检索结果-内蒙古大学图书馆

time-series data analysis Using SlidingWindow Based SVD for Motion Evaluation

JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS 2017年第7期21卷 1240-1250页

作者： Jiang, Yinlai Hayashi, Isao Wang, Shuoyu Ishida, Kenji Univ Electrocommun Brain Sci Inspired Life Support Res Ctr Chofu Tokyo 1828585 Japan Kansai Univ Grad Sch Informat Takatsuki Osaka 5691095 Japan Kochi Univ Technol Dept Intelligent Mech Syst Engn Kami Kochi 7828502 Japan Kurihara Cent Hosp Kurihara Miyagi 9872205 Japan

A method based on singular value decomposition (SVD) is proposed for extracting features from motion time-series data observed with various sensing systems. Matrices consisting of the sliding window (SW) subsets of time-series data are decomposed, yielding singular vectors as the patterns of the motion, and the singular values as a scalar, by which the corresponding singular vectors describe the matrices. The sliding window based singular value decomposition was applied to analyze acceleration during walking. Three levels of walking difficulty were simulated by restricting the right knee joint in the measurement. The accelerations of the middles of the shanks and the back of the waist were measured and normalized before the SW-SVD was performed. The results showed that the first singular values inferred from the acceleration data of the restricted side (the right shank) significantly related to the increase of the restriction among all the subjects while there were no common trends in the singular values of the left shank and the waist. The SW-SVD was suggested to be a reliablemethod to evaluate walking disability. Furthermore, a 2D visualization tool is proposed to provide intuitive information about walking difficulty which can be used in walking rehabilitation to monitor recovery.

关键词： singular value decomposition time-series data analysis sliding window motion analysis walking difficulty evaluation

来源：评论

学校读者我要写书评

暂无评论

time-series data analysis of Long-Term Home Blood Pressure Measurements in Relation to Lifestyle 15

Time-Series Data Analysis of Long-Term Home Blood Pressure M...

引用

15th World Congress on Health and Biomedical Informatics (MEDINFO)

作者： Takeuchi, Hiroshi Kodama, Naoki Takahashi, Shingo Takasaki Univ Hlth & Welf Dept Healthcare Informat 37-1 Nakaorui Machi Takasaki Gunma 3700033 Japan

ISBN: (纸本)9781614995647;9781614995630

We conducted a long-term time-series analysis of an individual's home blood pressure measurements, stored on a personal healthcare system in cloud, relative to the individual's lifestyle. In addition to daily scattering, apparent seasonal variations were observed in both systolic and diastolic blood pressure measurements. We examined the effect of seasonal variations on the outcome of a healthcare data mining process that extracts rules between blood pressure measurements and lifestyle components such as exercise and diet, and found that the daily blood pressure data approached a normal distribution when adjusted for the seasonal variations. This implies that an adjustment is desirable in order to produce appropriate rules in the healthcare data mining process.

关键词： Personal Healthcare Home Blood Pressure time-series data analysis Healthcare data Mining

来源：评论

学校读者我要写书评

暂无评论

time-series data analysis of blood sugar and HbA1c levels of diabetic

Time-series data analysis of blood sugar and HbA1c levels of...

引用

4th IET International Conference on Advances in Medical, Signal and Information Processing - MEDSIP 2008

作者： H. Takeuchi M. Ishikawa N. Kodama Department of Healthcare Informatics Taksasaki University of Health and Welfare Takasaki Gunma Japan

time-series data analyses of blood sugar and HbA1c levels of a diabetic were presented. These analyses were based on the simple idea that accumulation of the effects of a person's lifestyle could influence daily health with some delay, which may reflect complex bio-reactions in the human body. In these analyses, correlations of time-series data are checked focusing on the accumulation of effects of daily lifestyle, and on variation of daily health data. A retardation parameter is introduced. Rule-mining using the C5.0 algorithm following the time-series data analyses produced useful relationships among lifestyles, blood sugar level, and HbAlc level of a diabetic.

