http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Dat Van Anh Duong (검색결과 5 건)
- 무료
- 기관 내 무료
- 유료
-
A Workflow-based Mobility Model of Workers in Shipyards
Dat Van Anh Duong,Seokhoon Yoon(윤석훈) 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
In shipyards, the movements of workers greatly affect the performance of wireless networks and IoT services. To fully validate such services and networks, worker's movements should be considered. A lot of human movement models have been studied but most of them focus on the daily movements of people. That cannot reflect the worker's movements in shipyards. Therefore, we propose a new mobility model called the workflow-based mobility model of workers in shipyards (WMS). To fully reflect the worker's movements, we consider workflow of workers for movement generation. First, workers are classified into types. Workers in a type have similar movement characteristics (e.g., pause time and movement speed). Then, a type is divided into teams. Workers of a team have the same workflow and workplace. Workers move based on their workflow.
-
A Human Mobility Model in Shipyards
Duong, Dat Van Anh,Yoon, Seokhoon The Institute of Internet 2020 International Journal of Internet, Broadcasting an Vol.12 No.4
Shipyards are potential environments for using IoT services, sensor networks, and delay tolerant networks. Simulations of those services and networks strongly rely on human mobility models. Results obtained with an unrealistic model may not reflect the true performance of applications, protocols, and algorithms in a shipyard. A lot of synthetic models for human movements have been studied but most of them are generic and focus on the daily movements of humans on city scales. Nevertheless, workers in shipyards have unique movement characteristics such as movement speed, pause time, and attractions places. For instance, workers usually move to some places, where they work, and rarely move to other places in the factory. Movement characteristics of workers not only depend on workers but also on tasks, which they do. For instance, workers, who paint ships, have similar movement speed and pause time. Hence, in this paper, human movements in shipyards are studied. We propose a new human mobility model called the human mobility mode in shipyards (MIS). In MIS, workers are classified into multiple types. Movement characteristics of a worker are similar to other workers in the same type. Based on the visiting probability, workers have some places, where they frequently visits, and some places, where they rarely visit. We analyze real mobility traces and studie to achieve human movement characteristics from real traces. The results show that MIS provides a well-match to the movement characteristic from real traces.
-
A Human Movement Stream Processing System for Estimating Worker Locations in Shipyards
Duong, Dat Van Anh,Yoon, Seokhoon The Institute of Internet 2021 International Journal of Internet, Broadcasting an Vol.13 No.4
Estimating the locations of workers in a shipyard is beneficial for a variety of applications such as selecting potential forwarders for transferring data in IoT services and quickly rescuing workers in the event of industrial disasters or accidents. In this work, we propose a human movement stream processing system for estimating worker locations in shipyards based on Apache Spark and TensorFlow serving. First, we use Apache Spark to process location data streams. Then, we design a worker location prediction model to estimate the locations of workers. TensorFlow serving manages and executes the worker location prediction model. When there are requirements from clients, Apache Spark extracts input data from the processed data for the prediction model and then sends it to TensorFlow serving for estimating workers' locations. The worker movement data is needed to evaluate the proposed system but there are no available worker movement traces in shipyards. Therefore, we also develop a mobility model for generating the workers' movements in shipyards. Based on synthetic data, the proposed system is evaluated. It obtains a high performance and could be used for a variety of tasksin shipyards.
-
Duong, Dat Van Anh,Lan, Doi Thi,Yoon, Seokhoon The Institute of Internet 2022 International Journal of Internet, Broadcasting an Vol.14 No.4
Detecting anomalies in human movement is an important task in industrial applications, such as monitoring industrial disasters or accidents and recognizing unauthorized factory intruders. In this paper, we propose an abnormal worker movement detection system based on data stream processing and hierarchical clustering. In the proposed system, Apache Spark is used for streaming the location data of people. A hierarchical clustering-based anomalous trajectory detection algorithm is designed for detecting anomalies in human movement. The algorithm is integrated into Apache Spark for detecting anomalies from location data. Specifically, the location information is streamed to Apache Spark using the message queuing telemetry transport protocol. Then, Apache Spark processes and stores location data in a data frame. When there is a request from a client, the processed data in the data frame is taken and put into the proposed algorithm for detecting anomalies. A real mobility trace of people is used to evaluate the proposed system. The obtained results show that the system has high performance and can be used for a wide range of industrial applications.
-
Estimating Workers’ Locations in Industrial Sites
Quan T. Ngo(오딴콴),Dat Van Anh Duong(즈엉 반 안 닷),Doi Thi Lan(도이 티 란),Seokhoon Yoon(윤석훈) 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
Worker location estimation plays an important role in reducing the amount of time for rescue operations when an incident occurs, thus improves worker safety. In this paper, we address the problem of estimating the current location of a worker in the working sites, given his/her historical location records. A large-scale dataset of Wi-Fi traces is used to train and test the proposed model.
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
