• Title/Summary/Keyword: JMIS

Search Result 294, Processing Time 0.02 seconds

Fall Situation Recognition by Body Centerline Detection using Deep Learning

  • Kim, Dong-hyeon;Lee, Dong-seok;Kwon, Soon-kak
    • Journal of Multimedia Information System
    • /
    • v.7 no.4
    • /
    • pp.257-262
    • /
    • 2020
  • In this paper, a method of detecting the emergency situations such as body fall is proposed by using color images. We detect body areas and key parts of a body through a pre-learned Mask R-CNN in the images captured by a camera. Then we find the centerline of the body through the joint points of both shoulders and feet. Also, we calculate an angle to the center line and then calculate the amount of change in the angle per hour. If the angle change is more than a certain value, then it is decided as a suspected fall. Also, if the suspected fall state persists for more than a certain frame, then it is determined as a fall situation. Simulation results show that the proposed method can detect body fall situation accurately.

Behavior Tree-based Scenario Development Technology to Induce Various Experiences of VR content

  • Seo, Jinseok;Yang, Ungyeon
    • Journal of Multimedia Information System
    • /
    • v.7 no.4
    • /
    • pp.263-268
    • /
    • 2020
  • This paper introduces an event modeling and simulation system using behavior trees. The system aims to overcome the limitations of existing fixed, simple scenario-based training content, and to extend the behavior of objects to enable various experience deployments. To achieve this goal, we made specific tasks of behavior trees can change according to users' reaction and developed an adaptive simulation module that can analyze and execute behavior trees that changes at runtime. In order to validate our approach, we applied the adaptive behavior tree simulation to the scenarios in our virtual reality simulation-based fire training system we have been developing and demonstrated the implementation results.

Design and Implementation of a Smart Glass Application for XR Assisted Training of Core Nursing Skills

  • Kim, Sun Kyung;Yoon, Hyoseok;Shin, Choonsung;Choi, Jongmyung;Lee, Youngho
    • Journal of Multimedia Information System
    • /
    • v.7 no.4
    • /
    • pp.277-280
    • /
    • 2020
  • Extended reality-assisted training offers repeatable learning opportunities at a low cost. This paper proposes a smart glass application for training core nursing skills to nursing students, who often need to memorize and practice training sequences. The proposed smart glass application interactively presents a series of instructions to help students remember and perform two core nursing skills in the correct order. We conducted a usability test on 30 undergraduate nursing students in their third year using the smart glass application. Our initial findings show that many students have positively evaluated the possibility of using smart glasses for training, but have also encountered several challenges with the smart glass application's user interface, which takes time to adapt.

Augmentation of Hidden Markov Chain for Complex Sequential Data in Context

  • Sin, Bong-Kee
    • Journal of Multimedia Information System
    • /
    • v.8 no.1
    • /
    • pp.31-34
    • /
    • 2021
  • The classical HMM is defined by a parameter triple �� = (��, A, B), where each parameter represents a collection of probability distributions: initial state, state transition and output distributions in order. This paper proposes a new stationary parameter e = (e1, e2, …, eN) where N is the number of states and et = P(|xt = i, y) for describing how an input pattern y ends in state xt = i at time t followed by nothing. It is often said that all is well that ends well. We argue here that all should end well. The paper sets the framework for the theory and presents an efficient inference and training algorithms based on dynamic programming and expectation-maximization. The proposed model is applicable to analyzing any sequential data with two or more finite segmental patterns are concatenated, each forming a context to its neighbors. Experiments on online Hangul handwriting characters have proven the effect of the proposed augmentation in terms of highly intuitive segmentation as well as recognition performance and 13.2% error rate reduction.

A Data Provenance System for Myanmar Rice Cycle Based on Ethereum Blockchain

  • Latt, Cho Nwe Zin;Rahmadika, Sandi;Rhee, Kyung-Hyune
    • Journal of Multimedia Information System
    • /
    • v.8 no.1
    • /
    • pp.35-44
    • /
    • 2021
  • The Myanmar rice cycle's existing system is still relying on a third party to manage every rice data information from several organizations. It is inconvenient to supervise simultaneously due to the unreliability of information provided by organizations. Thus, the rice cycle's original data is challenging to be utterly trusted since irresponsible parties can manipulate the current state of information. Moreover, the applied system does not preserve a proper incentive for the involved parties. In this paper, we leverage the Ethereum blockchain to be adopted to tackle the aforementioned issues. The main objective is to build trust between parties in the Myanmar rice cycle system. Our proposed scheme allows customers to check and trace information about the rice cycle information without worrying about the integrity of the data. Furthermore, the authorized parties are also rewarded by the government through Ethereum smart contract features. Eventually, our scheme achieves traceability in the rice chain system and leads to the complete digitization and automation of the rice cycle information.

