Vol. 51, No. 8, Aug. 2024
Digital Library


Managing DISCARD Commands in F2FS File System for Improving Lifespan and Performance of SSD Devices

Jinwoong Kim, Donghyun Kang, Young Ik Eom

http://doi.org/10.5626/JOK.2024.51.8.669

The DISCARD command is an interface that helps improve the lifespan and performance of SSDs by informing the SSD devices about invalid file system blocks. However, in the F2FS file system, the DISCARD command is only sent to the SSD during idle time, which limits the potential for improving lifespan and performance. In this paper, we propose an EPD scheme to efficiently transfer DISCARD commands during short idle times, as well as a seg-ment allocation scheme called PSA, which replaces DISCARD commands with overwrite commands. To evaluate the effectiveness of these proposed schemes, we conducted several experiments using various workloads to verify the lifespan and performance of real SSD devices. The results showed that the proposed schemes can improve the write amplification factor (WAF) by up to 40% and throughput by up to 160%, when compared to the traditional F2FS file system.

Capsule Neural Networks as Noise Stabilizer for Time Series Data

Soyeon Kim, Jihyeon Seong, Hyunkyung Han, Jaesik Choi

http://doi.org/10.5626/JOK.2024.51.8.678

A Capsule is a vector-wise representation formed by multiple neurons that encodes conceptual information about an object, such as angle, position, and size. Capsule Neural Network (CapsNet) learns to be viewpoint invariant using these capsules. This property makes CapsNet more resilient to noisy data compared to traditional Convolutional Neural Networks (CNNs). The Dynamic-Routing Capsule Neural Network (DR-CapsNet) uses an affine matrix and dynamic routing mechanism to train the capsules. In this paper, we propose that DR-CapsNet has the potential to act as a noise stabilizer in time series sensor data that have high sensitivity and significant noise in real world. To demonstrate the robustness of DR-CapsNet as a stabilizer, we conduct manual and adversarial attacks on an electrocardiogram (ECG) dataset. Our study provides empirical evidence that CapsNet effectively functions as a noise stabilizer and highlights its potential in addressing the challenges of preprocessing noisy measurements in time series analysis.

An Earley Parser using Equi-LR Items

Gyung-Ok Lee

http://doi.org/10.5626/JOK.2024.51.8.685

Abstract The Earley parser is applicable to generalized grammars, including ambiguous ones, unlike the LR parser. As a result, the Earley parser has been widely used in fields such as natural language processing and image processing. However, the Earley parser has the drawback of higher time and space costs compared to the LR parser. This paper proposes an Equi-Earley parser that improves efficiency by modifying the items used in the original Earley parser. The Equi-Earley parser employs items composed of a prefix of a rule and a dot, in contrast to the Earley parser, which uses items composed of a rule and a dot, similar to LR items. Consequently, the number of items in a state of the Equi-Earley parser is reduced compared to that of the Earley parser. The Earley parser generates items during parsing, unlike the LR parser. Hence, the Equi-Earley parser has the advantage of reduced parsing time and memory space compared to the original Earley parser.

Photovoltaic Power Forecasting Scheme Based on Graph Neural Networks through Long- and Short-Term Time Pattern Learning

Jaeseung Lee, Sungwoo Park, Jaeuk Moon, Eenjun Hwang

http://doi.org/10.5626/JOK.2024.51.8.690

As the use of solar energy has become increasingly common in recent years, there has been active research in predicting the amount of photovoltaic power generation to improve the efficiency of solar energy. In this context, photovoltaic power forecasting models based on graph neural networks have been presented, going beyond existing deep learning models. These models enhance prediction accuracy by learning the interactions between regions. Specifically, they consider how the amount of photovoltaic power in a specific region is affected by the climate conditions of adjacent regions and the time pattern of photovoltaic power generation. However, existing models mainly rely on a fixed graph structure, making it difficult to capture temporal and spatial interactions. In this paper, we propose a graph neural networks-based photovoltaic power forecasting scheme that takes into account both long-term and short-term time patterns of regional photovoltaic power generation data. We then incorporate these patterns into the learning process to establish correlations between regions. Compared to other graph neural networks-based prediction models, our proposed scheme achieved a performance improvement of up to 7.49% based on the RRSE, demonstrating its superiority.

In-Depth Evaluations of the Primality Testing Capabilities of Large Language Models: with a Focus on ChatGPT and PaLM 2

Hyeonwoo Jung, Kunwoo Park

http://doi.org/10.5626/JOK.2024.51.8.699

This study aims to thoroughly evaluate the primality testing capabilities of two large language models, ChatGPT and PaLM 2. We pose two different yes/no questions for a given number, assessing whether it is prime or composite. To deem a model successful, it must correctly answer both questions while also avoiding any division errors in the generated prompt. Analyzing the inference results using a dataset consisting of 664 prime and 1458 composite numbers, we discovered a decrease in testing accuracy as the difficulty of the target numbers increased. Considering the calculation errors, both models experienced a decrease in testing accuracy, with PaLM 2 failing to conduct primality testing for all composite numbers with four high-difficulty digits. These findings highlight the potential for misleading evaluations of language models' reasoning abilities based on simple questions, emphasizing the need for comprehensive assessments.

