检索结果-内蒙古大学图书馆

5th IEEE International Conference on Cognitive Machine Intelligence, CogMI 2023

作者： Kim, Dohee Sim, Sunghyun Yoon, Bori Liu, Ling Bae, Hyerim Pusan National University Major in Industrial Data Science & Engineering Dept. Industrial Engineering Busan Korea Republic of Dong-Eui University Dept. Industrial Management & Big Data Engineering Busan Korea Republic of College of Computing Georgia Institute of Technology Georgia United States

ISBN: (纸本)9798350323832

Time-series data consists of a sequence of observations recorded in chronological order, where the data changes over time. This type of data exhibits various characteristics, such as temporal volatility, trends, and seasonality. Recently, a new layer structure called Correlation Recurrent Units (CRU) has been proposed to capture not only temporal variability but also trends and seasonality in time-series data. In this study, we propose an end-to-end model that utilizes a CRU autoencoder to learn temporal feature representations and address time-series classification problems simultaneously. To validate the performance of our proposed model, we conducted comparative experiments using 30 time-series classification datasets from six different types. The experimental results showed that the proposed model outperformed the baseline models in 20 out of the 30 time-series datasets. This indicates that the proposed approach effectively captures various temporal features in time-series data and improves the performance of time-series classification tasks. © 2023 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

DALDA: data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance Scaling

arXiv

引用

arXiv 2024年

作者： Jung, Kyuheon Seo, Yongdeuk Cho, Seongwoo Kim, Jaeyoung Min, Hyun-Seok Choi, Sungchul Major in Industrial Data Science & Engineering Department of Industrial and Data Engineering Pukyong National University Korea Republic of Teamreboott Inc. Tomocube Inc.

In this paper, we present an effective data augmentation framework leveraging the Large Language Model (LLM) and Diffusion Model (DM) to tackle the challenges inherent in data-scarce scenarios. Recently, DMs have opened up the possibility of generating synthetic images to complement a few training images. However, increasing the diversity of synthetic images also raises the risk of generating samples outside the target distribution. Our approach addresses this issue by embedding novel semantic information into text prompts via LLM and utilizing real images as visual prompts, thus generating semantically rich images. To ensure that the generated images remain within the target distribution, we dynamically adjust the guidance weight based on each image's CLIPScore to control the diversity. Experimental results show that our method produces synthetic images with enhanced diversity while maintaining adherence to the target distribution. Consequently, our approach proves to be more efficient in the few-shot setting on several benchmarks. Our code is available at https://***/kkyuhun94/dalda. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Understanding risk perceptions of e-scooter use: E-scooter users and non-users

引用

Heliyon 2025年第3期11卷 e42312页

作者： Son, Yu Gyeong Kim, Min Joo Lee, Yushin Park, Donggun Department of Media Communication Pukyong National University South Korea Major in Industrial Data Science & Engineering Department of Industrial and Data Engineering Pukyong National University South Korea

E-scooters share the roads with other users, making it crucial to understand how these different road users perceive the risky behaviors of e-scooter riders. While perceptions of risk situations caused by the e-scooter rider are likely complex and multifaceted, previous research has not adequately clarified these perspectives. Additionally, the specific roles of assessment tools in describing each distinct risk scenario have yet to be thoroughly examined. This study analyzed the validity of existing risk assessments by examining e-scooter risk perceptions among both users and non-users, grouped according to riding experience (non-users: fewer than five rides;users: five or more rides). The assessment included three primary analyses: (1) a comparison of perceived risk and perceived control across two descriptive assessment tools (text-based and video-based);(2) an examination of the relationships among perceived risk, perceived control, and willingness to share the road;and (3) an analysis of differences in how e-scooter users and non-users prioritize evaluation criteria when assessing specific risky situations. Participants (20 e-scooter users and 20 non-users) evaluated 14 risky scenarios. data on perceived risk and willingness to share were collected for each scenario, while perceived control was assessed once after viewing all 14 scenarios. Analyses were conducted using SPSS, with paired t-tests to assess differences across assessment tools, 2-tailed correlation tests to examine relationships among variables, and Kruskal-Wallis tests to rank the importance of different evaluation criteria by group. The results of the study confirmed that participants’ risk perceptions varied depending on the assessment tool used to describe risk. Additionally, it demonstrated that road user experience influences various perceptions of risk. The results underscore the importance of selecting appropriate assessment tools for effective risk communication and assessment strategies an

关键词： Descriptive assessment tool e-scooter riding Risk perception Road-user experience

来源：评论

学校读者我要写书评

暂无评论

Order batching and sequencing in a sequential zone order picking system with consideration of workload balance

Order batching and sequencing in a sequential zone order pic...

