• 인터넷정보학회논문지
• /
• 제21권6호
• /
• pp.33-39
• /
• 2020

The paper is to build recommendation systems leveraging Deep Learning and Big Data platform, Spark to predict item ratings of the Amazon e-commerce site. Recommendation system in e-commerce has become extremely popular in recent years and it is very important for both customers and sellers in daily life. It means providing the users with products and services they are interested in. Therecommendation systems need users' previous shopping activities and digital footprints to make best recommendation purpose for next item shopping. We developed the recommendation models in Amazon AWS Cloud services to predict the users' ratings for the items with the massive data set of Amazon customer reviews. We also present Big Data architecture to afford the large scale data set for storing and computation. And, we adopted deep learning for machine learning community as it is known that it has higher accuracy for the massive data set. In the end, a comparative conclusion in terms of the accuracy as well as the performance is illustrated with the Deep Learning architecture with Spark ML and the traditional Big Data architecture, Spark ML alone.

• 한국IT서비스학회지
• /
• 제16권1호
• /
• pp.1-26
• /
• 2017

Keeping good, talented people is one of the most significant factors in a company's success. HR analytics is an important area for applying big data analysis techniques to human resources. It provides organizational insight that enables effective management of employees, allowing management to reach their business goals quickly and efficiently. Job satisfaction and employee turnover analysis are the keys to HR analytics. Job review web services have been becoming popular. Because people exchange information about job satisfaction and turnover through these web services, useful information about HR Analytics is accumulated on the job review web sites. In this paper, we identified factors of employee retention by analyzing a Job Satisfaction/Retention group, and the factors of employee turnover by analyzing a Job Unsatisfaction/Turnover group. In order to do this, we first classified employees according to whether their self-reported job satisfaction or turnover was true. We collected and analyzed data from Jobplanet, a popular job review site. Through dominance analysis and LDA topic modeling, we found major factors, topics, and keywords of the classified groups by IT, service, and manufacturing domains. Our approach is a novel model to apply the analysis of reviews and text mining to the HR domain, and it will be practically helpful for setting new strategies that improve job satisfaction.

• 한국정보통신학회논문지
• /
• 제21권2호
• /
• pp.423-428
• /
• 2017

인터넷과 스마트 기기의 사용량 증가로 인해 다양한 교육정보와 많은 양의 데이터가 생성되어 빠르게 확산되고 있다. 최근 이러닝 이용률이 증가하면서 발생하는 빅데이터를 활용하여 학습자들의 교육 성과와 교육 시스템의 효과성을 극대화 하는 것을 목표로 하는 교육 데이터 관련 연구 분야에 대한 관심이 높아지고 있으며 온라인에서 학습자들이 학습한 수많은 기록과 데이터들이 정보로 쌓이게 된다. 이에 본 논문에서는 이러닝 학습자들이 시스템에 남긴 수강 기록을 기반으로 학습자 현황에 대해 객관적으로 파악할 수 있도록 신경망 알고리즘인 Word2Vec을 적용하여 단어 간 유사도를 구하고 클러스터링 알고리즘을 이용하여 군집화 하였다. Word2vec을 이용하여 학습을 시키면 연관된 의미의 단어가 나타나게 되고 학습을 반복해 나가는 과정에서 점차 가까운 벡터를 지니게 된다. 또한 클러스터 알고리즘을 이용하여 명사, 동사, 형용사, 부사가 중심점에서 최소의 거리를 두고 같은 거리에 위치해 있음을 실험 검증하였다.

