom University Bandung 40257 Indonesia Research Center for Data and Information Sciences Research Organization for Electronics and Informatics National Research and Innovation Agency (BRIN) Bandung 40135 Indonesia Faculty of Integrated Technologies Universiti Brunei Darussalam Gadong BE1410 Brunei Darussalam Department of Mathematics Universitas Sumatera Utara Medan 20155 Indonesia Bioinformatics and Data Science Research Centre Bina Nusantara University DKI Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University DKI Jakarta 11480 Indonesia

This study aims to address the common issue of biased estimation errors in time series modeling by analyzing the error in locating ideal hyperparameters and defining appropriate validation methods. Specifically, it focuses on predicting the stock price of Bank Rakyat Indonesia using a combination of historical stock prices, technical indicators, exchange rates, and news sentiment data, while determining the optimal variables for deep learning models. Employing a deep learning-based Long-Short Term Memory (LSTM) model, the study optimizes hyperparameters alongside walk-forward validation for time series prediction. It explores different combinations of variables and adapts the sliding window approach to the context of the data. The results highlight the importance of optimizing hyperparameters and utilizing walk-forward validation for accurate time series prediction. The model incorporating historical stock prices and sentiment scores outperforms others, achieving an RMSE of 96.61 and MAE of 86.97. Incorporating sentiment scores reduces RMSE by 39.55 % compared to models using only historical stock prices, while adding technical indicators does not yield improvement. This study contributes to the field by addressing the issue of biased estimation errors in time series modeling, offering insights into the optimization of hyperparameters and validation methods for accurate predictions. It also underscores the significance of incorporating sentiment analysis alongside historical stock prices for improved forecasting accuracy. © 2024 The Authors

关键词： LSTM Sentiment analysis Stock price prediction Time series modeling Validation methods

来源：评论

学校读者我要写书评

暂无评论

Design ethnomathematics mobile module to improve mathematics thinking ability

引用

AIP Conference Proceedings 2023年第1期2614卷

作者： Ratri Rahayu Henry Suryo Bintoro Alif Catur Murti Mathematics Education Study Program Teacher Training and Education Faculty Universitas Muria Kudus PO.BOX 53 Gondangmanis Bae Kudus Indonesia Informatics Engineering Study Program Faculty of Engineering Universitas Muria Kudus PO.BOX 53 Gondangmanis Bae Kudus Indonesia

The aims of this study are (1) analyzing the need for teaching materials in the form of mobile modules in mathematics learning; (2) produce a draft outline of the ethnomathematics mobile module. The subjects of this study were the principal, mathematics teacher, seventh-grade students of Junior High School in Kudus, Indonesia. Data obtained from literature studies and field surveys include questionnaires, interviews, and FGD. The data analysis technique used is data triangulation with stages: reduction, data presentation, and conclusions based on data descriptions. The results showed that (1) students’ mathematical thinking skills are still low, teachers have not used application-based media, teachers have not developed ethnomathematical-based media, students need learning media that can improve mathematical thinking skills and make students interested in learning mathematics; (2) the ethnomathematics component of the mobile module is divided into 3 main parts, namely the introduction, the core, and the end. The introductory section includes the initial login page, instructions for use, and information regarding basic competencies. The core section contains the content of learning activities that contain ASEP (apperception), JAYA (cultural bridge), SITI (material description), EDI (self-evaluation). The last part contains motivational sentences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic programming Algorithm using Furniture Industry 0/1 Knapsack Problem

Dynamic Programming Algorithm using Furniture Industry 0/1 K...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Mietha Anditta Natashya Amartya Laurens Spits Warnars Harco Leslie Hendric Spits Warnars Arief Ramadhan Teddy Siswanto Teddy Mantoro Nurulhuda Noordin Computer Science Departement School of Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Departement School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Departement BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia PJJ Informatika Telkom University Bandung Indonesia Information Systems Department Trisakti University Jakarta Indonesia Faculty of Engineering and Technology Sampoerna University Jakarta Indonesia School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Malaysia

Dynamic programming is a fundamental algorithm that can be found in our daily lives easily. One of the dynamic programming algorithm implementations consists of solving the 0/1 knapsack problem. A 0/1 knapsack problem can be seen from industrial production cost. It is prevalent that a production cost has to be as efficient as possible, but the expectation is to get the proceeds of the products higher. Thus, the dynamic programming algorithm can be implemented to solve the diverse knapsack problem, one of which is the 0/1 knapsack problem, which would be the main focus of this paper. The implementation was implemented using C language. This paper was created as an early implementation algorithm using a Dynamic program algorithm applied to an Automatic Identification System (AIS) dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Special issue on genome wide association study