引用

IISE Annual Conference and Expo 2022

作者： Park, Jeongwon Fibrianto, Henokh Y. Hong, Soondo Major in Industrial Data Science & Engineering Pusan National University Busan Korea Republic of GrabTaxi Holdings Pte. Ltd Singapore Singapore Department of Industrial Engineering Pusan National University Busan Korea Republic of

ISBN: (纸本)9781713858072

Due to the workload imbalance between zones, a sequential zone order picking system consistently experiences blocking delay when a tote cannot move to the next zone because the next zone is still occupied and starving delay when a zone needs to remain idle until the preceding zone passes a tote to work on. This study develops an order batching and sequencing model for zone workload balancing (OBZ) in a sequential zone order picking system with consecutive batch windows to mitigate blocking and starving. The OBZ model aims to minimize the sum of maximum picking time on each time window to balance the workload between zones and alleviate congestion for makespan reduction. To shorten the makespan in batch order picking, the proposed model considers the transition between batch windows to prevent the last batch in the earlier batch window from causing a blocking delay in the current batch window. The results from the simulation experiments report that OBZ obtains significant makespan reduction by mitigating blocking delay in a sequential zone picking system. © 2022 IISE Annual Conference and Expo 2022. All rights reserved.

关键词： Warehouses

来源：评论

学校读者我要写书评

暂无评论

Neural Bezier Interpolation with Manifold Learning for Reliable Vessel Trajectory Prediction

Neural Bezier Interpolation with Manifold Learning for Relia...

引用

IEEE International Conference on Cognitive Machine Intelligence (CogMI)

作者： Gawon Lee Dohee Kim Segil Park Sunghyun Sim Ling Liu Hyerim Bae Department of Industrial Engineering Major in Industrial Data Science & Engineering Pusan National University Pusan City South Korea Safe & Clean Supply Chain Research Center Pusan National University Pusan City South Korea Korea Research Institute of Ships and Ocean Engineering (KRISO) Daejeon City South Korea Major in Industrial Management and Big Data Engineering Dong-Eui University Pusan City South Korea College of Computing Georgia Institute of Technology Georgia USA Department of Data Science Graduate School of Data Science Pusan National University Pusan City South Korea

ISBN: (数字)9798350386721

ISBN: (纸本)9798350386738

With advancements in technology, large-scale ship operation data become more accessible, leading to growing interest in Automatic Identification System (AIS) research related to maritime transportation. However, the AIS requires long-distance data transmission between sea and land and is more susceptible to environmental conditions, resulting in frequent data loss and corruption. Low-frequency AIS data, caused by persistent transmission data losses, can compromise not only the data quality itself but also the quality of AIS data mining research, especially the reliability of vessel trajectory identification. To resolve this issue, this paper presents Neural Bezier Interpolation (NBI), an interpolation method that combines the predictive capabilities of deep learning model with Bezier Interpolation, aiming to capture and reflect the turning radius of a ship through control points. This hybrid approach mitigates the overfitting problem of deep learning models and overcomes the limitations of traditional interpolation models that cannot independently account for a vessel's speed and heading by integrating Bezier interpolation with deep learning. To verify the effectiveness of the proposed methodology to properly restore low-frequency data, we conduct performance comparison of the proposed approach with existing representative AIS methods. The results confirm that the proposed approach can effectively extract the characteristics of the sea area and improve restoration performance.

