NSTL国家科技图书文献中心

1. Large Language Models With Holistically Thought Could Be Better Doctors NSTL国家科技图书文献中心

Yixuan Weng | Bin Li ... - 《Natural Language Processing and Chinese Computing,Part II》 - CCF International Conference on Natural Language Processing and Chinese Computing - 2025, - 319～332 - 共14页

摘要： fields, such as mathematics, logic, and commonsense QA | (CQA) system aims at providing a series* of* | The medical conversational question answering | professional medical services to improve the efficiency of | medical care. Despite the success of large language

关键词： Large language model | Medical conversational QA | Holistically thought

2. Capturing Temporal Components for Time Series Classification NSTL国家科技图书文献中心

Venkata Ragavendra V... | Ranjith Ramanathan ... - 《Pattern Recognition,Part I》 - International Conference on Pattern Recognition - 2025, - 215～230 - 共16页

摘要： series classification, the task of categorizing | for time series* classification. We demonstrate its* | available time series* classification benchmarks* | Analyzing sequential data is crucial in many | domains, particularly due to the abundance of data

关键词： Time-series classification | Temporal compositionality | Time series segmentation

3. Semi-periodic Activation for Time Series Classification NSTL国家科技图书文献中心

Jose Gilberto Barbos... | Andre Guarnier de Mi...... - 《Intelligent Systems,Part IV》 - Brazilian Conference on Intelligent Systems - 2025, - 76～90 - 共15页

摘要： in time series* tasks. It highlights the need to* | periodicity, for activation in time series* neural networks* | for time series* classification, obtaining the best* | This paper investigates the lack of research | on activation functions for neural network models

关键词： Time series | Deep learning | Activation function

4. Mining Rare Temporal Pattern in Time Series NSTL国家科技图书文献中心

Long Van Ho | Nguyen Ho ... - 《Databases Theory and Applications》 - Australasian Database Conference - 2025, - 143～157 - 共15页

摘要：Time series* data from various domains is* | patterns within these series* can provide valuable* | Rare Temporal Pattern Mining from Time Series | time series* data as input and outputs rare temporal* | continuously growing, and extracting and analyzing temporal

关键词： Pattern mining | Rare temporal patterns | Time series

5. Auto-sktime: Automated Time Series Forecasting NSTL国家科技图书文献中心

Marc-Andre Zoller | Marius Lindauer ... - 《Learning and Intelligent Optimization》 - International Conference on Learning and Intelligent Optimization - 2025, - 456～471 - 共16页

摘要：In today's data-driven landscape, time series | series data, coupled with the expanding landscape of | framework for automated time series* forecasting. The* | series data. First, pipeline templates to account for | -world time series* datasets demonstrate the*

关键词： Automated machine learning | Time series | Forecasting

6. An Empirical Evaluation of DeepAR for Univariate Time Series Forecasting NSTL国家科技图书文献中心

Ricardo Urjais Gomes | Carlos Soares ... - 《Progress in Artificial Intelligence,Part III》 - EPIA Conference on Artificial Intelligence - 2025, - 188～199 - 共12页

摘要：DeepAR is a popular probabilistic time series | of related time series. For this reason, it is a | . We use 100 time series* from the M4 competition to* | forecasting algorithm. According to the authors, DeepAR is | particularly suitable to build global models using hundreds

关键词： Time series forecast | Probabilistic forecast | Deep time series

7. Bidirectional Dependency Representation Disentanglement for Time Series Classification NSTL国家科技图书文献中心

Tianren Zhao | Hua Zuo ... - 《AI 2024: Advances in Artificial Intelligence,Part I》 - Australasian Joint Conference on Artificial Intelligence - 2025, - 98～110 - 共13页

摘要：Time series* classification an important and* | -stationary property of time series* data hinders further* | time series* classification that leverages the power* | challenging real-world problem and has been extensively | studied by deep learning methods. However, the non

关键词： Time series classification | Domain generalization

8. bSAX: A Novel Sketch for Efficient Data Series Similarity Search NSTL国家科技图书文献中心

Han Hu | Jiye Qiu ... - 《Database Systems for Advanced Applications,Part V》 - International Conference on Database Systems for Advanced Applications | International Workshop on Big Data Management and Service | International Workshop on Graph Data Management and Analysis | International Workshop on Big Data Quality Management | Workshop on Emerging Results inData Science and Engineering - 2025, - 442～458 - 共17页