引用

Quantitative Biology 2021年第2期9卷 105-106页

作者： Lin Hou Qiongshi Lu Can Yang Hongyu Zhao Center for Statistical Science Department of Industrial EngineeringMOE Key Laboratory of BioinformaticsSchool of Life SciencesTsinghua UniversityBeijing 100084China Department of Biostatistics and Medical Informatics Department of StatisticsCenter for Demography of Health and AgingUniversity of Wisconsin-MadisonWl 53726USA Department of Mathematics the Hong Kong University of Science and TechnologyHong KongChina Department of Biostatistics Yale School of Public HealthNew HavenCT 06510USA Department of Genetics Yale UniversityNew HavenCT 06510USA Program of Computational Biology and Bioinformatics Yale UniversityNew HavenCT 06510USA

Since the first success of genome wide association study(GWAS)was reported in 2005 by Hoh and colleagues on the identification of a major gene for age related macular degeneration,many thousands of published studies have reported reproducible association signals between hundreds of thousands of genetic variants and thousands of traits and diseases in the past 16 *** is a growing number of biobanks with up to one million participants developed across the world to facilitate genetic studies of complex traits through ***,many consortium projects have been initiated to collect diverse types of data that have proved very valuable for integrated analysis of GWAS *** rich data present both great opportunities and challenges to scientists on data management,computation,analysis,integration,and *** special issue of Quantitative Biology collects nine papers that cover major progresses,challenges,and future directions for GWAS analysis.

关键词： hundreds GWAS initiated

来源：评论

学校读者我要写书评

暂无评论

"CoVid" Analysis using Online-Based Problem-Solving Approach on informatics mathematics Subject

引用

Journal of Physics: Conference Series 2021年第1期2123卷

作者： N W Ashari Salwah Ma'rufi Informatics Study Program Universitas Cokroaminoto Palopo Indonesia Mathematics Education Study Program Universitas Cokroaminoto Palopo Indonesia

During the COVID-19 pandemic, lecturers carry out online learning and this condition also force student to learn independently. One alternative solution given is online-based problem-solving approach. This approach are suitable implemented in the mathematics informatics course. The Approach challenges students to be able to express every result of thinking, transform information into various forms of representation, as well as the ability to adapt to online learning during this pandemic. This research is case study research that aims to analyse the Communication Skills, Visual thinking, and Adaptability (COVid) of students in the mathematics informatics course through Online-Based Problem-Solving Approach. This course examines combinatorics and pigeon holes principle. This lesson is useful in the context of making software that requires certain calculations and logic. The subjects of this study were second semester students of the 2020/2021 academic year at the informatics Study program at Univeritas Cokroaminoto Palopo. Data was collected by using assignments, questionnaires, and interviews to obtain valid data. The results show that only a few students are able to express every result of thinking, transform information into various forms of representation, as well as the ability to adapt to online learning during this pandemic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Applying Social Network Analysis on Courses relationship in informatics mathematics Curriculum

Applying Social Network Analysis on Courses relationship in ...

引用

作者： Kanyarat Bussaban Asekha KhantaVchai Informatics Mathematics Program Suan Sunandha Rajabhat University

This study investigates the relationship the courses achievement of undergraduate students in informatics mathematics curriculum. Social Network Analysis and Pearson product Moment Correlation Coefficient are used to determine which courses are significant important and influence predictors. Data collected is from the sample of 91 online report submitted by science graduated students who have graduated during the academic year 2010-2017. The results of the study indicate that Linear Algebra and Discrete mathematics are the highest score of weighted degree centrality as mathematics information technology is the highest score of betweenness centrality and English for informatics mathematics influence over the whole courses.

关键词： Social Network Analysis courses achievement centrality curriculum

来源：评论

学校读者我要写书评

暂无评论

On the Parameter Combinations that Matter and on Those that do Not

arXiv

引用

arXiv 2021年

作者： Evangelou, Nikolaos Wichrowski, Noah J. Kevrekidis, George A. Dietrich, Felix Kooshkbaghi, Mahdi McFann, Sarah Kevrekidis, Ioannis G. Department of Chemical and Biomolecular Engineering Johns Hopkins University United States Department of Applied Mathematics and Statistics Johns Hopkins University United States Department of Mathematics and Statistics University of Massachusetts Amherst United States Department of Informatics Technical University of Munich Germany The Program in Applied and Computational Mathematics Princeton University United States Department of Chemical and Biological Engineering Princeton University United States Lewis-Sigler Institute for Integrative Genomics Princeton University United States

