• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• 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.

• 대한공간정보학회지
• /
• 제24권1호
• /
• pp.89-98
• /
• 2016

본 연구에서는 축척과 갱신 주기가 상이한 이종의 공간 데이터 셋을 융합하기 위하여 사용자의 개입을 최소화하면서 다대다 관계에도 적용이 가능한 기하학적 방법론 기반의 면 객체 자동 매칭 방법을 제안하였다. 이를 위하여 첫째, 포함함수가 0.4 이상인 객체(노드)는 인접행렬에서 에지로 연결되었고, 이들 인접행렬의 곱을 반복적으로 수행하여 다대다 관계를 포함하는 후보 매칭 쌍을 선정하였다. 다대다 관계인 면 객체들은 알고리즘으로 생성된 convex hull로 단일 면 객체로 변환하였다. 기하학적 매칭을 위하여, 매칭 기준을 설정하고, 이들을 유사도 함수를 이용하여 유사도를 계산하였다. 다음으로 변환된 유사도와 CRITIC 방법으로 도출된 가중치를 선형 조합하여 형상 유사도를 계산하였다. 마지막으로 훈련자료에서 모든 가중치에 대한 정확도와 재현율을 나타낸 PR 곡선의 교차점인 EER로 임계값을 선정하고, 이 임계값을 기준으로 매칭 유무를 판별하였다. 제안된 방법을 수치지도와 도로명 주소기본도에 적용한 결과, 일부 다대다 관계에서 잘못 매칭되는 경우를 시각적으로 확인할 수 있었으나, 통계적 평가에서 정확도, 재현율, F-measure가 각각 0.951, 0.906, 0.928로 높게 나타났다. 이는 제안된 방법으로 이종의 공간 데이터 셋을 자동으로 매칭하는데 그 정확도가 높음을 의미한다. 그러나 일부 오류가 발생한 다대다 관계인 후보 매칭 쌍을 정확하게 정량화하기 위해서 포함함수나 매칭 기준에 대한 연구가 진행되어야 할 것이다.

• 한국응용곤충학회지
• /
• 제31권3호
• /
• pp.205-240
• /
• 1992

In reality, it is a green revolution of the entire agricultural matrix in Korea that integrated pest control plays an important role in the possible breakthrough in rice self-sufficiency. In paddy agroecosystem as man-modified environment, rice is newly established every year by transplantation under diverse water regimes which affect a microclimate. Standing water benefits rice by regulating the microclimate, but it favors the multiplication of certain pets through the amelioration of the microclimate. Further, the introduction of high yielding varieties with the changing of cultural practices results in changing occurrence pattern of certain pests. In general, japonica type varieties lack genes resistant to most of the important pests and insect-borne virus diseases, whereas indica type possesses more genes conferring varietal resistance. Thus, this differences among indica type, form the background of different approaches to pest management. The changes in rice cultivation such as double cropping, growing high-yielding varieties requiring heavy fertilization, earlier transplanting, intensvie-spacing transplanting, and intensive pesticide use as a consequence of the adoption of improves rice production technology, have intensified the pest problems rather than reduced them. The cultivation of resistant varieties are highly effective to the pest, their long term stability is threathened because of the development of new biotypes which can detroy these varieties. So far, three biotypes of N. lugens are reported in Korea. Since each resistant variety is expected to maintain several years the sequential release of another new variety with a different gene at intervals is practised as a gene rotation program. Another approach, breeding multilines that have more than two genes for resistance in a variety are successfully demonstrated. The average annual rice losses during the last 15 years of 1977-’91 are 9.3% due to insect pests without chemical control undertaken, wehreas there is a average 2.4% despite farmers’insecticide application at the same period. In other words, the average annual losses are prvented by 6.9% when chemical control is properly employed. However, the continuous use of a same group of insecticides is followed by the development of pest resistance. Resistant development of C. suppressalis, L. striatellus and N. cincticeps is observed to organophosphorous insecticides by the mid-1960s, and to carbamates by the early 1970s in various parts of the country. Thus, it is apparent that a scheduled chemical control for rice production systems becomes uneconomical and that a reduction in energy input without impairing the rice yield, is necessarily improved through the implementation of integrated pest management systems. Nationwide pest forecasting system conducted by the government organization is a unique network of investigation for purpose of making pest control timely in terms of economic thresholds. A wise plant protection is expected to establish pest management systems in appropriate integration of resistant varieties, biological agents, cultural practices and other measures in harmony with minimizing use of chemical applications as a last weapon relying on economic thresholds.