关键词： Deep learning Interpolation data integrity Transportation Predictive models Propagation losses Trajectory Reliability Artificial intelligence Marine vehicles

来源：评论

学校读者我要写书评

暂无评论

Temporal Attention Gate Network With Temporal Decomposition for Improved Prediction Accuracy of Univariate Time-Series data

Temporal Attention Gate Network With Temporal Decomposition ...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Sunghyun Sim Dohee Kim Seok Chan Jeong Industrial Management & Big Data Engineering Major Div. of Industrial Convergence System Engineering Dong-Eui University Busan South Korea Dept. of Industrial Engineering Industrial Data Science & Engineering Major Pusan National University Busan South Korea Dept. of e-Business College of Commerce and Economics & AI Grand ICT Research Center Dong-Eui University

Time-series forecasting has widely been addressed in data science and various domains, but many limitations persist in terms of prediction accuracy. We propose a network architecture called temporal attention gate network (TAGNet) to improve the prediction accuracy of time-series prediction. TAGNet integrates new concepts of temporal filter and temporal attention gate. First, the temporal filter learns information embedded in time-series data by decomposing the input data through variational mode decomposition. Second, the temporal attention gate learns the relationship between the decomposed time-series signals and hidden states to learn their relationships. To verify the performance of the proposed TAGNet, a comparative experiment was conducted on three univariate time-series datasets. The results show that the prediction performance improves by 15% on average for short-, medium-, and long-term predictions compared with various deep learning methods.

关键词： Deep learning Limiting Microprocessors Decision making Logic gates Network architecture data science

来源：评论

学校读者我要写书评

暂无评论

Improving Time-Series Classification Accuracy Based on Temporal Feature Representation Learning Using CRU-LSTM Autoencoder

Improving Time-Series Classification Accuracy Based on Tempo...

引用

IEEE International Conference on Cognitive Machine Intelligence (CogMI)

作者： Dohee Kim Sunghyun Sim Bori Yoon Ling Liu Hyerim Bae Dept. Industrial Engineering Major in Industrial Data Science & Engineering Pusan National University Busan South Korea Dept. Industrial Management & Big Data Engineering Dong-Eui University Busan South Korea College of Computing Georgia Institute of Technology Georgia USA

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised binary classification with latent distance learning

arXiv

引用

arXiv 2022年

作者： Kamal, Imam Mustafa Bae, Hyerim Institute of Intelligent Logistics Big Data Pusan National University Busan46241 Korea Republic of Major in Industrial Data Science & Engineering Department of Industrial Engineering Pusan National University Busan46241 Korea Republic of

Binary classification (BC) is a practical task that is ubiquitous in real-world problems, such as distinguishing healthy and unhealthy objects in biomedical diagnostics and defective and non-defective products in manufacturing inspections. Nonetheless, fully annotated data are commonly required to effectively solve this problem, and their collection by domain experts is a tedious and expensive procedure. In contrast to BC, several significant semi-supervised learning techniques that heavily rely on stochastic data augmentation techniques have been devised for solving multi-class classification. In this study, we demonstrate that the stochastic data augmentation technique is less suitable for solving typical BC problems because it can omit crucial features that strictly distinguish between positive and negative samples. To address this issue, we propose a new learning representation to solve the BC problem using a few labels with a random k-pair cross-distance learning mechanism. First, by harnessing a few labeled samples, the encoder network learns the projection of positive and negative samples in angular spaces to maximize and minimize their inter-class and intra-class distances, respectively. Second, the classifier learns to discriminate between positive and negative samples using on-the-fly labels generated based on the angular space and labeled samples to solve BC tasks. Extensive experiments were conducted using four real-world publicly available BC datasets. With few labels and without any data augmentation techniques, the proposed method outperformed state-of-the-art semi-supervised and self-supervised learning methods. Moreover, with 10% labeling, our semi-supervised classifier could obtain competitive accuracy compared with a fully supervised setting. © 2022, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Providing an Affective Design for a Door-Pulling Physical User Interface

SSRN

引用

SSRN 2023年

作者： Kang, Sang Hyeon Kim, Daemin Jin, Sangeun Department of Industrial and Manufacturing Systems Engineering Iowa State University AmesIA50011-2164 United States The Human Mechatronics Engineering Laboratory Division of Mechatronics Engineering Dongseo University Busan47011 Korea Republic of Major in Industrial Data Science & Engineering Department of Industrial Engineering Pusan National University Busan46241 Korea Republic of

