• Journal of the Korea Society for Simulation
• /
• v.3 no.2
• /
• pp.1-13
• /
• 1994

Deep reasoning procedures are model-based, inferring single or multiple causes and/or timing relations from the knowledge of behavior of component models and their causal structure. The overall goal of this paper is to develop an automated deep reasoning methodology that exploits deep knowledge of structure and behavior of a system. We have proceeded by building a software environment that uses such knowledge to reason from advanced symbolic simulation techniques introduced by Chi and Zeigler. Such reasoning system has been implemented and tested on several examples in the domain of performance evaluation, and event-based control.

• Journal of the Korean Society of Safety
• /
• v.20 no.3 s.71
• /
• pp.19-26
• /
• 2005

There are three reasoning method in fault diagnosis process. The shallow reasoning is based on the experiential knowledge and deep reasoning is based on physical model. Hybrid reasoning is mixing two type reasoning. This study describes about fault train embodiment of screw type air compressor that is used widely in industrial facilities by using various experimental method and shallow reasoning. We investigate macroscopic failure cause of air compressor through naked eye observation and then microscopic failure cause by various experimental method. We composed fault train with fault knowledge based on empirical data and scientific data that is acquired through several experiments. It is possible to analysis system reliability and failure rate with these fault train.

• Journal of KIISE
• /
• v.42 no.5
• /
• pp.601-608
• /
• 2015

In order to answer questions successfully on behalf of the human contestant in DeepQA environments such as 'Jeopardy!', the American quiz show, the computer needs to have the capability of fast temporal and spatial reasoning on a large-scale commonsense knowledge base. In this paper, we present a hybrid spatial reasoning algorithm, among various efficient spatial reasoning methods, for handling directional and topological relations. Our algorithm not only improves the query processing time while reducing unnecessary reasoning calculation, but also effectively deals with the change of spatial knowledge base, as it takes a hybrid method that combines forward and backward reasoning. Through experiments performed on the sample spatial knowledge base with the hybrid spatial reasoner of our algorithm, we demonstrated the high performance of our hybrid spatial reasoning algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.11
• /
• pp.46-57
• /
• 1998

Even though there are some studies on the deep drawing process and process planning, little study has been done on the methodology of process planning of secondary operations of deep drawing such as 'piercins'. In this paper, first, we systematized the methodology of the process planning of secondary operations on axisymmetric cup. Second we described the development of the expert system for their CAPP For these studies, we extracted the knowledge of their process planning from experts and analysed and systemized them. To develop the expert system, rule-based reasoning paradigm is used. The shape information of manufacturing features of secondary operations are manually input to the system through SUI. The process planning results are automatically connected to AutoCAD. We believe that the systematized process knowledge and the development of the expert system for its CAPP could give lots of aids to the associated field.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.3
• /
• pp.91-100
• /
• 2020

Unlike the existing Visual Question Answering(VQA) problems, the new Visual Commonsense Reasoning(VCR) problems require deep common sense reasoning for answering questions: recognizing specific relationship between two objects in the image, presenting the rationale of the answer. In this paper, we propose a novel deep neural network model, KG_VCR, for VCR problems. In addition to make use of visual relations and contextual information between objects extracted from input data (images, natural language questions, and response lists), the KG_VCR also utilizes commonsense knowledge embedding extracted from an external knowledge base called ConceptNet. Specifically the proposed model employs a Graph Convolutional Neural Network(GCN) module to obtain commonsense knowledge embedding from the retrieved ConceptNet knowledge graph. By conducting a series of experiments with the VCR benchmark dataset, we show that the proposed KG_VCR model outperforms both the state of the art(SOTA) VQA model and the R2C VCR model.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1992.04b
• /
• pp.82-90
• /
• 1992

본 논문은 어떤 시스템 (예를들면, 자동화된 제조시스템)에서 발생하는 징후에 대한 고장진단 모델을 개발하는 것이 목적이다. 이 모델은 계층적 시스템이론(Theory of Hierarchical Systems)과 인공지능의 혼성추론기법(Hybrid Reasoning Approach)을 사용한다. 일반적으로, 시스템은 스트라타(strata)와 에셸론(echelons)으로써 표현될 수 있으며, 한편 시스템에 대한 지식은 근본지식 (deep knowledge)과 경험지식(shallow knowledge)으로 나뉘어 질 수 있다. 이 모델에서의 고장진단에 대한 추론전략은 근본지식베이스에 의한 근본적 추론을 먼저하고 그 다음에 경험지식베이스에 의한 경험적 추론을 하는 혼성추론기법이다.

