检索结果-内蒙古大学图书馆

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Seungeun Kang Jin Kim Namgi Kim Division of AI Computer Science and Engineering Kyonggi University Suwon Republic of Korea

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

Lifelog data has become easier to collect due to the development of wearable technology and IoT devices, and its importance has increased with the growth of the healthcare industry. In particular, personalized services such as personalized healthcare and stress management are possible because of the personal characteristics of lifelog data. In this study, we build a sleep quality classification system using lifelog datasets. As a preprocessing of the time series data, we propose a method for using different time periods depending on the type of question to be considered, a method for synchronizing variable lengths, and a process for normalizing the data. In addition, this paper suggests Weighted Validation Loss Propagation and Set Lower Bound methods to enhance generalization performance in the process of building and training classification deep learning models with Convolution Neural Network (CNN) and Attention-based models. Then, we discuss model significance, applications, and limitations. We also propose future research to overcome the limitations.

关键词： Performance evaluation Deep learning Training Memory management Data preprocessing Time series analysis Medical services Sleep apnea Data models Load modeling

来源：评论

学校读者我要写书评

暂无评论

Abnormal Behavior Detection Using Deep-Learning-Based Video Data Structuring

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 2371-2386页

作者： Min-Jeong Kim Byeong-Uk Jeon Hyun Yoo Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea Contents Convergence Software Research Institute Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea

With the increasing number of digital devices generating a vast amount of video data,the recognition of abnormal image patterns has become more ***,it is necessary to develop a method that achieves this task using object and behavior information within video *** methods for detecting abnormal behaviors only focus on simple motions,therefore they cannot determine the overall behavior occurring throughout a *** this study,an abnormal behavior detection method that uses deep learning(DL)-based video-data structuring is *** and motions are first extracted from continuous images by combining existing DL-based image analysis *** weight of the continuous data pattern is then analyzed through data structuring to classify the overall *** performance of the proposed method was evaluated using varying parameter settings,such as the size of the action clip and interval between action *** model achieved an accuracy of 0.9817,indicating excellent ***,we conclude that the proposed data structuring method is useful in detecting and classifying abnormal behaviors.

关键词： Deep learning object detection abnormal behavior recognition classification data structuring

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Commonsense Reasoning over Machine Imagination

Zero-shot Commonsense Reasoning over Machine Imagination

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Park, Hyuntae Kim, Yeachan Park, Jun-Hyung Lee, SangKeun Department of Artificial Intelligence Korea University Seoul Korea Republic of Division of Language & AI Hankuk University of Foreign Studies Seoul Korea Republic of Department of Computer Science and Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798891761681

Recent approaches to zero-shot commonsense reasoning have enabled Pre-trained Language Models (PLMs) to learn a broad range of commonsense knowledge without being tailored to specific situations. However, they often suffer from human reporting bias inherent in textual commonsense knowledge, leading to discrepancies in understanding between PLMs and humans. In this work, we aim to bridge this gap by introducing an additional information channel to PLMs. We propose IMAGINE (Machine Imagination-based Reasoning), a novel zero-shot commonsense reasoning framework designed to complement textual inputs with visual signals derived from machine-generated images. To achieve this, we enhance PLMs with imagination capabilities by incorporating an image generator into the reasoning process. To guide PLMs in effectively leveraging machine imagination, we create a synthetic pretraining dataset that simulates visual question-answering. Our extensive experiments on diverse reasoning benchmarks and analysis show that IMAGINE outperforms existing methods by a large margin, highlighting the strength of machine imagination in mitigating reporting bias and enhancing generalization capabilities. © 2024 Association for Computational Linguistics.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Prescribed Performance Control for Euler-Lagrange Systems 11

Optimal Prescribed Performance Control for Euler-Lagrange Sy...

引用

11th IEEE International Conference on Systems and Control, ICSC 2023

作者： Malli, Ioanna Vlachos, Christos Bechlioulis, Charalampos P. Kyriakopoulos, Kostas J. School of Mechanical Engineering National Technical University of Athens Greece University of Patras Department of Electrical and Computer Engineering Greece New York University Engineering Division Center for Ai and Robotics Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350304886

This work introduces an optimal control policy aiming to stabilize an Euler-Lagrange system of unknown dynamics, while simultaneously satisfying predefined response criteria. The proposed methodology unfolds in two stages. In the initial phase, a neural network is trained online via an iterative process to capture the system's dynamics. Subsequently, in the second phase, by utilizing the acquired dynamics, a successive approximation algorithm is employed to derive a nearly optimal control law while taking into consideration prescribed performance specifications such as convergence speed and steady state error. Validation of our method is achieved through a simulated paradigm, confirming the success of both the identification process and the minimization of the adopted integral cost. © 2023 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science

