• Korean Journal of Mathematics
• /
• 제26권2호
• /
• pp.337-348
• /
• 2018

MNIST dataset is a database containing images of handwritten digits, with each image labeled by an integer from 0 to 9. It is used to benchmark the performance of machine learning algorithms. Neural networks for MNIST are regarded as the starting point of the studying machine learning algorithms. However it is not easy to start the actual programming. In this expository article, we will give a step-by-step instruction to build neural networks for MNIST dataset using MATLAB.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.787-800
• /
• 2021

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.96-99
• /
• 2003

Land cover map is a typical GIS database which shows the Earth's physical surface differentiated by standardized homogeneous land cover types. Satellite images acquired by Landsat TM were primarily used to produce a land cover map of 7 land cover classes; however, it now becomes to produce a more accurate land cover classification dataset of 23 classes thanks to higher resolution satellite images, such as SPOT-5 and IKONOS. The use of the newly produced high resolution land cover map of 23 classes for such activities to estimate non-point sources of pollution like water pollution modeling and atmospheric dispersion modeling is expected to result a higher level of accuracy and validity in various environmental monitoring results. The estimation of pollution from non-point sources using GIS-based modeling with land cover dataset shows fairly accurate and consistent results.

• Journal of Information Science Theory and Practice
• /
• 제12권2호
• /
• pp.64-78
• /
• 2024

Sentiment analysis is one of the promising approaches for developing a point of interest (POI) recommendation system. It uses natural language processing techniques that deploy expert insights from user-generated content such as reviews and feedback. By applying sentiment polarities (positive, negative, or neutral) associated with each POI, the recommendation system can suggest the most suitable POIs for specific users. The proposed study combines two models for POI recommendation. The first model uses bidirectional long short-term memory (BiLSTM) to predict sentiments and is trained on an election dataset. It is observed that the proposed model outperforms existing models in terms of accuracy (99.52%), precision (99.53%), recall (99.51%), and F1-score (99.52%). Then, this model is used on the Foursquare dataset to predict the class labels. Following this, user and POI embeddings are generated. The next model recommends the top POIs and corresponding coordinates to the user using the LSTM model. Filtered user interest and locations are used to recommend POIs from the Foursquare dataset. The results of our proposed model for the POI recommendation system using sentiment analysis are compared to several state-of-the-art approaches and are found quite affirmative regarding recall (48.5%) and precision (85%). The proposed system can be used for trip advice, group recommendations, and interesting place recommendations to specific users.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2585-2598
• /
• 2015

Hand posture recognition has played a very important role in Human Computer Interaction (HCI) and Computer Vision (CV) for many years. The challenge arises mainly due to self-occlusions caused by the limited view of the camera. In this paper, a robust hand posture recognition approach based on 3D point cloud from two RGB-D sensors (Kinect) is proposed to make maximum use of 3D information from depth map. Through noise reduction and registering two point sets obtained satisfactory from two views as we designed, a multi-viewed hand posture point cloud with most 3D information can be acquired. Moreover, we utilize the accurate reconstruction and classify each point cloud by directly matching the normalized point set with the templates of different classes from dataset, which can reduce the training time and calculation. Experimental results based on posture dataset captured by Kinect sensors (from digit 1 to 10) demonstrate the effectiveness of the proposed method.

• 한국컴퓨터정보학회논문지
• /
• 제29권1호
• /
• pp.21-30
• /
• 2024

본 논문에서는 자율협력주행 인프라를 위해 제작된 8가지 센서 전용 시설물들에 대해 라이다로 취득한 포인트 클라우드 데이터로부터 시설물들의 특징을 추출하여 샘플 데이터셋으로 구축하는 방법을 제안한다. 고휘도 반사지가 부착된 8가지 센서 전용 시설물들과 데이터 취득 시스템을 개발했고, 취득된 포인트 클라우드 데이터로부터 일정한 측정 거리 내에 위치한 시설물들의 특징을 추출하기 위해 포인트 대상의 DBSCAN 방법과 반사강도 대상의 OTSU 방법을 응용하여 추려낸 포인트들에 원통형 투영법을 적용했다. 3차원 포인트 좌표, 2차원 투영 좌표, 그리고 반사강도 등을 해당 시설물의 특징으로 설정했고, 정답 레이블과 함께 데이터셋으로 제작했다. 라이다로 취득한 데이터를 기반으로 구축된 시설물 데이터셋의 효용 가능성을 확인하기 위해서 기본적인 CNN 모델을 선정하여 학습 후 테스트를 진행하여 대략 90% 이상의 정확도를 보여 시설물 인식 가능성을 확인했다. 지속적인 실험을 통해 제시한 데이터셋 구축을 위한 특징 추출 알고리즘의 개선 및 성능 향상과 더불어 이에 적합한 자율협력주행을 위한 센서 전용 시설물을 인식할 수 있는 전용 모델을 개발할 예정이다.

