• Title/Summary/Keyword: edge intelligence

Search Result 155, Processing Time 0.019 seconds

Major Class Recommendation System based on Deep learning using Network Analysis (네트워크 분석을 활용한 딥러닝 기반 전공과목 추천 시스템)

  • Lee, Jae Kyu;Park, Heesung;Kim, Wooju
    • Journal of Intelligence and Information Systems
    • /
    • v.27 no.3
    • /
    • pp.95-112
    • /
    • 2021
  • In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.

Design Evaluation Model Based on Consumer Values: Three-step Approach from Product Attributes, Perceived Attributes, to Consumer Values (소비자 가치기반 디자인 평가 모형: 제품 속성, 인지 속성, 소비자 가치의 3단계 접근)

  • Kim, Keon-Woo;Park, Do-Hyung
    • Journal of Intelligence and Information Systems
    • /
    • v.23 no.4
    • /
    • pp.57-76
    • /
    • 2017
  • Recently, consumer needs are diversifying as information technologies are evolving rapidly. A lot of IT devices such as smart phones and tablet PCs are launching following the trend of information technology. While IT devices focused on the technical advance and improvement a few years ago, the situation is changed now. There is no difference in functional aspects, so companies are trying to differentiate IT devices in terms of appearance design. Consumers also consider design as being a more important factor in the decision-making of smart phones. Smart phones have become a fashion items, revealing consumers' own characteristics and personality. As the design and appearance of the smartphone become important things, it is necessary to examine consumer values from the design and appearance of IT devices. Furthermore, it is crucial to clarify the mechanisms of consumers' design evaluation and develop the design evaluation model based on the mechanism. Since the influence of design gets continuously strong, various and many studies related to design were carried out. These studies can classify three main streams. The first stream focuses on the role of design from the perspective of marketing and communication. The second one is the studies to find out an effective and appealing design from the perspective of industrial design. The last one is to examine the consumer values created by a product design, which means consumers' perception or feeling when they look and feel it. These numerous studies somewhat have dealt with consumer values, but they do not include product attributes, or do not cover the whole process and mechanism from product attributes to consumer values. In this study, we try to develop the holistic design evaluation model based on consumer values based on three-step approach from product attributes, perceived attributes, to consumer values. Product attributes means the real and physical characteristics each smart phone has. They consist of bezel, length, width, thickness, weight and curvature. Perceived attributes are derived from consumers' perception on product attributes. We consider perceived size of device, perceived size of display, perceived thickness, perceived weight, perceived bezel (top - bottom / left - right side), perceived curvature of edge, perceived curvature of back side, gap of each part, perceived gloss and perceived screen ratio. They are factorized into six clusters named as 'Size,' 'Slimness,' 'No-Frame,' 'Roundness,' 'Screen Ratio,' and 'Looseness.' We conducted qualitative research to find out consumer values, which are categorized into two: look and feel values. We identified the values named as 'Silhouette,' 'Neatness,' 'Attractiveness,' 'Polishing,' 'Innovativeness,' 'Professionalism,' 'Intellectualness,' 'Individuality,' and 'Distinctiveness' in terms of look values. Also, we identifies 'Stability,' 'Comfortableness,' 'Grip,' 'Solidity,' 'Non-fragility,' and 'Smoothness' in terms of feel values. They are factorized into five key values: 'Sleek Value,' 'Professional Value,' 'Unique Value,' 'Comfortable Value,' and 'Solid Value.' Finally, we developed the holistic design evaluation model by analyzing each relationship from product attributes, perceived attributes, to consumer values. This study has several theoretical and practical contributions. First, we found consumer values in terms of design evaluation and implicit chain relationship from the objective and physical characteristics to the subjective and mental evaluation. That is, the model explains the mechanism of design evaluation in consumer minds. Second, we suggest a general design evaluation process from product attributes, perceived attributes to consumer values. It is an adaptable methodology not only smart phone but also other IT products. Practically, this model can support the decision-making when companies initiative new product development. It can help product designers focus on their capacities with limited resources. Moreover, if its model combined with machine learning collecting consumers' purchasing data, most preferred values, sales data, etc., it will be able to evolve intelligent design decision support system.

