检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lee, Jaerin Park, JoonKyu Baik, Sungyong Lee, Kyoung Mu ASRI Department of ECE Seoul National University Seoul Korea Republic of Department of Data Science Hanyang University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Image restoration models are typically trained with a pixel-wise distance loss defined over the RGB color representation space, which is well known to be a source of blurry and unrealistic textures in the restored images. The reason, we believe, is that the three-channel RGB space is insufficient for supervising the restoration models. To this end, we augment the representation to hold structural information of local neighborhoods at each pixel while keeping the color information and pixel-grainedness unharmed. The result is a new representation space, dubbed augmented RGB (aRGB) space. Substituting the underlying representation space for the per-pixel losses facilitates the training of image restoration models, thereby improving the performance without affecting the evaluation phase. Notably, when combined with auxiliary objectives such as adversarial or perceptual losses, our aRGB space consistently improves overall metrics by reconstructing both color and local structures, overcoming the conventional perception-distortion trade-off. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Effects of a graphic organizer-based two-tier test approach on students’ learning achievement and behaviors in spherical video-based virtual learning contexts

引用

Computers and Education 2023年 198卷

作者： Hwang, Gwo-Jen Chen, Hui-Chueh Hsu, Chung-Yuan Hwang, Gwo-Haur Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology Taiwan Department of Child Care National Pingtung University of Science and Technology Taiwan Bachelor Program in Industrial Technology National Yunlin University of Science and Technology Taiwan Graduate Institute of Educational Information and Measurement National Taichung University of Education Taiwan Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Taiwan

Situating learners in a context relevant to scientific phenomena enables them to acquire knowledge through experience, reflection, conceptualization, and practice, which is an important learning mode in science education. However, learners generally do not have opportunities to experience many scientific phenomena in the real world. Therefore, virtual learning environments (VLE) are becoming a frequently adopted technology to provide authentic learning contexts. In particular, spherical video-based learning environments (SVLE), which are a low-tech form of VLE, have attracted the attention of school teachers and educational technology researchers. Additionally, effective assessment methods, such as the two-tier-test, have been adopted to examine learners' performance during the virtual learning process. On the other hand, researchers have pointed out that lack of effective learning strategies may decrease the learning effects in a virtual learning context. Hence, this study integrated a graphic organizer into a two-tier test-based learning mode, in which the first-tier questions were declarative items with a short answer (e.g., the questions of where, what, and when), whereas the second-tier questions were more in-depth, deeper causal-type questions (e.g., the questions of why and how), in the contexts of SVLE. To verify the effectiveness of this learning approach, a graphic organizer-based two-tier test SVLE was developed;moreover, a quasi-experimental design was conducted in the "Mysteries of the Earth" unit of the sixth graders' natural science course. A total of 41 sixth graders from two classes, with an average age of 12, were recruited in this experiment. One class was assigned to be the experimental group adopting the graphic organizer-based two-tier test SVLE (GT-SVLE), while the other was the control group adopting the conventional two-tier test-based SVLE (CT-SVLE). All of the students learned with the SVLE using tablet computers. Based on the results, the

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Design, Development and Performance Evaluation of a Miniature Electrostatic Precipitator in an Indoor Environment

SSRN

引用

SSRN 2024年

作者： Kumar, Aiswarya Nawale, Prashant Rohidas Sahu, Manoranjan Aerosol and Nanoparticle Technology Laboratory Environmental Science and Engineering Department Indian Institute of Technology Bombay Mumbai400076 India Interdisciplinary Program in Climate Studies Indian Institute of Technology Bombay Mumbai400076 India Centre for Machine Intelligence and Data Science Indian Institute of Technology Bombay Mumbai400076 India

Different PM capture technologies are available in market as well as on lab scale, they pose several drawbacks. Therefore, a miniature ESP was designed in laboratory and operated at optimal operating conditions to obtain maximised capture of PM. Results from study confirmed that designed ESP was capable of capturing various standard aerosol, major indoor sources and infiltrated PM with a total removal efficiency of 97.87% to 99.97% in PM sizes from 10 nm to 800 nm. Additionally, energy consumed/clean air delivery rate and emission of by-products were found to be comparatively lesser compared to commercial purifiers. © 2024, The Authors. All rights reserved.

关键词： Electrostatic precipitators

来源：评论

学校读者我要写书评

暂无评论

Digitizing Farmers' Land data Collection Systems in Indonesia with the Use of Tani Millenial Apps 4

Digitizing Farmers' Land Data Collection Systems in Indonesi...