MELT: Materials-aware Continued Pre-training for Language Mo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Junho Kim, Yeachan Park, Jun-Hyung Oh, Yerim Kim, Suho Lee, SangKeun Department of Artificial Intelligence Korea University Seoul Korea Republic of Division of Language & AI Hankuk University of Foreign Studies Seoul Korea Republic of Department of Computer Science and Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798891761681

We introduce a novel continued pre-training method, MELT (Materials-aware continued pretraining), specifically designed to efficiently adapt the pre-trained language models (PLMs) for materials science. Unlike previous adaptation strategies that solely focus on constructing domain-specific corpus, MELT comprehensively considers both the corpus and the training strategy, given that materials science corpus has distinct characteristics from other domains. To this end, we first construct a comprehensive materials knowledge base from the scientific corpus by building semantic graphs. Leveraging this extracted knowledge, we integrate a curriculum into the adaptation process that begins with familiar and generalized concepts and progressively moves toward more specialized terms. We conduct extensive experiments across diverse benchmarks to verify the effectiveness and generality of MELT. A comprehensive evaluation convincingly supports the strength of MELT, demonstrating superior performance compared to existing continued pretraining methods. In-depth analysis of MELT also shows that MELT enables PLMs to effectively represent materials entities compared to the existing adaptation methods, thereby highlighting its broad applicability across a wide spectrum of materials science. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Improved Time Feedforward Connections Recurrent Neural Networks

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 2743-2755页

作者： Jin Wang Yongsong Zou Se-Jung Lim School of Hydraulic&Environmental Engineering Changsha University of Science&TechnologyChangsha410014China School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410014China AI Liberal Arts Studies Division of ConvergenceHonam UniversityGwangju-si62399Korea

Recurrent Neural Networks(RNNs)have been widely applied to deal with temporal problems,such as flood forecasting and financial data *** the one hand,traditional RNNs models amplify the gradient issue due to the strict time serial dependency,making it difficult to realize a long-term memory *** the other hand,RNNs cells are highly complex,which will signifi-cantly increase computational complexity and cause waste of computational resources during model *** this paper,an improved Time Feedforward Connections Recurrent Neural Networks(TFC-RNNs)model was first proposed to address the gradient issue.A parallel branch was introduced for the hidden state at time t−2 to be directly transferred to time t without the nonlinear transforma-tion at time t−*** is effective in improving the long-term dependence of ***,a novel cell structure named Single Gate Recurrent Unit(SGRU)was *** cell structure can reduce the number of parameters for RNNs cell,consequently reducing the computational ***,applying SGRU to TFC-RNNs as a new TFC-SGRU model solves the above two ***,the performance of our proposed TFC-SGRU was verified through sev-eral experiments in terms of long-term memory and anti-interference *** results demonstrated that our proposed TFC-SGRU model can cap-ture helpful information with time step 1500 and effectively filter out the *** TFC-SGRU model accuracy is better than the LSTM and GRU models regarding language processing ability.

关键词： Time feedforward connections long-short term memory gated recurrent unit SGRU RNNs

来源：评论

学校读者我要写书评

暂无评论

SEED: Semantic Knowledge Transfer for Language Model Adaptation to Materials Science

SEED: Semantic Knowledge Transfer for Language Model Adaptat...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Yeachan Park, Jun-Hyung Kim, SungHo Park, Juhyeong Kim, Sangyun Lee, SangKeun Department of Artificial Intelligence Korea University Seoul Korea Republic of Division of Language & AI Hankuk University of Foreign Studies Seoul Korea Republic of Department of Computer Science and Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798891761667

Materials science is an interdisciplinary field focused on studying and discovering materials around us. However, due to the vast space of materials, downstream datasets in this field are typically scarce and have limited coverage. This inherent limitation poses challenges when adapting pre-trained language models (PLMs) to materials science, as existing methods rely heavily on frequency information from these limited datasets. In this paper, we propose Semantic Knowledge Transfer (SEED), a novel vocabulary expansion method designed to adapt pre-trained language models (PLMs) for materials science. The core strategy of SEED is to transfer materials knowledge from lightweight embeddings into PLMs. To achieve this, we introduce knowledge bridge networks, which learn to transfer the latent knowledge embedded in materials-specific embeddings into representations compatible with PLMs. By expanding the embedding layer of PLMs with these transformed embeddings, the models can comprehensively understand the complex terminology associated with materials science. We conduct extensive experiments across a broad range of materials-related benchmarks. The comprehensive evaluation results convincingly demonstrate that SEED mitigates the limitations of previous adaptation methods, showcasing the efficacy of embedding knowledge transfer into PLMs. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Building K-Contents Specialized Text2Image Pipeline

Research on Building K-Contents Specialized Text2Image Pipel...

