• Ocean Systems Engineering
• /
• v.7 no.4
• /
• pp.319-328
• /
• 2017

Higher prediction efficacy is a very challenging task in any field of engineering. Due to global warming, there is a considerable increase in the global sea level. Through this work, an attempt has been made to find the sea level variability due to climate change impact at Haldia Port, India. Different statistical downscaling techniques are available and through this paper authors are intending to compare and illustrate the performances of three regression models. The models: Wavelet Neural Network (WNN), Minimax Probability Machine Regression (MPMR), Feed-Forward Neural Network (FFNN) are used for projecting the sea level variability due to climate change at Haldia Port, India. Model performance indices like PI, RMSE, NSE, MAPE, RSR etc were evaluated to get a clear picture on the model accuracy. All the indices are pointing towards the outperformance of WNN in projecting the sea level variability. The findings suggest a strong recommendation for ensembled models especially wavelet decomposed neural network to improve projecting efficiency in any time series modeling.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.9
• /
• pp.1001-1009
• /
• 1992

In this paper, the standard A earth station antenna was designed by using the shaping techniques and also manufactured for I NTELSAT satellite. The designed antenna Is C-band shaped casse grain antenna with the diameter of 18m. The wide-angle radaiation patterns wholly satisfied CCIR Recommendation of sidelobe envelope line of 29-25 logo. The whole radiatlon characteristics satisfied the design specifications.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.2
• /
• pp.283-288
• /
• 1996

This paper presents the development technology of standard shielded resistor divider for full lightning impulse voltage. The ability of large-capacity power apparatus to withstand lighting stroke is usually evaluated by means of full lightning impulse voltage. Lightning impulse voltage test has been essential to evaluate the insulation performance of electrical power apparatus. Recently international standard (IEC 60) on high voltage measurement techniques is being revised and requests a formal traceability of high voltage measurements. Therefore, general interest for this area has grown considerably during last years, and several international intercomparisons have already completed worldwide, i.e. Europe, Japan, America etc., In this viewpoint, we have also investigated the step response of the standard shielded resistor divider, which satisfies the IEC recommendation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.601-604
• /
• 2001

도서 정보 추천 시스템에서 기존 사용자들의 정보를 이용하여 마이닝 기법중 군집 분석을 적용하여 사이트에 처음으로 접속하는 사용자와 접속률이 낮아 피드백 정보가 많이 없고 적절한 추천을 하지 못하는 사용자에게 비슷한 군집의 사용자들의 정보를 이용하여 적절한 정보를 추천한다. 본 논문에서는 기존의 멀티에이전트 추천 시스템에 데이터 마이닝 에이전트와 패턴 분석 에이전트를 접목하여 더 나은 추천 정보를 제공하기 위한 시스템을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.420-423
• /
• 2018

본 논문에서는 웹 및 문자 공지문을 자동으로 분류하고 추천함으로써 사용자가 원하는 공지문만을 볼 수 있도록 하는 애플리케이션을 개발한다. 본 애플리케이션은 공지문을 여러 카테고리로 자동 분류하여 사용자가 원하는 카테고리에 속한 공지문만을 볼 수 있도록 하며, 사용자가 선호할 만한 공지문을 추천하는 기능을 제공한다. 공지문 분류를 위해 다층 신경망 모델과 Naive Bayes 분류기를 사용하였으며, 공지문 추천을 위해 키워드 기반 자체 알고리즘을 사용하였다. 그 밖에 Word2Vec 을 활용한 검색어 추천 등 부가 기능을 제공하여 사용자가 쉽게 공지문을 찾을 수 있도록 하였다. 본 애플리케이션을 통해 사용자는 수많은 공지문 중 관심 있는 공지문만을 효율적으로 확인할 수 있다.

• Environmental Engineering Research
• /
• v.24 no.2
• /
• pp.191-201
• /
• 2019

Petroleum industry produces one of the popular hazardous waste known as Petroleum Sludge. The treatment and disposal of petroleum sludge has created a major challenge in recent years. This review provides insights into various approaches involved in the treatment, and disposal of petroleum sludge. Various methods used in the treatment and disposal of petroleum sludge such as incineration, stabilization/solidification, oxidation, and bio-degradation are explained fully and other techniques utilized in oil recovery from petroleum sludge such as solvent extraction, centrifugation, surfactant EOR, freeze/thaw, pyrolysis, microwave irradiation, electro-kinetic method, ultrasonic irradiation and froth flotation were discussed. The pros and cons of these methods were critically considered and a recommendation for economically useful alternatives to disposal of this unfriendly material was presented.

