• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.208-215
• /
• 2023

Deep learning techniques provide powerful solutions to several pattern-recognition problems, including Raman spectral classification. However, these networks require large amounts of labeled data to perform well. Labeled data, which are typically obtained in a laboratory, can potentially be alleviated by data augmentation. This study investigated various data augmentation techniques and applied multiple deep learning methods to Raman spectral classification. Raman spectra yield fingerprint-like information about chemical compositions, but are prone to noise when the particles of the material are small. Five augmentation models were investigated to build robust deep learning classifiers: weighted sums of spectral signals, imitated chemical backgrounds, extended multiplicative signal augmentation, and generated Gaussian and Poisson-distributed noise. We compared the performance of nine state-of-the-art convolutional neural networks with all the augmentation techniques. The LeNet5 models with background noise augmentation yielded the highest accuracy when tested on real-world Raman spectral classification at 88.33% accuracy. A class activation map of the model was generated to provide a qualitative observation of the results.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.156-165
• /
• 2023

IEEE 802.15.4e-TSCH is recognized as a wireless industrial sensor network standard used in IoT systems. To ensure both power savings and reliable communications, the TSCH standard uses techniques including channel hopping and bandwidth reserve. In TSCH mode, scheduling is crucial because it allows sensor nodes to select when data should be delivered or received. Because a wide range of applications may necessitate energy economy and transmission dependability, we present a distributed approach that uses a cluster tree topology to forecast scheduling requirements for the following slotframe, concentrating on the Poisson model. The proposed Optimized Minimal Scheduling Function (OMSF) is interested in the details of the scheduling time intervals, something that was not supported by the Minimal Scheduling Function (MSF) proposed by the 6TSCH group. Our contribution helps to deduce the number of cells needed in the following slotframe by reducing the number of negotiation operations between the pairs of nodes in each cluster to settle on a schedule. As a result, the cluster tree network's error rate, traffic load, latency, and queue size have all decreased.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.1
• /
• pp.173-182
• /
• 2001

In this paper, we discuss how ontology Plays roles in building a distributed and heterogeneous knowledge-base system. First, we discuss relationship between ontology and agent in the Knowledgeable Community which is a framework of knowledge sharing and reuse based on a multi-agent architecture. Ontology is a minimum requirement for each agent to join the Knowledgeable Community. Second we explain mediation by ontology to show how ontology is used in the Knowledgeable Community. A special agent called mediation analyzes undirected messages and infer candidates of recipient agents by consulting ontology and relationship between ontology and agents. Third we model ontology as combination of aspects each of which can represent a way of conceptualization. Aspects are combined either as combination aspect which means integration of aspects or category aspect which means choice of aspects. Since ontology by aspect allows heterogeneous and multiple descriptions for phenomenon in the world, it is appropriate for heterogeneous knowledge-base systems. We also show translation of messages as a wave of interpreting multiple aspects. A translation agent can translate a message with some aspect to one with another aspect by analyzing dependency of aspects. Mediation and translation of messages are important to build agents easily and naturally because less knowledge on other agents is requested for each agent.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.11
• /
• pp.2085-2092
• /
• 2016

One of the most important properties of the IC substrate is that it should be uniform over large areas. Among the various physical approaches of wafer defect characterization, special attention is to be payed to the infrared techniques of inspection. In particular, a high spatial resolution, near infrared absorption method has been adopted to directly observe defects in semi-insulating GaAs. This technique, which relies on the mapping of infrared transmission, is both rapid and non-destructive. This method demonstrates in a direct way that the infrared images of GaAs crystals arise from defect absorption process. A new interpretation is presented for the observed reversal of contrast in the infrared absorption of nonuniformly distributed deep centers, related to EL2, in semi-insulating GaAs. The low temperature photoquenching experiment has demonstrated in a direct way that the contrast inverse images of GaAs wafers arise from both absorption and scattering mechanisms rather than charge re-distribution or local variation of bandgap.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.50-55
• /
• 2021

Multi-path system is a system in which utilizes various networks simultaneously. It is expected that multi-path system can enhance communication speed, reliability, security of network. In this paper, we focus on path selection in multi-path system. To select optimal path, we propose deep reinforcement learning algorithm which is rewarded by the round-trip-time (RTT) of each networks. Unlike multi-armed bandit model, deep Q learning is applied to consider rapidly changing situations. Due to the delay of RTT data, we also suggest compensation algorithm of the delayed reward. Moreover, we implement testbed learning server to evaluate the performance of proposed algorithm. The learning server contains distributed database and tensorflow module to efficiently operate deep learning algorithm. By means of simulation, we showed that the proposed algorithm has better performance than lowest RTT about 20%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.109-116
• /
• 2021

