Study on the Technology Trend Screening Framework Using Unsupervised Learning
Outliers that deviate from a normal distribution are typically removed during the analysis process. However, the patterns of outliers are recognized as important information in the outlier detection method. This study proposes a technology trend screening framework based on a machine learning algori...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/17/8920 |
_version_ | 1797496166502367232 |
---|---|
author | Junseok Lee Sangsung Park Juhyun Lee |
author_facet | Junseok Lee Sangsung Park Juhyun Lee |
author_sort | Junseok Lee |
collection | DOAJ |
description | Outliers that deviate from a normal distribution are typically removed during the analysis process. However, the patterns of outliers are recognized as important information in the outlier detection method. This study proposes a technology trend screening framework based on a machine learning algorithm using outliers. The proposed method is as follows: first, we split the dataset by time into training and testing sets for training the Doc2Vec model. Next, we pre-process the patent documents using the trained model. The final outlier documents are selected from the preprocessed document data, through voting for the outlier documents extracted using the IQR, the three-sigma rule, and the Isolation Forest algorithm. Finally, the technical topics of the outlier documents extracted through the topic model are identified. This study analyzes the patent data on drones to describe the proposed method. Results show that, despite cumulative research on drone-related hardware and system technology, there is a general lack of research regarding the autonomous flight field. |
first_indexed | 2024-03-10T01:59:49Z |
format | Article |
id | doaj.art-6a41ca3f6d7b476aafcc7808e236e930 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T01:59:49Z |
publishDate | 2022-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-6a41ca3f6d7b476aafcc7808e236e9302023-11-23T12:49:09ZengMDPI AGApplied Sciences2076-34172022-09-011217892010.3390/app12178920Study on the Technology Trend Screening Framework Using Unsupervised LearningJunseok Lee0Sangsung Park1Juhyun Lee2Machine Learning Big Data Institute, Korea University, Seoul 02841, KoreaDepartment of Big Data and Statistics, Cheongju University, Cheongju 28503, KoreaInstitute of Engineering Research, Korea University, Seoul 02841, KoreaOutliers that deviate from a normal distribution are typically removed during the analysis process. However, the patterns of outliers are recognized as important information in the outlier detection method. This study proposes a technology trend screening framework based on a machine learning algorithm using outliers. The proposed method is as follows: first, we split the dataset by time into training and testing sets for training the Doc2Vec model. Next, we pre-process the patent documents using the trained model. The final outlier documents are selected from the preprocessed document data, through voting for the outlier documents extracted using the IQR, the three-sigma rule, and the Isolation Forest algorithm. Finally, the technical topics of the outlier documents extracted through the topic model are identified. This study analyzes the patent data on drones to describe the proposed method. Results show that, despite cumulative research on drone-related hardware and system technology, there is a general lack of research regarding the autonomous flight field.https://www.mdpi.com/2076-3417/12/17/8920patent analysisdroneDoc2Vectopic modeloutlier |
spellingShingle | Junseok Lee Sangsung Park Juhyun Lee Study on the Technology Trend Screening Framework Using Unsupervised Learning Applied Sciences patent analysis drone Doc2Vec topic model outlier |
title | Study on the Technology Trend Screening Framework Using Unsupervised Learning |
title_full | Study on the Technology Trend Screening Framework Using Unsupervised Learning |
title_fullStr | Study on the Technology Trend Screening Framework Using Unsupervised Learning |
title_full_unstemmed | Study on the Technology Trend Screening Framework Using Unsupervised Learning |
title_short | Study on the Technology Trend Screening Framework Using Unsupervised Learning |
title_sort | study on the technology trend screening framework using unsupervised learning |
topic | patent analysis drone Doc2Vec topic model outlier |
url | https://www.mdpi.com/2076-3417/12/17/8920 |
work_keys_str_mv | AT junseoklee studyonthetechnologytrendscreeningframeworkusingunsupervisedlearning AT sangsungpark studyonthetechnologytrendscreeningframeworkusingunsupervisedlearning AT juhyunlee studyonthetechnologytrendscreeningframeworkusingunsupervisedlearning |