Digital Library[ Search Result ]
A Time-Course Multi-Clustering Method for Single-Cell Trajectory Inference
http://doi.org/10.5626/JOK.2022.49.10.838
From time-series single-cell transcriptome data, gene expression information can be generated to observe the timing of significant cell differentiation changes while accounting for important biological phenomena in relation to experimental conditions. Due to recent surge of time-series single-cell transcriptome data, studies on various dynamic variation in cells such as cell cycle and cell differentiation have been actively conducted. Particularly, time series analysis at single-cell level for cell differentiation is advantageous for biological interpretation compared to a single time point as it is possible to observe changes in the time axis. In this paper, we proposed a multi-clustering method to infer cell trajectory by considering time information at the genetic-level of time-series single-cell transcriptome data. Analyses of gene expression data on the development of human neuron cell differentiation using this method showed similar results to biological results uncovered in a previous study.
Knowledge Completion System using Neuro-Symbolic-based Rule Induction and Inference Engine
Won-Chul Shin, Hyun-Kyu Park, Young-Tack Park
http://doi.org/10.5626/JOK.2021.48.11.1202
Recently, there have been several studies on knowledge completion methods aimed to solve the incomplete knowledge graphs problem. Methods such as Neural Theorem Prover (NTP), which combines the advantages of deep learning methods and logic systems, have performed well over existing methods. However, NTP faces challenges in processing large-scale knowledge graphs because all the triples of the knowledge graph are involved in the computation to obtain prediction results for one input. In this paper, we propose an integrated system of deep learning and logic inference methods that can learn vector representations of symbols from improved models of computational complexity of NTP to rule induction, and perform knowledge inference from induced rules using inference engines. In this paper, for rule-induction performance verification of the rule generation model, we compared test data inference ability with NTP using induced rules on Nations, Kinship, and UMLS data set. Experiments with Kdata and WiseKB knowledge inference through inference engines resulted in a 30% increase in Kdata and a 95% increase in WiseKB compared to the knowledge graphs used in experiments.
Distributed Processing of Deep Learning Inference Models for Data Stream Classification
Hyojong Moon, Siwoon Son, Yang-Sae Moon
http://doi.org/10.5626/JOK.2021.48.10.1154
The increased generation of data streams has subsequently led to increased utilization of deep learning. In order to classify data streams using deep learning, we need to execute the model in real-time through serving. Unfortunately, the serving model incurs long latency due to gRPC or HTTP communication. In addition, if the serving model uses a stacking ensemble method with high complexity, a longer latency occurs. To solve the long latency challenge, we proposed distributed processing solutions for data stream classification using Apache Storm. First, we proposed a real-time distributed inference method based on Apache Storm to reduce the long latency of the existing serving method. The present study"s experimental results showed that the proposed distributed inference method reduces the latency by up to 11 times compared to the existing serving method. Second, to reduce the long latency of the stacking-based inference model for detecting malicious URLs, we proposed four distributed processing techniques for classifying URL streams in real-time. The proposed techniques are Independent Stacking, Sequential Stacking, Semi-Sequential Stacking, and Stepwise-Independent Stacking. Our study experimental results showed that Stepwise-Independent Stacking, whose characteristics are similar to those of independent execution and sequential processing, is the best technique for classifying URL streams with the shortest latency.
Cross-Validated Ensemble Methods in Natural Language Inference
Kisu Yang, Taesun Whang, Dongsuk Oh, Chanjun Park, Heuiseok Lim
http://doi.org/10.5626/JOK.2021.48.2.154
An ensemble method is a machine learning technique that combines several models to make the final prediction, which guarantees improved performance for deep learning models. However, most techniques require additional models or operations only for an ensemble. To address this problem, we propose a cross-validated ensemble method for reducing the costs of ensemble operations with cross-validation and for improving the generalization effects with the ensemble. To demonstrate the effectiveness of the proposed method, we show the improved performances of the proposed ensemble over the previous ensemble methods using the BiLSTM, CNN, ELMo and BERT models on the MRPC and RTE datasets. We also discuss the generalization mechanism involved in cross-validation along with the performance changes caused by the hyper-parameter of cross-validation.
Open Domain Question Answering using Knowledge Graph
http://doi.org/10.5626/JOK.2020.47.9.853
In this paper, we propose a novel knowledge graph inference model called KGNet for answering the open domain complex questions. This model addresses the problem of knowledge base incompleteness. In this model, two different types of knowledge resources, knowledge base and corpus, are integrated into a single knowledge graph. Moreover, to derive answers to complex multi-hop questions effectively, this model adopts a new knowledge embedding and reasoning module based on Graph Neural Network (GNN). We demonstrate the effectiveness and performance of the proposed model through various experiments over two large question answering benchmark datasets, WebQuestionsSP and MetaQA.
