• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.79-92
• /
• 2015

Knowledge map is widely used to represent knowledge in many domains. This paper presents a method of integrating the national R&D data and assists of users to navigate the integrated data via using a knowledge map service. The knowledge map service is built by using a lightweight ontology and a topic modeling method. The national R&D data is integrated with the research project as its center, i.e., the other R&D data such as research papers, patents, and reports are connected with the research project as its outputs. The lightweight ontology is used to represent the simple relationships between the integrated data such as project-outputs relationships, document-author relationships, and document-topic relationships. Knowledge map enables us to infer further relationships such as co-author and co-topic relationships. To extract the relationships between the integrated data, a Relational Data-to-Triples transformer is implemented. Also, a topic modeling approach is introduced to extract the document-topic relationships. A triple store is used to manage and process the ontology data while preserving the network characteristics of knowledge map service. Knowledge map can be divided into two types: one is a knowledge map used in the area of knowledge management to store, manage and process the organizations' data as knowledge, the other is a knowledge map for analyzing and representing knowledge extracted from the science & technology documents. This research focuses on the latter one. In this research, a knowledge map service is introduced for integrating the national R&D data obtained from National Digital Science Library (NDSL) and National Science & Technology Information Service (NTIS), which are two major repository and service of national R&D data servicing in Korea. A lightweight ontology is used to design and build a knowledge map. Using the lightweight ontology enables us to represent and process knowledge as a simple network and it fits in with the knowledge navigation and visualization characteristics of the knowledge map. The lightweight ontology is used to represent the entities and their relationships in the knowledge maps, and an ontology repository is created to store and process the ontology. In the ontologies, researchers are implicitly connected by the national R&D data as the author relationships and the performer relationships. A knowledge map for displaying researchers' network is created, and the researchers' network is created by the co-authoring relationships of the national R&D documents and the co-participation relationships of the national R&D projects. To sum up, a knowledge map-service system based on topic modeling and ontology is introduced for processing knowledge about the national R&D data such as research projects, papers, patent, project reports, and Global Trends Briefing (GTB) data. The system has goals 1) to integrate the national R&D data obtained from NDSL and NTIS, 2) to provide a semantic & topic based information search on the integrated data, and 3) to provide a knowledge map services based on the semantic analysis and knowledge processing. The S&T information such as research papers, research reports, patents and GTB are daily updated from NDSL, and the R&D projects information including their participants and output information are updated from the NTIS. The S&T information and the national R&D information are obtained and integrated to the integrated database. Knowledge base is constructed by transforming the relational data into triples referencing R&D ontology. In addition, a topic modeling method is employed to extract the relationships between the S&T documents and topic keyword/s representing the documents. The topic modeling approach enables us to extract the relationships and topic keyword/s based on the semantics, not based on the simple keyword/s. Lastly, we show an experiment on the construction of the integrated knowledge base using the lightweight ontology and topic modeling, and the knowledge map services created based on the knowledge base are also introduced.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.4
• /
• pp.399-405
• /
• 2008

Recently, robot technology is actively going on progress to the field of various services such as home care, medical care, entertainment, and etc. Because these service robots are in use nearby person, they need to be operated safely even though hardware and software faults occur. This paper proposes a Fault-Tolerant middleware for a robot system, which has following two characteristics: supporting of heterogeneous network interface and processing of software components and network faults. The Fault-Tolerant middleware consists of a Service Layer(SL), a Network Adaptation Layer(NAL), a Network Interface Layer(NIL), a Operating System ion Layer(OSAL), and a Fault-Tolerant Manager(FTM). Especially, the Fault-Tolerant Manager consists of 4 components: Monitor, Fault Detector, Fault Notifier, and Fault Recover to detect and recover the faults effectively. This paper implements and tests the proposed middleware. Some experiment results show that the proposed Fault-Tolerant middleware is working well.

• Journal of the military operations research society of Korea
• /
• v.29 no.1
• /
• pp.57-75
• /
• 2003

Policy-based networking offers a network manager the ability to manage the network in a holistic and dynamic fashion rather than force a network manager to manage the network by dealing with each device individually. Policy-based networking is focusing on users and applications instead of emphasizing devices and interfaces. An important part of the policy-based networking is to simplify the task of administration and management for different disciplines. The Defense Information System(DIS) of today are complex and heterogeneous systems. Operational needs are not a trivial task and Quality of Service(QoS) is not generally guaranteed. So, important data may be missed or congested by trivial data. Policy-based networking provide a way to support QoS and simplify the management of multiple devices deploying complex technologies. This paper suggest implementation of policy-based networking in DIS to improvement of performance, and implementation is progressed step by step. Especially this paper is focusing on the providing QoS with policy-based networking using Lightweight Directory Access Protocol(LDAP) Server.

