• Smart Media Journal
• /
• v.13 no.4
• /
• pp.33-48
• /
• 2024

With the advent of 5G, characterized by Enhanced Mobile Broadband (eMBB), Ultra-Reliable Low Latency Communications (URLLC), and Massive Machine Type Communications (mMTC), efficient network management and service provision are becoming increasingly critical. This paper proposes a novel approach to address key challenges of 5G networks, namely ultra-high speed, ultra-low latency, and ultra-reliability, while dynamically optimizing network slicing and resource allocation using machine learning (ML) and deep learning (DL) techniques. The proposed methodology utilizes prediction models for network traffic and resource allocation, and employs Federated Learning (FL) techniques to simultaneously optimize network bandwidth, latency, and enhance privacy and security. Specifically, this paper extensively covers the implementation methods of various algorithms and models such as Random Forest and LSTM, thereby presenting methodologies for the automation and intelligence of 5G network operations. Finally, the performance enhancement effects achievable by applying ML and DL to 5G networks are validated through performance evaluation and analysis, and solutions for network slicing and resource management optimization are proposed for various industrial applications.

• Proceedings of the IEEK Conference
• /
• 2000.06b
• /
• pp.68-71
• /
• 2000

In this paper, we have measured the oxygen contents by FTIR in silicon wafer various process technology(slicing, lapping, polishing). The measured data are also compared with the data of etching process(KOH, Bright etching). Also we have measured the surface morpology in backside silicon wafer after etching treatment and etch pit density due to OISF after 4 step high temperature annealing process with optical microscope.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.306-311
• /
• 2000

We, Human beings, use both powers of reason and emotion simultaneously, which surely help us to obtain flexible adaptability against the dynamic environment. We assert that this principle can be applied into the general system. That is, it would be possible to improve the adaptability by covering a digital oriented information processing system with analog oriented emotion layer. In this paper, we proposed a vertical slicing model with an emotion layer in it. And we showed that the emotion-based control allows us to improve the adaptability of a system at least under some conditions.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.06a
• /
• pp.3-7
• /
• 2001

본 연구에서는 다종재료를 가공할 수 있는 RP(Rapid Prototyping)인 CAFL$^{VM}$의 구현을 위해 반드시 필요한 단면정보 추출기에 대하여 연구하였다. STL 3D 모형에서 단면정보를 추출하기 위해서, 패싯(facet)과 슬라이싱(slicing) 평면이 가질 수 있는 모든 경우를 고려한 알고리즘을 개발하였다. STL 파일의 구조적인 문제점 때문에 모호성과 처리량 증가 문제가 발생하지만, 본 연구에서는 창조 버퍼를 사용하여 이러한 문제점들을 효과적으로 해결하였으며, 이를 많은 STL 3D 샘플로 검증하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.132.3-132
• /
• 2001

In this paper, we focus on the analysis of the scheduling problem in FMS after slicing off some sub-nets using the transitive matrix. This class of Time Petri nets is obtained by merging subnets based on the machine's operations. We can divide original system into some subnets based on machine's operations using Time Petri nets slice and analyze the feasibility time in each schedules. In this paper, we show the usefulness of transitive matrix to slice off some subnets from the original net, and explain on an example.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.178.5-178
• /
• 2001

We, Human beings, use both powers of reason and emotion simultaneously, which surely help us to obtain flexible adaptability against the dynamic environment. We assert that this principle can be applied into the general system. That is, it would be possible to improve the adaptability by covering a digital oriented information processing system with an analog oriented emotion layer. In this paper, we proposed a vertical slicing model with an emotion layer in It. And we showed that the emotion-based control allows us to improve the adaptability of a system at least under some conditions.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.961-963
• /
• 2005

의존성 그래프는 컴파일러 최적화 분야에서 도입되어 유용하게 사용되고 있으며 프로그램 자르기(program slicing) 분야 등 활용가치를 높여가고 있는 프로그램 표현 방식이다. 우리는 실제적인 C 프로그램의 의존성 그래프를 생성하는 시스템을 구현하였으며 본 논문에서는 의존성 그래프의 개념과 구현과정을 설명한다.

• Journal of the Semiconductor & Display Technology
• /
• v.2 no.1
• /
• pp.21-24
• /
• 2003

Sludged silicon powders that are generated during silicon ingot slicing process have potential usage as silicon source in fabricating silicon carbide powders by adding carbon. A thermodynamic calculation is performed to consider a plausible formation condition for the silicon carbide powders. A thin silicon oxide layer around silicon powder is sufficient to supply equilibrium oxygen partial pressure at the formation temperature($1400^{\circ}C$) of the silicon carbide in the Si-C-O ternary system. Formation of silicon carbide by using the sludged silicon powders is more efficient than by using silicon oxide powders.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1654-1657
• /
• 2002

This paper presents a system for facility layout problem using an expert system and a genetic algorithm. The practical facility layout design can be effected by characteristics of constructing model, slicing tree model, closeness weight metric and expert system. The genetic algorithm searches the result layout. An experimental system is implemented and produced desired layout.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10a
• /
• pp.557-559
• /
• 1999

프로그램 슬라이싱은 프로그램의 특정 문장에서 변수에 영향을 주는 문장들을 분해하는 방법으로 디버깅, 최적화, 프로그램 유지보수, 테스팅, 재사용 부품 추출 그리고 프로그램 이해를 포함하는 여러 응용 분야들에서 그 유용성을 확인할 수 있다. 본 논문은 포인터 변수와 포인터 변수에 의해 참조되는 동적 객체, 구조체, 배열을 포함하는 프로그램에 대한 정확한 슬라이스 생성에 관한 연구이다. 포인터 변수와 같은 복잡한 구조를 가지는 프로그램에서 포인터 변수나 포인터 변수가 참조하는 객체의 상태를 파악하기 위해서 객체 참조상태 그래프를 제시한다.