• Electronics and Telecommunications Trends
• /
• v.34 no.6
• /
• pp.100-107
• /
• 2019

Recently, reinforcement learning (RL) has expanded from the research phase of the virtual simulation environment to a wide range of applications, such as autonomous driving, natural language processing, recommendation systems, and disease diagnosis. However, RL is less likely to be used in these complex real-world environments. In contrast, inverse reinforcement learning (IRL) can obtain optimal policies in various situations; furthermore, it can use expert demonstration data to achieve its target task. In particular, IRL is expected to be a key technology for artificial general intelligence research that can successfully perform human intellectual tasks. In this report, we briefly summarize various IRL techniques and research directions.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.163-171
• /
• 2022

Online services are widely spread, and their use increases day by day. As COVID-19 spread and people spent much time online, fraud scams have risen unexpectedly. Manipulation techniques have become more effective at swindling those lacking basic technological knowledge. Unfortunately, a user needs a quorum. The interest in preventing scammers from obtaining effective quality service has become the most significant obstacle, increasing the variety of daily Internet platforms. This paper is concerned with analyzing purchase data and extracting provided results. In addition, after examining relevant documents presenting research discussing them, the recommendation was made that future work avoids them; this would save a lot of effort, money, and time. This research highlights many problems a person may face in dealing with online institutions and possible solutions to the epidemic through theft operations on the Internet.

• Asia pacific journal of information systems
• /
• v.27 no.2
• /
• pp.126-138
• /
• 2017

The proliferation of items increased the difficulty of customers in finding the specific items they want to purchase. To solve this problem, companies adopted recommender systems, such as collaborative filtering systems, to provide personalization services. However, companies use only meaningful and essential data given the explosive growth of data. Some customers are concerned that their private information may be exposed because CF systems necessarily deal with personal information. Based on these concerns, we analyze the effects of the amount of information on recommendation performance. We assume that a customer could choose to provide overall information or partial information. Experimental results indicate that customers who provided overall information generally demonstrated high performance, but differences exist according to the characteristics of products. Our study can provide companies with insights concerning the efficient utilization of data.

• Journal of Dental Anesthesia and Pain Medicine
• /
• v.19 no.6
• /
• pp.323-341
• /
• 2019

Background: Local anesthetics alone or in combination with adjuncts, such as oral medications, have routinely been used for pain control during endodontic treatment. The best clinical choice amongst the vast numbers of agents and techniques available for pain control for irreversible pulpitis is unclear. This network meta-analysis combined the available evidence on agents and techniques for pulpal anesthesia in the maxilla and mandible, in order to identify the best amongst these approaches statistically, as a basis for future clinical trials. Methods: Randomized trials in MEDLINE, DARE, and COCHRANE databases were screened based on inclusion criteria and data were extracted. Heterogeneity was assessed and odds ratios were used to estimate effects. Inconsistencies between direct and indirect pooled estimates were evaluated by H-statistics. The Grading of Recommendation, Assessment, Development, and Evaluation working group approach was used to assess evidence quality. Results: Sixty-two studies (nine studies in the maxilla and 53 studies in the mandible) were included in the meta-analysis. Increased mandibular pulpal anesthesia success was observed on premedication with aceclofenac + paracetamol or supplemental 4% articaine buccal infiltration or ibuprofen+paracetamol premedication, all the above mentioned with 2% lignocaine inferior alveolar nerve block (IANB). No significant difference was noted for any of the agents investigated in terms of the success rate of maxillary pulpal anesthesia. Conclusion: Direct and indirect comparisons indicated that some combinations of IANB with premedication and/or supplemental infiltration had a greater chance of producing successful mandibular pulpal anesthesia. No ideal technique for maxillary anesthesia emerged. Randomized clinical trials with increased sample size may be needed to provide more conclusive data. Our findings suggest that further high-quality studies are required in order to provide definitive direction to clinicians regarding the best agents and techniques to use for mandibular and maxillary anesthesia for irreversible pulpitis.