Digital Library[ Search Result ]
Efficient Dynamic Graph Processing Based on GPU Accelerated Scheduling and Operation Reduction
Sangho Song, Jihyeon Choi, Donghyeon Cha, Hyeonbyeong Lee, Dojin Choi, Jongtae Lim, Kyoungsoo Bok, Jaesoo Yoo
http://doi.org/10.5626/JOK.2024.51.12.1125
Recent research has focused on utilizing GPUs to process large-scale dynamic graphs. However, processing dynamic graphs often leads to redundant data transmission and processing. This paper proposes an efficient scheme for processing large-scale dynamic graphs in memory-constrained GPU environments. The proposed scheme consists of dynamic scheduling and operation reduction methods. The dynamic scheduling method involves partitioning dynamic graph and maximizing GPU processing power by scheduling partitions based on active and potential active vertices. Also, snapshots are utilized to leverage the time-varying characteristics of the graph. The operation reduction method minimizes GPU computation and memory transfer costs by detecting redundant edge and vertex updates in dynamic graphs through snapshots. By avoiding redundant operations on the same edges or vertices, this method improves performance. Through various performance evaluations, the proposed scheme showed 280% and 108% performance improvements on average compared to a static graph processing scheme and a dynamic graph processing scheme, respectively.
A Survey of Advantages of Self-Supervised Learning Models in Visual Recognition Tasks
Euihyun Yoon, Hyunjong Lee, Donggeon Kim, Joochan Park, Jinkyu Kim, Jaekoo Lee
http://doi.org/10.5626/JOK.2024.51.7.609
Recently, the field of teacher-based artificial intelligence (AI) has been rapidly advancing. However, teacher-based learning relies on datasets with specified correct answers, which can increase the cost of obtaining these correct answers. To address this issue, self-supervised learning, which can learn general features of photos without needing correct answers, is being researched. In this paper, various self-supervised learning models were classified based on their learning methods and backbone networks. Their strengths, weaknesses, and performances were then compared and analyzed. Photo classification tasks were used for performance comparison. For comparing the performance of transfer learning, detailed prediction tasks were also compared and analyzed. As a result, models that only used positive pairs achieved higher performance by minimizing noise than models that used both positive and negative pairs. Furthermore, for fine-grained predictions, methods such as masking images for learning or utilizing multi-stage models achieved higher performance by additionally learning regional information.
Prediction of Antibiotic Resistance to Ciprofloxacin in Patients with Upper Urinary Tract Infection through Exploratory Data Analysis and Machine Learning
http://doi.org/10.5626/JOK.2023.50.3.263
Emergency medicine physicians use an empirical treatment strategy to select antibiotics before clinically confirming an antibiotic resistance profile for a patient with a urinary tract infection. Empirical treatment is a challenging task in the context of concern for increased antibiotic resistance of urinary tract pathogens in the community. As a single-institution retrospective study, this study proposed a method for predicting antibiotic resistance using a machine learning algorithm for patients diagnosed with upper urinary tract infection in the emergency department. First, we selected significant predictors using statistical test methods and a game theory based SHAP (SHapley Additive exPlanation), respectively. Next, we compared four classifier performances and proposed an algorithm to assist decision-making in empirical treatment by adjusting the prediction probability threshold. As a result, the SVM classifier using predictors selected through SHAP (65% of the total) showed the highest AUROC (0.775) among all conditions used in the experiment. By adjusting the predictive probability threshold in the SVM, we achieved classification accuracy with a specificity that was 3.9 times higher than empirical treatment while preserving the sensitivity of the doctor"s empirical treatment at 98%.
Knowledge Embedding Method for Implementing a Generative Question-Answering Chat System
Sihyung Kim, Hyeon-gu Lee, Harksoo Kim
http://doi.org/10.5626/JOK.2018.45.2.134
A chat system is a computer program that understands user"s miscellaneous utterances and generates appropriate responses. Sometimes a chat system needs to answer users’ simple information-seeking questions. However, previous generative chat systems do not consider how to embed knowledge entities (i.e., subjects and objects in triple knowledge), essential elements for question-answering. The previous chat models have a disadvantage that they generate same responses although knowledge entities in users’ utterances are changed. To alleviate this problem, we propose a knowledge entity embedding method for improving question-answering accuracies of a generative chat system. The proposed method uses a Siamese recurrent neural network for embedding knowledge entities and their synonyms. For experiments, we implemented a sequence-to-sequence model in which subjects and predicates are encoded and objects are decoded. The proposed embedding method showed 12.48% higher accuracies than the conventional embedding method based on a convolutional neural network.
