Earticle

Early and accurate detection of Alzheimer’s Disease (AD) is critical for timely intervention. While prior deep learning models have achieved promising results using sagittal and coronal slices, the potential diagnostic contribution of axial views remains underexplored. In this study, we propose an enhanced dual-path attention-guided convolutional neural network (CNN) that integrates multi-view 2D T1-weighted MRI slices, including parasagittal, coronal, and axial planes, to improve classification of AD, mild cognitive impairment (MCI), and cognitively normal (CN) subjects. The architecture combines a localized SNeurodCNN branch with a global Inception-v4 backbone augmented by Convolutional Block Attention Module (CBAM). The addition of axial slices produced statistically significant improvements, increasing accuracy from 97.98% to 98.83% (p < 0.05) and enhancing AUC from 0.990 to 0.996. These results demonstrate that axial T1- weighted views provide unique diagnostic cues including ventricular enlargement and cortical thinning that are not fully captured by sagittal or coronal planes, thus offering complementary value in multi-view Alzheimer’s detection frameworks.

카디널리티가 서로 다른 다중 범주형 속성을 효과적으로 학습하는 것은, 특히 일부 속성이 결측되는 상황에서 딥러닝 모델에 있어 중요한 도전 과제이다. 본 연구에서는 관측된 속성에 대해서는 원-핫 인코딩을 적용하고, 결측된 속성에 대해서 는 균등 분포로 표현하여 확률적 다중 범주형 입력을 구성하고, 이를 속성별로 서로 다른 차원의 블록으로 처리하는 입력 구조를 사용한다. 입력층에서 속성 블록의 경계가 명시적으로 제공되지 않음에도 불구하고, 딥러닝 모델은 입력의 희소성과 국소적 활성화 특성을 활용하여 각 속성 블록을 암묵적으로 구분하며 학습한다. 이러한 메커니즘은 속성별 독립적인 표현을 유도하며, 결측 데이터에 대해서도 정규화 효과를 통해 예측의 안정성과 강건성을 향상시킨다. 결과적으로 본 연구는 별도의 구조적 수정 없이도 일반적인 딥러닝 모델이 이질적인 범주형 입력의 블록 구조를 자율적으로 형성하고 학습할 수 있음을 이론적 분석과 실험을 통해 알아본다.

Effectively learning multi-categorical attributes with varying cardinalities poses a significant challenge for deep learning models, particularly when some attributes contain missing values. This study proposes an input structure in which observed attributes are encoded using one-hot encoding, while missing attributes are represented as uniform distributions. These are then combined into an input vector composed of attribute-specific blocks of differing dimensionalities. Despite the absence of explicit boundary information between attribute blocks at the input layer, the deep learning model implicitly distinguishes these blocks by leveraging the sparsity and localized activation patterns of the input. This mechanism promotes independent representations for each attribute and enhances prediction stability and robustness through a normalization effect, even in the presence of missing data. Overall, the study demonstrates through theoretical analysis and empirical results that a standard deep learning model can autonomously learn and represent the block structure of heterogeneous categorical inputs without requiring structural modifications.

CCTV 영상을 이용한 승가행위 탐지 연구는 side-view, top-view, 정형화된 실험 환경에서 촬영한 CCTV 영상에서 승가행위를 탐지하였다. 이 논문에서는 실제 축산농가에 설치된 다양한 환경의 CCTV 영상에서 승가행위를 탐지하고, 승가행위 구간을 추출하는 딥러닝 기반의 승가행위 검출 시스템을 제안한다. 제안 시스템에 서는 텐서플로우의 SSD 기반 객체인식 모델을 전이학습하여 생성한 학습모델(trained model)을 이용하여 CCTV 영상에서 추출한 프레임 이미지로부터 승가행위 객체를 탐지한 후, 평균 1-3초동안 이루어지는 승가행위 구간에서 탐지되는 다수의 정상탐지와 오탐지를 하나의 승가행위로 단일화하여 최종적인 승가행위를 검출한다. 실험 결과, 승가행위 탐지 학습모델의 정밀도, 정확도, 재현율은 각각 약 84%, 88%, 93%를 기록하였고, 프레임 단위의 탐지 결과에 단일화를 적용한 승가행위 검출 시스템의 정밀도, 정확도, 재현율은 각각 약 87%, 91%, 96%로 향상된 결 과를 기록하였다.

