• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• 제4권4호
• /
• pp.159-176
• /
• 2023

The conservation of the raccoon dog (Nyctereutes procyonoides) in South Korea requires the protection and preservation of natural habitats while additionally ensuring coexistence with human activities. Applying habitat map modeling techniques provides information regarding the distributional patterns of raccoon dogs and assists in the development of future conservation strategies. The purpose of this study is to generate potential habitat distribution maps for the raccoon dog in South Korea using geospatial technology-based models. These models include the frequency ratio (FR) as a bivariate statistical approach, the group method of data handling (GMDH) as a machine learning algorithm, and convolutional neural network (CNN) and long short-term memory (LSTM) as deep learning algorithms. Moreover, the imperialist competitive algorithm (ICA) is used to fine-tune the hyperparameters of the machine learning and deep learning models. Moreover, there are 14 habitat characteristics used for developing the models: elevation, slope, valley depth, topographic wetness index, terrain roughness index, slope height, surface area, slope length and steepness factor (LS factor), normalized difference vegetation index, normalized difference water index, distance to drainage, distance to roads, drainage density, and morphometric features. The accuracy of prediction is evaluated using the area under the receiver operating characteristic curve. The results indicate comparable performances of all models. However, the CNN demonstrates superior capacity for prediction, achieving accuracies of 76.3% and 75.7% for the training and validation processes, respectively. The maps of potential habitat distribution are generated for five different levels of potentiality: very low, low, moderate, high, and very high.

• 동의신경정신과학회지
• /
• 제22권4호
• /
• pp.185-199
• /
• 2011

In the present study, we assessed the effect of the PPA (Polygala japonica Houtt., Polygala tenuifolia WILLD. and Acorus gramineus SOLAND. mixed preparation), a traditional herbal prescription, on the learning and memory impairments induced by scopolamine. The cognition-enhancing effect of PPA was investigated using a passive avoidance test, Y-maze test and the Morris water maze test in mice. Drug-induced amnesia was induced by treating animals with scopolamine (1 mg/kg, i.p.). A single PPA (400 and 800 (mg/kg)) administration significantly reversed the scopolamine-induced cognitive impairments in the passive avoidance test (P<0.05). On the Y-maze test, PPA (400 and 800 (mg/kg)) also significantly reversed scopolamine-induced cognitive impairments in mice (P<0.05). PPA also improved escape latencies in training trials and increased swimming times and distances within the target zone of the Morris water maze (P<0.05). These results suggest that PPA attenuates amnesic state induced by scopolamine and that these Effect are mediated by enhancing the cholinergic dysfunction.

• 대한전자공학회논문지SP
• /
• 제48권1호
• /
• pp.54-63
• /
• 2011

본 논문은 저해상도 입력 영상을 고해상도 영상으로 복원하는 고속 학습기반 보간 기법을 제안한다. 일반적인 학습기반 초고해상도 기법은 여러 종류의 저해상도 영상과 고해상도 영상의 상관성을 통해 고주파 정보를 사전에 학습하고, 합성 단계에서 학습한 정보를 이용해 임의의 저해상도 영상을 고해상도 영상으로 복원한다. 이런 기존 학습기반 초 고해상도 기법은 방대한 양의 학습된 정보를 메모리에 저장해야만 하는 단점이 있을 뿐만 아니라 이차원 블록 단위 정합 과정을 거쳐야 하기 때문에 상당한 연산량이 요구된다. 이러한 문제점을 보완하기 위해 본 논문은 일차원 패치 단위 학습을 통해 학습 정보 저장용 메모리 크기 및 연산량을 크게 줄이는 기법을 제안한다. 실험 결과에 따르면, 제안한 기법은 전통적인 bicubic 보간 기법보다 평균 0.7dB 정도 높은 PSNR을 보이며, SSIM도 평균 0.01이상 향상되는 결과를 보인다.

