Earticle

In this research, we have explored state-of-the-art deep learning algorithms for face emotion recognition. In this regard, we utilize a transfer learning technique for recognizing seven classes of emotions using image classifiers such as MobileNetv2, GoogleNet, ResNet101, VGGNet19. In addition, we also compared our results with a specially designed deep learning model for face emotion recognition such as “Deep Emotion”. We have utilized the dataset FER2013 exploited by many researchers. We have analyzed the accuracy, time of training, complexity in terms of layers, and other parameters. After training on FER2013, we have deployed each model on a Korean dataset obtained from Korean dramas videos containing images of celebrities. Our ultimate goal was to label all unknown Korean dataset after training on FER2013. We have presented three different programs, i.e. (i) automatic labeling, (ii) transfer learning-based models for unknown images, (iii) deep-emotion model for face emotion recognition. We have presented a detailed analysis of all models and our corresponding programs.

Since the onset of the Coronavirus outbreak in December 2019, the virus has infected over six hundred million individuals, resulting in more than six million confirmed deaths, as reported by the World Health Organization (WHO). COVID- 19 is attributed to Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) and is recognized as a respiratory ailment, characterized by symptoms including fever, myalgia, dry cough, headache, sore throat and chest pain. As of October 2022, substantial efforts have been directed toward understanding and combatting the disease, particularly in the domains of vaccination and diagnosis. This paper focuses on the diagnosis of COVID-19 using X-ray images and leverages deep learning technologies. Specifically, we concentrate on employing three convolutional neural network models: ResNet50, InceptionV3 and MobileNetV2. The primary objective is to evaluate their performance in diagnosing COVID-19 from Xray images. During our research, we subjected these models to testing with unseen data. The results revealed that ResNet50 achieved an accuracy of 82.5%, outperforming InceptionV3 with 62.5% and MobileNetV2 with 65% accuracy. The adoption of these models not only alleviates the decision-making burden on medical experts but also enhances the precision of disease classification. The significance of this study lies in its contribution to fine-tuning diagnostic algorithms, paving the way for further research and advancements in the field.

색소 세포성 모반과 악성 흑색종은 형태가 유사하지만 유해성의 측면에서 악성 흑색종은 암으로써 무해한 색소 세포성 모반에 비해 위험한 질환이다. 이에 기반하여 기존 연구에서 색소 세포성 모반과 악성 흑색종을 구분하기 위한 연구가 있었지만, 데이터를 취득하는 과정에서 많은 cost 가 필요하였다. 본 연구에서는 이를 개선하기 위해 두 병변의 dermatoscopic 영상을 분류 학습의 데이터로 사용하여 연구를 진행하였다. 학습을 위한 데이터는 오픈소스 dermatoscopic 데이터셋인 HAM10000을 사용하였으며 모델은 CNN 에서 개선된 MobileNetV2 를 사용하였다. 실험 결과, MobileNetV2 를 사용한 학습은 3-layer CNN 에 비해 15 분의 1 가량 적은 파라미터를 가졌으며, 검증 성능과 테스트 성능에서 93%에 근사하는 성능을 보였다. 본 연구는 이전 연구에 비해 cost 측면에서 큰 개선을 이루었으며, 상용화 가능한 분류 기법을 발견했다는 점을 시사한다.

본 논문에서는 블랙 아이스를 정확하게 인식하고 도로 노면 정보를 운전자에게 미리 알려줘서 속도를 제어하고 예방 조치를 취할 수 있도록 하기 위해 열화 도로 영상을 기반으로 블랙 아이스 검출하기 위해 lightweight 네트워크를 제안한다. 전이학습을 이용하여 블랙 아이스 인식 실험을 하였고, 블랙 아이스 인식의 정확도 향상을 위해 MobileNetV2 기반의 개선된 lightweight 네트워크를 개발하였다. 계산량을 줄이기 위해 Linear Bottleneck 및 Inverted Residuals를 활용하여 4개의 Bottleneck 그룹을 사용하고 모델의 인식률 향상을 위해 각 Bottleneck 그룹에 3×3 컨볼루션 레이어를 연결하여 지역적 특징 추출을 강화하고 특징 맵의 수를 늘렸다. 마지막으로 구축된 블랙 아이스 데이터 세트 대상으로 블랙 아이스 인식 실험을 진행하였으며, 제안된 모델은 블랙 아이스에 대해 99.07%의 정확한 인식률을 나타내었다.

To accurately identify black ice and warn the drivers of information in advance so they can control speed and take preventive measures. In this paper, we propose a lightweight black ice detection network based on infrared road images. A black ice recognition network model based on CNN transfer learning has been developed. Additionally, to further improve the accuracy of black ice recognition, an enhanced lightweight network based on MobileNetV2 has been developed. To reduce the amount of calculation, linear bottlenecks and inverse residuals was used, and four bottleneck groups were used. At the same time, to improve the recognition rate of the model, each bottleneck group was connected to a 3×3 convolutional layer to enhance regional feature extraction and increase the number of feature maps. Finally, a black ice recognition experiment was performed on the constructed infrared road black ice dataset. The network model proposed in this paper had an accurate recognition rate of 99.07% for black ice.

최근 인공지능 기술의 발달에 따라 여러 분야에 인공지능 기술이 활발히 응용되고 있다. 그중 안전 관리 분야에서 사람 인식을 통한 안전 관리 시스템의 지속적인 개발이 요구되고 있다. 그러나 실내 한정된 공간에서 사람들의 밀집도가 높은 경우 오브젝트의 중복도가 높아져 인식 성능이 낮아질 수 있다. 이를 해결하기 위해 본 논문은 사람의 밀집도가 높은 실내 환경에서 기존 객체 인식 기법의 성능을 분석하였다. 그리고 이러한 제한적인 환경에서 최적의 좋은 성능을 보일 수 있는 SSDLite와 MobileNetV2 모델을 기반으로 soft-NMS 기법을 적용하여 성능을 분석하였다.

Plant diseases can substantially affect crop productivity and contribute to agricultural losses, creating a need for accurate and automated disease identification methods. Deep learning has become an effective approach for image-based plant disease recognition; however, relying on a single CNN architecture may limit the diversity of visual representations available for classification. This study presents a fine-tuned hybrid framework that combines MobileNetV2 and EfficientNetB0 through feature-level fusion for plant disease classification. The two backbone networks provide complementary representations, with MobileNetV2 offering a lightweight feature extraction capability and EfficientNetB0 providing richer visual representations. ImageNet-pretrained weights were employed, followed by selective fine-tuning to adapt the learned representations to the target plant disease dataset. Experiments were performed using the PlantVillage dataset containing 38 plant disease classes, with image preprocessing, augmentation, transfer learning, and fine-tuning incorporated into the experimental procedure. The proposed fine-tuned hybrid model achieved a validation accuracy of 98.90%, compared with 93.57% for MobileNetV2, 95.86% for EfficientNetB0, and 97.94% for the hybrid model without fine-tuning. The model also obtained high Precision, Recall, and F1-score values across the evaluated disease categories. Overall, the results indicate that combining complementary feature representations with selective fine-tuning can improve classification performance on the PlantVillage dataset and provide a promising basis for practical plant disease diagnosis in smart agriculture applications.