• International Journal of Computer Science & Network Security
• /
• 제21권12호
• /
• pp.356-364
• /
• 2021

In the formation of a socially oriented economy in the context of European integration, the development of tourism is one of the priority areas that positively affects the socio-economic situation of the country as a whole and its regions in particular, stimulates important economic activities and strengthens Ukraine's positive image in Europe and the world. In view of this, in the framework of a thorough study of the tourism industry it is necessary to assess its potential. This study proposes an assessment of tourism potential in the regional context, which consists of consistent implementation of six steps, namely: first, the definition of research objects for which the tourism potential is determined; secondly, the formation of a set of basic features for assessing tourism potential of certain objects; thirdly, the collection of information on individual indicators, which are selected to assess the tourism potential of the objects; fourth, the calculation of parametric indices by comparing the indicators of each individual object of study (region) with the average values in the set of objects under study; fifth, the definition of a generalized index of tourism potential of the region; sixth, grouping regions by the values of the generalized index of tourism potential. Execution of the stated algorithm involves the use of various methods, in particular, statistical, graphical, parametric, the analysis of hierarchies, matrix and cartographic. Approbation of the proposed assessment of tourism potential at the regional level in Ukraine allowed to group regions according to the values of the generalized index of tourism potential, which can be used as a basis for developing measures to increase and enhance their tourism potential in Ukraine in terms of European integration.

• 한국컴퓨터정보학회논문지
• /
• 제26권11호
• /
• pp.173-182
• /
• 2021

본 논문에서는 운전자의 주의산만을 유발하는 운전자, 탑승자의 동작을 분석하고 핸드폰과 관련된 운전자의 행동 10가지를 인식하였다. 먼저 주의산만을 유발하는 동작을 환경 및 요인으로 분류하고 관련 최근 논문을 분석하였다. 분석된 논문을 기반으로 주의산만을 유발하는 주요 원인인 핸드폰과 관련된 10가지 운전자의 행동을 인식하였다. 약 10만 개의 이미지 데이터를 기반으로 실험을 진행하였다. SURF를 통해 특징을 추출하고 3가지 모델(CNN, ResNet-101, 개선된 ResNet-101)로 실험하였다. 개선된 ResNet-101 모델은 CNN보다 학습 오류와 검증 오류가 8.2배, 44.6배가량 줄어들었으며 평균적인 정밀도와 f1-score는 0.98로 높은 수준을 유지하였다. 또한 CAM(class activation maps)을 활용하여 딥러닝 모델이 운전자의 주의 분산 행동을 판단할 때, 핸드폰 객체와 위치를 결정적 원인으로 활용했는지 검토하였다.

• 감성과학
• /
• 제21권4호
• /
• pp.91-102
• /
• 2018

인간이 외부 환경에 적절하게 대응하기 위해서는 정확한 시간 지각이 필요함에도 불구하고 다양한 비 시간적(non-temporal) 특성들이 시간 지각에 영향을 주는 것으로 나타났다. 그동안 시간 지각에 영향을 주는 다양한 요인들이 검증되었지만 참가자와 자극 간의 거리가 시간 지각에 영향을 주는지 직접 검증한 연구는 없다. 본 연구는 자극의 망막상 크기, 물리적 크기, 지각된 크기를 고려하여 관찰 거리가 시간 지각에 미치는 영향을 검증하였다. 연구 결과, 자극의 물리적 크기 및 지각된 크기가 동일한 실험에서 관찰 거리의 효과가 나타나지 않았으며, 자극의 망막상 크기가 동일한 실험에서만 관찰 거리의 효과가 나타났다. 이는 자극의 망막상 크기가 동일한 경우, 관찰 거리가 증가할수록 자극의 물리적 크기 또한 커지기 때문에 자극의 크기가 시간 지각에 영향을 준 결과일 수 있다. 이러한 실험 결과는 정보가 제한되지 않는 경우에 관찰거리가 변화하더라도 대상의 지속시간이 항상성 있게 지각될 수 있음을 시사한다.