• ETRI Journal
• /
• 제44권6호
• /
• pp.1034-1046
• /
• 2022

The learning-based multiview stereo (MVS) methods for three-dimensional (3D) reconstruction generally use 3D volumes for depth inference. The quality of the reconstructed depth maps and the corresponding point clouds is directly influenced by the spatial resolution of the 3D volume. Consequently, these methods produce point clouds with sparse local regions because of the lack of the memory required to encode a high volume of information. Here, we apply the atrous spatial pyramid pooling (ASPP) module in MVS methods to obtain dense feature maps with multiscale, long-range, contextual information using high receptive fields. For a given 3D volume with the same spatial resolution as that in the MVS methods, the dense feature maps from the ASPP module encoded with superior information can produce dense point clouds without a high memory footprint. Furthermore, we propose a 3D loss for training the MVS networks, which improves the predicted depth values by 24.44%. The ASPP module provides state-of-the-art qualitative results by constructing relatively dense point clouds, which improves the DTU MVS dataset benchmarks by 2.25% compared with those achieved in the previous MVS methods.

• Geomechanics and Engineering
• /
• 제34권1호
• /
• pp.43-49
• /
• 2023

Knowledge of minimum horizontal stress (S_hmin) is a significant step in determining full stress tensor. It provides crucial information for the production of sand, hydraulic fracturing, determination of safe mud weight window, reservoir production behavior, and wellbore stability. Calculating the S_hmin using indirect methods has been proved to be awkward because a lot of data are required in all of these models. Also, direct techniques such as hydraulic fracturing are costly and time-consuming. To figure these problems out, this work aims to apply the long-short-term memory (LSTM) algorithm to S_hmin time-series prediction. 13956 datasets obtained from an oil well logging operation were applied in the models. 80% of the data were used for training, and 20% of the data were used for testing. In order to achieve the maximum accuracy of the LSTM model, its hyper-parameters were optimized significantly. Through different statistical indices, the LSTM model's performance was compared with with other machine learning methods. Finally, the optimized LSTM model was recommended for S_hmin prediction in the well logging operation.

• 대한한의학방제학회지
• /
• 제25권1호
• /
• pp.69-87
• /
• 2017

Objectives : Cheongnoemyeongsin-hwan (CNMSH) is a herb medicine to treat cognitive impairment. This study was investigated the effects of CNMSH on learning and memory impairment induced by cerebral hypoperfusion. Cerebral hypoperfusion was produced chronically by permanent bilateral common carotid artery occlusion (BCCAO) in rats. Methods : CNMSH was administered orally once a day (250 mg/kg) for 28 days starting at 4th week after the BCCAO. The acquisition of learning and the retention of memory were tested on 9th week after the BCCAO using the Morris water maze. In addition, effect of CNMSH on neuronal apoptosis and ${\beta}-amyloid$ accumulation in the hippocmapus was evaluated with immunohistochemistry and Western blotting. Results : 1. CNMSH and ChAL significantly shortened the escape latencies on the 2nd day of acquisition training trials. 2. ChAL significantly prolonged the swimming time spent in the target and peri-target zones and CNMSH also significantly prolonged the swimming time spent in the peri-target zone. 3. CNMSH and ChAL significantly increased the number of target heading in the retention test. 4. ChAL significantly shortened the time of the 1st target heading in the retention test, but CNMSH insignificantly shortened the time of that. 5. CNMSH and ChAL significantly increased the memory score in the retention test. 6. CNMSH and ChAL significantly attenuated the reduction of CA1 neurons, but insignificantly attenuated the reduction of CA1 thickness. 7. CNMSH and ChAL significantly attenuated the up-regulation of Bax expression in the CA1 of hippocampus. 8. CNMSH and ChAL significantly attenuated the up-regulation of cascapse-3 expression in the CA1 of hippocampus. 9. CNMSH and ChAL significantly attenuated the ${\beta}-amyloid$ accumulation in the CA1 of hippocampus. 10. CNMSH and ChAL significantly attenuated the up-regulation of APP expression in the CA1 of hippocampus. 11. CNMSH and ChAL significantly attenuated the up-regulation of BACE-1 expression in the CA1 of hippocampus. Conclusions : The results show that CNMSH attenuates neuronal apoptosis and ${\beta}-amyloid$ accumulation in the hippocampus and alleviates the impairment of learning and memory produced by chronic cerebral hypoperfusion. These results suggest that CNMSH may be a beneficial medicinal herb to treat cognitive impairment associated with neurodegenerative diseases.

