• Journal of Animal Science and Technology
• /
• v.63 no.6
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.

• Journal of Advanced Navigation Technology
• /
• v.26 no.3
• /
• pp.166-171
• /
• 2022

In this paper, we propose an algorithm to improve DoA(direction of arrival) estimation performance of the subspace-based method by generating high robustness correlation matrix of the signals incident on the uniformly linear array antenna. The existing subspace-based DoA estimation method estimates the DoA by obtaining a correlation matrix and dividing it into a signal subspace and a noise subspace. However, the component of the correlation matrix obtained from the low SNR and small number of snapshots inaccurately estimates the signal subspace due to the noise component of the antenna, thereby degrading the DoA estimation performance. Therefore a robust correlation matrix is generated by arranging virtual signal vectors obtained from the existing correlation matrix in a sliding manner. As a result of simulation using MUSIC and ESPRIT, which are representative subspace-based methods,, the computational complexity increased by less than 2.5% compared to the existing correlation matrix, but both MUSIC and ESPRIT based on RMSE 1° showed superior DoA estimation performance with an SNR of 3dB or more.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.905-910
• /
• 2022

Drowsy driving requires a lot of social attention because it increases the incidence of traffic accidents and leads to fatal accidents. The number of accidents caused by drowsy driving is increasing every year. Therefore, in order to solve this problem all over the world, research for measuring various biosignals is being conducted. Among them, this paper focuses on non-contact biosignal analysis. Various noises such as engine, tire, and body vibrations are generated in a running vehicle. To measure the driver's heart rate and respiration rate in a driving vehicle with a piezoelectric sensor, a sensor plate that can cushion vehicle vibrations was designed and noise generated from the vehicle was reduced. In addition, we developed a system for classifying whether the driver is sleeping or not by extracting the model using the CNN-LSTM ensemble learning technique based on the signal of the piezoelectric sensor. In order to learn the sleep state, the subject's biosignals were acquired every 30 seconds, and 797 pieces of data were comparatively analyzed.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.1
• /
• pp.17-33
• /
• 2023

Disasters in coastal regions are a constant source of damage due to their uncertainty and complexity, leading to the proposal of green infrastructure as a nature-based solution that incorporates the concept of resilience to address the limitations of traditional grey infrastructure. This study analyzed trends in research related to coastal disasters and green infrastructure by conducting a co-occurrence keyword analysis of 2,183 articles collected from the Web of Science (WoS). The analysis resulted in the classification of the literature into four clusters. Cluster 1 is related to coastal disasters and tsunamis, as well as predictive simulation techniques, and includes keywords such as surge, wave, tide, and modeling. Cluster 2 focuses on the social system damage caused by coastal disasters and theoretical concepts, with keywords such as population, community, and green infrastructure elements like habitat, wetland, salt marsh, coral reef, and mangrove. Cluster 3 deals with coastal disaster-related sea level rise and international issues, and includes keywords such as sea level rise (or change), floodplain, and DEM. Finally, cluster 4 covers coastal erosion and vulnerability, and GIS, with the theme of 'coastal vulnerability and spatial technique'. Keywords related to green infrastructure in cluster 2 have been continuously appearing since 2016, but their focus has been on the function and effect of each element. Based on this analysis, implications for planning and management processes using green infrastructure in response to coastal disasters have been derived. This study can serve as a valuable resource for future research and policy in responding to and managing various disasters in coastal regions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.115-119
• /
• 2023

The natural language processing models used in current artificial intelligence are huge, causing various difficulties in processing and analyzing data in real time. In order to solve these difficulties, we proposed a method to improve the efficiency of processing by using less memory and checked the performance of the proposed model. The technique applied in this paper to evaluate the performance of the proposed model is to divide the large corpus by adjusting the number of attention heads and embedding size of the BERT[1] model to be small, and the results are calculated by averaging the output values of each forward. In this process, a random offset was assigned to the sentences at every epoch to provide diversity in the input data. The model was then fine-tuned for classification. We found that the split processing model was about 12% less accurate than the unsplit model, but the number of parameters in the model was reduced by 56%.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.411-425
• /
• 2023

Today, AI (Artificial Intelligence) technology is widely used in various fields, performing classification and regression tasks according to the purpose of use, and research is also actively progressing. Especially in the field of security, unexpected threats need to be detected, and unsupervised learning-based anomaly detection techniques that can detect threats without adding known threat information to the model training process are promising methods. However, most of the preceding studies that provide interpretability for AI judgments are designed for supervised learning, so it is difficult to apply them to unsupervised learning models with fundamentally different learning methods. In addition, previously researched vision-centered AI mechanism interpretation studies are not suitable for application to the security field that is not expressed in images. Therefore, In this paper, we use a technique that provides interpretability for detected anomalies by searching for and comparing optimization references, which are the source of intrusion attacks. In this paper, based on reference, we propose additional logic to search for data closest to real data. Based on real data, it aims to provide a more intuitive interpretation of anomalies and to promote effective use of an anomaly detection model in the security field.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.160-160
• /
• 2020

조류는 계절별 기상 및 수질 조건에 따라 규조, 녹조, 남조의 발생 및 천이가 이루어지는데 최근 기후 변화로 인해 출연종 별 발생 및 천이의 시기 또한 빨라지고 있다. 이 중 남조류의 경우 초여름에 발생하여 급격한 증식으로 대발생되어 녹조현상을 야기하고 이는 해당 수역의 생태계 파괴, 그 이외에도 사회적, 경제적, 환경적인 측면에서 많은 문제를 유발한다. 하천·호소의 조류의 발생과 거동에 대한 이해와 효과적인 대응책 마련을 위하여 현상에 대한 모니터링이 선행되어야 하지만 기존 조사방식은 점, 선 단위의 간헐적 측정을 통해 진행되고 있어 많은 인력과 시간이 필요로 하고 있는 실태이다. 현재 이에 따른 문제 해결을 위한 하천·호소의 원격탐사 기법을 이용한 조류의 발생 및 거동에 대한 모니터링 연구가 많이 진행되고 있다. 본 연구에서는 초분광 영상을 이용한 원격 탐사 모니터링을 위한 선행연구를 위해 400-1000 nm에서 NIR(visNIR)파장을 분석할 수 있는 초분광 카메라 CORNING사의 micro HSITM 410 shark와 영상 흔들림 보정을 위한 DJI사의 로닌-MX를, 이용하여 현재 녹조류, 남조류 5종의 배양액과 방사보정을 위해 99% 반사율의 반사판과 함께 촬영하여 영상을 수집하였다. 수집된 영상을 통하여 방사보정 및 해당 Base 제거를 통한 조류의 분광 정보 추출 과정을 통해 조류별 분광 정보를 추출, 분석하여 해당 조류의 분광특성을 파악하고 기초 라이브러리를 구축하여 제시함으로 추후 하천·호소에서의 초분광 영상 기반 원격탐사 모니터링에 적용하고자 한다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.845-850
• /
• 2023

In this paper, we propose a method for diagnosing ball bearing vibration using transfer learning. STFT, which can analyze vibration signals in time-frequency, was used as input to CNN to diagnose failures. In order to rapidly learn CNN-based deep artificial neural networks and improve diagnostic performance, we proposed a transfer learning-based deep learning learning technique. For transfer learning, the feature extractor and classifier were selectively learned using a VGG-based image classification model, the data set for learning was publicly available ball bearing vibration data provided by Case Western Reserve University, and performance was evaluated by comparing the proposed method with the existing CNN model. Experimental results not only prove that transfer learning is useful for condition diagnosis in ball bearing vibration data, but also allow other industries to use transfer learning to improve condition diagnosis.