• 한국전자파학회논문지
• /
• 제19권2호
• /
• pp.121-129
• /
• 2008

본 논문에서는 FMM(Fast Multipole Method)을 적용하여 평면형 다층 구조인 마이크로스트립 프랙탈 안테나 구조에 대한 고속 해석을 구현하였다. 우선 FMM 알고리즘에 이용되는 적분식인 MPIE(Mixed Potential Integral Equation)을 풀기 위해서 실수축 적 분 방법(RAIM: Real-Axis Integration Method)으로부터 정확한 공간 영역 그린함수를 구한다. 구해진 그린함수를 MoM(Method of Moment)을 이용하여 계산할 경우, 연산과 메모리 요구량 $O(N^2)$이 소요되는데, 이를 거대 구조의 해석에 대해 적용할 때나 높은 정확성을 위한 셀(미지수 N) 수의 증가하는 경우 계산량이 기하급수적으로 증가하여 구조 해석에 문제가 된다. FMM은 이와 같은 연산과 메모리 요구량의 문제점을 해결하기 위하여 개발되었다. FMM은 그린함수의 가법 정리(addition theorem)를 이용하여 행렬-벡터 곱의 복잡성을 줄여 연산과 메모리 요구량을 $O(N^{1.5})$으로 줄인다. 시어핀스키(Sierpinski) 프랙탈 안테나의 구조에 대해 MoM과 FMM를 적용, 상용 툴과 계산 결과의 정확성, 계산 시 메모리 크기, 해석 시간 등을 비교하여 효율성을 보여주었다.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제6권3호
• /
• pp.105-112
• /
• 2017

PCI Express는 고속, 저전력 등의 특성으로 인하여 프로세서와 주변 I/O 장치들을 연결하는 업계 표준의 버스 기술이다. PCI Express는 최근 고성능 컴퓨터나 클러스터/클라우드 컴퓨팅 등의 분야에서 시스템 인터커넥션 네트워크로서 그 활용가능성을 검증하고 있는 추세이다. PCI Express가 시스템 인터커넥션 네트워크로서 활용가능하게 된 계기는 PCI Express에 NTB(non-transparent bridge) 기술이 도입되면서부터이다. NTB 기술은 물리적으로 두 PCI Express subsystem을 연결가능하도록 하지만, 필요할 경우 논리적인 격리(isolation)를 제공하는 특징이 있다. 또한, PGAS(partitioned global address space)와 같은 공유 주소 공간(shared address space) 프로그래밍 모델은 최근 멀티코어 프로세서의 보편화로 인하여 병렬컴퓨팅 프레임워크로 각광받고 있다. 따라서, 본 논문에서는 차세대 병렬컴퓨팅 플랫폼을 위하여 PCI Express 환경에서 OpenSHMEM을 구현하기 위한 초기 OpenSHMEM API를 설계 및 구현하였다. 본 연구에서 구현한 15가지 OpenSHMEM API의 정확성을 검증하기 위해서 Github의 openshmem-example 벤치마크의 수행을 통하여 확인하였다. 현재 시중에서는 PCI Express 기반 인터커넥션 네트워크는 가격이 매우 비싸고 아직 일반인이 사용하기 용이하도록 NIC형태로 널리 보급되지 않은 실정이다. 이러한 기술개발 초기단계에서 본 연구는 PCI Express 기반 interconnection network를 RDK(evaluation board) 수준에서 실제로 동작하는 실험환경을 구축하고, 여기에 추가로 최근 각광받는 OpenSHMEM software stack를 자체적으로 구현하였다는 데 의의가 있다.

• 대한핵의학회지
• /
• 제30권3호
• /
• pp.332-337
• /
• 1996

기저막 성분인 type IV collagen을 분해하는 type IV collagenase의 농도와 종양의 전이사이에 상관관계가 있다는 동물 실험보고가 있다. 저자들은 유방암환자의 종양조직내 type IV collagenase의 농도와 골스캔상 골전이 소견과 비교하여 그 의의를 알아보고자 하였다. 원발성 및 전이성 유방암 환자의 종양조직에서 92kDa 및 72kDa type IV collagenase에 대한 면역조직화학염색을 각각 57명, 56명 환자에서 시행하여 각 효소 농도를 평가하고 골스캔상 골전이 소견을 관찰하고 등급을 부여하였다. 면역조직화학적으로 평가한 각 효소의 농도는 원발성 유방암과 전이성 유방암 환자 사이에 큰 차이가 있었으며, 골스캔 소견과 효소농도를 상호 비교한 결과 각 효소의 농도가 170이하일 경우에는 골스캔상 활동적인 골전이 소견을 볼 수 없었으나 효소의 농도가 200이상일 경우 골스캔 소견은 정상에서 골전이 소견까지 매우 다양하게 분포하였다. 결론적으로, 면역 조직화학적으로 측정한 92kDa 및 72kDa collagenase의 농도가 170이하일 때는 골스캔상 대부분 정상소견을 보여 골전이의 확률이 낮았다. 반면에 각 효소치의 농도가 200이상일 경우에는 골전이의 확진과 병소의 위치를 확인하고 추적검사를 위해서는 골스캔이 필요하다고 사료된다.