• 대한임베디드공학회논문지
• /
• 제18권5호
• /
• pp.203-208
• /
• 2023

Recently, with the growing interest in the field of autonomous driving, many researchers have been focusing on developing autonomous driving software platforms. In particular, we have concentrated on developing 3D object detection models that can improve real-time performance. In this paper, we introduce a self-constructed 3D LiDAR dataset specific to domestic environments and propose a VariFocal-based CenterPoint for the 3D object detection model, with improved performance over the previous models. Furthermore, we present experimental results comparing the performance of the 3D object detection modules using our self-built and public dataset. As the results show, our model, which was trained on a large amount of self-constructed dataset, successfully solves the issue of failing to detect large vehicles and small objects such as motorcycles and pedestrians, which the previous models had difficulty detecting. Consequently, the proposed model shows a performance improvement of about 1.0 mAP over the previous model.

• Communications for Statistical Applications and Methods
• /
• 제7권1호
• /
• pp.327-336
• /
• 2000

We are mainly interested in hazard rate changes which are usually occur in survival times of manufactured products or patients. We may expect early failures with one hazard rate and next another hazard rate. For this type of data we apply a hazard rate change-point model and estimate the unkown time point to improve the model adequacy. We introduce change-point logistic model to the discrete time hazard rates. The MLEs are obtained routinely and we also explain the suggested model through a dataset of survival times.

• 한국기록관리학회지
• /
• 제18권2호
• /
• pp.109-133
• /
• 2018

행정정보 데이터세트의 기록관리 필요성은 기록관리 연구자들 사이에서 넓은 공감대를 형성하고 있으며 지속적으로 연구되어 왔다. 그동안 정보 기술의 발전에 따라 행정정보시스템의 신규 구축 및 재개발이 증가하고 있음에도 불구하고 실제 공공기관에서 운영 중인 각종 행정정보시스템에서 생산된 데이터세트는 관리하지 못 하고 있는 실정이다. 그 원인은 현실 적용이 가능한 관리 방안의 부재에 있다고 하겠다. 본 연구는 구현 가능한 행정정보 데이터세트 관리 방안은 데이터세트 관리 환경의 실상에 기초하여야 한다는 판단 하에, 현재 운영 중인 행정정보시스템에서의 데이터세트 생산 및 관리 환경 사례를 조사함으로써 관리 방안 개발의 기초 자료와 유사 연구에서 활용할 수 있는 조사방법론을 제시하고자 한다.

• 한국정보통신학회논문지
• /
• 제26권11호
• /
• pp.1660-1665
• /
• 2022

최근 많은 산업체에서 3차원 스캐닝 기술을 활용하고 있다. 3D 스캐너의 성능이 향상됨에 따라 점데이터를 획득하면 후처리를 통해서 일정 비율만큼 줄이는 샘플링 단계를 수행하거나, 잡음이라고 판단되는 부분을 제거한다. 하지만, 이와 같은 추가과정 수행에도 불구하고 오랜 시간 동안 스캐닝하면 점데이터들을 한꺼번에 처리할 수 없다. 일반적으로 멀티스레드 환경을 이용하여 기획득된 점데이터를 먼저 처리하는 방식을 이용하지만, 스캐닝 프로세스 작업 시간이 증가함에 따라 다양한 환경 조건과 누적된 연산으로 인하여 점차 처리 성능이 낮아진다. 본 연구에서는 3D 스캐너로부터 실시간으로 들어오는 점데이터를 누적된 고속 특징점 히스토그램 계산을 이용하여 불필요하다고 판단되는 점데이터를 초기에 제거하는 방식을 제안한다. 이 방법을 이용하면 전체 3D 스캐닝 프로세스의 속도 향상을 가져온다.