• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.126-146
• /
• 2024

Caladium bicolor is one of the most popular plants in Thailand. The original species of Caladium bicolor was found a hundred years ago. Until now, there are more than 500 species through multiplication. The classification of Caladium bicolor can be done by using its color and shape. This study aims to develop a model to classify Caladium bicolor using a transfer learning technique. This work also presents a proof of concept, GUI design, and web application deployment using the user-design-center method. We also evaluated the performance of the following pre-trained models in this work, and the results are as follow: 87.29% for AlexNet, 90.68% for GoogleNet, 93.59% for XceptionNet, 93.22% for MobileNetV2, 89.83% for RestNet18, 88.98% for RestNet50, 97.46% for RestNet101, and 94.92% for InceptionResNetV2. This work was implemented using MATLAB R2023a.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.109-117
• /
• 2023

Defect detection is one of the key factors in fabric quality control. To improve the speed and accuracy of denim fabric defect detection, this paper proposes a defect detection algorithm based on cascading feature extraction architecture. Firstly, this paper extracts these weight parameters of the pre-trained VGG16 model on the large dataset ImageNet and uses its portability to train the defect detection classifier and the defect recognition classifier respectively. Secondly, retraining and adjusting partial weight parameters of the convolution layer were retrained and adjusted from of these two training models on the high-definition fabric defect dataset. The last step is merging these two models to get the defect detection algorithm based on cascading architecture. Then there are two comparative experiments between this improved defect detection algorithm and other feature extraction methods, such as VGG16, ResNet-50, and Xception. The results of experiments show that the defect detection accuracy of this defect detection algorithm can reach 94.3% and the speed is also increased by 1-3 percentage points.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.83-88
• /
• 2024

In this research, we propose a Semi-Supervised learning based railroad surface defect detection method. The Resnet50 model, pretrained on ImageNet, was employed for the training. Data without labels are randomly selected, and then labeled to train the ResNet50 model. The trained model is used to predict the results of the remaining unlabeled training data. The predicted values exceeding a certain threshold are selected, sorted in descending order, and added to the training data. Pseudo-labeling is performed based on the class with the highest probability during this process. An experiment was conducted to assess the overall class classification performance based on the initial number of labeled data. The results showed an accuracy of 98% at best with less than 10% labeled training data compared to the overall training data.

• Management & Information Systems Review
• /
• v.39 no.3
• /
• pp.1-16
• /
• 2020

The current tariff return system requires tax officials to calculate tax amount by themselves and pay the tax amount on their own responsibility. In other words, in principle, the duty and responsibility of reporting payment system are imposed only on the taxee who is required to calculate and pay the tax accurately. In case the tax payment system fails to fulfill the duty and responsibility, the additional tax is imposed on the taxee by collecting the tax shortfall and imposing the tax deduction on For this reason, item classifications, together with tariff assessments, are the most difficult and could pose a significant risk to entities if they are misclassified. For this reason, import reports are consigned to customs officials, who are customs experts, while paying a substantial fee. The purpose of this study is to classify HS items to be reported upon import declaration and to indicate HS codes to be recorded on import declaration. HS items were classified using the attached image in the case of item classification based on the case of the classification of items by the Korea Customs Service for classification of HS items. For image classification, CNN was used as a deep learning algorithm commonly used for image recognition and Vgg16, Vgg19, ResNet50 and Inception-V3 models were used among CNN models. To improve classification accuracy, two datasets were created. Dataset1 selected five types with the most HS code images, and Dataset2 was tested by dividing them into five types with 87 Chapter, the most among HS code 2 units. The classification accuracy was highest when HS item classification was performed by learning with dual database2, the corresponding model was Inception-V3, and the ResNet50 had the lowest classification accuracy. The study identified the possibility of HS item classification based on the first item image registered in the item classification determination case, and the second point of this study is that HS item classification, which has not been attempted before, was attempted through the CNN model.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.2
• /
• pp.17-26
• /
• 2022

