jongmo kim - Academia.edu (original) (raw)

Papers by jongmo kim

The Journal of Supercomputing

Data and information produced in network-centric environments are large and heterogeneous. As a s... more Data and information produced in network-centric environments are large and heterogeneous. As a solution to this challenge, ontology-based situation awareness (SA) is gaining attention because ontologies can contribute to the integration of heterogeneous data and information produced from different sources and can enhance knowledge formalization. In this study, we propose a novel method for enhancing ontology-based SA by integrating ontology and linked open data (LOD) called a multi-layered SA ontology and the relations between events in the layer. In addition, we described the characteristics and roles of each layer. Finally, we developed a framework to perform SA rapidly and accurately by acquiring and integrating information from the ontology and LOD based on the multi-layered SA ontology. We conducted three experiments to verify the effectiveness of the proposed framework. The results show that the performance of the SA of our framework is comparable to that of domain experts.

Innovative Mobile and Internet Services in Ubiquitous Computing, 2018

In this paper, we propose a method to reduce the difficulties of query caused by lack of informat... more In this paper, we propose a method to reduce the difficulties of query caused by lack of information about graph patterns even though the graph pattern is one of the important characteristics of the LOD. To do so, we apply the clustering methodology to find the RDF predicates that have similar patterns. In addition, we identify representative graph patterns that imply its characteristics each cluster. The representative graph patterns are used to extend the users’ query graphs. To show the difficulties of the query on the LOD, we developed an illustrative example. We propose the novel framework to support query extension using predicate clustering-based entity-centered graph patterns. Through the implementation of this framework, the user can easily query the LOD and at the same time collect appropriate query results.

As contents are overflowing in Social Network Services (SNSs), the Recommender System (RS) in SNS... more As contents are overflowing in Social Network Services (SNSs), the Recommender System (RS) in SNS became increasingly important. Traditional RSs focus on the relevance of contents to the users and therefore recommend obvious contents over and over again. To solve this problem, many researches have sought to find serendipity, but they have the limitation of recommending obvious or absurd posts. In this paper, we propose a novel method to recommend serendipity using tie strength of the users’ social relationships. Through the implementation of this method, serendipity can be recommended without analyzing user preferences or contents. We developed an illustrative example to prove validity of our framework.

2020 IEEE International Conference on Big Data and Smart Computing (BigComp), 2020

Synonym identification is the key factor for ontology alignment. There are several researches whi... more Synonym identification is the key factor for ontology alignment. There are several researches which proposed synonym identification methods. However, most of the researches focus on the words in general contexts, which occurs the problem in finding synonym relations in certain domains. To address this problem, we suggest ontology-aided word2vec based synonym identification method. In this paper, we find domain-specific documents based on ontology for training word2vec model. To do so, we use Kernel Density Estimation (KDE) to estimate distributions of words and we Kullback-Leibler (KL) divergence to compare the distributions. Through this, we can find the synonym relations considering domain-specific context which is hard to be identified with existing methods.

J. Internet Serv. Inf. Secur., 2022

This paper proposes a new method named evolving-graph generation framework to simultaneously solv... more This paper proposes a new method named evolving-graph generation framework to simultaneously solve the complexity and dynamic nature of the attribute networks that can occur in graph-based anomaly detection with Graph Neural Networks (GNN). The proposed framework consists of two components. The first component is a feature selection method that hybridizes filter-based and wrapper-based techniques to reduce the snapshots. The second component is an association method based on temporal patterns for the snapshots using the subgraph embedding technique and gaussianbase KL divergence. At the time, the association method finds intra-snapshots and inter-snapshots associations. As a result, we can obtain an evolving graph that is simplified and temporal patternsenhanced from original networks. It is used an input graph for a GNN-based anomaly detection model. To show the superiority of the proposed framework, we conduct experiments and evaluations on 8 real-world datasets with anomaly labels with comparative state-of-the-art models of graph-based anomaly detection. We show that the proposed framework outperforms state-of-the-art methods in the accuracy and stability of training with the trend of decreasing train loss.

Innovative Mobile and Internet Services in Ubiquitous Computing

International Journal of Web and Grid Services

Journal of the Korea Management Engineers Society

IEEE Access

In this paper, we propose an energy-saving framework for Wireless Sensor Networks (WSN) using mac... more In this paper, we propose an energy-saving framework for Wireless Sensor Networks (WSN) using machine learning techniques and meta-heuristics according to environmental states. Unlike conventional topology-based energy-saving methods, we focus on the energy savings of the sensor node in the WSN itself. We attempt two-phase energy savings on the sensor nodes. First, network-level energy saving, called N1-energy saving, is achieved by finding the minimum sensor nodes needed to ensure the performance of the WSN. To find the minimum sensor nodes, we apply hybrid filter-wrapper feature selection, a typical machine learning method, to find the best feature subsets. Second, we achieve energy savings of the WSNs by manipulating the sampling rate and the transmission interval of the sensor nodes to achieve node-level energy saving, which is referred to as N2-energy saving. To do so, we propose an optimization method based on Simulated Annealing (SA), which is an efficient method that can find the approximate global optimum in datasets where it is difficult to collect precise values due to noise problems, such as sensor data. Some numerical examples are shown with respect to several control parameters. We conduct several experiments with real-world sensor data in a smart home to prove the superiority of the proposed method. Through these experiments, the sensor nodes are shown to be selected by a method performing N1-energy savings effectively while minimizing the loss of performance compared to the original WSN. In addition, we demonstrate that N2-energy savings can be achieved while maintaining the QoS of the WSN through an optimal sampling rate and transmission interval determined by the SA.