Ontology and CNN-based Inference of the Threat Relationship Between UAVs and Surrounding Objects
MyungJoong Jeon, MinHo Lee, HyunKyu Park, YoungTack Park, Hyung-Sik Yoon, Yun-Geun Kim
http://doi.org/10.5626/JOK.2020.47.4.404
The technology that identifies the relationship between surrounding objects and recognizes the situation is considered as an important and necessary technology in various areas. Numerous methodologies are being studied for this purpose. Most of the studies have solved the problem by building the domain knowledge into ontology for reasoning of situation awareness. However, based on the existing approach; it is difficult to deal with new situations in the absence of domain experts due to the dependency of experts on relevant domain knowledge. In addition, it is difficult to build the knowledge to infer situations that experts have not considered. Therefore, this study proposes a model for using ontology and CNN for reasoning of the relationships between UAVs and surrounding objects to solve the existing problems. Based on the assumption that the accuracy of ontology reasoning is insufficient, first, the reasoning was performed using the information from the detected surrounding objects. Later, the results of ontology reasoning are revised by CNN inference. Due to the limitations of actual data acquisition, data generator was built to generate data similar to real data. For evaluation of this study, two models of relationships between two objects were built and evaluated; both the models showed over 90% accuracy.
Variational Recurrent Neural Networks with Relational Memory Core Architectures
Geon-Hyeong Kim, Seokin Seo, Shinhyung Kim, Kee-Eung Kim
http://doi.org/10.5626/JOK.2020.47.2.189
Recurrent neural networks are designed to model sequential data and learn generative models for sequential data. Therefore, VRNNs (variational recurrent neural networks), which incorporate the elements of VAE (variational autoencoder) into RNN (recurrent neural network), represent complex data distribution. Meanwhile, the relationship between inputs in each sequence has been attributed to RMC (relational memory core), which introduces self-attention-based memory architecture into RNN memory cell. In this paper, we propose a VRMC (variational relation memory core) model to introduce a relational memory core architecture into VRNN. Further, by investigating the music data generated, we showed that VRMC was better than in previous studies and more effective for modeling sequential data.
Inferring User Traits from Applications Installed on a Smart Phone
Hongdo Ki, Jaehong Lee, Heewoong Park, Moon-jung Chae, Sangwoo Choi, Jonghun Park
http://doi.org/10.5626/JOK.2018.45.12.1240
Needs for customized services are increasing as a smart phone personalized device, has been used generally. Demographic information is beneficial for customized services, so inferring user traits based various data using statistical learning has been actively studied. This study conducted experiments of inferring user traits with a list of installed applications differed by users’ interest and lifestyle, and may can be accessed easily as a snapshot without explicit permission. Four feature vectors are used for inferring user traits, including vectors using application category or description that can be collected from the application market. Especially, one of the feature vectors is generated by applying Doc2Vec, a text embedding method based on a neural network, to application description. The application selection method we proposed is also used to achieve better performances than could be achieved by using all applications on the list. Last, we collected 100 lists of installed applications for experiments of inferring gender, age, relationship status, residential type, living together or not, income, outcome, height, weight, religion, semester and college, and confirmed effectiveness of proposed feature vectors and the application selection method.
Document Summarization Considering Entailment Relation between Sentences
Youngdae Kwon, Noo-ri Kim, Jee-Hyong Lee
Document summarization aims to generate a summary that is consistent and contains the highly related sentences in a document. In this study, we implemented for document summarization that extracts highly related sentences from a whole document by considering both similarities and entailment relations between sentences. Accordingly, we proposed a new algorithm, TextRank-NLI, which combines a Recurrent Neural Network based Natural Language Inference model and a Graphbased ranking algorithm used in single document extraction-based summarization task. In order to evaluate the performance of the new algorithm, we conducted experiments using the same datasets as used in TextRank algorithm. The results indicated that TextRank-NLI showed 2.3% improvement in performance, as compared to TextRank.
Bayesian Network-based Probabilistic Management of Software Metrics for Refactoring
In recent years, the importance of managing software defects in the implementation stage has emerged because of the rapid development and wide-range usage of intelligent smart devices. Even if not a few studies have been conducted on the prediction models for software defects, their outcomes have not been widely shared. This paper proposes an efficient probabilistic management model of software metrics based on the Bayesian network, to overcome limits such as binary defect prediction models. We expect the proposed model to configure the Bayesian network by taking advantage of various software metrics, which can help in identifying improvements for refactoring. Once the source code has improved through code refactoring, the measured related metric values will also change. The proposed model presents probability values reflecting the effects after defect removal, which can be achieved by improving metrics through refactoring. This model could cope with the conclusive binary predictions, and consequently secure flexibilities on decision making, using indeterminate probability values.
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