Previous studies detected mounting in CCTV video taken in side-view, top-view and formatted experimental environments. In this paper, we propose deep learning based Mounting Detection System that detects mounting scene and extracts video section for mounting from CCTV video in various environments. We use the trained model created by transfer learning with TensorFlow’s SSD-based object detection model to detect mounting object from the frame image extracted from CCTV video. In addition, we finally extract video section for mounting by unifying a number of true and false mounting detections during an average of 1-3 seconds. As a result of the experiment, the precision, accuracy, and recall of the trained model were recorded at about 84%, 88%, and 93% respectively. And the performance of the Mounting Detection System that apply unification to the detection results of each frame were about 87%, 91%, and 96%, respectively.

Activity recognition in sports is often complex task resulting from the rapid dynamic interaction within players. In this paper, pre-trained VGG-16, deep learning based hockey activity recognition model has been proposed. Own hockey dataset consisting of four main activity includes free hit, goal, penalty corner and long corner was constructed as there are no existing field hockey datasets available. Experimental results indicate that the pre-trained deep learning model generates comparative results on this challenging dataset by tweaking the hyperparameters of this pre-trained model.

As the population and income levels rise, meat consumption steadily increases annually. However, the number of farms and farmers producing meat decrease during the same period, reducing meat sufficiency. Information and Communications Technology (ICT) has begun to be applied to reduce labor and production costs of livestock farms and improve productivity. This technology can be used for rapid pregnancy diagnosis of sows; the location and size of the gestation sacs of sows are directly related to the productivity of the farm. In this study, a system proposes to determine the number of gestation sacs of sows from ultrasound images. The system used the YOLOv7-E6E model, changing the activation function from sigmoid-weighted linear unit (SiLU) to a multi-activation function (SiLU + Mish). Also, the upsampling method was modified from nearest to bicubic to improve performance. The model trained with the original model using the original data achieved mean average precision of 86.3%. When the proposed multi-activation function, upsampling, and AutoAugment were applied, the performance improved by 0.3%, 0.9%, and 0.9%, respectively. When all three proposed methods were simultaneously applied, a significant performance improvement of 3.5% to 89.8% was achieved.

In this paper, we propose a soft actor?critic (SAC) algorithm with hindsight experience replay (HER), called SACHER, which is a class of deep reinforcement learning (DRL) algorithm. SAC is an off-policy model-free DRL algorithm that outperforms earlier DRL algorithms in terms of exploration and robustness. However, in SAC, maximizing the entropy-augmented objective degrades the optimality of learning outcomes. We propose SACHER to improve the learning performance of SAC. We apply SACHER to the path planning and collision avoidance control of unmanned aerial vehicles (UAVs). We demonstrate the effectiveness of SACHER in terms of the success rate, learning speed, and collision avoidance performance of UAV operation.

Fire is an extremely catastrophic disaster that leads to the destruction of forests, human assets, reduced soil fertility, land resources, and the cause of global warming. In the current decade, fire detection and its management are the major concern of several researchers to prevent social, ecological, and economic damages. To overcome such kind of losses, early fire detection, and the automatic response is very significant. Moreover, achieving high accuracy with reducing inference time and model size is also challenging for the Unmanned Aerial Vehicle (UAVs). Therefore, in this work, we enabled the VGG16 architecture for UAV in terms of reducing its learning parameters from 138 million to 11.4 million for early fire detection. The proposed system is inexpensive in terms of computation and size. The performance of our proposed work is evaluated over the custom dataset. We performed comprehensive experiments using various deep learning architectures such as VGG16, ResNet50, and the proposed CNN model. The experimental results based on the proposed model achieved an accuracy of 98% on 50 epochs.

