Malware is any malicious program that can attack the security of other computer systems for various purposes. The threat of malware has significantly increased in recent years. To protect our computer systems, we need to analyze an executable file to decide whether it is malicious or not. In this paper, we propose two malware classification methods: malware classification using Simhash and PCA (MCSP), and malware classification using Simhash and linear transform (MCSLT). PCA uses the symmetrical covariance matrix. The former method combines Simhash encoding and PCA, and the latter combines Simhash encoding and linear transform layer. To verify the performance of our methods, we compared them with basic malware classification using Simhash and CNN (MCSC) using tanh and relu activation. We used a highly imbalanced dataset with 10,736 samples. As a result, our MCSP method showed the best performance with a maximum accuracy of 98.74% and an average accuracy of 98.59%. It showed an average F1 score of 99.2%. In addition, the MCSLT method showed better performance than MCSC in accuracy and F1 score.

Breast cancer is a highly contagious disease that has killed many people all over the world. It can be fully recovered from early detection. To enable the early detection of the breast cancer, it is very important to classify accurately whether it is breast cancer or not. Recently, the deep learning approach method on the medical images such as these histopathologic images of the breast cancer is showing higher level of accuracy and efficiency compared to the conventional methods. In this paper, the breast cancer histopathological image that is difficult to be distinguished was analyzed visually. And among the deep learning algorithms, the CNN(Convolutional Neural Network) specialized for the image was used to perform comparative analysis on whether it is breast cancer or not. Among the CNN algorithms, VGG16 and InceptionV3 were used, and transfer learning was used for the effective application of these algorithms.The data used in this paper is breast cancer histopathological image dataset classifying the benign and malignant of BreakHis. In the 2-class classification task, InceptionV3 achieved 98% accuracy. It is expected that this deep learning approach method will support the development of disease diagnosis through medical images.

In this paper, we compared the performance of the classifiers according to feature vectors with Binary BOW, Count BOW and TF-IDF for malware detection. We used the feature of Opcode that extracted from PE file. For performance comparison, we measured the AUC score for the classifiers those are DT, KNN, MLP, MNB and SVM. As a result, we recommend neural network (MLP) and instance-based model (KNN) because they show the high AUC score and accuracy regardless of the unbalanced dataset and the feature vector. If you use classical classifiers, we recommend DT because it guarantees high AUC score and accuracy regardless of the same condition as the above. If you use SVM, you have to do Robust scaling to resolved outlier and unbalanced dataset. If you use MNB, you need to use N-gram technique to improve AUC score. In this paper, we compared the performance of the classifiers according to feature vectors with Binary BOW, Count BOW and TF-IDF for malware detection. We used the feature of Opcode that extracted from PE file. For performance comparison, we measured the AUC score for the classifiers those are DT, KNN, MLP, MNB and SVM. As a result, we recommend neural network (MLP) and instance-based model (KNN) because they show the high AUC score and accuracy regardless of the unbalanced dataset and the feature vector. If you use classical classifiers, we recommend DT because it guarantees high AUC score and accuracy regardless of the same condition as the above. If you use SVM, you have to do Robust scaling to resolved outlier and unbalanced dataset. If you use MNB, you need to use N-gram technique to improve AUC score.

Recently, semantic segmentation has been widely applied to image processing, scene understanding, and many others. Especially, in deep learning-based semantic segmentation, the U-Net with convolutional encoder-decoder architecture is a representative model which is proposed for image segmentation in the biomedical field. It used max pooling operation for reducing the size of image and making noise robust. However, instead of reducing the complexity of the model, max pooling has the disadvantage of omitting some information about the image in reducing it. So, this paper used two diagonal elements of down-sampling operation instead of it. We think that the down-sampling feature maps have more information intrinsically than max pooling feature maps because of keeping the Nyquist theorem and extracting the latent information from them. In addition, this paper used two other diagonal elements for the skip connection. In decoding, we used Subpixel Convolution rather than transposed convolution to efficiently decode the encoded feature maps. Including all the ideas, this paper proposed the new encoder-decoder model called Down-Sampling and Subpixel Convolution U-Net (DSSC-UNet). To prove the better performance of the proposed model, this paper measured the performance of the U-Net and DSSC-UNet on the Cityscapes. As a result, DSSC-UNet achieved 89.6% Mean Intersection Over Union (Mean-IoU) and U-Net achieved 85.6% Mean-IoU, confirming that DSSC-UNet achieved better performance.