引用

4th International Conference on Cybernetics and Intelligent System, ICORIS 2022

作者： Bimantio, Mohammad Prasanto Putra, Dian Pratama Suparyanto, Teddy Ferhat, Amallia Nugraha, Nanda Satya Hidayat, Alam Ahmad Pardamean, Bens Institute of Agriculture STIPER Department of Food and Agricultural Technology Yogyakarta Indonesia Institute of Agriculture STIPER Department of Agrotechnology Yogyakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Institute of Agriculture STIPER Department of Agricultural Socio-Economics Yogyakarta Indonesia Institute of Agriculture STIPER Department of Forestry Yogyakarta Indonesia Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665453950

In this era of digital world information, farmers face challenges about information management of huge data and the complexity of processes in precision farming. The data collection carried out so far can cause several difficulties, especially if the data is needed by the government or academics to support decision-making. Agricultural data collection applications only cover 12% of the market share of Android-based agriculture-based applications. In this study, Tani Milenial application is present as an alternative to support agricultural data collection activities in Indonesia. This application encourages farmers to be active and contribute independently to their role as subjects of agricultural development and is accustomed to digitally recording their agricultural activities. In this developed application system, the community, especially farmers and farmer groups, will find it easier to get information about agricultural potential data around where they carry out agricultural activities and can access this information online. Tani Milenial works as a guide to help farmers and transform agriculture but still have some gaps which should be checked and removed. The data collected can be used by various parties for research and decision-making. The app can be further improved to develop new features related to education, market information, and goods. © 2022 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Exploring the Relation between Blood Tests and Covid-19 Using Machine Learning

Exploring the Relation between Blood Tests and Covid-19 Usin...

引用

2020 International Conference on data Analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Almansoor, Mohamed Hewahi, Nabil M. University of Bahrain Big Data Science Analytics Program Bahrain University of Bahrain Department of Computer Science Bahrain

ISBN: (纸本)9781728196756

COVID-19 is a global pandemic that hit the world in 2019-2020 and caused massive losses. Every day, hundreds of thousands of tests are being done on possible infected cases. It usually takes several hours to get the results of virus test in advanced countries, whereas in other countries might take days. The aim of this study is to investigate whether normal blood medical tests help in detecting covid-19 using various machine learning approaches. If true, this would give an indication to people who should undergo the virus test. In this paper we independently use machine learning algorithms including support vector machines, adaptive boosting, random forest and k-nearest neighbors. These algorithms are then merged to form ensemble learning which leads to the classification. The results show that the ensemble learning is having the highest true positive rate of 30%. The obtained results show that normal blood tests do not help much in giving right indications about detecting COVID-19. © 2020 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning for Generalizable Connectome Modeling Across Heterogeneous Atlas Spaces 22

Meta-Learning for Generalizable Connectome Modeling Across H...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Liang, Qinghao Adkinson, Brendan D. Scheinost, Dustin Department of Biomedical Engineering Yale University New HavenCT United States Interdepartmental Neuroscience Program Yale University New HavenCT United States Department of Radiology and Biomedical Imaging Yale School of Medicine New HavenCT United States Department of Statistics and Data Science Yale University New HavenCT United States

ISBN: (纸本)9798331520526

Leveraging large-scale neuroimaging datasets to improve predictive modeling in smaller, specialized cohorts is essential for translating research findings into clinical applications. To address this challenge, we propose a meta-learning inspired approach that enhances phenotype prediction by exploiting inter-phenotype correlations across independent datasets, without requiring uniform imaging data processing. By employing mappings derived from a small, independent cohort with data processed using different atlases, we align the data in the meta-training set to the target space of the meta-testing set. This approach eliminates the need for extensive data reprocessing. Evaluation in the UK Biobank dataset shows that our framework significantly improves predictive performance on unseen phenotypes, demonstrating its potential to generalize connectome-based models to small, heterogeneous cohorts. © 2025 IEEE.

关键词： Sorting

来源：评论

学校读者我要写书评

暂无评论

Testing the Inference Accuracy of Accelerator-Friendly Approximate Phylogeny Tracking

Testing the Inference Accuracy of Accelerator-Friendly Appro...

引用

2025 IEEE Symposium on Computational Intelligence in Artificial Life and Cooperative Intelligent Systems, ALIFE-CIS 2025

作者： Moreno, Matthew Andres Ranjan, Anika Dolson, Emily Zaman, Luis University of Michigan Department of Ecology and Evolutionary Biology Ann Arbor United States Center for the Study of Complex Systems University of Michigan Ann Arbor United States Michigan Institute for Data and Ai in Society University of Michigan Ann Arbor United States Undergraduate Research Opportunities Program University of Michigan Ann Arbor United States Michigan State University Department of Computer Science and Engineering East Lansing United States Program in Ecology Evolution and Behavior Michigan State University East Lansing United States

ISBN: (纸本)9798331508371

Computer simulations are an important tool for studying the mechanics of biological evolution. In particular, agent-based approaches provide an opportunity to collect high-quality records of ancestry relationships. Such phylogenies can provide insight into evolutionary dynamics within these simulations. Previous work generally tracks lineages directly, yielding an exact phylogenetic record of evolutionary history. However, challenges exist in scaling direct ancestrytracking approaches to highly-distributed, many-processor evolution in silico. An alternative approach is to estimate phylogenetic history via noncoding annotations on digital genomes, akin to how bioinformaticians build phylogenies by assessing genetic similarities between organisms. Recent work has extended this 'hereditary stratigraphy' approach to support powerful hardware accelerator platforms, such as the Cerebras Wafer-Scale Engine. Although these second-generation 'surface'-based hereditary stratigraphy algorithms have demonstrated order-ofmagnitude speedups over first-generation 'column'-based algorithms, it remains unknown how they impact the accuracy of reconstructed phylogenies. To address this question, we assessed reconstruction accuracy under alternative configurations across a matrix of evolutionary conditions varying in selection pressure, spatial structure, and ecological dynamics. Encouragingly, we find that the second-generation approaches provide higher reconstruction quality across most surveyed conditions. © 2025 IEEE.