关键词： time-series data analysis Diabetic Rule-mining Diabetes Mellitus Human Body Blood Glucose time series data Life Style Glycated Hemoglobins hemoglobin A1c data analysis sugar Blood

来源：评论

学校读者我要写书评

暂无评论

Introduction to a new use-case based on MPEG-IoMT: time-series temperature data analysis by the flower condition 13

Introduction to a new use-case based on MPEG-IoMT: time-seri...

引用

13th International Conference on Ubiquitous and Future Networks (ICUFN)

作者： Moon, Jaewon Kum, Seungwoo Oh, Seungtaek Korea Elect Technol Inst Informat Media Res Ctr Seoul South Korea

ISBN: (纸本)9781665485500

data capturing from the farm environment helps farmers monitor and optimize crops, as well as adapt to changes in environmental status. The smart farm collects and analyzes data generated by various sensors and attempts to improve productivity by utilizing actuators. MPEG-IoMT is a data format and interface standard for media such as video, audio, and related items. In this study, we introduced a strawberry growth use case that covers both time series data and image data analysis. In addition to this, we proposed an additional class to exchange information between each object based on the MPEG-IoMT standard.

关键词： ISO/IEC 23093 MPEG-IoMT Internet of Media Things time-series data analysis

来源：评论

学校读者我要写书评

暂无评论

The physiology analysis system: An integrated approach for warehousing, management and analysis of time-series physiology data

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2007年第1期86卷 62-72页

作者： McKenna, Thomas M. Bawa, Gagandeep Kumar, Kamal Reifman, Jaques USA Med Res & Mat Command Bioinformat Cell Tekemed & Adv Technol Res Ctr Ft Detrick MD 21702 USA

The physiology analysis system (PAS) was developed as a resource to support the efficient warehousing, management, and analysis of physiology data, particularly, continuous time-series data that may be extensive, of variable quality, and distributed across many files. The PAS incorporates time-series data collected by many types of data-acquisition devices, and it is designed to free users from data management burdens. This Web-based system allows both discrete (attribute) and time-series (ordered) data to be manipulated, visualized, and analyzed via a client's Web browser. All processes occur on a server, so that the client does not have to download data or any application programs, and the PAS is independent of the client's computer operating system. The PAS contains a library of functions, written in different computer languages that the client can add to and use to perform specific data operations. Functions from the library are sequentially inserted into a function chain-based logical structure to construct sophisticated data operators from simple function building blocks, affording ad hoc query and analysis of time-series data. These features support advanced mining of physiology data. (c) 2007 Elsevier Ireland Ltd. All rights reserved.

关键词： physiology medical informatics data display time-series data analysis data base management system

来源：评论

学校读者我要写书评

暂无评论

An adversarial transformer for anomalous lamb wave pattern detection

引用

NEURAL NETWORKS 2025年 185卷 107153页

作者： Guo, Jiawei Zhang, Sen Amiri, Nikta Yu, Lingyu Wang, Yi Univ South Carolina Dept Mech Engn Columbia SC 29208 USA Univ South Carolina Dept Comp Sci & Engn Columbia SC 29208 USA

Lamb waves are widely used for defect detection in structural health monitoring, and various methods are developed for Lamb wave data analysis. This paper presents an unsupervised Adversarial Transformer model for anomalous Lamb wave pattern detection by analyzing the spatiotemporal images generated by a hybrid PZTscanning laser Doppler vibrometer (SLDV). The model includes the global attention and the local attention mechanisms, and both are trained adversarially. Given the different natures between the normal and anomalous wave patterns, global attention allows accurate reconstruction of normal wave data but is less capable of reproducing anomalous data and, hence, can be used for anomalous wave pattern detection. Local attention, however, serves as a sparring partner in the proposed adversarial training process to boost the quality of global attention. In addition, a new segment replacement strategy is also proposed to make global attention consistently extract textural contents found in normal data, which, however, are noticeably different from anomalies, leading to superior model performance. Our Adversarial Transformer model is also compared with several benchmark models and demonstrates an overall accuracy of 97.1 % for anomalous wave pattern detection. It is also confirmed that global attention and local attention in adversarial training are responsible for the superior performance of our model over the benchmark models (including the native Transformer model).

