• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.173-178
• /
• 2018

Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.123-124
• /
• 2019

This paper proposes an improved deep learning method based on small data sets for animal image classification. Firstly, we use a CNN to build a training model for small data sets, and use data augmentation to expand the data samples of the training set. Secondly, using the pre-trained network on large-scale datasets, such as VGG16, the bottleneck features in the small dataset are extracted and to be stored in two NumPy files as new training datasets and test datasets. Finally, training a fully connected network with the new datasets. In this paper, we use Kaggle famous Dogs vs Cats dataset as the experimental dataset, which is a two-category classification dataset.

• International Journal of Computer Science & Network Security
• /
• v.24 no.8
• /
• pp.72-84
• /
• 2024

Plant leaf classification is an imperative task when their use in real world is considered either for medicinal purposes or in agricultural sector. Accurate identification of plants is, therefore, quite important, since there are numerous poisonous plants which if by mistake consumed or used by humans can prove fatal to their lives. Furthermore, in agriculture, detection of certain kinds of weeds can prove to be quite significant for saving crops against such unwanted plants. In general, Artificial Neural Networks (ANN) are a suitable candidate for classification of images when small datasets are available. However, these suffer from local minima problems which can be effectively resolved using some global optimization techniques. Considering this issue, the present research paper presents an automated plant leaf classification system using optimized soft computing models in which ANNs are optimized using Grasshopper Optimization algorithm (GOA). In addition, the proposed model outperformed the state-of-the-art techniques when compared with simple ANN and particle swarm optimization based ANN. Results show that proposed GOA-ANN based plant leaf classification system is a promising technique for small image datasets.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.75-80
• /
• 2021

Artificial intelligence is becoming an important part of our lives providing incredible benefits. In this respect, facial expression recognition has been one of the hot topics among computer vision researchers in recent decades. Classifying small dataset of low resolution images requires the development of a new small scale deep CNN model. To do this, we propose a method suitable for small datasets. Compared to the traditional deep CNN models, this model uses only a fraction of the memory in terms of total learnable weights, but it shows very similar results for the FER2013 and FERPlus datasets.

• Genomics & Informatics
• /
• v.10 no.1
• /
• pp.23-32
• /
• 2012

There are lots of studies attempting to identify the expression changes in oral squamous cell carcinoma. Most studies include insufficient samples to apply statistical methods for detecting significant gene sets. This study combined two small microarray datasets from a public database and identified significant genes associated with the progress of oral squamous cell carcinoma. There were different expression scales between the two datasets, even though these datasets were generated under the same platforms - Affymetrix U133A gene chips. We discretized gene expressions of the two datasets by adjusting the differences between the datasets for detecting the more reliable information. From the combination of the two datasets, we detected 51 significant genes that were upregulated in oral squamous cell carcinoma. Most of them were published in previous studies as cancer-related genes. From these selected genes, significant genetic pathways associated with expression changes were identified. By combining several datasets from the public database, sufficient samples can be obtained for detecting reliable information. Most of the selected genes were known as cancer-related genes, including oral squamous cell carcinoma. Several unknown genes can be biologically evaluated in further studies.

• Journal of electromagnetic engineering and science
• /
• v.18 no.2
• /
• pp.136-140
• /
• 2018

We propose an improved semi-empirical scattering model for X-band radar backscattering from rough sea surfaces. This new model has a wider validity range of wind speeds than does the existing semi-empirical sea spectrum (SESS) model. First, we retrieved the small-roughness parameters from the sea surfaces, which were numerically generated using the Pierson-Moskowitz spectrum and measurement datasets for various wind speeds. Then, we computed the backscattering coefficients of the small-roughness surfaces for various wind speeds using the integral equation method model. Finally, the large-roughness characteristics were taken into account by integrating the small-roughness backscattering coefficients multiplying them with the surface slope probability density function for all possible surface slopes. The new model includes a wind speed range below 3.46 m/s, which was not covered by the existing SESS model. The accuracy of the new model was verified with two measurement datasets for various wind speeds from 0.5 m/s to 14 m/s.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.329-344
• /
• 2023

In this study, we comprehensively analyze the generalization performance of various deep learning-based active sonar target classifiers when applied to small and imbalanced active sonar datasets. To generate the active sonar datasets, we use data from two different oceanic experiments conducted at different times and ocean. Each sample in the active sonar datasets is a time-frequency domain image, which is extracted from audio signal of contact after the detection process. For the comprehensive analysis, we utilize 22 Convolutional Neural Networks (CNN) models. Two datasets are used as train/validation datasets and test datasets, alternatively. To calculate the variance in the output of the target classifiers, the train/validation/test datasets are repeated 10 times. Hyperparameters for training are optimized using Bayesian optimization. The results demonstrate that shallow CNN models show superior robustness and generalization performance compared to most of deep CNN models. The results from this paper can serve as a valuable reference for future research directions in deep learning-based active sonar target classification.

• Korean Journal of Remote Sensing
• /
• v.39 no.1
• /
• pp.87-97
• /
• 2023

Unmanned aerial vehicles (UAVs) can capture high-resolution imagery from a variety of viewing angles and altitudes; they are generally limited to collecting images of small scenes from larger regions. To improve the utility of UAV-appropriated datasetsfor use with deep learning applications, multiple datasets created from variousregions under different conditions are needed. To demonstrate a powerful new method for integrating heterogeneous UAV datasets, this paper applies a combined segmentation network (CSN) to share UAVid and semantic drone dataset encoding blocks to learn their general features, whereas its decoding blocks are trained separately on each dataset. Experimental results show that our CSN improves the accuracy of specific classes (e.g., cars), which currently comprise a low ratio in both datasets. From this result, it is expected that the range of UAV dataset utilization will increase.

• Genomics & Informatics
• /
• v.9 no.4
• /
• pp.173-180
• /
• 2011

Recent trends in generating multiple, large-scale datasets provide new challenges to manipulating the relationship of different types of components, such as gene expression and drug response data. Integrative analysis of compound response and gene expression datasets generates an opportunity to capture the possible mechanism of compounds by using signature genes on diverse types of cancer cell lines. Here, we integrated datasets of compound response and gene expression profiles on NCI60 cell lines and constructed a network, revealing the relationship for 801 compounds and 341 gene probes. As examples, obtusol, which shows an exclusive sensitivity on a small number of colon cell lines, is related to a set of gene probes that have unique overexpression in colon cell lines. We also found that the SLC7A11 gene, a direct target of miR-26b, might be a key element in understanding the action of many diverse classes of anticancer compounds. We demonstrated that this network might be useful for studying the mechanisms of varied compound response on diverse cancer cell lines.

• ETRI Journal
• /
• v.41 no.3
• /
• pp.358-370
• /
• 2019

The main aim of this study is to select the optimal set of genes from microarray cancer datasets that contribute to the prediction of specific cancer types. This study proposes the enhancement of the feature selection filter algorithm based on Joe's normalized mutual information and its use for gene selection. The proposed algorithm is implemented and evaluated on seven benchmark microarray cancer datasets, namely, central nervous system, leukemia (binary), leukemia (3 class), leukemia (4 class), lymphoma, mixed lineage leukemia, and small round blue cell tumor, using five well-known classifiers, including the naive Bayes, radial basis function network, instance-based classifier, decision-based table, and decision tree. An average increase in the prediction accuracy of 5.1% is observed on all seven datasets averaged over all five classifiers. The average reduction in training time is 2.86 seconds. The performance of the proposed method is also compared with those of three other popular mutual information-based feature selection filters, namely, information gain, gain ratio, and symmetric uncertainty. The results are impressive when all five classifiers are used on all the datasets.