• 농업과학연구
• /
• 제49권4호
• /
• pp.785-793
• /
• 2022

In this study, tomato maturity was estimated based on deep learning for a harvesting robot. Tomato images were obtained using a RGB camera installed on a monitoring robot, which was developed previously, and the samples were cropped to 128 × 128 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the mean-variance loss was used to learn implicitly the distribution of the data features by class. In the test stage, the tomato maturity was estimated as a continuous index, which has a range of 0 to 1, by calculating the expected class value. The results show that the F1-score of the classification was approximately 0.94, and the performance was similar to that of a deep learning-based classification task in the agriculture field. In addition, it was possible to estimate the distribution in each maturity stage. From the results, it was found that our approach can not only classify the discrete maturation stages of the tomatoes but also can estimate the continuous maturity.

• 전기전자학회논문지
• /
• 제24권2호
• /
• pp.523-528
• /
• 2020

스마트 모바일 장치의 확산은 인간의 일상 행동 분석을 보다 일반적이고 간단하게 만들었다. 행동 분석은 이미 본인 인증, 감시, 건강 관리 등 많은 분야에서 사용 중이고 그 유용성이 증명되었다. 본 논문에서는 스마트폰의 가속도 센서 신호를 사용하여 효율적이고 정확하게 행동 인식을 수행하는 합성곱 신경망(모델 A)과 순환 신경망까지 적용한(모델 B) 심층 신경망 모델을 제시한다. 모델 A는 batch normalization과 같은 단순한 기법만 적용해도 이전의 결과보다 더 작은 모델로 더 높은 성능을 달성할 수 있다는 것을 보인다. 모델 B는 시계열 데이터 모델링에 주로 사용되는 LSTM 레이어를 추가하여 예측 정확도를 더욱 높일 수 있음을 보인다. 이 모델은 29명의 피실험자를 대상으로 수집한 벤치마크 데이트 세트에서 종합 예측 정확도 97.16%(모델 A), 99.50%(모델 B)를 달성했다.

• Communications for Statistical Applications and Methods
• /
• 제26권6호
• /
• pp.591-610
• /
• 2019

Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권5호
• /
• pp.322-327
• /
• 2017

문서 분류 문제는 오랜 기간 동안 자연어 처리 분야에서 연구되어 왔다. 우리는 기존 컨볼루션 신경망을 이용했던 연구에서 나아가, 순환 신경망에 기반을 둔 문서 분류를 수행하였고 그 결과를 종합하여 제시하려 한다. 컨볼루션 신경망은 단층 컨볼루션 신경망을 사용했으며, 순환 신경망은 가장 성능이 좋다고 알려져 있는 장기-단기 기억 신경망과 회로형 순환 유닛을 활용하였다. 실험 결과, 분류 정확도는 Multinomial Naïve Bayesian Classifier < SVM < LSTM < CNN < GRU의 순서로 나타났다. 따라서 텍스트 문서 분류 문제는 시퀀스를 고려하는 것 보다는 문서의 feature를 추출하여 분류하는 문제에 가깝다는 것을 확인할 수 있었다. 그리고 GRU가 LSTM보다 문서의 feature 추출에 더 적합하다는 것을 알 수 있었으며 적절한 feature와 시퀀스 정보를 함께 활용할 때 가장 성능이 잘 나온다는 것을 확인할 수 있었다.

• Journal of Multimedia Information System
• /
• 제4권4호
• /
• pp.225-232
• /
• 2017

Understanding actions in videos is an important task. It helps in finding the anomalies present in videos such as fights. Detection of fights becomes more crucial when it comes to sports. This paper focuses on finding fight scenes in Hockey sport videos using blur & radon transform and convolutional neural networks (CNNs). First, the local motion within the video frames has been extracted using blur information. Next, fast fourier and radon transform have been applied on the local motion. The video frames with fight scene have been identified using transfer learning with the help of pre-trained deep learning model VGG-Net. Finally, a comparison of the methodology has been performed using feed forward neural networks. Accuracies of 56.00% and 75.00% have been achieved using feed forward neural network and VGG16-Net, respectively.