• Journal of The Korean Association For Science Education
• /
• v.29 no.2
• /
• pp.253-266
• /
• 2009

This study was focused on analyzing students' informal reasoning patterns and their considerations in decision-making on socioscientific issues. This study involved 20 undergraduate students (10 biology majors and 10 non-biology majors) and showed how the two groups responded on socioscientific issues. Semi-structured interviews were conducted twice respectively based on six scenarios of gene therapy and human cloning. The result showed 93% of the total number of participants' decisions were made by rationalistic reasoning, whereas emotional reasoning was 49%, and intuitive reasoning was 27%. Students usually used two or three informal reasoning patterns together. Most of the students took more consideration on social factors. Some perceived ethical and moral implications of the issues, but they did not consider them seriously. They made their decisions depending on their own values, etc. 65% of the participants got their information on socioscientific issues from the mass media. Biology majors hardly used intuitive reasoning compared to non-biology majors. The Biology major group took into deep considerations on socioscientific issues while the non-biology major group seemed to interpret the given scenarios simply. This implied that the content knowledge was a significant factor of their decision-making. Therefore, it is necessary to develop proper science courses for non-major students to improve their decision-making on socioscientific issues. So, when we develop educational materials or programs, we should consider students' reasoning patterns, their considerations in decision-making, and their content knowledge. And because the mass media has the potential to play a key role for an effective education, we need to make a plan to make a practical application.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4345-4363
• /
• 2021

Deep Learning as a Service (DLaaS), utilizing the cloud-based deep neural network models to provide customer prediction services, has been widely deployed on mobile cloud computing (MCC). Such services raise privacy concerns since customers need to send private data to untrusted service providers. In this paper, we devote ourselves to building an efficient protocol to classify users' images using the convolutional neural network (CNN) model trained and held by the server, while keeping both parties' data secure. Most previous solutions commonly employ homomorphic encryption schemes based on Ring Learning with Errors (RLWE) hardness or two-party secure computation protocols to achieve it. However, they have limitations on large communication overheads and costs in MCC. To address this issue, we present LeHE4SCNN, a scalable privacy-preserving and communication-efficient framework for CNN-based DLaaS. Firstly, we design a novel low-expansion rate homomorphic encryption scheme with packing and unpacking methods (LeHE). It supports fast homomorphic operations such as vector-matrix multiplication and addition. Then we propose a secure prediction framework for CNN. It employs the LeHE scheme to compute linear layers while exploiting the data shuffling technique to perform non-linear operations. Finally, we implement and evaluate LeHE4SCNN with various CNN models on a real-world dataset. Experimental results demonstrate the effectiveness and superiority of the LeHE4SCNN framework in terms of response time, usage cost, and communication overhead compared to the state-of-the-art methods in the mobile cloud computing environment.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Journal of Intelligence and Information Systems
• /
• v.2 no.2
• /
• pp.55-68
• /
• 1996

인공 지능의 주요 분야 중 하나의 전문가시스템 기술은 현재 산업현장에서 여러 가지 분야의 문제해결에 이용되고 있다. 본 논문은 축 대칭 원통형 제품의 deep drawing 공정 설계를 위한 전문가시스템 DOX(Deep drawing Opertion eXpert)의 개발에 관한 것이다. 시스템의 입력은 원통형 제품의 형상 정보와 재질 정보이며 자동 인식 또는 수동입력의 방법으로 입력된다. 시스템은 이러한 정보를 받아들여 deep drawing 공정설계에 필요한 다수의 요소들을 결정하며, 최종결과로서 process layout 도면을 CAD 시스템에서 자동 출력한다. 개발된 전문가시스템의 지식베이스는 산업 분야 전문가의 전문 지식과 경험지식을 획득, 분석하여 구성하였으며, 추론 전략으로는 규칙기반추론(rule-based reasoning)을 이용하였다.