• Journal of Animal Science and Technology
• /
• v.66 no.1
• /
• pp.167-177
• /
• 2024

Iris segmentation is an initial step for identifying the biometrics of animals when establishing a traceability system for livestock. In this study, we propose a deep learning framework for pixel-wise segmentation of bovine iris with a minimized use of annotation labels utilizing the BovineAAEyes80 public dataset. The proposed image segmentation framework encompasses data collection, data preparation, data augmentation selection, training of 15 deep neural network (DNN) models with varying encoder backbones and segmentation decoder DNNs, and evaluation of the models using multiple metrics and graphical segmentation results. This framework aims to provide comprehensive and in-depth information on each model's training and testing outcomes to optimize bovine iris segmentation performance. In the experiment, U-Net with a VGG16 backbone was identified as the optimal combination of encoder and decoder models for the dataset, achieving an accuracy and dice coefficient score of 99.50% and 98.35%, respectively. Notably, the selected model accurately segmented even corrupted images without proper annotation data. This study contributes to the advancement of iris segmentation and the establishment of a reliable DNN training framework.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.223-231
• /
• 2023

In this study, we propose a model that extracts and analyzes features from deep learning-based speech signals, generates filters, and utilizes these filters to recognize emotions in speech signals. We evaluate the performance of emotion recognition accuracy using the proposed model. According to the simulation results using the proposed model, the average emotion recognition accuracy of DNN and RNN was very similar, at 84.59% and 84.52%, respectively. However, we observed that the simulation time for DNN was approximately 44.5% shorter than that of RNN, enabling quicker emotion prediction.

• Korean Journal of Agricultural Science
• /
• v.49 no.4
• /
• pp.837-845
• /
• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.10
• /
• pp.89-96
• /
• 2024

In this paper, we propose a deep learning model and inference pipeline that can process high-resolution fog video in real-time, addressing limitations found in classical defogging algorithms and existing deep learning-based defogging models. The key idea is separating the tasks of inferring fog color and estimating the amount of fog into two distinct models, allowing for a more efficient, lightweight design that improves inference speed. While many deep defogging models perform well on synthetic fog images, they suffer from reduced effectiveness on real-world fog images with diverse fog colors and backgrounds. We solve this problem by introducing a synthetic fog dataset generation method tailored for real-world conditions. Through experiments, we demonstrate the increase in visible distance achieved by proposed model and compare its inference speed and defogging performance against pre-trained models on real-world CCTV fog images.

• Journal of Internet Technology
• /
• v.22 no.4
• /
• pp.903-911
• /
• 2021

As cyber-attacks on Cyber-Physical System (CPS) become more diverse and sophisticated, it is important to quickly detect malicious behaviors occurring in CPS. Since CPS can collect sensor data in near real time throughout the process, there have been many attempts to detect anomaly behavior through normal behavior learning from the perspective of data-driven security. However, since the CPS datasets are big data and most of the data are normal data, it has always been a great challenge to analyze the data and implement the anomaly detection model. In this paper, we propose and evaluate the Clustered Deep One-Class Classification (CD-OCC) model that combines the clustering algorithm and deep learning (DL) model using only a normal dataset for anomaly detection. We use auto-encoder to reduce the dimensions of the dataset and the K-means clustering algorithm to classify the normal data into the optimal cluster size. The DL model trains to predict clusters of normal data, and we can obtain logit values as outputs. The derived logit values are datasets that can better represent normal data in terms of knowledge distillation and are used as inputs to the OCC model. As a result of the experiment, the F1 score of the proposed model shows 0.93 and 0.83 in the SWaT and HAI dataset, respectively, and shows a significant performance improvement over other recent detectors such as Com-AE and SVM-RBF.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2806-2825
• /
• 2018