자율 주행과 교통 감시의 가장 중요한 것은 차량 감지 기술이다. 또한, 포트홀과 같이 도로의 특정 상황 은 교통사고와 차량 파손의 원인이다. 본 논문에서는 도로의 포트홀을 자동으로 발견하기 위해서 딥 러닝 모델을 사용한다. 본 연구에서는 이미지에서 차량 및 포트홀을 감지 할 수 있도록 빠른 영역 기반 컨볼루션 신경망 (Faster R-CNN)과 인셉션 네트워크 V2 모델을 사용하여 모델을 활용하였다. 제안하는 연구를 검증하기 위해 Faster R-CNN, Single Shot Detector(SSD), YOLO 알고리즘과 성능, 정확도수, 검출 시간 및 장단점을 비교 하였다. 논문에서 제안하는 방법은 SSD 및 YOLO와 같은 기존 방법보다 좋은 성능을 보여주었다. 여기서 성능 평가의 척도는 정확도를 사용하였다. 제안된 방법은 SSD 및 YOLO와 같은 이전 방법에 비해 6%의 개선을 보여준다.

Vehicle detection is the most crucial component of automated driving and traffic monitoring. Additionally, pothole-caused bad road conditions are to blame for collisions and car damage. Deep learning models are used in the suggested work. In this study, a fast region-based convolutional neural network (Faster R-CNN) and an inception network V2 model were utilized to detect vehicles and potholes in images. To verify the proposed study, Faster R-CNN, Single Shot Detector (SSD), and YOLO algorithms were compared in performance, number of accuracy, detection time, and strengths and weaknesses. Accuracy serves as the benchmark for performance evaluation. When compared to the earlier approaches, such as SSD and YOLO, the suggested method exhibits a 6% improvement.

산사태는 인명과 사회 경제적 인프라에 심각한 피해를 초래하는 대표적인 자연재해로, 위험지역의 정밀 한 공간 분할 및 조기 탐지가 재난관리에 필수적이다. 본 연구에서는 U-Net 딥러닝 아키텍처를 기반으로 패치 크기(128×128, 256×256)에 따른 산사태 위험지역 자동 분류 성능을 비교·분석하였다. 연구 대상지는 경북 예천군 보곡면의 급경사지로, 드론 영상 및 포인트 클라우드 자료를 활용해 0.1m 해상도의 디지털 표고 모델(DEM)을 구축하고, 이를 딥러닝 학습 및 평가에 적용하였다. 분석 결과, 128×128 패치 크기 모델은 전체 정확도 70.5%의 정확도를 기록했으며, 비위험과 위험 클래스에서 F1-score 0.582, 0.599를 보여 균형 잡힌 분류 성능을 나타냈다. 반면 256×256 패치 모델은 65.96%의 정확도와 매우 낮은 0.248, 0.007의 F1-score를 기록했으며, NoData 클래스에서는 0.786의 높은 F1-score를 보여 대부분의 예측이 NoData 영역에 집중됨을 나타냈다. 이러한 결과는 작은 패치 크기가 지역적 지형 변동성을 포착하고 산사태 감지 성능을 향상시키는데 더 효과적임을 시사한다.

Landslides are natural disasters that cause severe damage to human life and socio-economic infrastructure, making precise spatial delineation and early detection of hazardous areas essential for disaster management. This study compares automated classification performance of landslide hazard zones using U-Net deep learning architecture with different patch sizes (128×128 and 256×256). The study area is a steep slope in Bogok-ri, Hyoja-myeon, Yecheon-gun, Gyeongbuk Province, where a high-resolution DEM (0.1 m) was constructed using drone imagery and point cloud data. The 128×128 patch model achieved 70.5% accuracy with F1-scores of 0.582 and 0.599 for non-hazard and hazard classes, respectively, indicating balanced performance. In contrast, the 256×256 patch model yielded 65.96% accuracy, much lower F1-scores of 0.248 and 0.007, and a higher NoData F1-score of 0.786, reflecting predictions focused on NoData zones over hazard areas. Results suggest smaller patch sizes better capture local terrain variability and enhance landslide detection performance.

