Earticle

Door to door service is a typical method for individual parcel deliveries. In the current delivery information system, a delivery person manually inputs the information of many delivery results, which causes inefficiency and difficulties of tracking deliveries. This study suggests an enhanced delivery information system which has the following two characteristics. Firstly, a tagged RFID(Radio Frequency Identification) transmits the delivery result information to the main server by just collecting RFID at a place of destination. Secondly, with the characteristics of rewritable method, the collected RFID is to be input new information and tagged to other parcels.

Recently, due to the expansion of the logistics industry, demand for logistics automation equipment is increasing. The modern logistics industry is a high-tech industry that combines various technologies. In general, as various technologies are grafted, the complexity of the system increases, and the occurrence rate of defects and failures also increases. As such, it is time for a predictive maintenance model specialized for logistics automation equipment. In this paper, in order to secure the operational safety and reliability of the parcel loading system, a predictive maintenance platform was implemented based on the Naive Bayes-LSTM(Long Short Term Memory) model. The predictive maintenance platform presented in this paper works by collecting data and receiving data based on a RabbitMQ, loading data in an InMemory method using a Redis, and managing snapshot DB in real time. Also, in this paper, as a verification of the Naive Bayes-LSTM predictive maintenance platform, the function of measuring the time for data collection/storage/processing and determining outliers/normal values was confirmed. The predictive maintenance platform can contribute to securing reliability and safety by identifying potential failures and defects that may occur in the operation of the parcel loading system in the future.

주소는 현대사회에서 사람들이 위치를 개념화하는 기본적인 수단 중 하나이며, 위치의 정보를 지니는 주소는 개인행태나 특정 사상의 공간적 분포 분석 시 사용되고 있다. 현재 우리나라의 주소체계는 지번주소와 도로명주소가 병행되어 사용되고 있다. 우리나라의 주소표시방법인 지번주소체계는 산업화⋅도시화의 진전으로 도시의 구조가 복잡해지고 거대화됨에 따라 주소의 위치 표시기능에 대해 문제점이 많이 지적되었기 때문이다. 본 연구에서는 도로명주소체계는 도로망기반의 지오코딩이 가능해짐에 따라 위치정확도 를 평가하고 이를 개선시킬 수 있는 방안들을 제시하였다. 실험결과 도로세그먼트를 수정하지 않은 상태에서 지오코딩의 위치오차는 평균 6.88m이었으나, 도로세그먼트 수정을 통해 평균 3.94m로 위치정확도가 향상되었다. 이러한 결과는 향후 주소자료의 GIS데이터베이스 구축에 효과적으로 이용될 수 있다.

Addresses are one of conceptual means for location in modern world. They have important information of personal behavior or spatial analysis. Recently, address system in Korea is changing from parcel based system to street based address system. Parcel based system has been no longer providing of location information due to rapid industrialization, increase of population or sprawl of city. Therefore new address system based on street network introduced. The objectives of this study are improved position accuracy. This study reviews the fundamental geocoding process, concept, and address system in Korea. The main results of this study were summed up as followings; Firstly, the geocoding was possible as new address system based street network. Secondly, positional errors in geocoding quality were reduced by modifying street segments. This research result can be widely used for construction of GIS database for address-based data.

한국 택배 시장의 규모는 해가 지날수록 점점 성장하고 있다. 최근 코로나 19의 여파로 인해 그 성장 폭은 훨씬 급등하였다. 지난 2020년 국내 택배 시장 물동량 추이를 살펴보면 약 34억 박스로 전년 약 28억 개에 비해 약 21% 증가하였다. 그리고 매출은 약 7조 5천억 원으로 전년 약 6조 3천억 원과 비교하면 약 19%가 증가하였다. 택배 시장이 성장하면서 택배 피해 구제에 대한 비율도 적지 않은 비율로 발생하고 있다. 1000명 중 약 33%가 배송사고 경험이 있고 이 중 약 41%가 파손 또는 훼손 경험을 한 적이 있다고 설문하였다. 본 논문에서는 파손된 택배를 감지하기 위해 택배를 감지할 수 있는 딥러닝 모델을 생성하였다. 이 모델의 성능을 확인하고 실시간 감지 카메라와 이 모델을 이용하여 배송과정에서 택배를 감지하여 분류할 수 있는 시스템을 연구하였다.

The size of the delivery market in Korea is growing year by year. In recent years, the growth rate has skyrocketed due to the aftermath of the coronavirus. Looking at the domestic delivery market's volume trend in 2020, about 3.4 billion boxes increased by 21% compared to about 2.8 billion boxes last year. In addition, sales amounted to 7.5 trillion won, an increase of about 19% compared to 6.3 trillion won a year earlier. As the delivery market grows, the proportion of courier damage relief is also occurring at a considerable rate. About 33% of 1,000 people have experienced delivery accidents, and about 41% of the week have experienced damage or damage. In this paper, a deep learning model capable of detecting a parcel was created to detect a damaged parcel. A system that can check the performance of this model and detect and classify parcels during the delivery process using a real-time detection camera was studied.

This study addresses the network design problem for an advanced last-mile delivery system that integrates drones and parcel lockers, termed drone lockers. Drone lockers serve temporary parcel storage and platforms for drone operations, including landing, takeoff, and battery recharging. The objective of the optimization problem addressed in this research is to minimize total costs by strategically determining the locations of drone lockers, assigning customer demand zones, and determining the required number of drones. The total costs considered include the establishment costs of drone lockers, round-trip delivery costs of drones, drone procurement costs, and truck operation costs. The problem is mathematically formulated, and four relax-and-fix heuristics are proposed to solve it. The performance of these heuristics is validated through computational experiments using both gathered and generated data. Furthermore, the superiority of the proposed model is demonstrated through scenario analysis, which highlights the model’s practical applicability and effectiveness in reducing costs.

현대 도시의 상수도 업무를 효율화, 고도화하기 위해서는 적절한 상수도정보체계의 운용이 필요하다. 이는 궁극적으로 도시종합정보체계의 부분이 되야 한다. 이를 수행하기 위해, 서울시 강남지역을 사례로 한국의 상수도 업무를 분석하고, 이를 바탕으로, 벡테 GIS의 macro-programming language를 이용하여, 한국토지행정업무의 기본인 지번을 기초로 도시상수도정보체계를 구축하여, 사례지역에 적용 후, 한국에서의 도시상수도정보체계가 효율적으로 운용되기 위한 활용방안, 제도적, 기술적 문제점 등을 논의하였다.

Water Information Systems requires efficient management, fast and highly advanced data processing. To respond these requirements promptly, it is essential to operate proper information systems. In the future, the system should be extended to comprehensive urban information systems. To implement these tasks, the user needs assessment were done using the study site data, Nonhyun-dong, Kangnam-ku, Seoul. Based on these analyses, the parcel-address based water information system was developed using the Arc Macro Language(AML) in Arc/Info, a vector-based GIS. The system was tested at the study site, then, the technological and institutional problems to be solved were discussed for the successful water information system.

인공지능은 스스로 학습하며 기존 통계 분석보다 탁월한 분석 역량을 지니고 있어 스마트팩토리 혁신에 새로운 전기를 마련할 것으로 기대된다. 이를 증명하듯 스마트팩토리의 주요 분야인 공정 간 연계 제어, 전문가 공정 제어, 로봇 자동화 등에서 활발한 연구가 이어지고 있다. 본 논문에서는 소포물 분류 시스템에 전통적인 룰 기반의 제어 방식 대신 다중 에이전트 강화 학습 제어 방식을 설계 및 적용하여 효과적인 행동 제어가 가능함을 입증한다.