• Animal cells and systems
• /
• 제7권4호
• /
• pp.303-307
• /
• 2003

The aim of this study is to investigate whether alcohol alters learning and memory processes pertaining to emotional and spatial factors using the active avoidance and T-maze task in zebrafish. In the active avoidance task, zebrafish were trained to escape from one compartment to another to avoid electric shocks (unconditioned stimulus) following a conditioned light signal. Acquisition of active avoidance task appeared to be normal in zebrafish that were treated with 1% alcohol for 30 min for 17 days until the end of the behavioral test, and retention ability of learned behavior, tested 2 days later, was the same as control group. In the T-maze task, the time to find a reservoir was compared. While the latency was similar during the 1 st training session between control and alcohol-treated zebrafish, it was significantly longer in alcohol-treated zebrafish during retention test 24 h later. Furthermore, when alcohol was treated 30 min after 2nd session without prior treatment, zebrafish demonstrated similar retention ability compared to control. These results suggest that chronic alcohol treatment alters spatial learning of zebrafish, but not emotional learning.

• 음성과학
• /
• 제5권2호
• /
• pp.57-75
• /
• 1999

The purpose of this paper is to develop an English prosody training system using PC for Korean learners of English. The program is called Intonation Training Tool (ITT). It operates on DOS 5.0. The hardware for this program requires over IBM PC 386 with 4 MBytes main memory, SVGA (1 MByte or more) for graphic, soundblaster 16 and over 14 inch monitor size. The ITT program operates this way: the learners can listen as well as see the English teacher's stress and intonation patterns on the monitor. The learner practices the same patterns with a microphone. This program facilitates the learner's stress and intonation patterns to overlap the teacher's patterns. The learner can find his/her stress and intonation errors and correct these independently. This program is expected to be a highly efficient learning tool for Korean learners of English in their English prosody training in the English class without the aid of a native English speaker in the classroom.

• 한국추진공학회지
• /
• 제25권6호
• /
• pp.1-11
• /
• 2021

층류화염편 라이브러리에 대한 효율적인 계산과정을 개발하기 위하여 초임계 압력조건의 기체수소/액체산소 연소기에 대해 인공신경망을 이용한 기계학습과정이 적용되었다. 학습성능과 계산효율성에 근거한 최적의 계산과정을 찾기 위하여 은닉층에 대한 ReLU와 쌍곡탄젠트 함수의 25가지 조합이 선택되었다. 정확성이 우수한 높은 학습성능을 얻는데 쌍곡탄젠트 활성화함수가 적절하였다. 인공신경망의 학습성능을 개선하기 위해서 학습데이터 변환이 제안되었다. 4개의 은닉층에 최적의 노드를 배치할 때 학습성능 및 계산비용 관점에서 모두 효율적인 것으로 나타났다. 층류화염편 라이브러리의 보간법보다 인공신경망을 사용하는 경우 전체 계산시간은 37%, 시스템 메모리는 99.98% 감소되었다.

• 한국전산구조공학회논문집
• /
• 제36권5호
• /
• pp.315-321
• /
• 2023

장대교량은 낮은 고유진동수와 감쇠비를 가지는 초유연구조물로 진동사용성 문제에 취약하다. 하지만 현재 국내 설계지침에서는 풍속이나 진폭에 대한 임계값을 기반으로 유해진동 발생 여부를 평가하고 있다. 본 연구에서는 장대교량에서 발생하는 유해진동을 보다 정교하게 식별하기 위하여 딥러닝 기반 신호분할 모델을 활용한 데이터 포인트 단위의 와류진동 식별 방법론을 제안한다. 특별히 포락선을 가지는 사인파를 활용하여 와류진동에 해당하는 데이터를 합성함으로써 모델 구축에 필수적인 와류진동 데이터 획득 및 라벨링 과정을 대체하였다. 이후 푸리에 싱크로스퀴즈드 변환를 적용하여 시간-주파수 특징을 추출하여 신경망의 인풋 데이터로 사용하였다. 합성데이터만을 이용하여 양방향 장단기 기억신경망(Bidirectional Long-Short-Term-Memory) 모델을 훈련하였고 이를 라벨 정보를 포함한 실제 사장교의 계측데이터를 이용하여 학습한 모델과 비교하여 모델의 실시간 와류진동 식별 성능을 검증하였다.