• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.

• The KIPS Transactions:PartD
• /
• v.13D no.4 s.107
• /
• pp.513-524
• /
• 2006

Normalization transform is very useful for finding the overall trend of the time-series data since it enables finding sequences with similar fluctuation patterns. The previous subsequence matching method with normalization transform, however, would incur index overhead both in storage space and in update maintenance since it should build multiple indexes for supporting arbitrary length of query sequences. To solve this problem, we propose a single index approach for the normalization transformed subsequence matching that supports arbitrary length of query sequences. For the single index approach, we first provide the notion of inclusion-normalization transform by generalizing the original definition of normalization transform. The inclusion-normalization transform normalizes a window by using the mean and the standard deviation of a subsequence that includes the window. Next, we formally prove correctness of the proposed method that uses the inclusion-normalization transform for the normalization transformed subsequence matching. We then propose subsequence matching and index building algorithms to implement the proposed method. Experimental results for real stock data show that our method improves performance by up to $2.5{\sim}2.8$ times over the previous method. Our approach has an additional advantage of being generalized to support many sorts of other transforms as well as normalization transform. Therefore, we believe our work will be widely used in many sorts of transform-based subsequence matching methods.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.17 no.3
• /
• pp.207-216
• /
• 2015

The study was conducted to determine the effects of forest restoration methods and stand structure on solar radiation, air temperature, relative humidity, soil temperature, and soil water content, based on volume, in forest stand after forest fire. The changes of the micro-climate elements in naturally and artificially restored forest after forest fire were measured in Goseong and Samcheok, Gangwon province. Pinus spp. were commonly appeared in ridges, barren lands or planted areas of the study sites while the other areas were dominated by Quercus spp. In the early stage, trees in the naturally regenerated site grow better than the trees in artificially rehabilitated site. However, the growth ratio rapidly decreased by time passed in natural regeneration area. The environmental conditions (solar radiation, air temperature, relative humidity, soil temperature and soil water content) were significantly different by the regions and the methods (p<.05). However, the coefficients of variations of the environmental conditions were not significantly different at 95% confidence level. As the coverage and tree height in crown layer increased, the relative humidity and soil water content were increased while the temperature and solar radiation were decreased. Especially, the relative humidity, solar radiation, and soil water content were clearly affected by the tree height and coverage ratio ($R^2$ means from 0.628 to 0.924). Even though the data should have collected at least more than 5 years in meteorological analysis, the two year results show some clear relationship between forest structure and microclimate elements.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1261-1269
• /
• 1999

다층 퍼셉트론은 다양한 응용 분야에 성공적으로 적용되고 있는 대표적인 신경회로망 모델이다. 그러나 다층 퍼셉트론의 학습에서 나타나는 플라토에 기인한 느린 학습 속도와 지역 극소는 실제 응용문제에 적용함에 있어서 가장 큰 문제로 지적되어왔다. 이 문제를 해결하기 위해 여러 가지 다양한 학습알고리즘들이 개발되어 왔으나, 계산의 비효율성으로 인해 실제 문제에는 적용하기 힘든 예가 많은 등, 현재까지 만족할 만한 해결책은 제시되지 못하고 있다. 본 논문에서는 다층퍼셉트론의 베이시스 함수로 사용되는 시그모이드 함수를 보다 일반화된 형태로 정의하여 사용함으로써 학습에 있어서의 플라토를 완화하고, 지역극소에 빠지는 것을 줄이는 접근방법을 소개한다. 본 방법은 기존의 변형된 가중치 수정식을 사용한 학습 속도 향상의 방법들과는 다른 접근 방법을 택함으로써 기존의 방법들과 함께 사용하는 것이 가능하다는 특징을 갖고 있다. 제안하는 방법의 성능을 확인하기 위하여 간단한 패턴 인식 문제들에의 적용 실험 및 기존의 학습 속도 향상 방법을 함께 사용하여 시계열 예측 문제에 적용한 실험을 수행하였고, 그 결과로부터 제안안 방법의 효율성을 확인할 수 있었다. Abstract A multilayer perceptron is the most well-known neural network model which has been successfully applied to various fields of application. Its slow learning caused by plateau and local minima of gradient descent learning, however, have been pointed as the biggest problems in its practical use. To solve such a problem, a number of researches on learning algorithms have been conducted, but it can be said that none of satisfying solutions have been presented so far because the problems such as computational inefficiency have still been existed in these algorithms. In this paper, we propose a new learning approach to minimize the effect of plateau and reduce the possibility of getting trapped in local minima by generalizing the sigmoidal function which is used as the basis function of a multilayer perceptron. Adapting a new approach that differs from the conventional methods with revised updating equation, the proposed method can be used together with the existing methods to improve the learning performance. We conducted some experiments to test the proposed method on simple problems of pattern recognition and a problem of time series prediction, compared our results with the results of the existing methods, and confirmed that the proposed method is efficient enough to apply to the real problems.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.463-472
• /
• 2000

In this paper, we consider the problem of realizing associative memories via cellular neural network(CNN). After introducing qualitative properties of the CNN model, we formulate the synthesis of CNN that can store given binary vectors with optimal performance as a constrained optimization problem. Next, we observe that this problem's constraints can be transformed into simple inequalities involving linear matrix inequalities(LMIs). Finally, we reformulate the synthesis problem as a generalized eigenvalue problem(GEVP), which can be efficiently solved by recently developed interior point methods. Proposed method can be applied to both space varying template CNNs and space-invariant template CNNs. The validity of the proposed approach is illustrated by design examples.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.08a
• /
• pp.310-310
• /
• 2012