• 한국융합학회논문지
• /
• 제10권5호
• /
• pp.149-156
• /
• 2019

본 연구는 실라 르브랑 드 브레트빌의 작품세계에 일관되게 등장하는 '교차성(intersectionality)'을 주요 개념으로 채택하고 그의 디자인에 나타난 교차성 개념을 구체적으로 밝히는 것이 목적이다. 연구의 주요 개념인 교차성의 정의를 흑인 페미니즘 사상으로부터 그 시원을 찾아보고, 디자인에 있어서 교차성 개념이 어떻게 실천되는지 개괄했다. 드브레트빌의 디자인 작업에 나타나는 공통적 특징을 조형성, 디자인 방법론, 표현 매체 등을 기준으로 분석한 결과, 1)발언의 타이포그래피 2)내러티브의 수집 3)장소특정적 설치와 같은 특징으로 수렴할 수 있었다. 디자인이 놓인 권력의 맥락을 전복하여 잊히거나 덜 조명된 입장들을 포용하는 교차성 개념을 근간으로 실라 르브랑 드 브레트빌의 디자인에 나타난 교차성을 살펴본 결과 1)비가시성의 가시화 2) 객체의 주체화 3)변방의 탈주변화와 같은 세 가지 시사점을 도출할 수 있었다. 본고가 탈중앙화, 다양화되는 한국 사회 동시대 가치 변화에 발맞춰 디자인 철학을 정립하고자 하는 연구자와 실무자에게 통찰을 제공할 수 있기를 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4290-4309
• /
• 2020

In recent years, advancements in machine learning capabilities have allowed it to see widespread adoption for tasks such as object detection, image classification, and anomaly detection. However, despite their promise, a limitation lies in the fact that a network's performance quality is based on the data which it receives. A well-trained network will still have poor performance if the subsequent data supplied to it contains artifacts, out of focus regions, or other visual distortions. Under normal circumstances, images of the same scene captured from differing points of focus, angles, or modalities must be separately analysed by the network, despite possibly containing overlapping information such as in the case of images of the same scene captured from different angles, or irrelevant information such as images captured from infrared sensors which can capture thermal information well but not topographical details. This factor can potentially add significantly to the computational time and resources required to utilize the network without providing any additional benefit. In this study, we plan to explore using image fusion techniques to assemble multiple images of the same scene into a single image that retains the most salient key features of the individual source images while discarding overlapping or irrelevant data that does not provide any benefit to the network. Utilizing this image fusion step before inputting a dataset into the network, the number of images would be significantly reduced with the potential to improve the classification performance accuracy by enhancing images while discarding irrelevant and overlapping regions.

• 한국콘텐츠학회논문지
• /
• 제21권3호
• /
• pp.143-156
• /
• 2021

본 연구에서는 카이펑 시 역사 문화거리인 서점거리를 대상으로 서점거리의 경관 구성 요소에 나타난 경관 색채의 특징을 분석하여 서점거en리의 환경 색채에 대한 전체성을 이론적 배경을 제공하고자 한다. 문헌 고찰을 통해 역사 문화거리의 경관 구성요소에 대한 체크리스트를 도출하고, 청대 건축적 색채의 일반적인 특징과 경관 색채의 기본적인 분석방법에 대해 파악하였다. 또한, 서점거리 경관 구성의 요소 및 경관 색채에 대한 현장조사를 실시하고 색채 분석은 <한국표준색 색채분석> 프로그램을 적용하여 분석을 진행하였으며, 색상수치 표기는 먼셀 표색계를 사용하여 표기하였다. 연구 결과를 보게 되면 서점거리의 경관색채는 R계열, PB계열, Y계열, 무채색(N)계열로 구성되어 있으며 전체적으로 색채는 높은 전체성을 나타내었다. 청대 건축 색채의 일반적인 특성을 비교함으로써 서점거리의 전체적인 경관 색채는 청대 건축 색채의 일반적인 특성에 상당 부분 부합한다는 것을 알 수 있었다. 그러나 사인과 시설물, 조형물의 색채 활용에서는 미흡한 부분이 많이 존재하였기에 사인과 시설물 등 경관 요소의 색채계획을 추가하여 시각 정보의 식별 가능성을 강화하고 거리 색채의 단계적인 변화를 증가시켜야 할 필요성이 요구된다.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.193-202
• /
• 2022

