• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.107-113
• /
• 2024

Scheduling of semiconductor test facilities has been crucial since effective scheduling contributes to the profits of semiconductor enterprises and enhances the quality of semiconductor products. This study aims to solve the scheduling problems for the wafer burn-in test facilities of the semiconductor back-end process by utilizing simulation and deep reinforcement learning-based methods. To solve the scheduling problem considered in this study. we propose novel state, action, and reward designs based on the Markov decision process. Furthermore, a neural network is trained by employing the recent RL-based method, named proximal policy optimization. Experimental results showed that the proposed method outperformed traditional heuristic-based scheduling techniques, achieving a higher due date compliance rate of jobs in terms of total job completion time.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.161-172
• /
• 2024

Approximately 89% of all capsizing accidents involve small vessels, and despite their relatively high accident rates, small vessels are not subject to ship stability regulations. Small vessels, where the provision of essential basic design documents for stability calculations is omitted, face challenges in directly calculating their stability. In this study, considering that the majority of domestic coastal small vessels are of the Chine-type design, the goal is to establish the major hull form characteristic data of vessels, which can be identified from design documents such as the general arrangement drawing, as input data. Through the application of a deep learning approach, specifically a multilayer neural network structure, we aim to infer hydrostatic curves, operational draft ranges, and more. The ultimate goal is to confirm the possibility of directly calculating the initial stability of small vessels.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.22-34
• /
• 2024

Exposure to varied noisy environments impairs the recognition performance of artificial intelligence-based speech recognition technologies. Degraded-performance services can be utilized as limited systems that assure good performance in certain environments, but impair the general quality of speech recognition services. This study introduces an audiovisual speech recognition (AVSR) model robust to various noise settings, mimicking human dialogue recognition elements. The model converts word embeddings and log-Mel spectrograms into feature vectors for audio recognition. A dense spatial-temporal convolutional neural network model extracts features from log-Mel spectrograms, transformed for visual-based recognition. This approach exhibits improved aural and visual recognition capabilities. We assess the signal-to-noise ratio in nine synthesized noise environments, with the proposed model exhibiting lower average error rates. The error rate for the AVSR model using a three-feature multi-fusion method is 1.711%, compared to the general 3.939% rate. This model is applicable in noise-affected environments owing to its enhanced stability and recognition rate.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.37-47
• /
• 2024

This study presents the results of designing a system that determines the location of a person in an indoor environment based on a single IMU sensor attached to the tip of a person's shoe in an area where GPS signals are inaccessible. By adjusting for human footfall, it is possible to accurately determine human location and trajectory by correcting errors originating from the Inertial Measurement Unit (IMU) combined with advanced machine learning algorithms. Although there are various techniques to identify stepping, our study successfully recognized stepping with 98.7% accuracy using an artificial intelligence model known as Long Short-Term Memory (LSTM). Drawing upon the enhancements in our methodology, this article demonstrates a novel technique for generating a 200-meter trajectory, achieving a level of precision marked by a 2.1% error margin. Indoor pedestrian navigation systems, relying on inertial measurement units attached to the feet, have shown encouraging outcomes.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.212-220
• /
• 2024

When a typhoon or natural disaster occurs, a significant number of orchard fruits fall. This has a great impact on the income of farmers. In this paper, we introduce an AI-based method to enhance low-quality raw images. Specifically, we focus on apple images, which are being used as AI training data. In this paper, we utilize both a basic program and an artificial intelligence model to conduct a general image process that determines the number of apples in an apple tree image. Our objective is to evaluate high and low performance based on the close proximity of the result to the actual number. The artificial intelligence models utilized in this study include the Convolutional Neural Network (CNN), VGG16, and RandomForest models, as well as a model utilizing traditional image processing techniques. The study found that 49 red apple fruits out of a total of 87 were identified in the apple tree image, resulting in a 62% hit rate after the general image process. The VGG16 model identified 61, corresponding to 88%, while the RandomForest model identified 32, corresponding to 83%. The CNN model identified 54, resulting in a 95% confirmation rate. Therefore, we aim to select an artificial intelligence model with outstanding performance and use a real-time object separation method employing artificial function and image processing techniques to identify orchard fruits. This application can notably enhance the income and convenience of orchard farmers.