Development of Standard Hill Technology for Image Encryption over a 256-element Body

  • JarJar, Abdellatif
    • Journal of Multimedia Information System
    • /
    • v.8 no.1
    • /
    • pp.45-56
    • /
    • 2021
  • This document traces the new technologies development based on a deep classical Hill method improvement. Based on the chaos, this improvement begins with the 256 element body construction, which is to replace the classic ring used by all encryption systems. In order to facilitate the application of algebraic operators on the pixels, two substitution tables will be created, the first represents the discrete logarithm, while the second represents the discrete exponential. At the same time, a large invertible matrix whose structure will be explained in detail will be the subject of the advanced classical Hill technique improvement. To eliminate any linearity, this matrix will be accompanied by dynamic vectors to install an affine transformation. The simulation of a large number of images of different sizes and formats checked by our algorithm ensures the robustness of our method.

Secret Key and Tag Generation for IIoT Systems Based on Edge Computing

  • Koh, Giheon;Yu, Heungsik;Kim, Sungun
    • Journal of Multimedia Information System
    • /
    • v.8 no.1
    • /
    • pp.57-60
    • /
    • 2021
  • Industry 4.0 is continuous automation by applying the latest smart technologies to traditional manufacturing industries. It means that large-scale M2M (Machine-to-Machine) communication and IoT (Internet of Things) technologies are well integrated to build efficient production systems by analyzing and diagnosing various issues without human intervention. Edge computing is widely used for M2M services that handle real-time interactions between devices at industrial machinery tool sites. Here, secure data transmission is required while interacting. Thus, this paper focused on a method of creating and maintaining secret key and security tag used for message authentication between end-devices and edge-device.

Data Analytics Application: A Case Study of Online Business for Vietnamese Handicraft Products on Amazon

  • Lan, Nguyen Thi Thao;Phuong, Nguyen Pham Anh;Trang, Nguyen Thi My;Huong, Pham Thi My;An, Nguyen Thu;Le, Hoanh-Su
    • Journal of Multimedia Information System
    • /
    • v.8 no.1
    • /
    • pp.61-68
    • /
    • 2021
  • The paper is based on data collected from the Amazon website (specific in the Handmade's Category) to understand and analyze Vietnamese artisans' business context. Data analysis is also applied to determine the factors that bring success Handmade products and compare products of the same industry among competitors to find out potential products. By collecting data from Amazon and analyzing the data, we extracted useful information for online business developers. Besides, the list of potential products in Handmade sector can be referred to improve the business and compete with competitors. This paper also proposes solutions to help Vietnamese products become more appealing to international customers on the Amazon website.

Implementation of Customized Variable Insurance Management System Using Data Crawling and Fund Management Algorithm

  • Nam, Sung-hyun;Kwon, Soon-kak
    • Journal of Multimedia Information System
    • /
    • v.8 no.1
    • /
    • pp.69-74
    • /
    • 2021
  • This paper accumulates the product structure data such as bond obligation ratio and investment ratio for variable insurance using crawling from the insurance company's API, also accumulates variable insurance income and project expenses for variable insurance using crawling from the API of life insurance association. From these accumulated data, the correlation coefficient between fund product and customer preference is calculated with an investment algorithm, and variable insurance funds by customer investment preference and product structure are recommended according to market conditions. From the simulation results, it is shown that the proposed variable insurance management system properly recommends and manages variable insurance according to customer preferences.

Glanceable and Informative WearOS User Interface for Kids and Parents

  • Kim, Siyeon;Yoon, Hyoseok
    • Journal of Multimedia Information System
    • /
    • v.8 no.1
    • /
    • pp.17-22
    • /
    • 2021
  • This paper proposes a wearable user interface intended for kids and parents using WearOS smartwatches. We first review what constitutes a kids smartwatch and then design UI components for watchfaces to be used by kids and parents. Different UI components ranging from activity, education, voice search, app usage, video, location, health, and quick dial are described. These components are either implemented as complications or on watchfaces and may require on-device standalone function, cross-device communication, and external database. We introduce a theme-based amusing UI for kids whereas simple and easily accessible components are recommended to parents' watchface. To illustrate use cases, we present 3 scenarios for enhancing communication between parents and child. To show feasibility and potential of our approach, we implement our proof-of-concept using commercial smartwatches, smartphones, and external cloud database. Furthermore, performance of checking app usages on different devices are presented, followed by discussion on limitations and future work.