• International journal of advanced smart convergence
• /
• 제6권1호
• /
• pp.26-31
• /
• 2017

When mobile navigator device accesses data randomly, the cache memory performance is rapidly deteriorated due to low memory access locality. For instance, GPS (General Positioning System) of navigator program for automobiles or drones, that are currently in common use, uses data from 32 satellites and computes current position of a receiver. This computation of positioning is the major part of GPS which accounts more than 50% computation in the program. In this computation task, the satellite signals are received in real time and stored in buffer memories. At this task, since necessary data cannot be sequentially stored, the data is read and used at random. This data accessing patterns are generated randomly, thus, memory system performance is worse by low data locality. As a result, it is difficult to process data in real time due to low data localization. Improving the low memory access locality inherited on the algorithms of conventional communication applications requires a certain optimization technique to solve this problem. In this study, we try to do optimizations with data and memory to improve the locality problem. In experiment, we show that our case study can improve processing speed of core computation and improve our overall system performance by 14%.

• 융합보안논문지
• /
• 제13권4호
• /
• pp.19-25
• /
• 2013

백본(코어) 네트워크에서 유연하고 안정적인 품질이 보장되는 서비스 제공에 대한 요구가 폭발적으로 증가하면서 이러한 요구를 수용하기 위해 제어평면의 프로토콜로 MPLS/GMPLS가 도입되었다. GMPLS 기반 제어평면에서 경로계산 및 상호연동 기능은 최적의 서비스 품질을 제공하기 위한 핵심기술 중의 하나이다. 이를 위해 IETF에서는 Path Computation Element (PCE) 구조를 제안하였다. PCE는 경로계산 전용의 네트워크 요소이며 경로계산을 요청하는 Path Computation Clients (PCC) 와 경로계산을 수행하는 PCE 간의 통신은 PCE 프로토콜 (PCEP)을 이용한다. 본 논문은 PCE 기반 경로계산 구조에 대해서 살펴보고 이를 기반으로 PCEP 설계 및 구현을 위한 몇 가지 요소를 제시하였다. 우선 본 논문에서는 PCEP Finite State Machine (FSM)을 포함하여 각 상태에서 필요한 동작 요소를 정리하였다. 또한 본 논문에서는 PCEP에서 제공하는 통신 채널을 효과적으로 제어하기 위한 내부/외부 인터페이스를 더불어 제안하였다.

• 대한임베디드공학회논문지
• /
• 제17권6호
• /
• pp.347-353
• /
• 2022

In this paper, we propose a method that performs a text-video retrieval model by replacing video properties using captions. In general, the exisiting embedding-based models consist of both joint embedding space construction and the CNN-based video encoding process, which requires a lot of computation in the training as well as the inference process. To overcome this problem, we introduce a video-captioning module to replace the visual property of video with captions generated by the video-captioning module. To be specific, we adopt the caption generator that converts candidate videos into captions in the inference process, thereby enabling direct comparison between the text given as a query and candidate videos without joint embedding space. Through the experiment, the proposed model successfully reduces the amount of computation and inference time by skipping the visual processing process and joint embedding space construction on two benchmark dataset, MSR-VTT and VATEX.

• Journal of Information Processing Systems
• /
• 제18권2호
• /
• pp.188-196
• /
• 2022

Recently, neural architecture search (NAS) has received increasing attention as it can replace human experts in designing the architecture of neural networks for different tasks and has achieved remarkable results in many challenging tasks. In this study, a path-based computation neural architecture encoder (PCE) was proposed. Our PCE first encodes the computation of information on each path in a neural network, and then aggregates the encodings on all paths together through an attention mechanism, simulating the process of information computation along paths in a neural network and encoding the computation on the neural network instead of the structure of the graph, which is more consistent with the computational properties of neural networks. We performed an extensive comparison with eight encoding methods on two commonly used NAS search spaces (NAS-Bench-101 and NAS-Bench-201), which included a comparison of the predictive capabilities of performance predictors and search capabilities based on two search strategies (reinforcement learning-based and Bayesian optimization-based) when equipped with different encoders. Experimental evaluation shows that PCE is an efficient encoding method that effectively ranks and predicts neural architecture performance, thereby improving the search efficiency of neural architectures.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 A
• /
• pp.68-70
• /
• 1996

In this paper, an efficient parallel computation method for solving large sparse systems of linear algebraic equations by using Cholesky's method in the finite element method is studied. The methods of minimizing the number of fill-ins in the factorization process of factorization are investigated for minimizing the amount of memory and computation time. The parallel programming is implemented under the PVM(Parallel Virtual Machine) environment. The method of load-distribution is studied for minimizing the computation time and the communication time.

