检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Lee, Nahyuk Min, Juhong Lee, Junha Kim, Seungwook Lee, Kanghee Park, Jaesik Cho, Minsu Department of Computer Science and Engineering POSTECH Pohang Korea Republic of Graduate School of Artificial Intelligence POSTECH Pohang Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and compute. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://***/pmtr. Copyright 2024 by the author(s)

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Exploiting autoencoder’s weakness to generate pseudo anomalies

引用

Neural Computing and Applications 2024年第23期36卷 14075-14091页

作者： Astrid, Marcella Zaheer, Muhammad Zaigham Aouada, Djamila Lee, Seung-Ik Department of Artificial Intelligence University of Science and Technology Daejeon34113 Korea Republic of Field Robotics Research Section Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Interdisciplinary Centre for Security Reliability and Trust University of Luxembourg Luxembourg1855 Luxembourg Department of Computer Vision Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

Due to the rare occurrence of anomalous events, a typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal training data. At test time, the trained AE is expected to well reconstruct normal but to poorly reconstruct anomalous data. However, contrary to the expectation, anomalous data are often well reconstructed as well. In order to further separate the reconstruction quality between normal and anomalous data, we propose creating pseudo anomalies from learned adaptive noise by exploiting the aforementioned weakness of AE, i.e., reconstructing anomalies too well. The generated noise is added to the normal data to create pseudo anomalies. Extensive experiments on Ped2, Avenue, ShanghaiTech, CIFAR-10, and KDDCUP datasets demonstrate the effectiveness and generic applicability of our approach in improving the discriminative capability of AEs for anomaly detection. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Fetal Health Risk Classification Using Important Feature Selection and Cart Model on Cardiotocography Data

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第1期49卷 193-206页

作者： Ilham, Ahmad Nagara, Thahta Ardhika Prabu Kamaruddin, Mudyawati Khikmah, Laelatul Mantoro, Teddy Department of Informatics Universitas Muhammadiyah Semarang Semarang Indonesia Intelligent Data Science Research Group Universitas Muhammadiyah Semarang Semarang Indonesia Postgraduate Program of Medical Laboratory Science Universitas Muhammadiyah Semarang Semarang Indonesia Interdisciplinary Research Laboratory for Experimental Plasma Medicine Universitas Muhammadiyah Semarang Semarang Indonesia Department of Statistics Institut Teknologi Statistika dan Bisnis Muhammadiyah Semarang Semarang Indonesia School of Computer Science Nusa Putra University West Java Indonesia

Fetal mortality and newborn health issues require urgent attention because of high maternal and infant mortality rates during labor, highlighting the critical need for accurate fetal condition monitoring to reduce complications. This study proposes the development of a fetal health risk classification model based on Important Feature Selection (IFS) and a Classification and Regression Tree (CART) using cardiotocography (CTG) data from the UCI Machine Learning Repository. The IFS method was used to select the most relevant features, reduce model complexity, and increase generalization to prevent overfitting. The IFS-CART model was tested with 10-fold cross-validation and showed an accuracy of 94.50%, superior to the conventional CART, which only reached 93.83%. In addition, the average values of the True Positive Rate (TPR) and True Negative Rate (TNR) also increased, indicating that this model is effective in distinguishing normal, suspected, and pathological fetal conditions. Evaluation using the area under the curve receiver operating characteristic (AUC-ROC) showed that the model had high performance in detecting at-risk conditions, with an AUC of 0.981 for the"suspect" class. This finding confirmed that IFS-CART is not only accurate but also has high interpretability, making it easy for medical personnel to use for clinical decision support. The results of this study show that IFS-CART can serve as a reliable decision support system for real-time fetal health monitoring. Further implementation is expected to improve diagnostic accuracy and prevent complications during pregnancy and labor © 2025 Slovene Society Informatika. All rights reserved.

