• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.8B
• /
• pp.769-776
• /
• 2006

It is important for evaluation execution about technology development. And it is necessary to settle together with technology development activity to evaluation execution. Purpose of this paper is to decide request for proposal and suitable to proposed enterprise contents about technology part in performance. Therefore let estimate the data about it. So suitable enterprise is selected through applying evaluation data to TEPM(Technology Evaluation Process Model).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.892-894
• /
• 2014

논문을 검색할 때 키워드를 이용한 검색 방법이 주로 사용된다. 논문에서 사용하는 이미지는 논문의 내용을 설명하는 중요한 요소임에도 불구하고 검색에 있어서 고려되지 않은 점이 있다. 특히, 이미지 검색은 의학 논문을 검색할 경우에 키워드를 대신할 수 있는 유용한 검색방법이 될 수 있을 것으로 사료된다. 본 논문에서는 기존의 이미지 검색이 쓰였던 관련 연구들을 살펴보고 의학 논문 사이트를 대표하는 펍메드와 코리아메드를 비교 분석한다. 더 나아가 빠르고 정확한 이미지 검색을 위한 이미지 분류 기준을 설정하여 본다.

• 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.19 no.12
• /
• pp.209-218
• /
• 2014

The more mobile devices consuming web services, the more QoS-aware selection of mobile web services, we need. A QoS(Quality of Service) contract is an agreement between the web service provider and the mobile user that specifies the level of the service quality. Web services users can be assured of the level of the service quality specified by the QoS contract. We propose a broker-based framework for QoS-aware mobile web services selection in this work. Under this architecture, the mobile users can request the web services through the service broker on the wireless networks. The service broker utilizes agents to monitor the web services quality and manages the service quality by notifying the service provider and mobile user of the service contract violation. Reliability, response time, and cost were the metrics used for QoS monitoring. Futhermore mobile users can select a web service best suited for his/her needs through the service broker.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.12
• /
• pp.2379-2386
• /
• 2016

This study conducted an analysis using IPA metrics targeting college students to get strategic implications for marketing in the recently fast-growing mobile shopping market. The IPA analysis result about the selection of mobile shopping malls is as follows. First, out of the 21 features, 'reliability of the offered products(6.09)' had the highest level of importance and 'convenience of payment(5.29)' had the highest level of performance. Second, in the area of 'Doing great, Keep it up' 11 features were included such as 'convenience of payment' and 'reliability of the offered products'. Third, the feature that needed to be corrected in the area of 'Focus here' was 'shortening the waiting time for exchange, refund or warranty service'. Fourth, low priority areas in terms of importance and performance, there were 3 features including 'push/notification helps purchases'. Fifth, to the area of 'overdone' 4 features belonged such as 'variety in the type of products'.

• Journal of Communications and Networks
• /
• v.18 no.3
• /
• pp.327-332
• /
• 2016

The routing protocol for low-power and lossy networks (RPL) is an internet protocol based routing protocol developed and standardized by IETF in 2012 to support a wide range of applications for low-power and lossy-networks (LLNs). In LLNs consisting of resource-constrained devices, the energy consumption of battery powered sensing devices during network operations can greatly impact network lifetime. In the case of inefficient route selection, the energy depletion from even a few nodes in the network can damage network integrity and reliability by creating holes in the network. In this paper, a composite energy-aware node metric ($RER_{BDI}$) is proposed for RPL; this metric uses both the residual energy ratio (RER) of the nodes and their battery discharge index. This composite metric helps avoid overburdening power depleted network nodes during packet routing from the source towards the destination oriented directed acyclic graph root node. Additionally, an objective function is defined for RPL, which combines the node metric $RER_{BDI}$ and the expected transmission count (ETX) link quality metric; this helps to improve the overall network packet delivery ratio. The COOJA simulator is used to evaluate the performance of the proposed scheme. The simulations show encouraging results for the proposed scheme in terms of network lifetime, packet delivery ratio and energy consumption, when compared to the most popular schemes for RPL like ETX, hop-count and RER.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1986-2009
• /
• 2024

The integration of blockchain technology with the rapid growth of Internet of Things (IoT) devices has enabled secure and decentralised data exchange. However, security vulnerabilities and performance limitations remain significant challenges in IoT blockchain networks. This work proposes a novel approach that combines transaction representation and machine learning techniques to address these challenges. Various clustering techniques, including k-means, DBSCAN, Gaussian Mixture Models (GMM), and Hierarchical clustering, were employed to effectively group unlabelled transaction data based on their intrinsic characteristics. Anomaly transaction prediction models based on classifiers were then developed using the labelled data. Performance metrics such as accuracy, precision, recall, and F1-measure were used to identify the minority class representing specious transactions or security threats. The classifiers were also evaluated on their performance using balanced and unbalanced data. Compared to unbalanced data, balanced data resulted in an overall average improvement of approximately 15.85% in accuracy, 88.76% in precision, 60% in recall, and 74.36% in F1-score. This demonstrates the effectiveness of each classifier as a robust classifier with consistently better predictive performance across various evaluation metrics. Moreover, the k-means and GMM clustering techniques outperformed other techniques in identifying security threats, underscoring the importance of appropriate feature selection and clustering methods. The findings have practical implications for reinforcing security and efficiency in real-world IoT blockchain networks, paving the way for future investigations and advancements.

• The Journal of Korean Association of Computer Education
• /
• v.17 no.6
• /
• pp.93-102
• /
• 2014

A mobile office environment using mobile devices, such as tablet PC, mobile phone is gradually increased in enterprises, banking and public institutions etc which is no limitation on places. It occurs advanced and persist security threats that are required effective security management policy and technical solution to be secure. For BYOD (Bring Your Own Device) environment, technical security management solutions of network control based, MDM (Mobile Device Management), MAM (Mobile Application Management), MCM (Mobile Contents Management) were released, evolved and mixed used. In perspective of integrated security management solution, mobile security product should be selected to consider user experience and environment and correct quality evaluation model of product is needed which is provided standards and guidance on the selection criteria when it was introduced. In this paper, the most widely used MDM solution is selected to take a look at its features and it was reviewed the product attributes with related international standard ISO/IEC25010 software quality attributes. And then it was derived evaluation elements and calculated the related metrics based on the quality analysis model. For the verification of quality evaluation model, security checks list and testing procedures were established; it applied metrics and analyzed the testing result through scenario based case study.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.1-7
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.