• 대한음성학회지:말소리
• /
• 제51호
• /
• pp.71-84
• /
• 2004

In this paper, we propose the automatic speech database verification method(or called automatic verification) based on confidence measure for a large speech database. This method verifies the consistency between given transcription and speech using the confidence measure. The automatic verification process consists of two stages : the word-level likelihood computation stage and multi-level likelihood ratio computation stage. In the word-level likelihood computation stage, we calculate the word-level likelihood using the viterbi decoding algorithm and make the segment information. In the multi-level likelihood ratio computation stage, we calculate the word-level and the phone-level likelihood ratio based on confidence measure with anti-phone model. By automatic verification, we have achieved about 61% error reduction. And also we can reduce the verification time from 1 month in manual to 1-2 days in automatic.

• 한국정보과학회논문지:데이타베이스
• /
• 제28권4호
• /
• pp.596-605
• /
• 2001

본 논문은 OLAP에서의 I/O 비용을 줄이는 큐브 계산 방법으로, 구간 기반 큐브 분할 기법을 제안한다. 제안하는 방법은 큐브 분할 단계들 사이에 존재하는 계산의 일부를 중복시켜 처리하는 방법을 통해 큐브 분할 작업의 I/O 성능을 향상시킨다. 계산의 중복을 위하여 제안하는 방법은 애트리뷰트의 단 일 값이 아닌 애트리뷰트 값의 일정 구간을 기준으로 큐브를 분할한다 분석과 실험을 통하여 제안하는 방법의 성능을 기존 큐브 분할 방법과 비교하여 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3482-3497
• /
• 2021

Artificial intelligence has emerged as the core of the 4th industrial revolution, and large amounts of data processing, such as big data technology and rapid data analysis, are inevitable. The most fundamental and universal data interpretation technique is an analysis of information through regression, which is also the basis of machine learning. Ridge regression is a technique of regression that decreases sensitivity to unique or outlier information. The time-consuming calculation portion of the matrix computation, however, basically includes the introduction of an inverse matrix. As the size of the matrix expands, the matrix solution method becomes a major challenge. In this paper, a new algorithm is introduced to enhance the speed of ridge regression estimator calculation through series expansion and computation recycle without adopting an inverse matrix in the calculation process or other factorization methods. In addition, the performances of the proposed algorithm and the existing algorithm were compared according to the matrix size. Overall, excellent speed-up of the proposed algorithm with good accuracy was demonstrated.

• 스마트미디어저널
• /
• 제12권3호
• /
• pp.68-76
• /
• 2023

Emerging mobile edge computing (MEC) can be used in battery-constrained Internet of things (IoT). The execution latency of IoT applications can be improved by offloading computation-intensive tasks to an MEC server. Recently, the popularity of unmanned aerial vehicles (UAVs) has increased rapidly, and UAV-based MEC systems are receiving considerable attention. In this paper, we propose a dynamic computation offloading paradigm for UAV-based MEC systems, in which a UAV flies over an urban environment and provides edge services to IoT devices on the ground. Since most IoT devices are energy-constrained, we formulate our problem as a Markov decision process considering the energy level of the battery of each IoT device. We also use model-free Q-learning for time-critical tasks to maximize the system utility. According to our performance study, the proposed scheme can achieve desirable convergence properties and make intelligent offloading decisions.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.812-815
• /
• 2005

The incremental forming process employs several tens or hundreds of continuous local strokes, so the entire process is difficult to analyze due to much computation time and large computer memory. The objective of this work is to propose a new numerical scheme of the finite element method, automatic expansion of domain (AED), and to reduce computation time and computer memory. In the AED scheme, an effective analysis domain in each local forming step is defined and then the domain is automatically expanded in accordance with the repeated process. In order to verify the validity of the criterion for the AED scheme and the applicability of the AED scheme, two-dimensional incremental plane-strain forging process is first analyzed using the proposed scheme with various criteria and full domain. In addition, three-dimensional incremental radial forging process is analyzed to verify the applicability of the proposed scheme to a practical incremental forging process.