In this paper, we propose a novel method of performing convolutional operations on a 2-D Processing Element(PE) array. The conventional method [1] of mapping the convolutional operation using the 2-D PE array lacks flexibility and provides low utilization of PEs. However, by mapping a convolutional operation from a 2-D PE array to a 1-D PE array, the proposed method can increase the number and utilization of active PEs. Consequently, the throughput of the proposed Deep Convolutional Neural Network(DCNN) accelerator can be increased significantly. Furthermore, the power consumption for the transmission of weights between PEs can be saved. Based on the simulation results, the performance of the proposed method provides approximately 4.55%, 13.7%, and 2.27% throughput gains for each of the convolutional layers of AlexNet, VGG16, and ResNet50 using the DCNN accelerator with a (weights size) x (output data size) 2-D PE array compared to the conventional method. Additionally the proposed method provides approximately 63.21%, 52.46%, and 39.23% power savings.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.217-228
• /
• 2022

Currently, there are increasing demands for applying deep neural networks (DNNs) in the embedded domain such as classification and object detection. The DNN processing in embedded domain often requires custom hardware such as NPU for acceleration due to the constraints in power, performance, and area. Processing DNN models requires a large amount of data, and its seamless transfer to NPU is crucial for performance. In this paper, we developed a cycle-accurate NPU simulator to evaluate diverse NPU microarchitectures. In addition, we propose a novel technique for reducing the number of memory accesses when processing convolutional layers in convolutional neural networks (CNNs) on the NPU. The main idea is to reuse data with memory interleaving, which recycles the overlapping data between previous and current input windows. Data memory interleaving makes it possible to quickly read consecutive data in unaligned locations. We implemented the proposed technique to the cycle-accurate NPU simulator and measured the performance with LeNet-5, VGGNet-16, and ResNet-50. The experiment shows up to 2.08x speedup in processing one convolutional layer, compared to the baseline.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.2
• /
• pp.41-50
• /
• 2023

Gait analysis is an important tool in the clinical management of cerebral palsy, allowing for the assessment of condition severity, identification of potential gait abnormalities, planning and evaluation of interventions, and providing a baseline for future comparisons. However, traditional methods of gait analysis are costly and time-consuming, leading to a need for a more convenient and continuous method. This paper proposes a method for analyzing the posture of cerebral palsy patients using only smartphone videos and deep learning models, including a ResNet-based image tilt correction, AlphaPose for human pose estimation, and SmoothNet for temporal smoothing. The indicators employed in medical practice, such as the imbalance angles of shoulder and pelvis and the joint angles of spine-thighs, knees and ankles, were precisely examined. The proposed system surpassed pose estimation alone, reducing the mean absolute error for imbalance angles in frontal videos from 4.196° to 2.971° and for joint angles in sagittal videos from 5.889° to 5.442°.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.493-494
• /
• 2023

본 논문은 벚꽃나무 영상 데이터를 활용하여 벚꽃의 상태(개화, 만개, 낙화)를 실시간으로 분류하는 연구를 소개한다. 이 연구의 목적은, 실시간으로 취득되는 벚꽃나무의 영상 데이터를 사전에 학습된 CNN 기반 이미지 분류 모델을 통해 벚꽃의 상태에 따라 분류하는 것이다. 약 1,000장의 벚꽃나무 이미지를 활용하여 CNN 모델을 학습시키고, 모델이 새로운 이미지에 대해 얼마나 정확하게 벚꽃의 상태를 분류하는지를 평가하였다. 학습데이터는 훈련 데이터와 검증 데이터로 나누었으며, 개화, 만개, 낙화 등의 상태별로 폴더를 구분하여 관리하였다. 또한, ImageNet 데이터셋에서 사전 학습된 ResNet50 가중치를 사용하는 전이학습 방법을 적용하여 학습 과정을 더 효율적으로 수행하고, 모델의 성능을 향상시켰다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.252-254
• /
• 2019

본 논문은 합성곱 기반의 Single Shot Multibox Detector(SSD) [1] 의 구조를 이용하여 다양한 스케일의 얼굴들을 잘 검출하도록 하였다. 얼굴 검출은 물체 검출과는 다르게 얼굴의 높이와 너비의 비율이 다소 일정하고 크기가 작은 경우가 많은데, 이에 맞게 얼굴 검출이 용이하도록 anchor의 스케일, 비율, 크기를 변경하였다. 특징점 추출 네트워크는 깊은 네트워크의 최적화를 용이하게 하는 skip connection을 이용한 ResNet-50 [2] 기반을 사용하였다. 다양한 크기, 조명, 환경, 각도의 얼굴들을 포함하는 영상들로 이뤄진 Wider Face[3] 데이터 셋의 easy validation set으로 실험한 결과 0.782과 hard validation set에서 0.611의 average precision을 보였다.