Vol. 51, No. 1,
Jan. 2024
Digital Library
CSDVirt: An Emulator for Computational Storage Device
Ilkueon Kang, Jaehoon Shim, Jin-Soo Kim
http://doi.org/10.5626/JOK.2024.51.1.1
Since Computational Storage Device (CSD) concept was proposed, various forms of CSDs have been presented in both academia and industries. The standardization of CSD interfaces is currently undergoing, but they are still in a very early stage. As a result, the existing CSD proposals lack uniformity in interfaces and internal device architectures. This has led to significant engineering efforts for CSD research. In this paper, we propose CSDVirt to facilitate the CSD research and provide an environment similar to actual devices. CSDVirt is an emulator that offers CSD functionalities using NVMeVirt. With CSDVirt, the characteristics of various workloads on CSDs can be evaluated easily.
Energy Optimization in Multicore Systems with Wake-Up Overhead Awareness
http://doi.org/10.5626/JOK.2024.51.1.7
This paper presents heuristics to optimize the energy consumption of multicore systems with wake-up overhead. A multicore system can optimize its energy consumption by strategically (de)activating itself. Given the task information of the system, OSPAL algorithm was previously known to find a schedule that maximizes the common idle time. However, this schedule does not necessarily minimize energy consumption because of the wake-up overhead associated with the storage of memory footprint to non-volatile memory. Previous research proposed to address this issue by modifying their algorithm so that it does not keep common idle times shorter than a threshold. We observe that their choice of threshold is not optimal and propose a randomized heuristic to improve the energy consumption. We also present a dynamic-programming-based postprocessing heuristic to adjust common idle times. We conducted computational experiments to measure the performance of the proposed heuristics, which indicated an average improvement of 37.69% in energy consumption compared to the previous algorithm.
Automatic Generation of Custom Advertisement Messages based on Literacy Styles of Classified Personality Types
Jimin Seong, Yunjong Choi, Doyeon Kwak, Hansaem Kim
http://doi.org/10.5626/JOK.2024.51.1.23
This study introduces a novel framework that defines marketing styles based on the MBTI personality types, and presents a machine learning technique to generate customized advertising messages aligned to these types. We use the BART algorithm to synthesize customized advertising content by training on the advertisement texts incorporating personality type prefixes. Our experiments confirm the model’s efficacy in transforming generic advertising copy into custom messages that embody the distinct style characteristics of each personality type, via prefix manipulation. Theoretically, our research establishes the relationship between style characteristics and personality types; practically, it provides the technique to fine-tune a language model to generate advertising messages that align with specific personality types. Moreover, this research serves as a foundational work for systematizing and replicating stylistic differences across various languages and regions.
Denoising Method for Document Grounded Conversation Datasets via Back Translation Process
Damrin Kim, Boeun Kim, Youngjin Jang, Harksoo Kim
http://doi.org/10.5626/JOK.2024.51.1.34
Document Grounded Conversation is a conversation between two or more speakers based on a given document. Document-based dialogue systems are tasks that generate responses to the last utterance of dialogue, and various document-based dialogue datasets in English have been released and actively studied. Notably, There is no active research in Korean that has been conducted due to the absence of a document-based conversation dataset in Korean. While KoDoc2dial, which translates the English document-based conversation dataset Doc2dial into Korean, was recently released, it contains the noise generated during the translation process. The noise in the KoDoc2Dial should be reduced because noise-containing datasets can negatively affect training and system consistency aspects. In this paper, we propose a method for reducing the noise contained in the KoDoc2Dial through filtering using the reverse translation process. The results of the experiments showed that the method proposed in this paper had a performance improvement of about 3.6%p in SacreBLEU compared to before filtering.
Hierarchical Representation and Label Embedding for Semantic Classification of Domestic Research Paper
Heejin Kook, Yeonghwa Kim, Sehui Yoon, Byungha Kang, Youhyun Shin
http://doi.org/10.5626/JOK.2024.51.1.41
The sentence"s meaning in the paper is that it has a hierarchical structure, and there is data imbalance among subcategories. In addition, the meaning of the sentence in the paper is closely related to its position within the paper. Existing flat classification methods mainly consider only subcategories, leading to a decrease in classification accuracy due to data imbalance. In response to this, this study proposes hierarchical representation and label embedding methods to perform hierarchical semantic classification of sentences effectively. In addition, the section names of the paper are actively utilized to represent the positional information of the paper sentences. Through experiments, it is demonstrated that the proposed method, which explicitly considers hierarchical and positional information in the KISTI domestic paper sentence semantic tagging dataset, achieves excellent performance in terms of F1 score.