关键词： Biostratigraphy

来源：评论

学校读者我要写书评

暂无评论

Learner Action Patterns in the Problem-Solving Process Related to program Code Composition Based on Tracking System Activities 7

Learner Action Patterns in the Problem-Solving Process Relat...

引用

7th International Conference on Informatics and Computing, ICIC 2022

作者： Syahidi, Aulia Akhrian Supianto, Ahmad Afif Hirashima, Tsukasa Watanobe, Yutaka Politeknik Negeri Banjarmasin Smart City Information System Applied Undergraduate Program Banjarmasin City Indonesia Research Center for Data and Information Sciences Bandung City Indonesia Graduate School of Advanced Science and Engineering Hiroshima University Kagamiyama Learning Engineering Laboratory Higashihiroshima Japan University of Aizu Division of Information Systems Department of Computer Science and Engineering Fukushima AizuWakamatsu Japan

ISBN: (纸本)9798350345711

Learning activities are an indicator of the learner's desire to learn during the learning process. The pattern of learner action is related to learning activities. In this case, in extracting the learning process, it is necessary to collect a lot of data through analysis of the learning process. The purpose of this study is to recommend and report the performance of an activity tracking system equipped with visual artifacts as an educational data mining approach to analyze action patterns when learners complete the arrangement of program code lines in each programming problem. In this study, data were taken from activity recordings when learners used interactive learning media for a basic programming subject called TOLSYASUPI-EduMed which had problem-solving learning models embedded in their interactions. Learning Analytics is used as a method of this research and data relationships from learner actions during the learning process using the 'if-then' rule. Log data is used for recording and detecting activities carried out by learners. We confirm that the results of the study are based on the findings of the data relationship that if the lines of program code are too long (more than five lines) then almost all learners experience a bottleneck condition. The completion time of each question and the number of iterations in completing the program code lines for each question have also been recorded and have a pattern of connection between the data. The information that has been obtained is then forwarded to teachers or stakeholders as key information to make appropriate feedback to learners based on the results as a means of analyzing and evaluating the programming learning process. © 2022 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

BERT-based Topic Modeling Approach for Malaria Research Publication

BERT-based Topic Modeling Approach for Malaria Research Publ...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Alam Ahmad Hidayat Rudi Nirwantono Arif Budiarto Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781665473286

Malaria is a communicable disease with half of the global population at risk due to its high morbidity and mortality rates. A massive number of studies are dedicated to malaria research, so it plays a key role in formulating the proper prevention strategy and effective malaria treatment. With the overwhelming number of updated publications in the field, an unsupervised text mining approach such as topic modeling may provide an alternative method for the malaria researcher to keep pace with new insights. In this work, we collect metadata of malaria publications from the PubMed database to perform BERT-based topic modeling to find well-defined topics regarding malaria research. The method is largely based on the popular BERTopic pipeline. We compare the performance of three different language models to generate document embeddings from the data. The dimension reduction and the density-based clustering algorithm are used to cluster the embeddings. The topic representation is computed based on the semantic similarity of the class TF-IDF representation. The substance of the resulting topics is then manually annotated based on the top words of each topic. We demonstrate that by merging initial topics into larger topics using hierarchical clustering and manual content-based examination, the evaluated coherence measure can be further improved, thus enhancing the topic's interpretability. Our modeling result is able to extract ten major topics recurring in the malaria research publication published from 2017–2022. The result provides preliminary insight to understand the dynamics and patterns of malaria research over the years

关键词： Text mining Heuristic algorithms Multimedia systems Time series analysis Sociology Semantics Pipelines

来源：评论

学校读者我要写书评

暂无评论

Position: Insights from Survey Methodology can Improve Training data

arXiv

引用

arXiv 2024年

作者： Eckman, Stephanie Plank, Barbara Kreuter, Frauke Social Data Science Center University of Maryland College ParkMD United States LMU Munich Germany Computer Science Department IT University of Copenhagen Denmark LMU Munich Germany Institute for Statistics LMU Munich Germany Joint Program in Survey Methodology University of Maryland College ParkMD United States

Whether future AI models are fair, trustworthy, and aligned with the public’s interests rests in part on our ability to collect accurate data about what we want the models to do. However, collecting high-quality data is difficult, and few AI/ML researchers are trained in data collection methods. Recent research in data-centric AI has show that higher quality training data leads to better performing models, making this the right moment to introduce AI/ML researchers to the field of survey methodology, the science of data collection. We summarize insights from the survey methodology literature and discuss how they can improve the quality of training and feedback data. We also suggest collaborative research ideas into how biases in data collection can be mitigated, making models more accurate and human-centric. © 2024, CC BY-NC-ND.

关键词： data acquisition

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：