• 한국IT서비스학회지
• /
• 제17권1호
• /
• pp.17-32
• /
• 2018

The city image is considered one of important symbolic and important factors in selecting the travel destination. Many cities are trying to be an attractive and popular city to tourists through the construction of a good brand image by utilizing their representative characteristics. This study measures the city brand image by applying a big data analytic method. In addition, the big data measurement results were rearranged and analyzed to identify further detailed city images by utilizing several previous interpretation methods. Our study has chosen Dubai since this city has the diverse images due to its regional as well as economic characteristics. In particular, nowadays Dubai has been recognized as one of the most important touristic places in the Middle East region for its modern and innovative images in spite of the limitations of location, weather, religion, and even political issues of neighbor countries. Founded on a big data analysis rather than a questionnaire-based survey, the presented interpretation methods are evaluated to improve the understanding of Dubai's diverse city images. In addition, based on the results of this research, it is expected to have a practical impact on establishing the effective marketing strategies to build and implement the valuable city brand image.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.297-307
• /
• 2021

In the vibrant environment, documentation and managing systems are maintained autonomously through education foundations, book materials and libraries at the same time as information are not voluntarily accessible in a centralized location. At the moment Libraries are providing online resources and services for education activities. Moreover, libraries are applying outlets of social media such as Facebook as well as Instagrams to preview their services and procedures. Librarians with the assistance of promising tools and technology like analytics software are capable to accumulate more online information, analyse them for incorporating worth to their services. Thus Libraries can employ big data to construct enhanced decisions concerning collection developments, updating public spaces and tracking the purpose of library book materials. Big data is being produced due to library digitations and this has forced restrictions to academicians, researchers and policy creator's efforts in enhancing the quality and effectiveness. Accordingly, helping the library clients with research articles and book materials that are in line with the users interest is a big challenge and dispute based on Taibah university in Saudi Arabia. The issues of this domain brings the numerous sources of data from various institutions and sources into single place in real time which can be time consuming. The most important aim is to reduce the time that lapses among the authentic book reading and searching the specific study material.

• 사물인터넷융복합논문지
• /
• 제8권3호
• /
• pp.69-74
• /
• 2022

빅데이터 관련 분석 기법에서 처방적 분석 방법론은 적극적인 학습이 양질의 학습 데이터를 확보함으로써 수동적인 학습모델의 성능을 개선하고, 해당 시스템을 최적화하여 성능의 극대화를 통해 처리 프로세싱 과정을 다루며 판단의 근거가 되는 이유를 제시하고 있다. 그리고 범주 정보가 없는 데이터의 경우 기계가 이를 분석하여 애매한 것과 경계지점에 놓인 것들을 찾아내 수동으로 판단하게 하여 값비싼 범주 데이터를 매우 효과적으로 구축하는 방식이다. 연구자 역량을 강화하기 위하여 연구자의 연구 분야, 연구 성향, 연구 활동정보 등을 수집하여 데이터가 가진 가치를 확장하기 위해 데이터 전처리 후 실행 시점의 상황 예측하고 실행 가능한 대안 도출을 통해 상황 변동에 따른 대안 유효성 검토 등 처방적 분석을 통하여 연구자 맞춤형 연구정보 서비스를 제공한다.

• 경영정보학연구
• /
• 제25권1호
• /
• pp.27-46
• /
• 2023

최근에는 외식 산업의 발달과 레스토랑 수요의 증가로 인해 레스토랑 추천 시스템 연구가 활발하게 제안되고 있다. 기존 레스토랑 추천 시스템 연구는 정량적인 평점 정보 또는 온라인 리뷰의 감성분석을 통해 소비자의 선호도 정보를 추출하였는데 이는 소비자의 의미론적 선호도 정보는 반영하지 못한다는 한계가 존재한다. 또한, 레스토랑이 포함하는 세부적인 속성을 반영한 추천 시스템 연구는 부족한 실정이다. 이를 해결하기 위해 본 연구에서는 소비자의 선호도와 레스토랑 속성 간의 상호작용을 효과적으로 학습할 수 있는 딥러닝 기반 모델을 제안하였다. 먼저, 합성곱 신경망을 온라인 리뷰에 적용하여 소비자의 의미론적 선호도 정보를 추출했고, 레스토랑 정보에 임베딩 기법을 적용하여 레스토랑의 세부적인 속성을 추출했다. 최종적으로 요소별 연산을 통해 소비자 선호도와 레스토랑 속성 간의 상호작용을 학습하여 소비자의 선호도 평점을 예측했다. 본 연구에서 제안한 모델의 추천 성능을 평가하기 위해 Yelp.com의 온라인 리뷰를 사용한 실험 결과, 기존 연구의 다양한 모델과 비교했을때 본 연구의 제안 모델이 우수한 추천 성능을 보이는 것을 확인하였다. 본 연구는 레스토랑 산업의 빅데이터를 활용한 맞춤형 레스토랑 추천 시스템을 제안함으로써 레스토랑 연구 분야와 온라인 서비스 제공자에게 학술적 및 실무적 측면에서 다양한 시사점을 제공할 수 있을 것으로 기대한다.