关键词： Anomaly detection Unsupervised learning Deep learning Adversarial learning Transformer model Computer vision time-series data analysis

来源：评论

学校读者我要写书评

暂无评论

Stock Market Insights Using Basic Recurrent Neural Networks Models

Stock Market Insights Using Basic Recurrent Neural Networks ...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and Computer Science, SCEECS 2025

作者： Pranathi, P. Sai Ketepalli, Gayatri Chandrika, A. Harshitha, S. Vignan's Foundation for Science Technology and Research Department of It&ca Andhra Pradesh Guntur522213 India

ISBN: (纸本)9798331529833

Using a confusion matrix-based methodology, this study explores the use of Simple RNNs for stock price forecasting. Our technology generates accurate forecasts by examining past data to reveal hidden trends and patterns. The model's strong points and opportunities for development are reveal by a careful analysis of the confusion matrix. To assess the model's performance, we categorize continuous price predictions into discrete bins. Our findings suggest that Simple RNNs are effective in predicting these prices. The study adds to the expanding body of research on the application of deep neural architecture in the financial sector. © 2025 IEEE.

关键词： Confusion matrix analysis Deep learning applications Financial prediction models Simple RNNs Stock market forecasting time-series data analysis

来源：评论

学校读者我要写书评

暂无评论

Two-stage deep learning model for Alzheimer's disease detection and prediction of the mild cognitive impairment time

引用

NEURAL COMPUTING & APPLICATIONS 2022年第17期34卷 14487-14509页

作者： El-Sappagh, Shaker Saleh, Hager Ali, Farman Amer, Eslam Abuhmed, Tamer Galala Univ Fac Comp Sci & Engn Suez 435611 Egypt Benha Univ Fac Comp & Artificial Intelligence Informat Syst Dept Banha 13518 Egypt South Valley Univ Fac Comp & Artificial Intelligence Hurghada Egypt Sejong Univ Dept Software Seoul South Korea Misr Int Univ Fac Comp Sci Cairo Egypt Sungkyunkwan Univ Coll Comp & Informat Suwon South Korea

Alzheimer's disease (AD) is an irreversible neurodegenerative disease characterized by thinking, behavioral and memory impairments. Early prediction of conversion from mild cognitive impairment (MCI) to AD is still a challenging task. No study has been able to predict the exact conversion time of MCI patients. In addition, most studies have achieved poor performance making this prediction using only a small number of features (e.g., using only MRI images). Therefore, previous approaches have not gained the trust of medical experts. This study proposes a novel two-stage deep learning AD progression detection framework based on information fusion of several patient longitudinal multivariate modalities, including neuroimaging data, cognitive scores, cerebrospinal fluid biomarkers, neuropsychological battery markers, and demographics. The first stage of the progression detection framework employs a multiclass classification task that predicts a patient's diagnosis (i.e., cognitively normal, MCI, or AD). In the second stage, a regression task that predicts the exact conversion time of MCI patients is used. The study is based on data of 1,371 subjects collected by the Alzheimer's Disease Neuroimaging Initiative (ADNI). Comprehensive experiments were carried out to evaluate the framework stages and find the optimal model for each stage. Proposed model was compared with various machine learning models, including decision tree (DT), random forest (RF), support vector machine (SVM), logistic regression (LR), and K-nearest neighbor (KNN). In the classification stage, the proposed long-short term memory (LSTM) model achieved an accuracy of 93.87%, precision of 94.070%, recall of 94.07%, and F1-score of 94.07%. The results showed that the LSTM model outperformed other machine learning models (i.e., decision tree by 2.48%, random forest by 1.27%, support vector machine by 1.86%, logistic regression by 1.59%, and K-nearest neighbor by 14.77%). In the regression stage, the proposed