摘要：, data series* similarity search holds great* | series indices for exact similarity search. The iSAX | index for data series, with a cost model involving | In contemporary applications of data analysis | significance. A substantial body of research design data

关键词： Similarity search | Summarization | Data series

9. Bitcoin Forecasting Using Deep Learning and Time Series Ensemble Techniques NSTL国家科技图书文献中心

Huma Zafar | Stylianos Kapetanaki... - 《Artificial Intelligence XLI,Part I》 - SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence - 2025, - 105～115 - 共11页

摘要：, comparing Time Series* and Deep Learning models, evaluating* | reviewed existing studies on Deep Learning, Time Series | with slightly higher errors. Time Series* models were* | This research investigates Bitcoin price | prediction by reviewing the current state of the art

关键词： Blockchain | Deep learning | Time series

10. Structural and Semantic Data Layers in Time Series Analyses NSTL国家科技图书文献中心

Alexander Grass | Christian Beecks ... - 《Intelligent Data Engineering and Automated Learning - IDEAL 2024,Part I》 - International Conference on Intelligent Data Engineering and Automated Learning - 2025, - 505～511 - 共7页

摘要： temporal data is crucial for effective time series | levels range from entire time series* collections down* | associated with time series* data, including labels and* | time series* approaches. To this end, we specify a* | compositions of time series* data, while also defining*

摘要： fields, such as mathematics, logic, and commonsense QA | (CQA) system aims at providing a series* of* | The medical conversational question answering | professional medical services to improve the efficiency of | medical care. Despite the success of large language

关键词： Large language model | Medical conversational QA | Holistically thought

摘要： series classification, the task of categorizing | for time series* classification. We demonstrate its* | available time series* classification benchmarks* | Analyzing sequential data is crucial in many | domains, particularly due to the abundance of data

关键词： Time-series classification | Temporal compositionality | Time series segmentation

摘要： in time series* tasks. It highlights the need to* | periodicity, for activation in time series* neural networks* | for time series* classification, obtaining the best* | This paper investigates the lack of research | on activation functions for neural network models

关键词： Time series | Deep learning | Activation function

摘要：Time series* data from various domains is* | patterns within these series* can provide valuable* | Rare Temporal Pattern Mining from Time Series | time series* data as input and outputs rare temporal* | continuously growing, and extracting and analyzing temporal

关键词： Pattern mining | Rare temporal patterns | Time series

摘要：In today's data-driven landscape, time series | series data, coupled with the expanding landscape of | framework for automated time series* forecasting. The* | series data. First, pipeline templates to account for | -world time series* datasets demonstrate the*

关键词： Automated machine learning | Time series | Forecasting

摘要：DeepAR is a popular probabilistic time series | of related time series. For this reason, it is a | . We use 100 time series* from the M4 competition to* | forecasting algorithm. According to the authors, DeepAR is | particularly suitable to build global models using hundreds

关键词： Time series forecast | Probabilistic forecast | Deep time series

摘要：Time series* classification an important and* | -stationary property of time series* data hinders further* | time series* classification that leverages the power* | challenging real-world problem and has been extensively | studied by deep learning methods. However, the non

关键词： Time series classification | Domain generalization

摘要：, data series* similarity search holds great* | series indices for exact similarity search. The iSAX | index for data series, with a cost model involving | In contemporary applications of data analysis | significance. A substantial body of research design data

关键词： Similarity search | Summarization | Data series

摘要：, comparing Time Series* and Deep Learning models, evaluating* | reviewed existing studies on Deep Learning, Time Series | with slightly higher errors. Time Series* models were* | This research investigates Bitcoin price | prediction by reviewing the current state of the art

关键词： Blockchain | Deep learning | Time series

摘要： temporal data is crucial for effective time series | levels range from entire time series* collections down* | associated with time series* data, including labels and* | time series* approaches. To this end, we specify a* | compositions of time series* data, while also defining*

关键词： Time series | Data analytics | Knowledge discovery

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： fields, such as mathematics, logic, and commonsense QA | (CQA) system aims at providing a series of | The medical conversational question answering | professional medical services to improve the efficiency of | medical care. Despite the success of large language