• 무역학회지
• /
• 제47권3호
• /
• pp.57-73
• /
• 2022

The process and change of convergence in the economy and industry with the development of digital technology and combining with new technologies is called Digital Transformation. Specifically, it refers to innovating existing businesses and services by utilizing information and communication technologies such as big data analysis, Internet of Things, cloud computing, and artificial intelligence. Digital transformation is changing the shape of business and has a wide impact on businesses and consumers in all industries. Among them, the big data and analytics market is emerging as one of the most important growth drivers of digital transformation. Integrating intelligent data into an existing business is one of the key tasks of digital transformation, and it is important to collect and monitor data and learn from the collected data in order to efficiently operate a data-based business. In developed countries overseas, research on new business models using various data accumulated at the level of government and private companies is being actively conducted. However, although the trade and import/export data collected in the domestic public sector is being accumulated in various types and ranges, the establishment of an analysis and utilization model is still in its infancy. Currently, we are living in an era of massive amounts of big data. We intend to discuss the value of trade big data possessed from the past to the present, and suggest a strategy to activate trade big data for trade digital transformation and a new direction for future trade big data research.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.721-727
• /
• 2022

Construction safety remains an ongoing concern, and project managers have been increasingly forced to cope with myriad uncertainties related to human operations on construction sites and the lack of a skilled workforce in hazardous circumstances. Various construction fatality monitoring systems have been widely proposed as alternatives to overcome these difficulties and to improve safety management performance. In this study, we propose an intelligent, automatic control system that can proactively protect workers using both the analysis of big data of past safety accidents, as well as the real-time detection of worker non-compliance in using personal protective equipment (PPE) on a construction site. These data are obtained using computer vision technology and data analytics, which are integrated and reinforced by lessons learned from the analysis of big data of safety accidents that occurred in the last 10 years. The system offers data-informed recommendations for high-risk workers, and proactively eliminates the possibility of safety accidents. As an illustrative case, we selected a pilot project and applied the proposed system to workers in uncontrolled environments. Decreases in workers PPE non-compliance rates, improvements in variable compliance rates, reductions in severe fatalities through guidelines that are customized according to the worker, and accelerations in safety performance achievements are expected.

• 디지털융복합연구
• /
• 제11권11호
• /
• pp.143-153
• /
• 2013

빅데이터는 막대한 경제적 기회뿐만 아니라 공적 가치를 낳을 것으로 예상된다. 하지만 공공기관은 물론 민간기업의 빅데이터 사용은 프라이버시 침해에 대한 우려를 지속적으로 제기하고 있다. 행위패턴의 프라이버시 등 기존에는 없었던 새로운 위험을 유발함으로써 빅데이터는 프라이버시에 대한 기존 논의의 틀을 와해시킬 우려가 크다는 것이다. 반면, 빅데이터는 쿠키 등 행위추적에 근거한 개인정보의 부작용을 불식시키는 대안으로 인식되기도 한다. 본 논문은 빅데이터가 행위정보를 기반으로 하는 개인정보와는 어떻게 다른지를 밝히는데 초점을 둔다. 나아가, 개인정보로부터 파행되는 기존의 프라이버시 문제를 해결하기 위해 빅데이터에 대한 정책이 어떠한 대안을 가질 수 있는지도 제시할 것이다.