• Journal of Information Processing Systems
• /
• 제16권4호
• /
• 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.

• 한국컴퓨터정보학회논문지
• /
• 제23권1호
• /
• pp.17-24
• /
• 2018

With improvement of speech recognition and natural language processing, dialog systems are recently adapted to various service domains. It became possible to get desirable services by conversation through the dialog system, but it is still necessary to improve separate modules, such as domain detection, intention detection, named entity recognition, and out-of-domain detection, in order to achieve stable service offer. When it misclassifies an in-domain sentence of conversation as out-of-domain, it will result in poor customer satisfaction and finally lost business. As there have been relatively small number of studies related to the out-of-domain detection, in this paper, we introduce a new method using a hierarchical Dirichlet process and demonstrate the effectiveness of it by experimental results on Korean dataset.

• Smart Structures and Systems
• /
• 제29권6호
• /
• pp.791-797
• /
• 2022

A complex system is comprised of numerous entities containing physical components, devices and hardware, events or phenomena, and subsystems, there are intricate interactions among these entities. To reasonably identify the critical fault propagation paths, a system fault propagation model is essential based on the system failure mechanism and failure data. To establish an appropriate mathematical model for the complex system, these entities and their complicated relations must be represented objectively and reasonably based on the structure. Taking a command and control system as an example, this paper proposes a hierarchical fault propagation analysis method, analyzes and determines the edge betweenness ranking model and the importance degree of each sub-system.

• Asia Marketing Journal
• /
• 제22권1호
• /
• pp.1-26
• /
• 2020

Firms employing hierarchical loyalty programs (HLPs) periodically demote customers from higher to lower status level to divest from unprofitable customers and boost profitability. However, existing literature lacks objective evidence on how customer demotion affects demoted customers' future purchase behaviors and ultimately profitability for the firm. Moreover, customers in the HLP's higher position may respond to customer demotion differently from those in the HLP's lower position. Drawing upon emotions and equity theories, this study quantifies how the profits that customers contribute to the firm change after customer demotion, and compares demoted customers' behavioral reactions from top-tier with those from bottom-tier based on customers' actual behavior data from a major retail bank in South Korea. The findings show that withdrawing customer status actually deteriorates customer profitability, and customers with top-tier status decrease their profitability more dramatically than those with bottom-tier status after demotion. The results contribute to previous literature on customer demotion and relationship marketing, and provide specific guidelines into how firms should design and implement customer demotion in HLPs.

• 한국의류학회지
• /
• 제24권5호
• /
• pp.652-662
• /
• 2000

Most of established study about consumer behavior was directly connected abstract value with concrete purchase behavior, nevertheless several recognizable process is intervened between abstract concept and concept behavior. Of course researchers suggest hierarchical causality through means-end chain model. However empirical study is insufficient. And it's not certain whether the consumer's personal value affects actual evaluation about product attributes. Thus the purpose of this paper was to explore hierarchical causality of personal value, benefits sought and clothing product attributes and to suggest an alternative approach method. For the empircial study the data sets were collected through 150 female consumers living in Pusan and SAS and LISREL VIII were used for statistical analysis. As the result, hierarchical causality suggested by means-end chain model was positively substantiated. That is, benefits sought is differentiated according to personal value, and actual product attributes are indirectly influenced by personal value through benefits sought. Benefits sought are found to be key mediating variables.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제21권6호
• /
• pp.436-441
• /
• 2015

군집화 알고리즘은 그 종류에 따라 만들어낼 수 있는 군집의 종류와 보여줄 수 있는 정보의 수준이 차이가 난다. 밀도기반 군집화 알고리즘은 데이터 분포 상의 임의의 모양을 가진 군집을 잘 잡아내지만 보여줄 수 있는 계층정보가 매우 적거나 없는 수준이고, 반면 계층적 군집화 알고리즘은 자세한 계층 정보를 보여주지만 구 모양의 군집 외에는 잘 잡아내지 못한다. 이 논문에서는 이러한 두 군집화 방식의 대표적 알고리즘인 OPTICS와 응집 계층 군집화 알고리즘의 장점만을 취하는 계층 발생 프레임워크를 제시하고 이와 더불어 효과적 데이터 분석을 위한 여러 시각화, 상호작용 기법을 지원하는 시각적 분석 애플리케이션을 제공한다.