Safety Requirement Elicitation for Small Aircraft Collision Avoidance Software using STPA, FTA and FMEA

Jongwon Lee, Uicheon Lee, Taehwan Kim, Seonah Lee

http://doi.org/10.5626/JOK.2024.51.8.706

With the growing trend of urban air traffic, aircraft are becoming smaller and more reliant on software. As a result, safety analysis techniques and standards, which have traditionally focused on ARP4761, the aircraft safety evaluation process, must evolve to incorporate a software-centered approach. In this paper, we propose how to link STPA method to FTA and FMEA for safety analysis in air mobility, which is a software-intensive system. To assess the feasibility and effectiveness of this approach, we conducted a safety analysis case study focusing on the collision avoidance software of a small aircraft. The results of the study confirmed the effectiveness of linking STPA, FTA, and FMEA methods and enabled the derivation of safety requirements.

An Empirical Study of MISRA-C Related Source Code Changes in Open-source Software Projects

Suhyun Park, Jaechang Nam, Shin Hong

http://doi.org/10.5626/JOK.2024.51.8.718

This paper presents empirical studies on 75 open-source projects hosted on GitHub to explore how source code changes align with MISRA C coding guidelines. Through our analysis of the studied projects, we have identified eight distinctive keywords that represent the software domains where compliance with MISRA C coding guidelines is likely to be found. Additionally, we discovered that 54.75% of the studied projects utilizes at least one static rule checker. In the 75 studied projects, we found code changes associated with 75 MISRA C coding rules. The analyses of these code changes reveal that multiple MISRA C-related code changes often occur in a short timeframe, and, on average, each MISRA C-related code change modifies 1124 lines of code at once.

Enhanced Image Harmonization Scheme Using LAB Color Space-based Loss Function and Data Preprocessing

Doyeon Kim, Eunbeen Kim, Hyeonwoo Kim, Eenjun Hwang

http://doi.org/10.5626/JOK.2024.51.8.729

Image composition, which involves combining the background and foreground from different images to create a new image, is a useful technique in image editing. However, it often results in awkward images due to differences in brightness and color tones between the background and foreground. Image harmonization techniques aim to reduce this incongruity and have gained significant attention in the field of image editing. These techniques allow for realistic matching of color tones between the foreground and background. Existing deep learning models for image harmonization have shown promise in achieving harmonization performance through the use of large-scale training datasets. However, these models tend to exhibit poor generalization performance when the loss function does not effectively consider brightness or when the dataset has a biased brightness distribution. To address these issues, we propose an image harmonization scheme that is robust to variations in brightness. This scheme incorporates an LAB color space-based loss function, which explicitly calculates the brightness of a given image, and an LAB color space-based preprocessing scheme to create a dataset with a balanced brightness distribution. Experimental results on public image datasets demonstrate that the proposed scheme exhibits robust harmonization performance under various brightness conditions.

Constructing a Korean Knowledge Graph Using Zero Anaphora Resolution and Dependency Parsing

Chaewon Lee, Kangbae Lee, Sungyeol Yu

http://doi.org/10.5626/JOK.2024.51.8.736

This study introduces a novel approach to creating a Korean-based knowledge graph by employing zero anaphora resolution, dependency parsing, and knowledge base extraction using ChatGPT. In order to overcome the limitations of conventional language models in handling the grammatical and morphological characteristics of Korean, this research incorporates prompt engineering techniques that combine zero anaphora resolution and dependency parsing. The main focus of this research is the 'Ko-Triple Extraction' method, which involves restoring omitted information in sentences and analyzing dependency structures to extract more sophisticated and accurate triple structures. The results demonstrate that this method greatly enhances the efficiency and accuracy of Korean text processing, and the validity of the triples has been confirmed through precision metrics. This study serves as fundamental research in the field of Korean text processing and suggests potential applications in various industries. Future research aims to apply this methodology to different industrial sectors and by expanding and connecting knowledge graph, generate valuable business insights. This approach is expected to contribute significantly make an important contribution not only to the advancement of natural language processing technologies but also to the effective of Korean in the field of artificial intelligence.

Continual Learning using Memory-Efficient Parameter Generation

Hyung-Wook Lim, Han-Eol Kang, Dong-Wan Choi

http://doi.org/10.5626/JOK.2024.51.8.747

Continual Learning with Parameter Generation shows remarkable stability in retaining knowledge from previous tasks. However, it suffers from a gradual decline in parameter generation performance due to its lack of adaptability to new tasks. Furthermore, the difficulty in predetermining the optimal size of the parameter generation model (meta-model) can lead to memory efficiency issues. To address these limitations, this paper proposed two novel techniques. Firstly, the Chunk Save & Replay (CSR) technique selectively stored and replayed vulnerable parts of the generative neural network, maintaining diversity in the parameter generation model while efficiently utilizing memory. Secondly, the Automatically Growing GAN (AG-GAN) technique automatically expanded the memory of the parameter generation model based on learning tasks, enabling effective memory utilization in resource-constrained environments. Experimental results demonstrated that these proposed techniques significantly reduced memory usage while minimizing performance degradation. Moreover, their ability to recover from deteriorated network performance was observed. This research presents new approaches to overcoming limitations of parameter generation-based continual learning, facilitating the implementation of more effective and efficient continual learning systems.


Search




Journal of KIISE

  • ISSN : 2383-630X(Print)
  • ISSN : 2383-6296(Electronic)
  • KCI Accredited Journal

Editorial Office

  • Tel. +82-2-588-9240
  • Fax. +82-2-521-1352
  • E-mail. chwoo@kiise.or.kr