Identification of Attack Group using Malware and Packer Detection
Heaeun Moon, Joonyoung Sung, Hyunsik Lee, Gyeongik Jang, Kiyong Kwak, Sangtae Woo
http://doi.org/10.5626/JOK.2018.45.2.106
Recently, the number of cyber attacks using malicious code has increased. Various types of malicious code detection techniques have been researched for several years as the damage has increased. In recent years, profiling techniques have been used to identify attack groups. This paper focuses on the identification of attack groups using a detection technique that does not involve malicious code detection. The attacker is identified by using a string or a code signature of the malicious code. In addition, the detection rate is increased by adding a technique to confirm the packing file. We use Yara as a detection technique. We have research about RAT (remote access tool) that is mainly used in attack groups. Further, this paper develops a ruleset using malicious code and packer main feature signatures for RAT which is mainly used by the attack groups. It is possible to detect the attacker by detecting RAT based on the newly created ruleset.
Context Based Real-time Korean Writing Correction for Foreigners
Young-Keun Park, Jae-Min Kim, Seong-Dong Lee, Hyun Ah Lee
http://doi.org/10.5626/JOK.2017.44.10.1087
Educating foreigners in Korean language is attracting increasing attention with the growing number of foreigners who want to learn Korean or want to reside in Korea. Existing spell checkers mostly focus on native Korean speakers, so they are inappropriate for foreigners. In this paper, we propose a correction method for the Korean language that reflects the contextual characteristics of Korean and writing characteristics of foreigners. Our method can extract frequently used expressions by Koreans by constructing syllable reverse-index for eojeol bi-gram extracted from corpus as correction candidates, and generate ranked Korean corrections for foreigners with upgraded edit distance calculation. Our system provides a user interface based on keyboard hooking, so a user can easily use the correction system along with other applications. Our system improves the detection rate for foreign language users by about 45% compared to other systems in foreign language writing environments. This will help foreign users to judge and correct their own writing errors.
Title Generation Model for which Sequence-to-Sequence RNNs with Attention and Copying Mechanisms are used
http://doi.org/10.5626/JOK.2017.44.7.674
In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.
Multi-core Scalable Real-time Flash Storage Simulation
Hyeon-gyu Lee, Sang Lyul Min, Kanghee Kim
http://doi.org/10.5626/JOK.2017.44.6.566
As NAND flash storage is being widely used, its simulation methodologies have been studied in various aspects such as performance, reliability, and endurance. As a result, there have been advances in NAND flash storage simulation for both functional modeling and timing modeling. However, in addition to these advances, there is a need to drastically reduce the long simulation time that is required to evaluate the aging effect on flash storage. This paper proposes a so-called multi-core scalable real-time flash storage simulation method, which can control the simulation speed according to the user’s preference. According to this method, it is possible to speed up the simulation in proportion to the number of CPU cores arbitrarily given while guaranteeing the correctness of the simulation result. Using our simulator implemented in the form of the Linux kernel module, we demonstrate the multi-core scalability and correctness of the proposed method.
A Pedestrian Detection Method using Deep Neural Network
Su Ho Song, Hun Beom Hyeon, Hyun Lee
Pedestrian detection, an important component of autonomous driving and driving assistant system, has been extensively studied for many years. In particular, image based pedestrian detection methods such as Hierarchical classifier or HOG and, deep models such as ConvNet are well studied. The evaluation score has increased by the various methods. However, pedestrian detection requires high sensitivity to errors, since small error can lead to life or death problems. Consequently, further reduction in pedestrian detection error rate of autonomous systems is required. We proposed a new method to detect pedestrians and reduce the error rate by using the Faster R-CNN with new developed pedestrian training data sets. Finally, we compared the proposed method with the previous models, in order to show the improvement of our method.
Answer Snippet Retrieval for Question Answering of Medical Documents
Hyeon-gu Lee, Minkyoung Kim, Harksoo Kim
With the explosive increase in the number of online medical documents, the demand for question-answering systems is increasing. Recently, question-answering models based on machine learning have shown high performances in various domains. However, many question-answering models within the medical domain are still based on information retrieval techniques because of sparseness of training data. Based on various information retrieval techniques, we propose an answer snippet retrieval model for question-answering systems of medical documents. The proposed model first searches candidate answer sentences from medical documents using a cluster-based retrieval technique. Then, it generates reliable answer snippets using a re-ranking model of the candidate answer sentences based on various sentence retrieval techniques. In the experiments with BioASQ 4b, the proposed model showed better performances (MAP of 0.0604) than the previous models.
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