• 센서학회지
• /
• 제30권1호
• /
• pp.20-24
• /
• 2021

The electrocardiogram (ECG) is one of the most extensively employed signals used to diagnose and predict cardiovascular diseases (CVDs). In recent years, several deep learning (DL) models have been proposed to improve detection accuracy. Among these, deep neural networks (DNNs) are the most popular, wherein the features are extracted automatically. Despite the increment in classification accuracy, DL models require exorbitant computational resources and power. This causes the mapping of DNNs to be slow; in addition, the mapping is challenging for a wearable device. Embedded systems have constrained power and memory resources. Therefore full-precision DNNs are not easily deployable on devices. To make the neural network faster and more power-efficient, spiking neural networks (SNNs) have been introduced for fewer operations and less complex hardware resources. However, the conventional SNN has low accuracy and high computational cost. Therefore, this paper proposes a new binarized SNN which modifies the synaptic weights of SNN constraining it to be binary (+1 and -1). In the simulation results, this paper compares the DL models and SNNs and evaluates which model is optimal for ECG classification. Although there is a slight compromise in accuracy, the latter proves to be energy-efficient.

• 통합자연과학논문집
• /
• 제11권4호
• /
• pp.204-208
• /
• 2018

Comparison of different optimizer performance in photovoltaic power modeling using artificial neural deep learning techniques is described in this paper. Six different deep learning optimizers are tested for Long-Short-Term Memory networks in this study. The optimizers are namely Adam, Stochastic Gradient Descent, Root Mean Square Propagation, Adaptive Gradient, and some variants such as Adamax and Nadam. For comparing the optimization techniques, high and low fluctuated photovoltaic power output are examined and the power output is real data obtained from the site at Mokpo university. Using Python Keras version, we have developed the prediction program for the performance evaluation of the optimizations. The prediction error results of each optimizer in both high and low power cases shows that the Adam has better performance compared to the other optimizers.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.166-175
• /
• 2023

Reinforcement learning can be applied to a wide variety of problems. However, the fundamental limitation of reinforcement learning is that it is difficult to derive an answer within a given time because the problems in the real world are too complex. Then, with the development of neural network technology, research on deep reinforcement learning that combines deep learning with reinforcement learning is receiving lots of attention. In this paper, two types of neural networks are combined with reinforcement learning and their characteristics were compared and analyzed with existing value-based reinforcement learning algorithms. Two types of neural networks are FNN and CNN, and existing reinforcement learning algorithms are SARSA and Q-learning.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.352-368
• /
• 2021

Sign-in point of interest (POI) are extremely sparse in location-based social networks, hindering recommendation systems from capturing users' deep-level preferences. To solve this problem, we propose a content-aware POI recommendation algorithm based on a convolutional neural network. First, using convolutional neural networks to process comment text information, we model location POI and user latent factors. Subsequently, the objective function is constructed by fusing users' geographical information and obtaining the emotional category information. In addition, the objective function comprises matrix decomposition and maximisation of the probability objective function. Finally, we solve the objective function efficiently. The prediction rate and F1 value on the Instagram-NewYork dataset are 78.32% and 76.37%, respectively, and those on the Instagram-Chicago dataset are 85.16% and 83.29%, respectively. Comparative experiments show that the proposed method can obtain a higher precision rate than several other newer recommended methods.

• 전자통신동향분석
• /
• 제38권5호
• /
• pp.12-22
• /
• 2023

The development of neural networks is evolving towards the adoption of transformer structures with attention modules. Hence, active research focused on extending the concept of lightweight neural network algorithms and hardware acceleration is being conducted for the transition from conventional convolutional neural networks to transformer-based networks. We present a survey of state-of-the-art research on lightweight neural network algorithms and hardware architectures to reduce memory usage and accelerate both inference and training. To describe the corresponding trends, we review recent studies on token pruning, quantization, and architecture tuning for the vision transformer. In addition, we present a hardware architecture that incorporates lightweight algorithms into artificial intelligence processors to accelerate processing.