본문 바로가기
KERD
논문KCI 등재

생활물류 서비스의 지역적 형평성 고려를 위한 서비스이용 취약지역 분류에 관한 연구

A Study on Classifying Under-Serviced Areas with Consideration of Regional Equity in Customer Logistics Services

장소영|남대식|김진재
한국로지스틱스학회 (Korea Logistics Society)|2023.12|로지스틱스연구 (Korean Journal of Logistics)|제31권 제6호|pp. 17-29|DOI 10.15735/kls.2023.31.6.002

0

조회

0

다운로드

2

인용

0

참고문헌

키워드

Machine LearningDeep Neural Network(DNN)Lastmile DeliveryCustomer LogisticsUnderserved Area
주제분류경영학

초록

In the past decade, the last-mile market within the logistics industry has witnessed an unprecedented growth of nearly 100% in the last five years. Gradually recognized as “Customer logistics,” the last-mile market is now considered an essential part of the urban service, leading to the recent implementation of the Last-mile Logistics Service Act. Despite the increasing interest and significance, there are not much thorough researches and studies yet done in this customer logistics field. This research aims to address this gap by designing a predictive model based on real parcel delivery data. By comparing and analyzing the model against actual data, the study classifies 229 administrative regions (municipalities) in Korea into four distinct types. Through this approach, the research provides a framework for analyzing under-served areas in the customer logistics that takes into account various social factors (economy, population, etc.), beyond the traditional papers which focused on geographical factors such as remote areas. The analysis of the predictive model reveals that around 50% of metropolitan cities exhibit lower levels of customer logistics compared to the predicted quantities. Even in highly developed cities like Seoul, there is a likeliness of being an under-served area in approximately 20% of 25 districts. Furthermore, 77% of regions, previously classified as delivery service vulnerable areas (rural areas), are identified as under-served areas. Additionally, it is observed that the actual volume of deliveries in remote areas, particularly in rural and mountainous regions, is insufficient. Thus, resolving the unequal distribution of logistics services between regions requires a comprehensive consideration of multiple factors.

Abstract

In the past decade, the last-mile market within the logistics industry has witnessed an unprecedented growth of nearly 100% in the last five years. Gradually recognized as “Customer logistics,” the last-mile market is now considered an essential part of the urban service, leading to the recent implementation of the Last-mile Logistics Service Act. Despite the increasing interest and significance, there are not much thorough researches and studies yet done in this customer logistics field. This research aims to address this gap by designing a predictive model based on real parcel delivery data. By comparing and analyzing the model against actual data, the study classifies 229 administrative regions (municipalities) in Korea into four distinct types. Through this approach, the research provides a framework for analyzing under-served areas in the customer logistics that takes into account various social factors (economy, population, etc.), beyond the traditional papers which focused on geographical factors such as remote areas. The analysis of the predictive model reveals that around 50% of metropolitan cities exhibit lower levels of customer logistics compared to the predicted quantities. Even in highly developed cities like Seoul, there is a likeliness of being an under-served area in approximately 20% of 25 districts. Furthermore, 77% of regions, previously classified as delivery service vulnerable areas (rural areas), are identified as under-served areas. Additionally, it is observed that the actual volume of deliveries in remote areas, particularly in rural and mountainous regions, is insufficient. Thus, resolving the unequal distribution of logistics services between regions requires a comprehensive consideration of multiple factors.

참고문헌 (53)