The classification of hyperspectral imagery (HSI) is essential in the surface of earth observation. Due to the continuous large number of bands, HSI data provide rich information about the object of study; however, it suffers from the curse of dimensionality. Dimensionality reduction is an essential aspect of Machine learning classification. The algorithms based on feature extraction can overcome the data dimensionality issue, thereby allowing the classifiers to utilize comprehensive models to reduce computational costs. This paper assesses and compares two HSI classification techniques. The first is based on the Joint Spatial-Spectral Stacked Autoencoder (JSSSA) method, the second is based on a shallow Artificial Neural Network (SNN), and the third is used the SVM model. The performance of the JSSSA technique is better than the SNN classification technique based on the overall accuracy and Kappa coefficient values. We observed that the JSSSA based method surpasses the SNN technique with an overall accuracy of 96.13% and Kappa coefficient value of 0.95. SNN also achieved a good accuracy of 92.40% and a Kappa coefficient value of 0.90, and SVM achieved an accuracy of 82.87%. The current study suggests that both JSSSA and SNN based techniques prove to be efficient methods for hyperspectral classification of snow features. This work classified the labeled/ground-truth datasets of snow in multiple classes. The labeled/ground-truth data can be valuable for applying deep neural networks such as CNN, hybrid CNN, RNN for glaciology, and snow-related hazard applications.

• 천문학회지
• /
• 제55권2호
• /
• pp.23-36
• /
• 2022

We present a method to determine nitrogen abundance ratios with respect to iron ([N/Fe]) from molecular CN-band features observed in low-resolution (R ~ 2000) stellar spectra obtained by the Sloan Digital Sky Survey (SDSS) and the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST). Various tests are carried out to check the systematic and random errors of our technique, and the impact of signal-to-noise (S/N) ratios of stellar spectra on the determined [N/Fe]. We find that the uncertainty of our derived [N/Fe] is less than 0.3 dex for S/N ratios larger than 10 in the ranges T_eff = [4000, 6000] K, log g = [0.0, 3.5], [Fe/H] = [-3.0, 0.0], [C/Fe] = [-1.0, +4.5], and [N/Fe] = [-1.0, +4.5], the parameter space that we are interested in to identify N-enhanced stars in the Galactic halo. A star-by-star comparison with a sample of stars with [N/Fe] estimates available from the Apache Point Observatory Galactic Evolution Experiment (APOGEE) also suggests a similar level of uncertainty in our measured [N/Fe], after removing its systematic error. Based on these results, we conclude that our method is able to reproduce [N/Fe] from low-resolution spectroscopic data, with an uncertainty sufficiently small to discover N-rich stars that presumably originated from disrupted Galactic globular clusters.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.

• 센서학회지
• /
• 제32권2호
• /
• pp.88-94
• /
• 2023

Recently, piezoelectric tactile sensors have garnered considerable attention in the field of texture recognition owing to their high sensitivity and high-frequency detection capability. Despite their remarkable potential, improving their mechanical flexibility to attach to complex surfaces remains challenging. In this study, we present a flexible piezoelectric sensor that can be bent to an extremely small radius of up to 2.5 mm and still maintain good electrical performance. The proposed sensor was fabricated by controlling the thickness that induces internal stress under external deformation. The fabricated piezoelectric sensor exhibited a high sensitivity of 9.3 nA/kPa ranging from 0 to 10 kPa and a wide frequency range of up to 1 kHz. To demonstrate real-time texture recognition by rubbing the surface of an object with our sensor, nine sets of fabric plates were prepared to reflect their material properties and surface roughness. To extract features of the objects from the detected sensing data, we converted the analog dataset to short-term Fourier transform images. Subsequently, texture recognition was performed using a convolutional neural network with a classification accuracy of 97%.