• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.4
• /
• pp.165-172
• /
• 2023

Heterogeneous computing is a technology that utilizes different types of processors to perform parallel processing. It maximizes task processing and energy efficiency by leveraging various computing resources such as CPUs, GPUs, and FPGAs. On the other hand, edge computing has developed with IoT and 5G technologies. It is a distributed computing that utilizes computing resources close to clients, thereby offloading the central server. It has evolved to intelligent edge computing combined with artificial intelligence. Intelligent edge computing enables total data processing, such as context awareness, prediction, control, and simple processing for the data collected on the edge. If heterogeneous computing can be successfully applied in the edge, it is expected to maximize job processing efficiency while minimizing dependence on the central server. In this paper, experiments were conducted to verify the feasibility of various parallel programming models on high-end and low-end edge devices by using benchmark applications. We analyzed the performance of five parallel programming models on the Raspberry Pi 4 and Jetson Orin Nano as low-end and high-end devices, respectively. In the experiment, OpenACC showed the best performance on the low-end edge device and OpenSYCL on the high-end device due to the stability and optimization of system libraries.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.258-259
• /
• 2017

Recently, as science and technology is very growing, wire and wireless communication is merged and interconnected. Therefore, advanced internet technology allow all kinds of communication to integrate with heterogeneous device and sensors. The representative example is smart home network based on internet of things. Communication surroundings under IoT services are more complex. Conventional encryption techniques can't provide to IoT application because of its limited resources such as small memory capacity and low computing power. In this paper, we analyzed authentication procedure between home gateway and node in sensor under smart home network.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1238-1249
• /
• 2020

Throughout the world, aging populations and doctor shortages have helped drive the increasing demand for smart healthcare systems. Recently, these systems have benefited from the evolution of the Internet of Things (IoT), big data, and machine learning. However, these advances result in the generation of large amounts of data, making healthcare data analysis a major issue. These data have a number of complex properties such as high-dimensionality, irregularity, and sparsity, which makes efficient processing difficult to implement. These challenges are met by big data analytics. In this paper, we propose an innovative analytic framework for big healthcare data that are collected either from IoT wearable devices or from archived patient medical images. The proposed method would efficiently address the data heterogeneity problem using middleware between heterogeneous data sources and MapReduce Hadoop clusters. Furthermore, the proposed framework enables the use of both fog computing and cloud platforms to handle the problems faced through online and offline data processing, data storage, and data classification. Additionally, it guarantees robust and secure knowledge of patient medical data.

• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1175-1182
• /
• 2017

Recent trend in the manufacturing industry is focused on the convergence with IoT and Big Data, by emergence of the 4th Industrial Revolution. To realize a smart factory, the proposed system based on MTConnect technology collects and integrates various status information of machines from many production facilities including heterogeneous devices. Also it can distribute the acquisited status of heterogeneous manufacturing machines to the remote devices. As a key technology of a flexible automated production line, the proposed system can provide much possibility to manage important information such as error detection and processing state management in the unmanned automation line.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.4
• /
• pp.871-878
• /
• 2017

As the interest of things to the Internet increases, the market of IoT grows larger and devices and protocols related with IoT are evolving.As these IoT devices and protocols evolve, There was a problem with interoperability. As a result, market and standard of IoT are confused, and communication between objects and objects is being hindered by different platforms. Currently, various IoT platforms are being developed and interoperability with heterogeneous platforms is under study, but the protocols used on each platform are limited and designed to have no generalized structure. Therefore, in this paper, we analyze services of HTTP, CoAP, and MQTT protocols, which are typical in the Internet market, and design services that enable selective protocol communication. We also design resources that apply the RESTful API to generalize platform usage. and We implemented the platform through database modeling for quick processing and safety of the collected data. Through this process, devices communicating with different protocols can be interworked on one platform and We propose a "generalized selective protocol based Internet object data collecting platform" that can be applied to various protocols.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.3
• /
• pp.623-630
• /
• 2016

Heterogeneous IoT devices must satisfy a certain level of security for mutual connections and communications. However, a performance degradation of cryptographic algorithms in resource constrained devices is inevitable and so an optimization or efficient implementation method is necessary. In this paper, we study an efficient implementation method for rotation operations regarding registers for running ARX lightweight block ciphers. In a practical sense, we investigate the performance of modified rotation operations through experiments using real experiment devices. We show the improved performance of modified rotation operations and discover the significant difference in measured performance between simulations and real experiments, particularly for 16-bit MSP microcontrollers.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.1-9
• /
• 2022

As various services are linked to IoT(Internet of Things) and portable communication terminals, cyber attacks that exploit security vulnerabilities of the devices are rapidly increasing. In particular, cyber attacks targeting heterogeneous devices in large-scale network environments through advanced persistent threat (APT) attacks are on the rise. Therefore, in order to improve the effectiveness of the response system in the event of a breach, it is necessary to apply a data enrichment mechanism for the collected artifact data to improve threat analysis and detection performance. Therefore, in this study, by analyzing the data supplementation common elements performed in the existing incident management framework for the artifacts collected for the analysis of intrusion accidents, characteristic elements applicable to the actual system were derived, and based on this, an improved accident analysis framework The prototype structure was presented and the suitability of the derived data supplementary extension elements was verified. Through this, it is expected to improve the detection performance when analyzing cyber incidents targeting artifacts collected from heterogeneous devices.

• Smart Media Journal
• /
• v.6 no.2
• /
• pp.42-49
• /
• 2017

It is important to realize automation services by communicating in IoT with humans, objects & objects, and forming a common network. People used web like the most powerful network way to sharing things and communication. Therefore the efficiency method communication between each device and the web in IoT could be different from ones. The best method for high quality software product in web applications is software reuse ; Modules, classes, patterns, frameworks, and business components are reusable elements of various perspectives. Components is plugged with others through well-defined interfaces, which can overcome the operation and complexity of application development. A web-based distributed environment for IoT applications is a standard architecture use information collected from various devices for developing and using applications. For that reason, the network management which manages the constituent resources for the best service control in IoT application is required as a sub-layer support service in most applications as well as individual applications. In this paper, we measure to develop a network management system based not only by components but on heterogeneous internetworks. For procedure this, we clarify a component architecture for classifying and classify also the component needed in the IOT and network domain or order the type of real network management system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.617-618
• /
• 2017

Recently, IoT can provide a service considering user's convenience by configuring the inside of the home as a smart environment. However, the existing system can not change the configuration of the home smart environment by the user, and there is a problem in compatibility between the server and the heterogeneous device. In this paper, we propose a system to reconfigure the relationship between the device and the server in the smart home environment to solve that. In a smart home environment, The user can add and delete devices through the application. In addition, when a new device is added, the server searches the schema for the device and establishes an automatic relationship. This makes it possible for the user to easily change the configuration of the smart home environment.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.5
• /
• pp.211-218
• /
• 2017

Recent robot software platform research focuses on providing intelligent service via abstraction of robot devices. Context-aware techniques are necessary for intelligent robot services, which are based on the perception of environmental information obtained from heterogeneous sensors in IoT environment. Robot Operating System (ROS) provides protocols to operate robot devices. ROS includes functions for abstracting heterogeneous sensors themselves in order to control the robot, however, it lacks the ability to provide context information that the robot can perceive based on environmental information through consistent collection methods. In this paper, we propose a relay system for ROS to provide context-aware robot service. The proposed system makes it possible for ROS to control and provide context-aware robot services with relay of an external context-aware system and ROS. In experiments, we demonstrate procedures that robot services abstracted from ROS and an external context-aware system works together based on the proposed system.