• Convergence Security Journal
• /
• v.5 no.4
• /
• pp.49-58
• /
• 2005

We propose a specific ubiquitous sensor network (USN) architecture as a promising candidate of the future telemedicine model which offers the patient's mobility and more cost-efficient medical care system. This new USN architecture is a kind of cell-based secure sensor network supporting encrypted multi-casting communications and it has a hybrid routing protocol by adapting flat routing to hierarchical routing. For the patient's privacy and the protection of patient's vital information from eavesdropping, we adopt a lightweight PKI-based secure communication protocol with some formal presentation on its core procedure.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.413-420
• /
• 2006

The speed of present-day network technology exceeds a gigabit and is developing rapidly. When using TCP/IP in these high-speed networks, a high load is incurred in processing TCP/IP protocol in a host CPU. To solve this problem, research has been carried out into TCP/IP Offload Engine (TOE). The TOE processes TCP/IP on a network adapter instead of using a host CPU; this reduces the processing burden on the host CPU. In this paper, we developed two software-based TOEs. One is the TOE implementation using an embedded Linux. The other is the TOE implementation using Lightweight TCP/IP (lwIP). The TOE using an embedded Linux did not have the bandwidth more than 62Mbps. To overcome the poor performance of the TOE using an embedded Linux, we ported the lwIP to the embedded system and enhanced the lwIP for the high performance. We eliminated the memory copy overhead of the lwIP. We added a delayed ACK and a TCP Segmentation Offload (TSO) features to the lwIP and modified the default parameters of the lwIP for large data transfer. With the aid of these modifications, the TOE using the modified lwIP shows a bandwidth of 194 Mbps.

• Convergence Security Journal
• /
• v.15 no.2
• /
• pp.63-68
• /
• 2015

Current ICT(Information & Communication Technology) infrastructures (Internet and server/client communication) are struggling for a wide variety of devices, services, and business and technology evolution. Cloud computing originated simply to request and execute the desired operation from the network of clouds. It means that an IT resource that provides a service using the Internet technology. It is getting the most attention in today's IT trends. In the distributed cloud environments, management costs for the network and computing resources are solved fundamentally through the integrated management system. It can increase the cost savings to solve the traffic explosion problem of core network via a distributed Micro DC. However, traditional flooding methods may cause a lot of traffic due to transfer to all the neighbor DCs. Restricted Path Flooding algorithms have been proposed for this purpose. In large networks, there is still the disadvantage that may occur traffic. In this paper, we developed Lightweight Path Flooding algorithm to improve existing flooding algorithm using hop count restriction.

• Journal of Communications and Networks
• /
• v.3 no.4
• /
• pp.317-323
• /
• 2001

Traditional configuration management involves complex labor-intensive processes performed by experts. The configuration tasks such as installing or reconfiguring a system, provisioning network services and allocating resources typically involve a large number of activities involving multiple network elements. The network elements may be associated with proprietary configuration management instrumentation and may also be spread across heterogeneous network domains thereby increasing the complexity of configuration management. This paper introduces an architecture for the self-configuration of networks (SELFCON). The proposed architecture involves a directory server, which is uses to maintain configuration information. The configuration information stared in the directory server is modeled using the standard DEN specification thereby allowing effective exchange of network, system and configuration management data among heterogeneous management domains. SELFCON associates configuration intelligence with the components of the network, rather than limit it to a centralized management station. The network elements are notified about related changes in configuration policies, based upon which, they perform self-configuration. SELFCON is able to provide automation of configuration management and also an effective unifying framework for enterprise management.

• ETRI Journal
• /
• v.31 no.5
• /
• pp.525-533
• /
• 2009

This paper proposes a distributed borrowing addressing (DIBA) scheme to solve problems of failure in address assignments resulting from limited tree depth and width when the distributed address assignment mechanism is used in a ZigBee/IEEE 802.15.4 wireless sensor network. DIBA is a method of borrowing addresses from neighbor nodes for newly entering nodes and assigning the borrowed addresses. Its network or sensing coverage can increase with almost the same overhead as the existing method. DIBA is a simple and lightweight means of addressing and routing, making it suitable for wireless sensor networks. Simulations showed that DIBA is a distributed addressing scheme with consistently excellent performance.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.4
• /
• pp.289-293
• /
• 2016

As more mobile devices are equipped with multi-core CPUs and are required to execute many compute-intensive multimedia applications, it is important to optimize the systems, considering the underlying parallel hardware architecture. In this paper, we implement and optimize ray-tracing application tailored to a given mobile computing platform with multiple heterogeneous processing elements. In this paper, a lightweight ray-tracing application is specified and implemented in Kahn process network (KPN) model-of-computation, which is known to be suitable for the description of real-time applications. We take an open-source C/C++ implementation of ray-tracing and adapt it to KPN description in the Distributed Application Layer framework. Then, several possible configurations are evaluated in the target mobile computing platform (Exynos 5422), where eight heterogeneous ARM cores are integrated. We derive the optimal degree of parallelism and a suitable distribution of the replicated tasks tailored to the target architecture.