关键词： Fetal monitoring

来源：评论

学校读者我要写书评

暂无评论

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection 38

Textual Training for the Hassle-Free Removal of Unwanted Vis...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lee, Saehyung Mok, Jisoo Park, Sangha Shin, Yongho Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm Korea YH Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effect of Attention Mechanism and Aspect Embedding on the Performance of Long Short-term Memory Model for Aspect-Based Sentiment Analysis

Comparing the Effect of Attention Mechanism and Aspect Embed...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

The attention mechanism is one of the key enablers which have positioned transformer models as the state-of-the-art models in Natural Language Processing. By having the attention mechanism, the first version (vanilla) transformer model can retrieve the hidden state but at the same time can maintain a low requirement on the context vector dimension by selectively choosing to which encoder hidden states to give priority attention. The objective of this study is to evaluate the effect of modified Long Short-term Memory models architecture on the model performance as a predictive model. The first model is modified by adding an attention mechanism to its architecture;whilst, the second model is modified by adding additional input to its architecture. The performance of both models is compared by assigning each model the same task: to address the aspect-based sentiment analysis task. The experiment results show that adding an attention mechanism is not significantly increase the performance of the Long Short-term Memory model in comparison to adding input to the same model. In particular, the average training accuracy of the former model is 0.885;whilst, the average training accuracy of the latter model is 0.942. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Restaurant Customer Feedback Sentiment Analysis using Aspect Embedding Long Short-term Memory Model

Restaurant Customer Feedback Sentiment Analysis using Aspect...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

In the past ten years, there has been a proliferation of unstructured textual data from a variety of fields, allowing for the analysis of the sentiment polarity of the text authors in each of those datasets. To analyze sentiment polarity from unstructured data, machine learning tasks such as aspect-based sentiment analysis are used. The public dataset of restaurant patron feedback was used as the input for this study's empirical results of aspect-based sentiment analysis utilizing the Aspect Embedding Long Short-Term Memory model. The primary experiment's results show that the aspect embedding long short-term memory model can predict aspect sentiment polarization from customer feedback to restaurant service and aspect text representation (aspect text embedding) as input with excellent performance. For example, the Aspect Embedding Long Short-term Memory model, which uses ReLU as its activation function in the Dense layer tends to achieve higher performance (0.97 average accuracies) than the same model equipped with Sigmoid, and Tanh functions which achieve 0.954 and 0.956 average training accuracy respectively. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Robust temporal knowledge inference via pathway snapshots with liquid neural network

引用

Methods 2025年 241卷 24-32页

作者： Han, Peifu Wang, Jianmin Liu, Dayan Liu, Lin Song, Tao College of Computer Science and Technology China University of Petroleum Qingdao 266580 China The Interdisciplinary Graduate Program in Integrative Biotechnology Yonsei University Incheon 21983 South Korea Department of Stomatology The First Medical Center Chinese PLA General Hospital Beijing 100853 China

Static graphs play a pivotal role in modeling and analyzing biological and biomedical data. However, many real-world scenarios—such as disease progression and drug pharmacokinetic processes—exhibit dynamic behaviors. Consequently, static graph methods often struggle to robustly address new environments characterized by complex and previously unseen relationship changes. Here, we propose a method for constructing temporal knowledge inference agents tailored to disease pathways, enabling effective relation reasoning beyond their training environment under complex shifts. To achieve this, we developed an imitation learning framework using liquid neural networks, a class of continuous-time neural models inspired by the brain function that are causal and adaptable to changing conditions. Our findings indicate that liquid agents can distill the essential tasks from knowledge graph inputs while accounting temporal evolution, thereby enabling the transfer of temporal skills to novel time nodes. Compared to state-of-the-art deep reinforcement learning agents, experiments demonstrate that temporal robustness in decision-making emerges uniquely in liquid networks. © 2025

关键词： Disease Pathways Liquid Neural Networks Relation Reasoning Robust Decision-Making Temporal Knowledge Inference

来源：评论

学校读者我要写书评

暂无评论

Aspect-based Sentiment Analysis using Long Short-term Memory Model for Leveraging Restaurant Service Management

Aspect-based Sentiment Analysis using Long Short-term Memory...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