As the number of vehicle drivers is increasing day by day, the risk of traffic accidents is also increasing. Among the accidents, there are tire-related accidents causes huge damage if it occurs. These kinds of accidents could be prevented through safety checks of tire, but drivers usually overlook it because they don’t have the knowledge to know what the condition of the tire and don’t want to spend time and money to safety inspection and so on. To solve these problems, we propose tire life prediction mobile application with deep-learning method to check the condition of tires simply. Also, considering the embedded environment that has low power and capacity, we apply lightweight technique called pruning

The main visual feature is surface cracks, which are caused by loopholes that are embedded into the structures due to manufacturing faults and overloading factors. The structural health monitoring must be precise and more efficient for detecting surface cracks in concrete structures. Human inspection is used to identify damage on concrete surfaces. But, these traditional visual observation techniques are not more effective for large concrete structures. Moreover, this outmoded human labor practice for crack detection is intensive, expensive, and inefficient. To predict potentially hazardous situations caused by cracks on concrete surfaces, it is crucial to have an efficient, fast, and well-organized inspection system for concrete surface cracks. The automatic crack detection system must be effective in identifying cracks, damage, and segmenting them. In this research, a deep learning (DL) algorithm model is active for crack detection in concrete structure images to assess the influence on structural health. This design work is projected to provide a fast and active solution for identifying dust/duct type to prevent power losses using an image classification model based on DL. The VGG-16 DL model significantly analyzes the precision and accuracy of identifying the crack surfaces on concrete structures. The exceptional performance of the projected model achieves a training accuracy of 99.99% and a test accuracy of 99.96%, with an F1 score of 0.9995, precision of 0.9995, and a sensitivity of 0.9997. This is more precise, costeffective, and more efficient than human resources to find the defect on concrete surfaces that may support the healthy life of concrete structures.

The rise of cryptocurrencies has also led to an increase in fraudulent activities, posing challenges in fraud detection on decentralized platforms like Ethereum. This issue is particularly pronounced in decentralized environments like Ethereum, where new transaction patterns continue to emerge. In this dynamic and changing environment, it is important to address the problem of concept drift, which refers to the continuous evolution of data patterns. To address the dynamic nature of these fraud patterns, we propose an automated hyperparameter optimization (HPO) approach using Proximal Policy Optimization (PPO). Unlike traditional HPO methods, PPO efficiently navigates the complex hyperparameter space, adapting to evolving fraud schemes with minimal human intervention. Our method enhances the adaptability and robustness of fraud detection models, effectively improving detection accuracy. Experimental results demonstrate that PPO outperforms existing HPO techniques, offering a more flexible and powerful tool for maintaining the performance of fraud detection systems in the rapidly changing cryptocurrency landscape.

A specific area of research in artificial intelligence, known as deep learning (DL) has turned into a strong source for the solutions of complicated issues in computer vision and many more. A real application of that is real and fake faces detection. Detection of is real and fake faces became increasingly important these days with increasing deepfake technology. Fake images pose great dangers to information security, trustworthiness in multimedia content, and even to society's stability. In his proposal the design of a deep learning-based model in VGG-16 architecture to make high accuracy and reliability distinctions between real and fake faces. The performance of the proposed model was evaluated by a number of metrics, including accuracy, specificity, recall, precision, and misclassification rate. The results showed that the model obtained an excellent accuracy of 99.61% with a very low misclassification rate of 0.39%. It obtained perfect specificity of 99.15%, which means all fake faces were identified correctly, and a precision value of 99.29%, ensuring that all faces classified as real were indeed real. The recall of the model was high, at 100%, meaning nearly all real faces were correctly identified. The obtained results are the proof of how effective DL and, in this case, using a pre-trained model like VGG-16, is at recognizing real and fake faces. It shows how strong and reliable the proposed.

Accurate classification of public policy is essential for effective policy analysis, design, comparison, and formulation across countries. However, manual classification by policy experts can lead to inconsistencies and human errors, highlighting the need for a more reliable and efficient approach. This study proposes a deep learning-based model to support policy classification using artificial intelligence. Leveraging Korean policy datasets, comprising administrative data (1988–2018), legislative data (1987–2018), and media data (1988–2020), previously curated by experts, we developed an AI model for automated policy classification based on the KoBERT language model. Designed as a supplementary tool for policy experts, this model enhances classification consistency, reduces decision-making time, and improves overall productivity. Moreover, the model enables the classification, comparison, and evaluation of diverse policies at both local and national levels, offering valuable support for strategic public policy development. The proposed model achieved a Top-1 accuracy of 62.4% and a Top-3 accuracy of 71.6%, outperforming traditional baselines and demonstrating its practical potential for real-world policy analysis.