An Object Pseudo-Label Generation Technique based on Self-Supervised Vision Transformer for Improving Dataset Quality
Dohyun Kim, Jiwoong Jeon, Seongtaek Lim, Hongchul Lee
http://doi.org/10.5626/JOK.2024.51.1.49
Image segmentation is one of the most important tasks. It localizes objects into bounding boxes and classifies pixels in an image. The performance of an Instance segmentation model requires datasets with labels for objects of various sizes. However, the recently released "Image for Small Object Detection" dataset has large and common objects that lack labels, causing potential performance degradation. In this paper, we improve the quality of datasets by generating pseudo-labels for general objects using an unsupervised learning-based pseudo-labeling methodology to solve the aforementioned problems. Specifically, small object detection performance was improved by (+2.54 AP) compared to the original dataset. Moreover, we were able to prove an increase in performance using only a small amount of data. As a result, it was confirmed that the quality of the dataset was improved through the proposed method.
Test Bed for Abstraction and Reasoning
Subin Kim, Phunyaphibarn Prin, Donghyun Ahn, Sundong Kim
http://doi.org/10.5626/JOK.2024.51.1.59
Abstraction and Reasoning Corpus (ARC) proposed by François Chollet is a benchmark designed to develop generalizable intelligence, suitable for measuring cognitive abilities of both humans and computers. While most problems can be solved by humans, a computing-based ARC-Solver that can solve more than 30% of the problems is not yet known. In this study, a benchmark dataset, Mini-ARC, was introduced to simplify the model complexity while maintaining the difficulty level of the original ARC. To collect Mini-ARC, O2ARC was designed. It is an interface that can track the human solution process. A total of 3,000 solutions were collected from 25 people. This study proposed a new approach to developing a computing-based ARCSolver by constructing a system that could massively secure the simplified cognitive solution process. The Mini-ARC dataset can be found at https://github.com/ksb21ST/Mini-ARC.
Voice Phishing Detection Scheme Using a GPT-3.5-based Large Language Model
http://doi.org/10.5626/JOK.2024.51.1.67
In this paper, we introduce a novel approach for voice phishing call detection, using text-davinci-003, which is a recently updated model from the generative pre-trained transformer (GPT) -3.5 language model series. To achieve this, we devised a prompt to let the language model respond with an integer ranging from 0 to 10, which indicates the likelihood that a given conversation is a voice phishing attempt. For prompt tuning, hyperparameter adjustment, and performance validation,we use a total of 105 actual Korean voice phishing transcripts and 704 transcripts from various topics of general conversations as our dataset. The proposed scheme includes a function to send voice phishing alarm during a call and a function to finally determine whether the call was a voice phishing after the call ends. Performance is evaluated in five different scenarios using different types of training and test data, demonstrating an accuracy range of 0.95 to 0.97 for the proposed technique. In particular, when tested with data from sources different from those used in training, the proposed scheme performs better than the existing bidirectional encoder representations from transformer (BERT) model-based schemes.
Polyphonic Music Generation with Sequence Generative Adversarial Networks
Sang-gil Lee, Uiwon Hwang, Seonwoo Min, Sungroh Yoon
http://doi.org/10.5626/JOK.2024.51.1.78
In this paper, we propose an application of sequence generative adversarial networks (SeqGAN) for generating polyphonic musical sequences. We introduce a representation of polyphonic MIDI files that could encapsulate both chords and melodies with dynamic timings. This method condensed the duration, octaves, and keys of both melodies and chords into a single word vector representation. Our generator composed of recurrent neural networks was trained to predict distributions of musical word sequences. Additionally, we employed the least square loss function for the discriminator to stabilize training of the model. Our model could create sequences that are musically coherent. It exhibited improved quantitative and qualitative measures.
Single-Modal Pedestrian Detection Leveraging Multimodal Knowledge for Blackout Situations
http://doi.org/10.5626/JOK.2024.51.1.86
Multispectral pedestrian detection using both visible and thermal data is an actively researched topic in the field of computer vision. However, the majority of the existing studies have only considered scenarios where the camera operates without challenges, leading to a significant decline in performance when a camera blackout happens. Recognizing the importance of addressing the camera blackout challenge in multispectral pedestrian detection, this paper researched models that remain robust even during camera blackouts. Our model, proposed in this study, utilizes the Feature Tracing Method during training phase to apply the knowledge from multiple modalities to single-modal pedestrian detection. Even if the camera experiences a blackout and only one modality is input, the model predicts and operates as if it"s using multiple modalities. Through this approach, pedestrian detection performance in blackout situations is improved.
Location-Dependent and Task-Oriented Power Allocation in Holographic MIMO: A Transformer-based Approach
Apurba Adhikary, Avi Deb Raha, Monishanker Halder, Mrityunjoy Gain, Ji Su Yoon, Seong Bae Park, Choong Seon Hong
http://doi.org/10.5626/JOK.2024.51.1.93
Future communication networks are expected to provide improved throughput data services with minimal power for beamforming. The location-dependent and task-oriented resource allocation approach for holographic beamforming ensures the improvement of the channel capacity for the users by activating the required number of grids from the holographic grid array. An optimization problem is obtained for maximizing the channel capacity considering the location and task priority of the users. In this study, a Transformer-based approach that allocates the required power for serving the users to generate holographic beamforming is proposed as the solution for the optimization problem. The simulation results demonstrate that the proposed location-dependent and task-oriented Transformer-based approach effectively allocate power for holographic beamforming to serve the users.
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