• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.133-143
• /
• 2023

In this study, we propose a big data set of strawberry pests collected directly for diagnosis model learning and an automatic pest diagnosis model architecture based on deep learning. First, a big data set related to strawberry pests, which did not exist anywhere before, was directly collected from the web. A total of more than 12,000 image data was directly collected and classified, and this data was used to train a deep learning model. Second, the deep-learning-based automatic pest diagnosis module is a module that classifies what kind of pest or disease corresponds to when a user inputs a desired picture. In particular, we propose a model architecture that can optimally classify pests based on a convolutional neural network among deep learning models. Through this, farmers can easily identify diseases and pests without professional knowledge, and can respond quickly accordingly.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.223-229
• /
• 2021

Classification of different blood cell types is an essential task for human's medical treatment. The white blood cells have different types of cells. Counting total White Blood Cells (WBC) and differential of the WBC types are required by the physicians to diagnose the disease correctly. This paper used transfer learning methods to the pre-trained deep learning models to classify different WBCs. The best pre-trained model was Inception ResNetV2 with Adam optimizer that produced classification accuracy of 98.4% for the dataset comprising four types of WBCs.

• Electronics and Telecommunications Trends
• /
• v.34 no.2
• /
• pp.40-50
• /
• 2019

Considerable accuracy improvements in deep learning have recently been achieved in many applications that require large amounts of computation and expensive memory. However, recent advanced techniques for compacting and accelerating the deep learning model have been developed for deployment in lightweight devices with constrained resources. Lightweight deep learning techniques can be categorized into two schemes: lightweight deep learning algorithms (model simplification and efficient convolutional filters) in nature and transferring models into compact/small ones (model compression and knowledge distillation). In this report, we briefly summarize various lightweight deep learning techniques and possible research directions.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.571-585
• /
• 2021

Applications for object detection are expanding as it is automated through artificial intelligence-based processing, such as deep learning, on a large volume of images and videos. High dependence on training data and a non-transparent way to find answers are the common characteristics of deep learning. Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. This paper summarizes the security issues that need to be addressed for future applications and analyzes the state-of-the-art security studies related to robustness, privacy, and integrity of object detection for images and videos.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.212-216
• /
• 2024

Feature Selection have turned into the main point of investigations particularly in bioinformatics where there are numerous applications. Deep learning technique is a useful asset to choose features, anyway not all calculations are on an equivalent balance with regards to selection of relevant features. To be sure, numerous techniques have been proposed to select multiple features using deep learning techniques. Because of the deep learning, neural systems have profited a gigantic top recovery in the previous couple of years. Anyway neural systems are blackbox models and not many endeavors have been made so as to examine the fundamental procedure. In this proposed work a new calculations so as to do feature selection with deep learning systems is introduced. To evaluate our outcomes, we create relapse and grouping issues which enable us to think about every calculation on various fronts: exhibitions, calculation time and limitations. The outcomes acquired are truly encouraging since we figure out how to accomplish our objective by outperforming irregular backwoods exhibitions for each situation. The results prove that the proposed method exhibits better performance than the traditional methods.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.294-299
• /
• 2023

Micro ribonucleic acids (miRNAs) can regulate the protein expression levels of genes in the human body and have recently been reported to be closely related to the cause of disease. Determining the genes related to miRNAs will aid in understanding the mechanisms underlying complex miRNAs. However, the identification of miRNA-related genes through wet experiments (in vivo, traditional methods are time- and cost-consuming). To overcome these problems, recent studies have investigated the prediction of miRNA relevance using deep learning models. This study presents a method for predicting the relationships between miRNAs and genes. First, we reconstruct a negative dataset using the proposed method. We then extracted the feature using an autoencoder, after which the feature vector was concatenated with the original data. Thereafter, the concatenated data were used to train a long short-term memory model. Our model exhibited an area under the curve of 0.9609, outperforming previously reported models trained using the same dataset.

• Journal of KIBIM
• /
• v.9 no.4
• /
• pp.31-40
• /
• 2019

With Building Information Modeling(BIM) becoming the de facto standard for data sharing in the AEC industry, additional needs have increased to ensure the data integrity of BIM models themselves. Although the Industry Foundation Classes provide an open and neutral data format, its generalized schema leaves it open to data loss and misclassifications This research applied deep learning to automatically classify BIM elements and thus check the integrity of BIM-to-IFC mappings. Multi-view CNN(MVCC) and PointNet, which are two deep learning models customized to learn and classify in 3 dimensional non-euclidean spaces, were used. The analysis was restricted to classifying subtypes of architectural walls. MVCNN resulted in the highest performance, with ACC and F1 score of 0.95 and 0.94. MVCNN unitizes images from multiple perspectives of an element, and was thus able to learn the nuanced differences of wall subtypes. PointNet, on the other hand, lost many of the detailed features as it uses a sample of the point clouds and perceived only the 'skeleton' of the given walls.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.1-16
• /
• 2023

Accurate traffic information prediction is considered to be one of the most important aspects of intelligent transport systems(ITS), as it can be used to guide users of transportation facilities to avoid congested routes. Various deep learning models have been developed for accurate traffic prediction. Recently, ensemble techniques have been utilized to combine the strengths and weaknesses of various models in various ways to improve prediction accuracy and stability. Therefore, in this study, we developed and evaluated a traffic information prediction model using various deep learning models, and evaluated the performance of the developed deep learning models as a stacking ensemble. The individual models showed error rates within 10% for traffic volume prediction and 3% for speed prediction. The ensemble model showed higher accuracy compared to other models when no cross-validation was performed, and when cross-validation was performed, it showed a uniform error rate in long-term forecasting.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.15-22
• /
• 2019

Recent technological advances in three-dimensional (3D) sensing devices and machine learning such as deep leaning has enabled data-driven 3D applications. Research on artificial intelligence has developed for the past few years and 3D deep learning has been introduced. This is the result of the availability of high-quality big data, increases in computing power, and development of new algorithms; before the introduction of 3D deep leaning, the main targets for deep learning were one-dimensional (1D) audio files and two-dimensional (2D) images. The research field of deep leaning has extended from discriminative models such as classification/segmentation/reconstruction models to generative models such as those including style transfer and generation of non-existing data. Unlike 2D learning, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become increasingly popular owing to advances in 3D vision technology, the generation/acquisition of 3D data is still very difficult. Even if 3D data can be acquired, post-processing remains a significant problem. Moreover, it is not easy to directly apply existing network models such as convolution networks owing to the various ways in which 3D data is represented. In this paper, we summarize technological trends in AI-based 3D content generation.