We present a data-driven approach to characterizing nonidentifiability of a model’s parameters and illustrate it through dynamic as well as steady kinetic models. By employing Diffusion Maps and their extensions, we discover the minimal combinations of parameters required to characterize the output behavior of a chemical system: a set of effective parameters for the model. Furthermore, we introduce and use a Conformal Autoencoder Neural Network technique, as well as a kernel-based Jointly Smooth Function technique, to disentangle the redundant parameter combinations that do not affect the output behavior from the ones that do. We discuss the interpretability of our data-driven effective parameters, and demonstrate the utility of the approach both for behavior prediction and parameter estimation. In the latter task, it becomes important to describe level sets in parameter space that are consistent with a particular output behavior. We validate our approach on a model of multisite phosphorylation, where a reduced set of effective parameters (nonlinear combinations of the physical ones) has previously been established *** Codes 37E99 (Primary), 68T07 (Secondary) Copyright © 2021, The Authors. All rights reserved.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI 41

Position: Bayesian Deep Learning is Needed in the Age of Lar...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Self-Trapped Exciton and Near-Infrared Emission in Bi3+/Er3+ Co-Doped Cs2Ag0.4Na0.6InCl6 Double Perovskite for Optical Telecommunications

SSRN

引用

SSRN 2022年

作者： Dave, Kashyap Huang, Wen-Tse Leśniewski, Tadeusz Lazarowska, Agata Grzegorczyk, Maciej Mahlik, Sebastian Leniec, Grzegorz Kaczmarek, Slawomir M. Liu, Ru-Shi Department of Chemistry National Taiwan University Taipei106 Taiwan Nanoscience and Technology Program Taiwan International Graduate Program Academia Sinica National Taiwan University Taipei115 Taiwan Institute of Experimental Physics Faculty of Mathematics Physics and Informatics University of Gdańsk Gdańsk80-308 Poland Department of Technical Physics Faculty of Mechanical Engineering and Mechatronics West Pomeranian University of Technology in Szczecin Piastow 48 Szczecin70-311 Poland Advanced Research Center of Green Materials Science and Technology National Taiwan University Taipei106 Taiwan

Erbium (Er) complexes are used as optical gain material for signal generation in the telecom C-band at 1540 nm, but they need a sensitizer to enhance absorption. Na+ substitution at Ag+ and Bi3+ doping at the In3+ site are possible strategies to enhance broadband emission in Cs2AgInCl6, which could be used as sensitizers to energy transfer into rare-earth elements. Herein, self-trapped exciton (STE) energy transfer to Er3+ at 1540 nm for low loss optical telecommunication applications is reported. An acid precipitation method is used to synthesize Cs2AgInCl6 and its derivative with Er3+, Bi3+, and Na+. Bare Cs2AgInCl6:Er emission signals are found to be weak at 1540 nm, but Bi3+ doping increased by 12 times, and Bi3+ and Na+ doping increased by up to 25 times signal intensity. Electron paramagnetic resonance spectroscopy characterized a decrease in axial symmetry over the Er3+ ion after substitutions of Na+ and Bi3+ in Cs2AgInCl6 at low temperature ( © 2022, The Authors. All rights reserved.

关键词： Bismuth compounds

来源：评论

学校读者我要写书评

暂无评论

Text data labeling process for semi-supervised learning modeling

引用

AIP Conference Proceedings 2024年第1期3165卷

作者： Ahmad Abdul Chamid Widowati Widowati Retno Kusumaningrum Doctoral Program in Information Systems School of Postgraduate Studies Diponegoro University Jl. Prof Sudarto S.H. Tembalang Semarang 50275 Indonesia Department of Informatics Engineering Faculty of Engineering Muria Kudus University Jl. Lingkar Utara UMK Gondangmanis Kudus 59327 Indonesia Department of Mathematics Faculty of Science and Mathematics Diponegoro University Jl. Prof Sudarto S.H. Tembalang Semarang 50275 Indonesia Department of Informatics Faculty of Science and Mathematics Diponegoro University Jl. Prof Sudarto S.H. Tembalang Semarang 50275 Indonesia

To develop a semi-supervised learning model, it is necessary to have a little labeled data and a lot of unlabeled data. The data labeling process requires great effort and must involve experts. In the process of labeling text data requires a linguist to do the labeling. In this study using text data in the form of marketplace user reviews, in general the data is still dirty and data preprocessing needs to be done. The data preprocessing techniques applied are normalization, tokenization, stopword removal, and stemming. After the data goes through the preprocessing stage, labeling is carried out by involving more than one linguist. The results of the labeling that have been carried out by linguists will be carried out a consistency test process by applying the Cohen Kappa method. The data that has been labeled by 2 linguists is 820 data, after the consistency test is obtained the delivery aspect with a kappa value of 1, the service aspect with a kappa value of 0.960, the quality aspect with a kappa value of 0.981, the size aspect with a kappa 0.997, the color aspect with a kappa value of 1. Based on the results of the consistency test from the 2 experts for the 5 aspects, consistent results were obtained. So that the data that has been labeled can be used as training data to carry out the process of developing a semi-supervised learning model. A series of labeling processes up to consistency testing will be the main basis for developing a semi-supervised learning model.

关键词：

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：