Understanding how certain engineering design factors influence users’ affective emotions is gaining attention in order to achieve better designs for high-end products. This study examines how to quantify users' emotional satisfaction with the door-pulling operation. A series of pilot tests are conducted as follows: (1) an in-house developed force-stroke machine captures 132 door motions and reveals great reproducibility at 10mm/s with a 100mm displacement (r = 0.973);(2) the captured door motions are expressed as force-stroke curves (kgf on the y-axis, millimeters on the x-axis) to identify physical properties;(3) nine experts evaluate the doors’ overall operating sensitivity for the 132 latch-hook modules by using a 100mm visual analog scale, figuring out the proper spring force range (0.5-2kgf) and displacement range (5-11mm);(4) 23 semantic pairs collected from the nine experts describe the door-operating sensitivity;and (5) 30 participants rate the 23 semantic pairs based on a semantic differential scale while using the doors to identify primary affective factors. Factor analysis derives four semantic pairs: reaction intensity, softness, luxuriousness, and robustness. Based on them, the 30 participants evaluate the door-operating sensitivity for FORCE (latch spring force: 1kgf, 1.5kgf, 2kgf) and STROKE (stroke lengths: 5mm, 10mm, 15mm). Results show STROKE is a better predictor of emotional satisfaction and suggest a longer stroke length more evenly distributes the tension on the tender and elastic pulling load while opening the door. This property may give users more time to feel the overall operating sensitivity, especially for luxuriousness (which accounts for about 50% of the overall satisfaction). These results can be utilized to achieve better designs for high-end products that reflect users’ affective emotions. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Reynosin protects neuronal cells from microglial neuroinflammation by suppressing NLRP3 inflammasome activation mediated by NADPH oxidase

引用

Chinese Journal of Natural Medicines 2024年第6期22卷 486-500页

作者： YANG Yanqiu CHE Yue FANG Mingxia YAO Xiaohu ZHOU Di WANG Feng CHEN Gang LIANG Dong LI Ning HOU Yue Key Laboratory of Bioresource Research and Development of Liaoning Province College of Life and Health SciencesNorth-eastern UniversityShenyang 110000China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Key Laboratory of Data Analytics and Optimization for Smart IndustryMinistry of EducationNortheastern UniversityShenyang 110000China School of Traditional Chinese Materia Medica Key Laboratory of Innovative Traditional Chinese Medicine for Major Chronic Diseases of Liaoning provinceKey Laboratory for TCM Material Basis Study and Innovative Drug Development of Shenyang CityShenyang Pharmaceutical UniversityShenyang 110000China State Key Laboratory for Chemistry and Molecular Engineering of Medicinal Resources School of Chemistry and Pharmaceutical SciencesGuangxi Normal UniversityGuilin 541000China

Neuroinflammation,mediated by the nucleotide-binding oligomerization domain-like receptor family pyrin domain-containing-3(NLRP3)inflammasome,is a significant contributor to the pathogenesis of neurodegenerative diseases(NDDs).Reynos-in,a natural sesquiterpene lactone(SL),exhibits a broad spectrum of pharmacological effects,suggesting its potential therapeutic ***,the effects and mechanism of reynosin on neuroinflammation remain *** current study explores the effects and mechanisms of reynosin on neuroinflammation using mice and BV-2 microglial cells treated with lipopolysaccharide(LPS).Our findings reveal that reynosin effectively reduces microglial inflammation in vitro,as demonstrated by decreased CD11b expression and lowered interleukin-1 beta(IL-1β)and interleukin-18(IL-18)mRNA and protein ***,in vivo,results showed a re-duction in the number of Iba-1 positive cells and alleviation of morphological alterations,alongside decreased expressions of IL-1βand *** analysis indicates that reynosin inhibits NLRP3 inflammasome activation,evidenced by reduced transcription of NLRP3 and caspase-1,diminished NLRP3 protein expression,inhibited apoptosis-associated speck-like protein containing a CARD(ASC)oli-gomerization,and decreased caspase-1 ***,reynosin curtailed the activation of nicotinamide adenine dinuc-leotide phosphate(NADPH)oxidase,demonstrated by reduced NADP^(+)and NADPH levels,downregulation of gp91^(phox) mRNA,pro-tein expression,suppression of p47^(phox) expression and translocation to the ***,reynosin exhibited a neuroprotective effect against microglial inflammation in vivo and in *** collective findings underscore reynosin’s capacity to mitigate mi-croglial inflammation by inhibiting the NLRP3 inflammasome,thus highlighting its potential as a therapeutic agent for managing neuroinflammation.

关键词： Microglia NLRP3 inflammasome Reactive oxygen species NADPH oxidase Neuron Reynosin

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：