ISBN: (纸本)9798350320954

In general, the hospitality industry has been acknowledged as a major sector that gives a high contribution to economic development in many countries including Indonesia. For that reason, many initiatives have been implemented to help the growth of the hospitality industry in many countries including Indonesia to rebound from the harsh impact of the Covid-19 Pandemic. One such initiative is improving restaurant services as the main sector of the hospitality industry. This paper presents empirical results of sentiment analysis as a means to assess the quality of restaurant services as the first step to improving service quality. In particular, this study explores the aspect-based sentiment analysis method to identify some aspects of restaurant service which need improvement by learning the polarity of customers toward the restaurant services without having to meet the customers directly. By using the aspect-based sentiment analysis method, the customer sentiments comprising opinions, sentiments, evaluations, attitudes, and emotions from restaurant service can be analyzed using customers' online reviews as input. The main experiment findings showed that the Long Short-term Memory model can achieve high performance in predicting aspect polarization in restaurant service reviews. Other findings suggest that Sigmoid as an activation function achieved 0.97 average training accuracy and 0.69 average testing accuracy giving a better performance to the model in comparison to ReLU, Tanh, and ELU activation functions. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Multivariate Prediction of Building Energy Performance of Residential Buildings

引用

computers, Materials & Continua 2023年第6期75卷 5947-5964页

作者： Ibrahim Aliyu Tai-Won Um Sang-Joon Lee Chang Gyoon Lim Jinsul Kim Department of ICT Convergence System Engineering Chonnam National UniversityGwangju61186Korea Graduate School of Data Science Chonnam National UniversityGwangju61186Korea Interdisciplinary Program of Digital Future Convergence Service Chonnam National UniversityGwangju61186Korea Department of Computer Engineering Chonnam National UniversityYeosu59626Korea

In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest ***,effective design and planning for estimating heating load(HL)and cooling load(CL)for energy saving have become *** this vein,efforts have been made to predict the HL and CL using a univariate ***,this approach necessitates two models for learning HL and CL,requiring more computational ***,the one-dimensional(1D)convolutional neural network(CNN)has gained popularity due to its nominal computa-tional complexity,high performance,and low-cost hardware *** this paper,we formulate the prediction as a multivariate regression problem in which the HL and CL are simultaneously predicted using the 1D *** the building shape characteristics,one kernel size is adopted to create the receptive fields of the 1D CNN to extract the feature maps,a dense layer to interpret the maps,and an output layer with two neurons to predict the two real-valued responses,HL and *** the 1D data are not affected by excessive parameters,the pooling layer is not applied in this ***,the use of pooling has been questioned by recent *** performance of the proposed model displays a comparative advantage over existing models in terms of the mean squared error(MSE).Thus,the proposed model is effective for EPB prediction because it reduces computational time and significantly lowers the MSE.

关键词： Artificial intelligence(AI) convolutional neural network(CNN) cooling load deep learning energy energy load energy building performance heating load prediction

来源：评论

学校读者我要写书评

暂无评论

Involution symmetry quantification using recurrences

引用

Physical Review E 2024年第2期110卷 024203-024203页

作者： Gabriel Marghoti Thiago de Lima Prado Sergio Roberto Lopes Yoshito Hirata Physics Department Degree Program in Computer Science Interdisciplinary Center for Science Technology and Innovation CICTI Departament of Physics - Telegraphenberg 14473 Potsdam Germany Institute of Systems and Information Engineering

Symmetries are ubiquitous in science, aiding theoretical comprehension by discerning patterns in mathematical models and natural phenomena. This work introduces a method for assessing the extent of symmetry within a time series. We explore both microscopic and macroscopic features extracted from a recurrence plot. By analyzing the statistics of small recurrence matrices, our approach delves into microscale dynamics, facilitating the identification of symmetric time series segments through diagonal macroscale structures on a recurrence plot. We validate our approach by successfully quantifying involution symmetries for three-dimensional dynamical models, specifically, order-2 rotational symmetry in the Lorenz '63 model, and inversion symmetry in the Chua circuit. Our quantifier also detects symmetry breaking in the modified Lorenz model for El Niño phenomenon. The method can be applied in a versatile manner, not only to three-dimensional trajectories but also to univariate time series. Symmetry quantification in time series is promising for enhancing dynamical system modeling and profiling.

关键词： Chaos Dynamical systems Time series analysis

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：