• Asia pacific journal of information systems
• /
• 제21권2호
• /
• pp.89-116
• /
• 2011

In collaborative tagging systems such as Delicious.com and Flickr.com, users assign keywords or tags to their uploaded resources, such as bookmarks and pictures, for their future use or sharing purposes. The collection of resources and tags generated by a user is called a personomy, and the collection of all personomies constitutes the folksonomy. The most significant need of the folksonomy users Is to efficiently find useful resources or experts on specific topics. An excellent ranking algorithm would assign higher ranking to more useful resources or experts. What resources are considered useful In a folksonomic system? Does a standard superior to frequency or freshness exist? The resource recommended by more users with mere expertise should be worthy of attention. This ranking paradigm can be implemented through a graph-based ranking algorithm. Two well-known representatives of such a paradigm are Page Rank by Google and HITS(Hypertext Induced Topic Selection) by Kleinberg. Both Page Rank and HITS assign a higher evaluation score to pages linked to more higher-scored pages. HITS differs from PageRank in that it utilizes two kinds of scores: authority and hub scores. The ranking objects of these pages are limited to Web pages, whereas the ranking objects of a folksonomic system are somewhat heterogeneous(i.e., users, resources, and tags). Therefore, uniform application of the voting notion of PageRank and HITS based on the links to a folksonomy would be unreasonable, In a folksonomic system, each link corresponding to a property can have an opposite direction, depending on whether the property is an active or a passive voice. The current research stems from the Idea that a graph-based ranking algorithm could be applied to the folksonomic system using the concept of mutual Interactions between entitles, rather than the voting notion of PageRank or HITS. The concept of mutual interactions, proposed for ranking the Semantic Web resources, enables the calculation of importance scores of various resources unaffected by link directions. The weights of a property representing the mutual interaction between classes are assigned depending on the relative significance of the property to the resource importance of each class. This class-oriented approach is based on the fact that, in the Semantic Web, there are many heterogeneous classes; thus, applying a different appraisal standard for each class is more reasonable. This is similar to the evaluation method of humans, where different items are assigned specific weights, which are then summed up to determine the weighted average. We can check for missing properties more easily with this approach than with other predicate-oriented approaches. A user of a tagging system usually assigns more than one tags to the same resource, and there can be more than one tags with the same subjectivity and objectivity. In the case that many users assign similar tags to the same resource, grading the users differently depending on the assignment order becomes necessary. This idea comes from the studies in psychology wherein expertise involves the ability to select the most relevant information for achieving a goal. An expert should be someone who not only has a large collection of documents annotated with a particular tag, but also tends to add documents of high quality to his/her collections. Such documents are identified by the number, as well as the expertise, of users who have the same documents in their collections. In other words, there is a relationship of mutual reinforcement between the expertise of a user and the quality of a document. In addition, there is a need to rank entities related more closely to a certain entity. Considering the property of social media that ensures the popularity of a topic is temporary, recent data should have more weight than old data. We propose a comprehensive folksonomy ranking framework in which all these considerations are dealt with and that can be easily customized to each folksonomy site for ranking purposes. To examine the validity of our ranking algorithm and show the mechanism of adjusting property, time, and expertise weights, we first use a dataset designed for analyzing the effect of each ranking factor independently. We then show the ranking results of a real folksonomy site, with the ranking factors combined. Because the ground truth of a given dataset is not known when it comes to ranking, we inject simulated data whose ranking results can be predicted into the real dataset and compare the ranking results of our algorithm with that of a previous HITS-based algorithm. Our semantic ranking algorithm based on the concept of mutual interaction seems to be preferable to the HITS-based algorithm as a flexible folksonomy ranking framework. Some concrete points of difference are as follows. First, with the time concept applied to the property weights, our algorithm shows superior performance in lowering the scores of older data and raising the scores of newer data. Second, applying the time concept to the expertise weights, as well as to the property weights, our algorithm controls the conflicting influence of expertise weights and enhances overall consistency of time-valued ranking. The expertise weights of the previous study can act as an obstacle to the time-valued ranking because the number of followers increases as time goes on. Third, many new properties and classes can be included in our framework. The previous HITS-based algorithm, based on the voting notion, loses ground in the situation where the domain consists of more than two classes, or where other important properties, such as "sent through twitter" or "registered as a friend," are added to the domain. Forth, there is a big difference in the calculation time and memory use between the two kinds of algorithms. While the matrix multiplication of two matrices, has to be executed twice for the previous HITS-based algorithm, this is unnecessary with our algorithm. In our ranking framework, various folksonomy ranking policies can be expressed with the ranking factors combined and our approach can work, even if the folksonomy site is not implemented with Semantic Web languages. Above all, the time weight proposed in this paper will be applicable to various domains, including social media, where time value is considered important.