• Journal of Information Technology Applications and Management
• /
• 제22권2호
• /
• pp.149-169
• /
• 2015

This study tried to find out how to overcome multicollinearity problems in the structural equation model by creating a hierarchical construct model about the repurchase intention of social commerce. This study selected, as independent variables, price, quality, service, and social influence, based on literature review about social commerce, and then, as detailed variables of independent variables, selected system quality, information quality, transaction safety, order fulfillment and after-sales service, communication, subjective norms, and reputation. As results of empirical analysis about hierarchical construct model, all the independent variables were accepted having a significant impact on repurchase intention of social commerce. Next, this study analyzed the competition model that eight independent variables of price, system quality, information quality, transaction safety, order fulfillment and after-sales service, communication, subjective norm, and reputation directly influence the repurchase intention of social commerce. As results of empirical analysis, system quality, information quality, transaction safety, communication appeared to be insignificant. This study showed that hierarchical construct model is useful to overcome the multicollinearity problem in structural equational model and to increase explanatory power.

• 한국항행학회논문지
• /
• 제12권6호
• /
• pp.598-603
• /
• 2008

릴레이 시스템은 차세대 무선통신시스템에서 고속하향통신과 서비스 커버리지 확장을 실현하기 위한 주요 기술이다. 본 논문에서는 직교주파수다중화변조 기반에서 계층변조를 사용하는 릴레이 시스템을 위한 효율적인 전송방식을 제안한다. 본 전송방식은 기지국 전력의 큰 증가 없이 셀 외곽지역의 사용자들에게 셀 내에 위치한 사용자들과 같은 고속하향통신을 제공할 수 있다. 전산모의실험을 통해서 제안 전송방식의 성능을 계층변조가 적용되지 않은 기존 방식과 비교 분석하며, 그 결과 제안 전송방식이 일대일전송 및 일대다중전송의 경우 모두 기존방식에 비해서 기지국 전력사용 측면에서 우수한 성능을 보임을 확인한다.

• 디지털융복합연구
• /
• 제15권3호
• /
• pp.201-209
• /
• 2017

본 논문은 계층적 Convolutional Nerual Network(CNN)을 이용한 스마트폰용 객체 인식 시스템이다. 전체적인 구성은 스마트폰과 서버를 연결하여 서버에서 컨볼루셔널 뉴럴 네트워크로 객체 인식을 하고 수집된 데이터를 매칭시켜 스마트폰으로 객체의 상세정보를 전달하는 방법이다. 또한 계층적 컨볼루셔널 뉴럴 네트워크와 단편적 컨볼루셔널 뉴럴 네트워크와 비교하였다. 계층적 컨볼루셔널 뉴럴 네트워크는 88%, 단편적 컨볼루셔널 뉴럴 네트워크는 73%의 정확도를 가지며 15%p의 성능 향상을 보였다. 이를 기반으로 스마트폰과 방송매체와 연동한 T-Commerce 시장 확장의 가능성을 보여준다. 아울러 방송영상을 시청하면서 Information Retrieval, AR/VR 서비스도 제공 가능하다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권11호
• /
• pp.4644-4661
• /
• 2015

Wireless sensor networks are often organized in the form of clusters leading to the new framework of WSN called cluster or hierarchical WSN where each cluster head is responsible for its own cluster and its members. These hierarchical WSN are prone to various routing layer attacks such as Black hole, Gray hole, Sybil, Wormhole, Flooding etc. These routing layer attacks try to spoof, falsify or drop the packets during the packet routing process. They may even flood the network with unwanted data packets. If one cluster head is captured and made malicious, the entire cluster member nodes beneath the cluster get affected. On the other hand if the cluster member nodes are malicious, due to the broadcast wireless communication between all the source nodes it can disrupt the entire cluster functions. Thereby a scheme which can detect both the malicious cluster member and cluster head is the current need. Abnormal energy consumption of nodes is used to identify the malicious activity. To serve this purpose a learning based energy prediction algorithm is proposed. Thus a two level energy prediction based intrusion detection scheme to detect the malicious cluster head and cluster member is proposed and simulations were carried out using NS2-Mannasim framework. Simulation results achieved good detection ratio and less false positive.