  1. 인공지능 기술 및 산업 분야별 적용 사례, "국경완", 정보통신기획평가원, 15~27 (2019)
  2. "국민의 스마트 행복을 실현하기위해 민관이 함께 스마트+빌딩 활성화에 착수" (2023)[URL]
  3. "팍세권⋅슬세권⋅욕세권?…요즘나온 ○세권 용어 총정리!." (2021)[URL]
  4. 김병관, "수도권 택배 물동량 추정에 관한 탐색적 연구: 경기도를 중심으로", 로지스틱스연구, 31(2), pp.47~58 (2023), 한국로지스틱스학회[DOI]
  5. 김수빈, "물류시장의 변화에 따라 등장한 도심형 소형 물류센터의 공간 특성 분석", 대한건축학회논문집, 39(1), pp.89~99 (2023), 대한건축학회
  6. 김승철, "광양항 컨테이너물동량의 구조적 변화추이분석", 한국항만경제학회지, 38(4), pp.171~185 (2022), 한국항만경제학회
  7. 김시구, "인공지능 기반 콜드체인 배송차량 에너지 소비량 예측", 국제상학, 37(2), pp.173~190 (2022), 한국국제상학회[DOI]
  8. 김재성, "딥러닝 기법을 활용한 가구 부자재 주문 수요예측", 한국빅데이터학회 학회지, 5(2), pp.111~120 (2020), 사)한국빅데이터학회[DOI]
  9. 김진수, "딥러닝 (LSTM)기반 항만 진출입 컨테이너 트럭의 터미널 도착량 예측", 대한교통학회 학술대회지, pp.240~241 (2020)
  10. 김진하, "택배기사 근로환경 문제와 개선방안", 정책리포트, pp.1~24 (2021)
  11. "물류통계-생활물류통계-년도별 생활물류실적" (2023)[URL]
  12. 박인선, "우리나라 택배 물동량 예측 모형에 대한 연구", 경영교육연구, 33(1), pp.47~65 (2018), 한국경영교육학회[DOI]
  13. 배규식, "코로나 19 로 늘어난 택배와 배달노동", 월간교통, pp.2~4 (2020)
  14. SK 텔레콤, "새벽 배송을 넘어 당일 배송, 2시간배송이 트렌드라고?", SK텔레콤, ~ (2021)
  15. 서민교, "한국에서의 드론을 활용한 물류배송 상용화 가능성에 관한 연구", 인터넷전자상거래연구, 18(6), pp.377~393 (2018), 한국인터넷전자상거래학회[DOI]
  16. 서성호, "비선형 회귀 분석을 이용한 부유식 해양 구조물의중량 추정 모델 연구", 대한조선학회 논문집, 51(6), pp.530~538 (2014), 대한조선학회
  17. 송민주, "대구경북통합신공항 건설에 따른 지역 항공물동량 추정 및 활성화 방안 연구 -기종점(OD)분석을 중심으로-", 국제상학, 37(3), pp.57~75 (2022), 한국국제상학회
  18. 신승진, "한･중 해상-철도 연계 컨테이너 운송의 교역규모와 물동량 분석", 해양정책연구, 34(1), pp.89~120 (2019), 한국해양수산개발원[DOI]
  19. 신승진, "생활밀착형 도시물류시설의 확보 방안", 교통기술과정책, 17(1), pp.37~45 (2020)
  20. 양재훈, "IPA를 이용한 택배서비스 품질 요인의 활용방안에 관한 연구", 로지스틱스연구, 22(1), pp.65~88 (2014), 한국로지스틱스학회[DOI]
  21. 수도권 생활물류시설의 입지 및 시설 특성 연구, "유재성", 국토연구원(KRIHS), 5~41 (2022)
  22. ASTI MARKET INSIGHT 93: 빅데이터 분석 및 수집 시장, "이준우", ASTI, 1~ (2022)
  23. 이철희, "장래 시군구별 인구변화가 지역 물류수요에 미치는 영향", 한국경제연구, 39(3), pp.5~34 (2021), 한국경제연구학회
  24. 이충배, "우리나라와 동아시아 항만간의 수출 컨테이너 물동량 추이 분석", 한국항만경제학회지, 34(2), pp.97~114 (2018), 한국항만경제학회[DOI]
  25. 임진우, "물류사각지대 해소를 위한 Drone 기반의 물류서비스에 대한 탐색적 고찰", 한국SCM학회지, 16(2), pp.23~33 (2016), 한국SCM학회
  26. 임현우, "지역분할기법을 이용한 택배 영업소 배송권역 설정 에 관한 연구", 로지스틱스연구, 21(3), pp.83~94 (2013), 한국로지스틱스학회[DOI]
  27. AI 기반 자동물류 스마트 팩토리 솔루션, "장영재", KAIST, 1~2 (2019)
  28. 물류창고를 활용한 우체국 소포사업 경쟁력 제고방안, "정호상", 우정사업본부, 7~30 (2016)
  29. 조현준, "컨테이너터미널 입항 선박별 야드 트랙터 소요량 예측에 관한 연구", 한국항만경제학회지, 37(4), pp.33~40 (2021), 한국항만경제학회
  30. 차현섭, "자동 변수 생성을 통한 수요 예측 프로세스 개선에 관한 연구: 물동량 데이터 중심으로", 한국통신학회 학술대회논문집, pp.344~348 (2019)
  31. 최명진, "머신러닝을 활용한 공군 수리부속 수요예측 정확도 개선에 관한 연구", 한국SCM학회지, 21(2), pp.43~51 (2021), 한국SCM학회[DOI]
  32. "서울 서남권에서 만난 배송기사들의 ‘통곡의 언덕’" (2022)[URL]
  33. 서울시 스마트모빌리티 거점시설 도입방안, "홍상연", 서울연구원, 1~123 (2021)
  34. Bergstra, J., "Random search for hyper-parameter optimization", Journal of machine learning research, 13(2) (2012)
  35. Carlini, N., "Towards evaluating the robustness of neural networks", 2017ieee symposium on security and privacy (sp), pp.39~57 (2017)
