• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.820-831
• /
• 2020

Extractive document summarization aims to select a few sentences while preserving its main information on a given document, but the current extractive methods do not consider the sentence-information repeat problem especially for news document summarization. In view of the importance and redundancy of news text information, in this paper, we propose a neural extractive summarization approach with joint sentence semantic clipping and selection, which can effectively solve the problem of news text summary sentence repetition. Specifically, a hierarchical selective encoding network is constructed for both sentence-level and document-level document representations, and data containing important information is extracted on news text; a sentence extractor strategy is then adopted for joint scoring and redundant information clipping. This way, our model strikes a balance between important information extraction and redundant information filtering. Experimental results on both CNN/Daily Mail dataset and Court Public Opinion News dataset we built are presented to show the effectiveness of our proposed approach in terms of ROUGE metrics, especially for redundant information filtering.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.8
• /
• pp.87-93
• /
• 2019

These days, as interest in the recommendation system with deep learning is increasing, a number of related studies to develop a performance for collaborative filtering through autoencoder, a state-of-the-art deep learning neural network architecture has advanced considerably. The purpose of this study is to propose autoencoder which is used by the recommendation system to predict ratings, and we added more hidden layers to the original architecture of autoencoder so that we implemented deep autoencoder with 3 to 5 hidden layers for much deeper architecture. In this paper, therefore we make a comparison between the performance of them. In this research, we use 2-dimensional arrays and 3-dimensional tensor as the input dataset. As a result, we found a correlation between matrix entry of the 3-dimensional dataset such as item-time and user-time and also figured out that deep autoencoder with extra hidden layers generalized even better performance than autoencoder.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.69-78
• /
• 2019

The amount of data is increasing significantly as information and communication technology advances, mobile, cloud computing, the Internet of Things and social network services become commonplace. As the data grows exponentially, there is a growing demand for services that recommend the information that users want from large amounts of data. Collaborative filtering method is commonly used in information recommendation methods. One of the problems with collaborative filtering-based recommendation method is the cold start problem. In this paper, we propose a method to improve the cold start problem. That is, it solves the cold start problem by mapping the item evaluation data that does not exist to the initial user to the automatically generated data from the mobile app. We describe the main contents of the proposed method and explain the proposed method through the book recommendation scenario. We show the superiority of the proposed method through comparison with existing methods.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1141-1155
• /
• 2019

Today, most approaches used in the recommendation system provide correct data prediction similar to the data that users need. The method that researchers are paying attention and apply as a model in the recommendation system is the communities' detection in the big social network. The outputted result of this approach is effective in improving the exactness. Therefore, in this paper, the personalized movie recommendation system that combines data mining for the k-clique method is proposed as the best exactness data to the users. The proposed approach was compared with the existing approaches like k-clique, collaborative filtering, and collaborative filtering using k-nearest neighbor. The outputted result guarantees that the proposed method gives significant exactness data compared to the existing approach. In the experiment, the MovieLens data were used as practice and test data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4463-4483
• /
• 2019

Privacy-preserving collaborative filtering schemes take privacy concerns into its primary consideration without neglecting the prediction accuracy. Different schemes are proposed that are built upon different data partitioning scenarios such as a central server, two-, multi-party or peer-to-peer network. These data partitioning scenarios have been investigated in terms of claimed privacy promises, recently. However, to the best of our knowledge, any peer-to-peer privacy-preserving scheme lacks such study that scrutinizes privacy promises. In this paper, we apply three different attack techniques by utilizing auxiliary information to derive private ratings of peers and conduct experiments by varying privacy protection parameters to evaluate to what extent peers' data can be reconstructed.

• Smart Structures and Systems
• /
• v.29 no.3
• /
• pp.421-431
• /
• 2022

Concrete slab cracks monitoring of modern high-speed railway is important for safety and reliability of train operation, to prevent catastrophic failure, and to reduce maintenance costs. This paper proposes a curvature filtering improved crack detection method in concrete slabs of high-speed railway via graph-based anomalies calculation. Firstly, large curvature information contained in the images is extracted for the crack identification based on an improved curvature filtering method. Secondly, a graph-based model is developed for the image sub-blocks anomalies calculation where the baseline of the sub-blocks is acquired by crack-free samples. Once the anomaly is large than the acquired baseline, the sub-block is considered as crack-contained block. The experimental results indicate that the proposed method performs better than convolutional neural network method even under different curvature structures and illumination conditions. This work therefore provides a useful tool for concrete slabs crack detection and is broadly applicable to variety of infrastructure systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.305-318
• /
• 2022

Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.366-369
• /
• 2022

The glut of information aggravated the process of data analysis and other procedures including data mining. Many algorithms were devised in Big Data and Data Mining to solve such an intricate problem. In this paper, we conducted research about the comparison of several similarity measures and community detection algorithms in collaborative filtering for movie recommendation systems. Movielense data set was used to do an empirical experiment. We applied three different similarity measures: Cosine, Euclidean, and Pearson. Moreover, betweenness and eigenvector centrality were used to detect communities from the network. As a result, we elucidated which algorithm is more suitable than its counterpart in terms of recommendation accuracy.

• International journal of advanced smart convergence
• /
• v.12 no.1
• /
• pp.1-8
• /
• 2023

Smart IoT over high speed network and high performance smart devices explodes the ubiquitous services and applications. Nearest Neighbor(NN) query is one of the important type of queries that have to be supported for ubiquitous information services. In order to process efficiently NN queries in the wireless broadcast environment, it is important that the clients determine quickly the search space and filter out NN from the candidates containing the search space. In this paper, we propose a hybrid index of Voronoi and grid partition to provide quick search space decision and rapid filtering out NN from the candidates. Grid partition plays the role of helping quick search space decision and Voronoi partition providing the rapid filtering. We show the effectiveness of the proposed index by comparing the existing indexing schemes in the access time and tuning time. The evaluation shows the proposed index scheme makes the two performance parameters improved than the existing schemes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12A
• /
• pp.982-990
• /
• 2009

The IEEE 802.15.4 wireless sensor network is composed of the unique sensor devices to monitor and collect physical or environmental conditions. The interests in a positioning technology, which is one of the environment monitoring technologies, are gradually increased according to the development of the sensor technology and IT infrastructure. Generally, it is difficult for the positioning system using RSSI (Received Signal Strength Indication) based implementation to get accurate position because of obstacles, RF wave's delay and multipath. Therefore, in this paper, we investigate the improved positioning technologies for RSSI-based positioning system. This paper also proposes the enhanced scheme to improve the accuracy of positioning system by applying the Gaussian Filter algorithm, which is widely used for enhancing the performance of image processing system. For the implementation of proposed scheme, we firstly make a look-up tables, which represent the distance between target node and master node and corresponding RSSI value of each target node which are recorded as an average value after investigating the characteristics of attenuation of transmitted signal By applying the pre-determined look-up tables and Gaussian Filtering in the proposed scheme, we analyzed the positioning performance and compared with other conventional RSSI-based positioning algorithms.