최근 전자산업의 발달에 따른 전자제품의 소형화 및 고기능화 요구에 대응하기 위하여 저항(resistor), 커패시터(capacitor), IC (integrated circuit) 등의 수동소자를 개별 칩(discrete chip) 형태로 형성하여 기판의 표면에 실장하는 기술이 일반화되고 있다. 그러나, 수동 소자의 내장 기술은 기판의 패턴 밀도의 급격한 향상과 더불어 수동소자의 내장 공간도 협소해지는 문제점이 있다. 상기의 문제점을 해결하기 위해 개별 칩 형태의 내장형 저항체를 박막 형태의 내장 저항체를 구현하는 기술의 개발이 최근 주목을 받고 있다. 박막 저항체는 기존의 권선저항 및 후막저항과 비교하여 정밀한 온도저항계수를 가지며 이동통신에 적용시 고주파 영역(GHz)에서의 안정성과 주파수 특성이 좋다는 장점들을 가지고 있다. 박막 저항 물질로는 높은 경도와 우수한 열적 안정성을 가지고 있는 TaN (tantalum nitride)이 주로 사용되고 있다. 일반적으로, TaN 박막은 스퍼터링을 사용하며 제조되며 TaN 박막의 성질은 탄탈륨과 질소의 화학정량비, 박막의 결함 정도, 또는 공정압력 및 증착 온도, 플라즈마 파워 등과 같은 공정조건 등의 변화에 민감하게 변화하므로, TaN 박막의 다양한 연구가 더 필요한 실정이다. 본 연구에서는 반응성 마크네트론 스퍼터링을 사용하여 TaN 박막을 Si 기판 위에 증착하였고 TaN 박막의 원하는 특성을 제어할 수 있도록 질소 분압과 total gas volume을 조절하여 공정을 최적화하는 연구를 진행하였다. 또한 tensile pull-off 방법을 이용하여 TaN 박막의 부착강도를 평가하였고, 온도 사이클 및 고온고습 환경에 노출된 TaN 박막들의 열화 특성들에 대하여 연구하였다.

• Journal of the Korean Chemical Society
• /
• v.61 no.4
• /
• pp.191-196
• /
• 2017

One-phase method to prevent the initial formation of Ag(I) thiolate layered materal from the mixture of $AgNO_3$ and thiols was previously developed to generate TP (Thiolate-Protected)-nanosilver. In this modified method, $AgNO_3$ is added to the mixtures of $NaBH_4$ and thiols in ethanol. This method was so successful that it was applied to synthesize TP-nanogold and nanoplatinum. The synthesis and characterization of these nanoparticles by ultraviolet-visible (UV-vis) absorption spectra, transmission electron microscopy (TEM) pictures, X-ray powder differaction (XRD) patterns and infrared(IR) spectra are described. The results show that colloidal nanoparticles are spherical or oval shape and the mean sizes for TP-nanogold and nanoplatinum are about 3~7 nm and below 2 nm, respectively. The conformation of polymethylene [$-(CH_2)_7-$] sequence in octanethiolate attached to nanogold was elucidated as trans.

• Korean Chemical Engineering Research
• /
• v.49 no.3
• /
• pp.352-356
• /
• 2011

In this paper, we prepared new type of hydrophilic block copolymers that exhibit the long-ranged lateral ordering in thin film. It was previously demonstrated that poly(ethyleneoxide-b-styrene) and poly(ethyleneoxide-b-metharylate-b-styrene) block copolymer thin films have a high degree of lateral ordering after solvent annealing process. In these cases, the relative humidity plays an important role in long-ranged lateral ordering. However, the origin of the humidity effect on the orders of these hydrophilic block copolymers is not fully understood. To investigate the effect of the humidity further, we prepared other hydrophilic poly(N,N-dimethylacrylamide-b-styrene)(PDMA-b-PS) block copolymers via RAFT polymerization. As with PEO-containing block copolymers, PDMA-b-PS block copolymers exhibit the long-ranged lateral ordering after solvent annealing process.

• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1396-1403
• /
• 2016

In streaming data analysis where underlying data distribution may be changed or the concept of interest can drift with the progress of time, the ability to adapt to concept drift can be very powerful especially in the process of incremental learning. In this paper, we develop a general framework for an adaptive incremental classifier on data stream with concept drift. A distribution, representing the performance pattern of a classifier, is constructed by utilizing the distance between the confidence score of a classifier and a class indicator vector. A hypothesis test is then performed for concept drift detection. Based on the estimated p-value, the weight of outdated data is set automatically in updating the classifier. We apply our proposed method for two types of linear discriminant classifiers. The experimental results on streaming data with concept drift demonstrate that the proposed adaptive incremental learning method improves the prediction accuracy of an incremental classifier highly.

• Journal of Educational Research in Mathematics
• /
• v.16 no.1
• /
• pp.79-94
• /
• 2006

The purpose of this study is to find out the characteristics of the types(levels) of justification which are appeared by elementary mathematically gifted students in solving the tasks of plane division and spatial division. Selecting 10 fifth or sixth graders from 3 different groups in terms of mathematical capability and letting them generalize and justify some patterns. This study analyzed their responses and identified their differences in justification strategy. This study shows that mathematically gifted students apply different types of justification, such as inductive, generic or formal justification. Upper and lower groups lie in the different justification types(levels). And mathematically gifted children, especially in the upper group, have the strong desire to justify the rules which they discover, requiring a deductive thinking by themselves. They try to think both deductively and logically, and consider this kind of thought very significant.