  36. Chong, I. G., "Performance of some variable selection methods when multicollinearity is present", Chemometrics and intelligent laboratory systems, 78(1-2), pp.103~112 (2005)
  37. Dhull, S. K., "ECG beat classifiers : a journey from ANN to DNN", Procedia Computer Science, 167, pp.747~759 (2020)
  38. Hodge, V., "A survey of outlier detection methodologies", Artificial intelligence review, 22, pp.85~126 (2004)
  39. Kingma, D. P., "Adam : A method for stochastic optimization", arXiv preprint arXiv:1412.6980, ~ (2014)
  40. Landro, N., "Mixing Adam and SGD : a combined optimization method", arXiv preprint arXiv:2011.08042, ~ (2020)
  41. Mishra, N. P., "Global impacts of pre-and post-COVID-19 pandemic : Focus on socio-economic consequences", Sensors International, 1, pp.100042~ (2020)
  42. Montavon, G., "Methods for interpreting and understanding deep neural networks", Digital signal processing, 73, pp.1~15 (2018)
  43. Mozo, A., "Anticipatory analysis of AGV trajectory in a 5G network using machine learning", Journal of Intelligent Manufacturing, pp.1~29 (2023)
  44. Park, K. H., "Impact of the COVID-19 pandemic on the lifestyle, mental health, and quality of life of adults in South Korea", Plos one, 16(2), pp.e0247970~ (2021)
  45. A procedure for estimation of trip length frequency distributions, "Pearson, D. F.", Texas Transportation Institute, Texas A & M University, ~, pp.No. Res. Rept. No. 17-1 (1974)
  46. Pope, P. T., "The use of an F-statistic in stepwise regression procedures", Technometrics, 14(2), pp.327~340 (1972)
  47. Rumelhart, D. E., "Learning representations by back-propagating errors", nature, 323(6088), pp.533~536 (1986)
  48. Sanders, H., "Garbage in, garbage out:how purportedly great ML models can be screwed up by bad data", Proceedings of Blackhat (2017)
  49. Saravanan, M., "IoT enabled indoor autonomous mobile robot using CNN and Q-learning", 2019 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), pp.7~13 (2019), IEEE
  50. Tjeng, V., "Evaluating robustness of neural networks with mixed integer programming", arXiv preprint arXiv:1711.07356, ~ (2017)
  51. Weng, T. W., "Evaluating the robustness of neural networks : An extreme value theory approach", arXiv preprint arXiv : 1801, ~ (2018)
  52. Yang, H., "A large-scale analytical residential parcel delivery model evaluating greenhouse gas emissions, COVID-19impact, and cargo bikes", International Journal of Transportation Science and Technology (2023)[DOI]
  53. Yin, W., "Comparative study of CNN and RNN for natural language processing", arXiv preprint arXiv: 1702.01923, ~ (2017)

이 간행물의 다른 논문 (7건)

도심 내 물류거점 입지선정 및 친환경 배송수단 라스트마일 배송경로 최적화신광섭, 이강현, 방선호pp. 1-16A Competitive Analysis of Top 20 Container Ports in Asia Using Super-Efficiency Model진가영, 이향숙pp. 31-43리던던시가 전투력에 미치는 영향에 관한 시뮬레이션 게임이명곤, 문성암, 임정혁pp. 45-57택배 배송 서비스 품질향상을 위한 YOLO 기반 택배 상자 파손 탐지 및 DCGAN 기반 데이터 증강김설희, 이상덕pp. 59-67계약 유형을 고려한 간선수송 내 트럭 할당 계획 최적화 모델강지훈, 김우영, 김준수, 정호상pp. 69-79
원문 보기