关键词： Large language model | Medical conversational QA | Holistically thought

摘要： series classification, the task of categorizing | for time series classification. We demonstrate its | available time series classification benchmarks | Analyzing sequential data is crucial in many | domains, particularly due to the abundance of data

关键词： Time-series classification | Temporal compositionality | Time series segmentation

摘要： in time series tasks. It highlights the need to | periodicity, for activation in time series neural networks | for time series classification, obtaining the best | This paper investigates the lack of research | on activation functions for neural network models

关键词： Time series | Deep learning | Activation function

摘要：Time series data from various domains is | patterns within these series can provide valuable | Rare Temporal Pattern Mining from Time Series | time series data as input and outputs rare temporal | continuously growing, and extracting and analyzing temporal

关键词： Pattern mining | Rare temporal patterns | Time series

摘要：In today's data-driven landscape, time series | series data, coupled with the expanding landscape of | framework for automated time series forecasting. The | series data. First, pipeline templates to account for | -world time series datasets demonstrate the

关键词： Automated machine learning | Time series | Forecasting

摘要：DeepAR is a popular probabilistic time series | of related time series. For this reason, it is a | . We use 100 time series from the M4 competition to | forecasting algorithm. According to the authors, DeepAR is | particularly suitable to build global models using hundreds

关键词： Time series forecast | Probabilistic forecast | Deep time series

摘要：Time series classification an important and | -stationary property of time series data hinders further | time series classification that leverages the power | challenging real-world problem and has been extensively | studied by deep learning methods. However, the non

关键词： Time series classification | Domain generalization

摘要：, data series similarity search holds great | series indices for exact similarity search. The iSAX | index for data series, with a cost model involving | In contemporary applications of data analysis | significance. A substantial body of research design data

关键词： Similarity search | Summarization | Data series

摘要：, comparing Time Series and Deep Learning models, evaluating | reviewed existing studies on Deep Learning, Time Series | with slightly higher errors. Time Series models were | This research investigates Bitcoin price | prediction by reviewing the current state of the art

关键词： Blockchain | Deep learning | Time series

摘要： temporal data is crucial for effective time series | levels range from entire time series collections down | associated with time series data, including labels and | time series approaches. To this end, we specify a | compositions of time series data, while also defining

关键词： Time series | Data analytics | Knowledge discovery

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： fields, such as mathematics, logic, and commonsense QA | (CQA) system aims at providing a series* of* | The medical conversational question answering | professional medical services to improve the efficiency of | medical care. Despite the success of large language

摘要： series classification, the task of categorizing | for time series* classification. We demonstrate its* | available time series* classification benchmarks* | Analyzing sequential data is crucial in many | domains, particularly due to the abundance of data

摘要： in time series* tasks. It highlights the need to* | periodicity, for activation in time series* neural networks* | for time series* classification, obtaining the best* | This paper investigates the lack of research | on activation functions for neural network models

摘要：Time series* data from various domains is* | patterns within these series* can provide valuable* | Rare Temporal Pattern Mining from Time Series | time series* data as input and outputs rare temporal* | continuously growing, and extracting and analyzing temporal

摘要：In today's data-driven landscape, time series | series data, coupled with the expanding landscape of | framework for automated time series* forecasting. The* | series data. First, pipeline templates to account for | -world time series* datasets demonstrate the*

摘要：DeepAR is a popular probabilistic time series | of related time series. For this reason, it is a | . We use 100 time series* from the M4 competition to* | forecasting algorithm. According to the authors, DeepAR is | particularly suitable to build global models using hundreds

摘要：Time series* classification an important and* | -stationary property of time series* data hinders further* | time series* classification that leverages the power* | challenging real-world problem and has been extensively | studied by deep learning methods. However, the non

摘要：, data series* similarity search holds great* | series indices for exact similarity search. The iSAX | index for data series, with a cost model involving | In contemporary applications of data analysis | significance. A substantial body of research design data

摘要：, comparing Time Series* and Deep Learning models, evaluating* | reviewed existing studies on Deep Learning, Time Series | with slightly higher errors. Time Series* models were* | This research investigates Bitcoin price | prediction by reviewing the current state of the art

摘要： temporal data is crucial for effective time series | levels range from entire time series* collections down* | associated with time series* data, including labels and* | time series* approaches. To this end, we specify a* | compositions of time series* data, while also defining*