The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
최근에는 모바일 기기에서의 머신러닝 접근법과 사용자 이동 이력 분석이 많은 주목을 받고 있습니다. 일반적으로 기계 학습의 전처리 접근 방식으로 단어 벡터를 획득하기 위해 단어 임베딩 도구에 텍스트 데이터를 적용해야 합니다. 그러나 모바일 장치에서는 고차원 벡터 계산에 드는 막대한 비용을 감당하기 어렵습니다. 따라서 저비용의 사용자 행동 및 사용자 이동 이력 분석 접근 방식이 고려되어야 한다. 이 문제를 해결하기 위해 먼저 텍스트 주소 정보 대신 우편번호와 도로명 주소를 벡터로 변환하여 공간 벡터 계산 비용을 절감합니다. 둘째, 우편번호 기반 벡터를 적용한 저비용 고성능 의미 및 물리적 거리(실제 거리) 계산 방법을 제안한다. 마지막으로 제안한 방법의 타당성을 검증하기 위해 미국 우편번호 데이터를 활용하여 의미적 거리와 물리적 거리를 모두 계산하고 그 결과를 이전 방법과 비교한다. 실험 결과, 제안한 방법이 거리 계산 성능을 크게 향상시키고 비용을 낮은 수준으로 효과적으로 제어할 수 있음을 보여주었습니다.
Da LI
Kyoto Sangyo University
Yuanyuan WANG
Yamaguchi University
Rikuya YAMAMOTO
Kyoto Sangyo University
Yukiko KAWAI
Kyoto Sangyo University,Osaka University
Kazutoshi SUMIYA
Kwansei Gakuin University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Da LI, Yuanyuan WANG, Rikuya YAMAMOTO, Yukiko KAWAI, Kazutoshi SUMIYA, "A Low-Cost High-Performance Semantic and Physical Distance Calculation Method Based on ZIP Code" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 5, pp. 920-927, May 2022, doi: 10.1587/transinf.2021DAP0005.
Abstract: Recently, machine learning approaches and user movement history analysis on mobile devices have attracted much attention. Generally, we need to apply text data into the word embedding tool for acquiring word vectors as the preprocessing of machine learning approaches. However, it is difficult for mobile devices to afford the huge cost of high-dimensional vector calculation. Thus, a low-cost user behavior and user movement history analysis approach should be considered. To address this issue, firstly, we convert the zip code and street house number into vectors instead of textual address information to reduce the cost of spatial vector calculation. Secondly, we propose a low-cost high-performance semantic and physical distance (real distance) calculation method that applied zip-code-based vectors. Finally, to verify the validity of our proposed method, we utilize the US zip code data to calculate both semantic and physical distances and compare their results with the previous method. The experimental results showed that our proposed method could significantly improve the performance of distance calculation and effectively control the cost to a low level.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021DAP0005/_p
부
@ARTICLE{e105-d_5_920,
author={Da LI, Yuanyuan WANG, Rikuya YAMAMOTO, Yukiko KAWAI, Kazutoshi SUMIYA, },
journal={IEICE TRANSACTIONS on Information},
title={A Low-Cost High-Performance Semantic and Physical Distance Calculation Method Based on ZIP Code},
year={2022},
volume={E105-D},
number={5},
pages={920-927},
abstract={Recently, machine learning approaches and user movement history analysis on mobile devices have attracted much attention. Generally, we need to apply text data into the word embedding tool for acquiring word vectors as the preprocessing of machine learning approaches. However, it is difficult for mobile devices to afford the huge cost of high-dimensional vector calculation. Thus, a low-cost user behavior and user movement history analysis approach should be considered. To address this issue, firstly, we convert the zip code and street house number into vectors instead of textual address information to reduce the cost of spatial vector calculation. Secondly, we propose a low-cost high-performance semantic and physical distance (real distance) calculation method that applied zip-code-based vectors. Finally, to verify the validity of our proposed method, we utilize the US zip code data to calculate both semantic and physical distances and compare their results with the previous method. The experimental results showed that our proposed method could significantly improve the performance of distance calculation and effectively control the cost to a low level.},
keywords={},
doi={10.1587/transinf.2021DAP0005},
ISSN={1745-1361},
month={May},}
부
TY - JOUR
TI - A Low-Cost High-Performance Semantic and Physical Distance Calculation Method Based on ZIP Code
T2 - IEICE TRANSACTIONS on Information
SP - 920
EP - 927
AU - Da LI
AU - Yuanyuan WANG
AU - Rikuya YAMAMOTO
AU - Yukiko KAWAI
AU - Kazutoshi SUMIYA
PY - 2022
DO - 10.1587/transinf.2021DAP0005
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2022
AB - Recently, machine learning approaches and user movement history analysis on mobile devices have attracted much attention. Generally, we need to apply text data into the word embedding tool for acquiring word vectors as the preprocessing of machine learning approaches. However, it is difficult for mobile devices to afford the huge cost of high-dimensional vector calculation. Thus, a low-cost user behavior and user movement history analysis approach should be considered. To address this issue, firstly, we convert the zip code and street house number into vectors instead of textual address information to reduce the cost of spatial vector calculation. Secondly, we propose a low-cost high-performance semantic and physical distance (real distance) calculation method that applied zip-code-based vectors. Finally, to verify the validity of our proposed method, we utilize the US zip code data to calculate both semantic and physical distances and compare their results with the previous method. The experimental results showed that our proposed method could significantly improve the performance of distance calculation and effectively control the cost to a low level.
ER -