Current status and future of insect smart factory farm using ICT technology (ICT기술을 활용한 곤충스마트팩토리팜의 현황과 미래)

  • Seok, Young-Seek
    • Food Science and Industry
    • /
    • v.55 no.2
    • /
    • pp.188-202
    • /
    • 2022
  • In the insect industry, as the scope of application of insects is expanded from pet insects and natural enemies to feed, edible and medicinal insects, the demand for quality control of insect raw materials is increasing, and interest in securing the safety of insect products is increasing. In the process of expanding the industrial scale, controlling the temperature and humidity and air quality in the insect breeding room and preventing the spread of pathogens and other pollutants are important success factors. It requires a controlled environment under the operating system. European commercial insect breeding facilities have attracted considerable investor interest, and insect companies are building large-scale production facilities, which became possible after the EU approved the use of insect protein as feedstock for fish farming in July 2017. Other fields, such as food and medicine, have also accelerated the application of cutting-edge technology. In the future, the global insect industry will purchase eggs or small larvae from suppliers and a system that focuses on the larval fattening, i.e., production raw material, until the insects mature, and a system that handles the entire production process from egg laying, harvesting, and initial pre-treatment of larvae., increasingly subdivided into large-scale production systems that cover all stages of insect larvae production and further processing steps such as milling, fat removal and protein or fat fractionation. In Korea, research and development of insect smart factory farms using artificial intelligence and ICT is accelerating, so insects can be used as carbon-free materials in secondary industries such as natural plastics or natural molding materials as well as existing feed and food. A Korean-style customized breeding system for shortening the breeding period or enhancing functionality is expected to be developed soon.

A Study on Improvements on Legal Structure on Security of National Research and Development Projects (과학기술 및 학술 연구보고서 서비스 제공을 위한 국가연구개발사업 관련 법령 입법론 -저작권법상 공공저작물의 자유이용 제도와 연계를 중심으로-)

  • Kang, Sun Joon;Won, Yoo Hyung;Choi, San;Kim, Jun Huck;Kim, Seul Ki
    • Proceedings of the Korea Technology Innovation Society Conference
    • /
    • 2015.05a
    • /
    • pp.545-570
    • /
    • 2015
  • Korea is among the ten countries with the largest R&D budget and the highest R&D investment-to-GDP ratio, yet the subject of security and protection of R&D results remains relatively unexplored in the country. Countries have implemented in their legal systems measures to properly protect cutting-edge industrial technologies that would adversely affect national security and economy if leaked to other countries. While Korea has a generally stable legal framework as provided in the Regulation on the National R&D Program Management (the "Regulation") and the Act on Industrial Technology Protection, many difficulties follow in practice when determining details on security management and obligations and setting standards in carrying out national R&D projects. This paper proposes to modify and improve security level classification standards in the Regulation. The Regulation provides a dual security level decision-making system for R&D projects: the security level can be determined either by researcher or by the central agency in charge of the project. Unification of such a dual system can avoid unnecessary confusions. To prevent a leakage, it is crucial that research projects be carried out in compliance with their assigned security levels and standards and results be effectively managed. The paper examines from a practitioner's perspective relevant legal provisions on leakage of confidential R&D projects, infringement, injunction, punishment, attempt and conspiracy, dual liability, duty of report to the National Intelligence Service (the "NIS") of security management process and other security issues arising from national R&D projects, and manual drafting in case of a breach. The paper recommends to train security and technological experts such as industrial security experts to properly amend laws on security level classification standards and relevant technological contents. A quarterly policy development committee must also be set up by the NIS in cooperation with relevant organizations. The committee shall provide a project management manual that provides step-by-step guidance for organizations that carry out national R&D projects as a preventive measure against possible leakage. In the short term, the NIS National Industrial Security Center's duties should be expanded to incorporate national R&D projects' security. In the long term, a security task force must be set up to protect, support and manage the projects whose responsibilities should include research, policy development, PR and training of security-related issues. Through these means, a social consensus must be reached on the need for protecting national R&D projects. The most efficient way to implement these measures is to facilitate security training programs and meetings that provide opportunities for communication among industrial security experts and researchers. Furthermore, the Regulation's security provisions must be examined and improved.

  • PDF

Query-based Answer Extraction using Korean Dependency Parsing (의존 구문 분석을 이용한 질의 기반 정답 추출)

  • Lee, Dokyoung;Kim, Mintae;Kim, Wooju
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.3
    • /
    • pp.161-177
    • /
    • 2019
  • In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.