• 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.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.11 no.3
• /
• pp.159-166
• /
• 2007

This paper evaluates the soundness of structural elements using Wavelet Packet Transform (WPT). WPT is applied to the response acceleration of a framed structure which is subjected to earthquake load to decompose the response acceleration, then the energy of each component is calculated. The first five largest components in energy magnitude among the decomposed components are selected as input to an ANN to identify the damage location and severity. Two nodes in output layer yield damaged element and damage severity respectively. This method successfully evaluates the amount of damage and its location in the structure.

• Earthquakes and Structures
• /
• v.27 no.3
• /
• pp.177-189
• /
• 2024

Accurately predicting the failure modes of reinforced concrete (RC) columns is essential for structural design and assessment. In this study, the challenges of imbalanced datasets and complex feature selection in machine learning (ML) methods were addressed through an optimized ML approach. By combining feature selection and oversampling techniques, the prediction of seismic failure modes in rectangular RC columns was improved. Two feature selection methods were used to identify six input parameters. To tackle class imbalance, the Borderline-SMOTE1 algorithm was employed, enhancing the learning capabilities of the models for minority classes. Eight ML algorithms were trained and fine-tuned using k-fold shuffle split cross-validation and grid search. The results showed that the artificial neural network model achieved 96.77% accuracy, while k-nearest neighbor, support vector machine, and random forest models each achieved 95.16% accuracy. The balanced dataset led to significant improvements, particularly in predicting the flexure-shear failure mode, with accuracy increasing by 6%, recall by 8%, and F1 scores by 7%. The use of the Borderline-SMOTE1 algorithm significantly improved the recognition of samples at failure mode boundaries, enhancing the classification performance of models like k-nearest neighbor and decision tree, which are highly sensitive to data distribution and decision boundaries. This method effectively addressed class imbalance and selected relevant features without requiring complex simulations like traditional methods, proving applicable for discerning failure modes in various concrete members under seismic action.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.671-682
• /
• 2024

Violence can be committed anywhere, even in crowded places. It is hence necessary to monitor human activities for public safety. Surveillance cameras can monitor surrounding activities but require human assistance to continuously monitor every incident. Automatic violence detection is needed for early warning and fast response. However, such automation is still challenging because of low video resolution and blind spots. This paper uses ResNet50v2 and the gated recurrent unit (GRU) algorithm to detect violence in the Movies, Hockey, and Crowd video datasets. Spatial features were extracted from each frame sequence of the video using a pretrained model from ResNet50V2, which was then classified using the optimal trained model on the GRU architecture. The experimental results were then compared with wavelet feature extraction methods and classification models, such as the convolutional neural network and long short-term memory. The results show that the proposed combination of ResNet50V2 and GRU is robust and delivers the best performance in terms of accuracy, recall, precision, and F1-score. The use of ResNet50V2 for feature extraction can improve model performance.

• Journal of Platform Technology
• /
• v.11 no.6
• /
• pp.13-20
• /
• 2023

Regularly inspecting vehicle tires' condition is imperative for driving safety and comfort. Poorly maintained tires can pose fatal risks, leading to accidents. Unfortunately, manual tire visual inspections are often considered no less laborious than employing an automatic tire inspection system. Nevertheless, an automated tire inspection method can significantly enhance driver compliance and awareness, encouraging routine checks. Therefore, there is an urgency for automated tire inspection solutions. Here, we focus on developing a deep learning (DL) model to predict cracked tires. The main idea of this study is to demonstrate the comparative analysis of DenseNet121, VGG-19 and EfficientNet Convolution Neural Network-based (CNN) Transfer Learning (TL) and suggest which model is more recommended for cracked tire classification tasks. To measure the model's effectiveness, we experimented using a publicly accessible dataset of 1028 images categorized into two classes. Our experimental results obtain good performance in terms of accuracy, with 0.9515. This shows that the model is reliable even though it works on a dataset of tire images which are characterized by homogeneous color intensity.