Unsupervised learning has shown good performance on image, video and audio classification tasks, and much progress has been made so far. It studies how systems can learn to represent particular input patterns in a way that reflects the statistical structure of the overall collection of input patterns. Many promising deep learning systems are commonly trained by the greedy layerwise unsupervised learning manner. The performance of these deep learning architectures benefits from the unsupervised learning ability to disentangling the abstractions and picking out the useful features. However, the existing unsupervised learning algorithms are often difficult to train partly because of the requirement of extensive hyperparameters. The tuning of these hyperparameters is a laborious task that requires expert knowledge, rules of thumb or extensive search. In this paper, we propose a simple and effective unsupervised feature learning algorithm for image classification, which exploits an explicit optimizing way for population and lifetime sparsity. Firstly, a sparse target matrix is built by the competitive rules. Then, the sparse features are optimized by means of minimizing the Euclidean norm ($L_2$) error between the sparse target and the competitive layer outputs. Finally, a classifier is trained using the obtained sparse features. Experimental results show that the proposed method achieves good performance for image classification, and provides discriminative features that generalize well.

• Journal of Ocean Engineering and Technology
• /
• v.34 no.2
• /
• pp.147-154
• /
• 2020

Underwater acoustics that is the study of the phenomenon of underwater wave propagation and its interaction with boundaries, has mainly been applied to the fields of underwater communication, target detection, marine resources, marine environment, and underwater sound sources. Based on the scientific and engineering understanding of acoustic signals/data, recent studies combining traditional and data-driven machine learning methods have shown continuous progress. Machine learning, represented by deep learning, has shown unprecedented success in a variety of fields, owing to big data, graphical processor unit computing, and advances in algorithms. Although machine learning has not yet been implemented in every single field of underwater acoustics, it will be used more actively in the future in line with the ongoing development and overwhelming achievements of this method. To understand the research trends of machine learning applications in underwater acoustics, the general theoretical background of several related machine learning techniques is introduced in this paper.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.180-181
• /
• 2019

This paper proposes a rate control algorithm for intra coding frame in HEVC encoder using a deep learning approach. The proposed algorithm is designed for CTU level bit allocation in intra frame by considering visual features spatially and temporally. Our features are generated using visual geometry group (VGG-16) with deep convolutional layers, then it is used for bit allocation per each CTU within an intra frame. According to our experiments, the proposed algorithm can achieve -2.04% Luma component BD-rate gain with minimal bit accuracy loss against the HM-16.20 rate control model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3790-3803
• /
• 2018

Content-based image retrieval is an approach used to query images based on their semantics. Semantic based retrieval has its application in all fields including medicine, space, computing etc. Semantically generated binary hash codes can improve content-based image retrieval. These semantic labels / binary hash codes can be generated from unlabeled data using convolutional autoencoders. Proposed approach uses semi-supervised deep hashing with semantic learning and binary code generation by minimizing the objective function. Convolutional autoencoders are basis to extract semantic features due to its property of image generation from low level semantic representations. These representations of images are more effective than simple feature extraction and can preserve better semantic information. Proposed activation and loss functions helped to minimize classification error and produce better hash codes. Most widely used datasets have been used for verification of this approach that outperforms the existing methods.

• The Journal of Korea Robotics Society
• /
• v.14 no.3
• /
• pp.157-162
• /
• 2019

The video game Tetris is one of most popular game and it is well known that its game rule can be modelled as MDP (Markov Decision Process). This paper presents a DQN (Deep Q-Network) based game agent for Tetris game. To this end, the state is defined as the captured image of the Tetris game board and the reward is designed as a function of cleared lines by the game agent. The action is defined as left, right, rotate, drop, and their finite number of combinations. In addition to this, PER (Prioritized Experience Replay) is employed in order to enhance learning performance. To train the network more than 500000 episodes are used. The game agent employs the trained network to make a decision. The performance of the developed algorithm is validated via not only simulation but also real Tetris robot agent which is made of a camera, two Arduinos, 4 servo motors, and artificial fingers by 3D printing.