In this paper, we propose a non-intrusive load monitoring(NILM) system which can find the power of each home appliance from the aggregated total power as the activation in the trading market of the distributed resource and the increasing importance of energy management. We transform the amount of appliances' power into a power on-off state by preprocessing. We use LSTM as a model for predicting states based on these data. Accuracy is measured by comparing predicted states with real ones after postprocessing. In this paper, the accuracy is measured with the different number of electronic products, data postprocessing method, and Time step size. When the number of electronic products is 6, the data postprocessing method using the Round function is used, and Time step size is set to 6, the maximum accuracy can be obtained.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.527-534
• /
• 2023

Triple modular redundancy (TMR) systems can continue their mission by virtue of their structural redundancy even if one processor is attacked by faults. In this paper, we propose a new fault tolerance strategy by introducing checkpoints into the TMR system in which data saving and fault detection processes are separated while they corporate together in the conventional checkpoints. Faults in one processor are tolerated by synchronizing the state of three processors upon detecting faults. Simultaneous faults occurring to more than one processor are tolerated by re-executing the task from the latest checkpoint. We propose the checkpoint placement and fault detection strategy to maximize the probability of successful execution of a task within the given deadline. We develop the Markov chain model for the TMR system having the proposed checkpoint strategy, and derive the optimal fault detection and checkpoint interval.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.1
• /
• pp.75-84
• /
• 2018

Increasing the operation rate of components and stabilizing the operation through timely management of the core parts are crucial for improving the efficiency of the railroad maintenance industry. The demand for diagnosis technology to assess the condition of rolling stock components, which employs history management and automated big data analysis, has increased to satisfy both aspects of increasing reliability and reducing the maintenance cost of the core components to cope with the trend of rapid maintenance. This study developed a big data platform-based system to manage the rolling stock component condition to acquire, process, and analyze the big data generated at onboard and wayside devices of railroad cars in real time. The system can monitor the conditions of the railroad car component and system resources in real time. The study also proposed a machine learning technique that enabled the distributed and parallel processing of the acquired big data and automatic component fault diagnosis. The test, which used the virtual instance generation system of the Amazon Web Service, proved that the algorithm applying the distributed and parallel technology decreased the runtime and confirmed the fault diagnosis model utilizing the random forest machine learning for predicting the condition of the bearing and wheel parts with 83% accuracy.

• The KIPS Transactions:PartA
• /
• v.16A no.6
• /
• pp.481-488
• /
• 2009

GIS is used to isolate large power electrical equipment using SF6 gas. While GIS has simple structure, it has few break down, relatively high reliability. But it is hard to check up faults for reason of pressure. Faults of GIS should have a ripple effect on community and be hard to recovery. Consequently, GIS imports a preventive diagnostic system to find internal faults in advance. It is most important that reliability on the GIS preventive diagnostic system, because it estimates abnormality of system by analysis result of collected data. But, exist system which used central data management is low efficiency, and hard to guarantee timeliness and accuracy of data. To guarantee timeliness and accuracy, the GIS preventive diagnostic system needs accordingly to use a real-time middleware. So, in this paper, to improve reliability of the GIS preventive diagnostic system, we use a middleware based on TMO for guaranteeing timeliness of real-time distributed computing. And we propose an improved GIS preventive diagnostic system applying data acquisition, monitoring and control methods based on the TMO model. The presented system uses the Communication Control Unit(CCU) for distributed data handling which is supported by TMO. CCU can improve performance of the GIS preventive diagnostic system by guaranteeing timeliness of data handling process and increasing reliability of data through the TMO middleware. And, it has designed to take full charge of overload on a data acquisition task had been processed in an exist server. So, it could reduce overload of the server and apply distribution environment from now. Therefore, the proposed system can improve performance and reliability of the GIS preventive diagnostic system and contribute to stable operation of GIS.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.11
• /
• pp.1094-1103
• /
• 2012

Recently, software industry regarding national defense increases system development of distributed simulation system of M&S based to overcome limit of resource and expense. It is one of key technologies for offering of mutual validation among objects and reuse of objects which are discussed for developing these systems. RTI, implementation of HLA interface specification as software providing these technologies uses Federation Object Model for exchanging information with joined federates in the federation and each federate has a characteristic that is supposed to have identical FOM in the federation. This technology is a software which is to provide the core technology which was suggested by the United state's military M&S standard framework. Simulator, virtual simulation, and inter-connection between military weapons system S/W which executes on network which is M&S's core base technology, and it is a technology which also can be used for various inter-connection between S/W such as game and on-line phone. These days although RTI is used in military war game or tactical training unit field, there is none in Korea. Also, it is used in mobile-game, distribution game, net management, robot field, and other civilian field, but the number of examples are so small and informalized. Through this developing project, we developed the core technique and RTI software and provided performance of COTS level to improve communication algorithms.