Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

4 Annals of Computer Science and Information Systems

4 2019

Znaleziono wyników: 4

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Analysis of relationship between personal factors and visiting places using random forest technique

100%

Kim Y. M. , Song H. Y.

Annals of Computer Science and Information Systems

2019

tom Vol. 18

725--732

There has been research regarding relationship between human personalities and visiting places using Big Five Factor (BFF). However, other factors such as Social media usage, Hobby, Gender, Age, and Religion and so on are regarded as also major factors which effects the choice of visiting place of a person. Using questionnaire designed by authors, these factors as well as BFF were prepared for this research. The visiting places were collected by a smartphone app called SWARM and classified in 10 categories. In sum, personal data of 34 participants had been collected for several months. To figure out the relationship between these factors and visiting places, random forest technique of ensemble method was used.

An adaptation of IoT to improve parcel delivery system

100%

Song H. Y. , Han H. C.

Annals of Computer Science and Information Systems

2019

tom Vol. 18

497--500

Recently, IoT technology has been applied in various field. Especially this IoT technology can also be applied to delivery system. Current delivery system is high costly but somewhat inefficient. A delivery must go through the logistics hub, even if it's not a minimum distance. In this paper, we propose an enhanced parcel delivery system based on IoT technology. Firstly, we designed a sort of IoT devices which can be attached parcels. This devices has various functionalities including the ability to figure out current delivery route. Secondly, we introduce some difficulties such as : (i) issues linking IoT device into its platform; (ii) issues for designing IoT devices functionalities. Thirdly, we propose ways to improve the efficiency of IoT based parcel delivery system. From these considerations, our system may improve total economics of parcel delivery system.

Analysis of the correlation between personal factors and visiting locations with boosting technique

100%

Song H. Y. , Yun J.

Annals of Computer Science and Information Systems

2019

tom Vol. 18

743--746

The paper analyzed the relationship between the person's fourteen characteristic factors and place to visit. The personal factors consist of personality, marital Status, final education, majors, religion, monthly income, commuting means and time, number of travel, use of SNS, time for SNS per day, life of culture. In addition, the analysis was done on which factors have the greatest impact. The analysis involved thirty-four participants and the boosting technique was used as a method of analysis. Personality data was obtained through the Big Five Factors (BFF), data for the rest of the factors were obtained through a self-created questionnaire. Location data was obtained through a Swarm application. For each location categories, the most effective factors were identified in this research.

Generating human mobility route based on generative adversarial network

80%

Song H. Y. , Baek M. S. , Sung M.

Annals of Computer Science and Information Systems

2019

tom Vol. 18

91--99

Recently, many researches on human mobility are aiming to suggest the personal customized solution in the diverse field, usually by academia and industry. Combined with deep learning methods, the mobility data can predict and generate routes of objects from the given past trends. In this work, the Generative Adversarial Network (GAN) model is introduced for creating individual mobility routes based on sets of accumulated personal mobility data. The mobility data had been collected by use of geopositioning system and personal mobile devices. GAN has Discriminator and Generator which are composed of neural networks, and can extract and train geopositionig information. A sequence of longitude and latitude can be geographically mapped and such images can be handled by GAN. The GAN based model successfully handled individual mobility routes in this way. Consequently, our model can generate and suggest unexplored routes from the existing sets of personal geolocation data.