引用

International Conference on Advanced Communication Technology (ICACT)

作者： Seungeun Kang Dahyun Lee Sangbum Han Seokjae Lim Namgi Kim Division of AI Computer Science and Engineering Kyonggi University Suwon Republic of Korea AI Tech Team LOTTE INNOVATE Seoul Republic of Korea

ISBN: (数字)9791188428137

ISBN: (纸本)9798331507602

Recently, there has been a lot of research on the Text2Image generative model as social and technological interest in generative models has increased. In addition, the interest in Korean contents (K-Contnets) has increased. In this paper, we propose "K-Contents Specialized Text2Image Pipeline". "K-Contents Specialized Text2Image Pipelilne" is specialized for understanding Korean prompts and aims to generate images specialized for various K-Contents. To build the pipeline, we collect and preprocess text and image data. Then, we train the Korean Text Encoder on the text data and train three specialized K-Contents generation pipelines on the image data. We also propose to use the SDXL model’s Img2Img Refiner with the SD model for time-efficient image generation. After that, we use the learned pipelines to generate real images and analyze their performance. Finally, we discuss the utilization of the above pipelines, limitations, and future research.

关键词： Image synthesis Pipelines Buildings Communications technology

来源：评论

学校读者我要写书评

暂无评论

Moleco: Molecular Contrastive Learning with Chemical Language Models for Molecular Property Prediction

Moleco: Molecular Contrastive Learning with Chemical Languag...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Park, Jun-Hyung Park, Hyuntae Kim, Yeachan Lim, Woosang Lee, SangKeun Division of Language & AI Hankuk University of Foreign Studies Korea Republic of Department of Artificial Intelligence Korea University Korea Republic of POSCO Holdings Korea Republic of Department of Computer Science and Engineering Korea University Korea Republic of

ISBN: (纸本)9798891761667

Pre-trained chemical language models (CLMs) excel in the field of molecular property prediction, utilizing string-based molecular descriptors such as SMILES for learning universal representations. However, such string-based descriptors implicitly contain limited structural information, which is closely associated with molecular property prediction. In this work, we introduce Moleco, a novel contrastive learning framework to enhance the understanding of molecular structures within CLMs. Based on the similarity of fingerprint vectors among different molecules, we train CLMs to distinguish structurally similar and dissimilar molecules in a contrastive manner. Experimental results demonstrate that Moleco significantly improves the molecular property prediction performance of CLMs, outperforming state-of-the-art models. Moreover, our in-depth analysis with diverse Moleco variants verifies that fingerprint vectors are highly effective features in improving CLMs’ understanding of the structural information of molecules1 © 2024 Association for Computational Linguistics.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Approach to Cardiac Health: Machine Learning for Heart Disease Prediction

A Data-Driven Approach to Cardiac Health: Machine Learning f...

引用

2023 IEEE Technology and engineering Management Conference - Asia Pacific, TEMSCON-ASPAC 2023

作者： Talaviya, Jeel Trivedi, Dhruv Ramani, Ronish Diwan, Anjali Mahadeva, Rajesh Mahadeva, Rajesh Marwadi University Computer-Engineering with Ai Rajkot India Khalifa University Department of Physics Abu Dhabi United Arab Emirates Uttaranchal University Division of Research and Innovation Dehradun India

ISBN: (纸本)9798350384659

Heart disease remains one of the leading causes of death worldwide, underscoring the critical need for accurate and timely prediction models. The outcome of cardiac disease is one area where machine learning algorithms have shown substantial potential. A rapidly advancing area of research is focused on using machine learning for heart disease prediction. Recent studies have extensively explored machine learning methods to anticipate heart disease in patients. This research aims to develop precise prediction models that can identify individuals at high risk of developing heart disease. These models consider various characteristics such as age, gender, medical history, and lifestyle choices to calculate the likelihood of heart disease. Notably, the accuracy of these machine learning models often surpasses that of traditional methods used for predicting cardiac disease. Integrating machine learning algorithms into heart disease diagnosis and treatment can improve patient outcomes and overall health. © 2023 IEEE.

关键词： Forecasting

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：