关键词： Alzheimer's disease Alzheimer's progression detection time-series data analysis Deep learning

来源：评论

学校读者我要写书评

暂无评论

Methodology to automatically detect abnormal values of vital parameters in anesthesia time-series: Proposal for an adaptable algorithm

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2016年 129卷 160-171页

作者： Lamer, Antoine Jeanne, Mathieu Marcilly, Romaric Kipnis, Eric Schiro, Jessica Logier, Regis Tavernier, Benoit Univ Hosp INSERM CIC IT 1403 Lille France Univ Hosp Pole Anesthesie Reanimat Lille France Univ Lille Nord France EA 2694 Lille France

Abnormal values of vital parameters such as hypotension or tachycardia may occur during anesthesia and may be detected by analyzing time-series data collected during the procedure by the Anesthesia Information Management System. When crossed with other data from the Hospital Information System, abnormal values of vital parameters have been linked with postoperative morbidity and mortality. However, methods for the automatic detection of these events are poorly documented in the literature and differ between studies, making it difficult to reproduce results. In this paper, we propose a methodology for the automatic detection of abnormal values of vital parameters. This methodology uses an algorithm allowing the configuration of threshold values for any vital parameters as well as the management of missing data. Four examples illustrate the application of the algorithm, after which it is applied to three vital signs (heart rate, SpO2, and mean arterial pressure) to all 2014 anesthetic records at our institution. (C) 2016 Elsevier Ireland Ltd. All rights reserved.

关键词： Medical informatics time-series data analysis Algorithm Anesthesia

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based Explainable Control System for Reconfigurable Networks of Edge Devices

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2022年第1期9卷 7-19页

作者： Dassanayake, Priyanthi M. Anjum, Ashiq Bashir, Ali Kashif Bacon, Joseph Saleem, Rabia Manning, Warren Univ Leicester Sch Informat Leicester LE1 7RH Leics England Manchester Metropolitan Univ Dept Comp & Math Manchester M15 6BH Lancs England Natl Univ Sci & Technol Sch Elect Engn & Comp Sci Islamabad Pakistan Make IT Different Ltd London EC1V 2NX England Univ Derby Coll Engn & Technol Derby DE22 1GB England

Edge devices that operate in real-world environments are subjected to unpredictable conditions caused by environmental forces such as wind and uneven surfaces. Since most edge systems such as autonomous vehicles exhibit dynamic properties, it is clear that reinforcement learning can be a powerful tool for improving system accuracy. Successful maintenance of the position of a vehicle in such environments has been recently achieved with the aid of Deep Reinforcement Learning (DRL) that dynamically adjusts the Reconfigurable Wireless Network (RWN) response. Deep Neural Networks (DNNs) are often seen as black boxes, as neither the acquired knowledge nor the decision rationale can be explained. This raises issues with the transparency and trustworthiness of the system because the underlying AI models are not governed by any mathematical or physics laws. In this paper, we explain the process of a DNN utilisation in an autonomous dynamic positioning system by gauging reactions of the DNN to predefined constraints and capturing the associated conditions that influence the DNN in a time series. We introduce a novel digitisation technique that reduces interesting patterns of time series data into single-digits to obtain a cross comparable view of the conditions. By analysing the clusters formed on this cross comparable view, we discovered multiple intensities of environmental conditions spanning across 44% of moderate conditions and 33% and 23% of harsh and mild conditions respectively. Our analysis showed that the proposed system can provide stable responses to uncertain conditions by predicting randomness.

关键词： time series analysis data analysis Biological system modeling Reinforcement learning data models Force Vehicle dynamics Deep Neural Networks Explainable Artificial Intelligence Edge Computing time-series data analysis Deep Reinforcement Learning Motif discovery

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：