The Journal of Korean Institute of Communications and Information Sciences

Pervasive and Mobile Computing, 2015

The Journal of Supercomputing

Multimedia Tools and Applications

The Journal of Supercomputing

Data and information produced in network-centric environments are large and heterogeneous. As a s... more Data and information produced in network-centric environments are large and heterogeneous. As a solution to this challenge, ontology-based situation awareness (SA) is gaining attention because ontologies can contribute to the integration of heterogeneous data and information produced from different sources and can enhance knowledge formalization. In this study, we propose a novel method for enhancing ontology-based SA by integrating ontology and linked open data (LOD) called a multi-layered SA ontology and the relations between events in the layer. In addition, we described the characteristics and roles of each layer. Finally, we developed a framework to perform SA rapidly and accurately by acquiring and integrating information from the ontology and LOD based on the multi-layered SA ontology. We conducted three experiments to verify the effectiveness of the proposed framework. The results show that the performance of the SA of our framework is comparable to that of domain experts.

Innovative Mobile and Internet Services in Ubiquitous Computing, 2018

In this paper, we propose a method to reduce the difficulties of query caused by lack of informat... more In this paper, we propose a method to reduce the difficulties of query caused by lack of information about graph patterns even though the graph pattern is one of the important characteristics of the LOD. To do so, we apply the clustering methodology to find the RDF predicates that have similar patterns. In addition, we identify representative graph patterns that imply its characteristics each cluster. The representative graph patterns are used to extend the users’ query graphs. To show the difficulties of the query on the LOD, we developed an illustrative example. We propose the novel framework to support query extension using predicate clustering-based entity-centered graph patterns. Through the implementation of this framework, the user can easily query the LOD and at the same time collect appropriate query results.

As contents are overflowing in Social Network Services (SNSs), the Recommender System (RS) in SNS... more As contents are overflowing in Social Network Services (SNSs), the Recommender System (RS) in SNS became increasingly important. Traditional RSs focus on the relevance of contents to the users and therefore recommend obvious contents over and over again. To solve this problem, many researches have sought to find serendipity, but they have the limitation of recommending obvious or absurd posts. In this paper, we propose a novel method to recommend serendipity using tie strength of the users’ social relationships. Through the implementation of this method, serendipity can be recommended without analyzing user preferences or contents. We developed an illustrative example to prove validity of our framework.

2020 IEEE International Conference on Big Data and Smart Computing (BigComp), 2020

Synonym identification is the key factor for ontology alignment. There are several researches whi... more Synonym identification is the key factor for ontology alignment. There are several researches which proposed synonym identification methods. However, most of the researches focus on the words in general contexts, which occurs the problem in finding synonym relations in certain domains. To address this problem, we suggest ontology-aided word2vec based synonym identification method. In this paper, we find domain-specific documents based on ontology for training word2vec model. To do so, we use Kernel Density Estimation (KDE) to estimate distributions of words and we Kullback-Leibler (KL) divergence to compare the distributions. Through this, we can find the synonym relations considering domain-specific context which is hard to be identified with existing methods.

J. Internet Serv. Inf. Secur., 2022

This paper proposes a new method named evolving-graph generation framework to simultaneously solv... more This paper proposes a new method named evolving-graph generation framework to simultaneously solve the complexity and dynamic nature of the attribute networks that can occur in graph-based anomaly detection with Graph Neural Networks (GNN). The proposed framework consists of two components. The first component is a feature selection method that hybridizes filter-based and wrapper-based techniques to reduce the snapshots. The second component is an association method based on temporal patterns for the snapshots using the subgraph embedding technique and gaussianbase KL divergence. At the time, the association method finds intra-snapshots and inter-snapshots associations. As a result, we can obtain an evolving graph that is simplified and temporal patternsenhanced from original networks. It is used an input graph for a GNN-based anomaly detection model. To show the superiority of the proposed framework, we conduct experiments and evaluations on 8 real-world datasets with anomaly labels with comparative state-of-the-art models of graph-based anomaly detection. We show that the proposed framework outperforms state-of-the-art methods in the accuracy and stability of training with the trend of decreasing train loss.

Innovative Mobile and Internet Services in Ubiquitous Computing

International Journal of Web and Grid Services

Journal of the Korea Management Engineers Society

IEEE Access

In this paper, we propose an energy-saving framework for Wireless Sensor Networks (WSN) using mac... more In this paper, we propose an energy-saving framework for Wireless Sensor Networks (WSN) using machine learning techniques and meta-heuristics according to environmental states. Unlike conventional topology-based energy-saving methods, we focus on the energy savings of the sensor node in the WSN itself. We attempt two-phase energy savings on the sensor nodes. First, network-level energy saving, called N1-energy saving, is achieved by finding the minimum sensor nodes needed to ensure the performance of the WSN. To find the minimum sensor nodes, we apply hybrid filter-wrapper feature selection, a typical machine learning method, to find the best feature subsets. Second, we achieve energy savings of the WSNs by manipulating the sampling rate and the transmission interval of the sensor nodes to achieve node-level energy saving, which is referred to as N2-energy saving. To do so, we propose an optimization method based on Simulated Annealing (SA), which is an efficient method that can find the approximate global optimum in datasets where it is difficult to collect precise values due to noise problems, such as sensor data. Some numerical examples are shown with respect to several control parameters. We conduct several experiments with real-world sensor data in a smart home to prove the superiority of the proposed method. Through these experiments, the sensor nodes are shown to be selected by a method performing N1-energy savings effectively while minimizing the loss of performance compared to the original WSN. In addition, we demonstrate that N2-energy savings can be achieved while maintaining the QoS of the WSN through an optimal sampling rate and transmission interval determined by the SA.

The Journal of Korean Institute of Communications and Information Sciences

Pervasive and Mobile Computing, 2015

The Journal of Supercomputing

Multimedia Tools and Applications