Planthopper is a major problem pest of agricultural crops and rice, feeding mainly on the leaves and stems of crops and causing devastating damage to farmers in South Korea. Planthoppers reduce nutrients in the body of crops and cause crop diseases by destroying tissue or transmitting viruses, so accurate detection and diagnosis is essential to minimize the damage. With the development of artificial intelligence in recent years, deep learning has been widely used to diagnose the pests. Most of the pest diagnosis research and programs use approaches based on object detection and image classification. However, traditional planthopper detection models may misidentify other pests as planthoppers, which can reduce user confidence in the diagnostic model. To address this misrecognition problem, this study investigates a deep learning-based planthopper Image detection and discrimination model for detecting and classifying the planthopper images. The proposed model combines the Faster RCNN object detection model and the Resnet50 classification model to automatically detect planthoppers among other pests in aerial entomology net images. The performance measurements showed that the benchmark model using the Faster RCNN algorithm achieved a high Recall of 91.23%, but a relatively low Precision of 24.34%. On the other hand, the model proposed in this study has a high recall of 96.22% and a high precision of 96.73%, proving that it can detect planthoppers well.

부동산 가격평가를 위한 전통적 접근은 선형회귀모형을 활용하는 것으로서, 이러한 접근은 설명변수와 종속변수(주택 가격)간 선형의 관계를 가정한다는 한계가 있다. 본 연구는 이러한 한계를 극복하고자 딥러닝 방식, 즉 다층신경망 모형(multilayer neural net model)을 활용하였다. 다층신경망 모형이 전통적 회귀모형보다 주택 가격 예측 성능이 일관되게 탁월함을 4개 사례지역(서울 강남구, 경남 김해시, 전주 덕진구, 전남 해남군) 모두에서 확인하였다. 이러한 성능 향상의 주원인은 다층신경망 모형이 설명변수와 종속변수 간 비선형 관계를 효율적으로 포착할 수 있기 때문인 것으로 해석된다. 설명변수 중 하나인 지리좌표(X, Y)값과 주택 가격 간의 관계를 효율적으로 모델링한 것을 비선형 관계 포착의 예로 들 수 있다. 또 다른 특이점은 사례지역의 이질성이 강해질수록 두 모형 간 성능 격차가 커지는 것을 발견할 수 있었다. 즉, 사례지역에 소재하는 주택의 이질성이 심한 경우, 전통적 모형은 가격 예측의 정확성이 상당히 감소하였으나 다층신경망 모형은 상대적으로 강건한 예측 성능을 보여주었다.

The traditional approach to property valuation has been the use of a linear regression model, which has been criticized for assumption of a linear relationship between predictors and the house prices. We tried to overcome the limitation through the deep learning approach, that is, using a multi-hidden layer neural net model. Our finding is that the neural net model outperformed the traditional approach across all the four study areas. We interpreted that the outstanding performance of the neural net model could be attributed to the capability of non-linear modeling of predictors with the example being geographical coordinates. Another noticeable result is that the gap of the model performance between the neural net model and the traditional approach widened as the study area became more heterogeneous. The neural net model was proven to be able to perform more efficiently in the heterogeneous area where the traditional linear regression model suffered when predicting the house prices.

This study proposes a surrogate model framework that integrates finite element analysis and deep learning to rapidly estimate equivalent material properties of patterned sheets. Conventional homogenization methods can only be applied after the pattern geometry has been finalized, requiring additional modeling and simulation. In contrast, the proposed approach establishes a surrogate model in advance, enabling the immediate estimation of equivalent material properties once the pattern geometry is defined. A dataset of 5,000 cases was generated using simulations, and Bayesian hyperparameter optimization was applied to improve model performance. The surrogate model achieved R² values above 0.99 for all target properties, confirming high internal consistency. Experimental validation with patterned STS304 specimens yielded meaningful results, with all errors remaining within 15%, which demonstrates the reliability of the proposed surrogate model despite minor deviations caused by fabrication imperfections and limited training data. Despite these limitations, the proposed system enables instant estimation of equivalent properties from pattern geometries, offering significant reduction in computational cost and design time. This approach enhances design reliability and provides a practical tool for the application of patterned materials in industrial engineering.