• Journal of the Korean Society of Radiology
• /
• v.18 no.2
• /
• pp.93-99
• /
• 2024

The digital medical imaging, especially, computed tomography (CT), should necessarily be considered in terms of noise distribution caused by converting to X-ray photon to digital imaging signal. Recently, the denoising technique based on deep learning architecture is increasingly used in the medical imaging field. Here, we evaluated noise reduction effect according to various noise types based on the U-net deep learning model in the lung CT images. The input data for deep learning was generated by applying Gaussian noise, Poisson noise, salt and pepper noise and speckle noise from the ground truth (GT) image. In particular, two types of Gaussian noise input data were applied with standard deviation values of 30 and 50. There are applied hyper-parameters, which were Adam as optimizer function, 100 as epochs, and 0.0001 as learning rate, respectively. To analyze the quantitative values, the mean square error (MSE), the peak signal to noise ratio (PSNR) and coefficient of variation (COV) were calculated. According to the results, it was confirmed that the U-net model was effective for noise reduction all of the set conditions in this study. Especially, it showed the best performance in Gaussian noise.

• Journal of Multimedia Information System
• /
• v.3 no.3
• /
• pp.97-102
• /
• 2016

Deep learning enables machines to have perception and can potentially outperform humans in the medical field. It can save a lot of time and reduce human error by detecting certain patterns from medical images without being trained. The main goal of this paper is to build the optimal model for breast mass classification by applying various methods that influence the performance of Convolutional Neural Network (CNN). Google's newly developed software library Tensorflow was used to build CNN and the mammogram dataset used in this study was obtained from 340 breast cancer cases. The best classification performance we achieved was an accuracy of 0.887, sensitivity of 0.903, and specificity of 0.869 for normal tissue versus malignant mass classification with augmented data, more convolutional filters, and ADAM optimizer. A limitation of this method, however, was that it only considered malignant masses which are relatively easier to classify than benign masses. Therefore, further studies are required in order to properly classify any given data for medical uses.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.73-88
• /
• 2023

Brain tumors can also be an abnormal collection or accumulation of cells in the brain that can be life-threatening due to their ability to invade and metastasize to nearby tissues. Accurate diagnosis is critical to the success of treatment planning, and resonant imaging is the primary diagnostic imaging method used to diagnose brain tumors and their extent. Deep learning methods for computer vision applications have shown significant improvements in recent years, primarily due to the undeniable fact that there is a large amount of data on the market to teach models. Therefore, improvements within the model architecture perform better approximations in the monitored configuration. Tumor classification using these deep learning techniques has made great strides by providing reliable, annotated open data sets. Reduce computational effort and learn specific spatial and temporal relationships. This white paper describes transfer models such as the MobileNet model, VGG19 model, InceptionResNetV2 model, Inception model, and DenseNet201 model. The model uses three different optimizers, Adam, SGD, and RMSprop. Finally, the pre-trained MobileNet with RMSprop optimizer is the best model in this paper, with 0.995 accuracies, 0.99 sensitivity, and 1.00 specificity, while at the same time having the lowest computational cost.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.355-356
• /
• 2021

본 논문에서는 Python 3의 Keras 모듈을 이용하여 특정 자동차에 대한 최적의 판매자권장소비자가격(MSRP)을 예측하는 시스템을 제안한다. 이 시스템은 2004년에 미국에서 시판된 428종류의 자동차에 대한 정보를 제조사, 차종, 생산지, 엔진 크기, 실린더 수, 시내 주행 시 연비, 고속도로 주행 시 연비, 마력, 차체 무게, 차체 길이의 독립변수를 사용하여 자체적으로 딥러닝한 회귀모델을 통해 특정 지표가 주어진 차량에 대해 종속변수인 판매자권장소비자가격을 예측한다. Optimizer를 adam으로, 학습률을 0.005으로 설정한 경우의 검증 MAE 값이 3842.98로 가장 낮게 산출되었고, 해당 모델의 결과는 예측값과 실제값의 오차율이 ±15% 정도 내외로 예측된 표본의 비율이 약 80.14%로 측정되었다. 위 모델은 향후 신차 가격 결정 및 중고차 시장에서 구매, 판매 결정을 돕는 등 특정 시장 내에서 다양한 자동차의 가치를 판단하기에 유용할 것으로 전망된다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.3
• /
• pp.71-80
• /
• 2021

The selection of an appropriate neural network algorithm is an important step for accurate data prediction in machine learning. Many algorithms based on basic artificial neural networks have been devised to efficiently predict future data. These networks include deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and gated recurrent unit (GRU) neural networks. Developers face difficulties when choosing among these networks because sufficient information on their performance is unavailable. To alleviate this difficulty, we evaluated the performance of each algorithm by comparing their errors and processing times. Each neural network model was trained using a tax dataset, and the trained model was used for data prediction to compare accuracies among the various algorithms. Furthermore, the effects of activation functions and various optimizers on the performance of the models were analyzed The experimental results show that the GRU and LSTM algorithms yields the lowest prediction error with an average RMSE of 0.12 and an average R2 score of 0.78 and 0.75 respectively, and the basic DNN model achieves the lowest processing time but highest average RMSE of 0.163. Furthermore, the Adam optimizer yields the best performance (with DNN, GRU, and LSTM) in terms of error and the worst performance in terms of processing time. The findings of this study are thus expected to be useful for scientists and developers.

• Journal of the Korean Society of Radiology
• /
• v.16 no.3
• /
• pp.295-302
• /
• 2022

Sparse-view computed tomography (CT) imaging technique is able to reduce radiation dose, ensure the uniformity of image characteristics among projections and suppress noise. However, the reconstructed images obtained by the sparse-view CT imaging technique suffer from severe artifacts, resulting in the distortion of image quality and internal structures. In this study, we proposed a convolutional neural network (CNN) with wavelet transformation and residual learning for reducing artifacts in sparse-view CT image, and the performance of the trained model was quantitatively analyzed. The CNN consisted of wavelet transformation, convolutional and inverse wavelet transformation layers, and input and output images were configured as sparse-view CT images and residual images, respectively. For training the CNN, the loss function was calculated by using mean squared error (MSE), and the Adam function was used as an optimizer. Result images were obtained by subtracting the residual images, which were predicted by the trained model, from sparse-view CT images. The quantitative accuracy of the result images were measured in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The results showed that the trained model is able to improve the spatial resolution of the result images as well as reduce artifacts in sparse-view CT images effectively. Also, the trained model increased the PSNR and SSIM by 8.18% and 19.71% in comparison to the imaging model trained without wavelet transformation and residual learning, respectively. Therefore, the imaging model proposed in this study can restore the image quality of sparse-view CT image by reducing artifacts, improving spatial resolution and quantitative accuracy.

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.101-113
• /
• 2021

In this paper, we introduce a speaker overlap system and look at the process of converting the existed system on the specific framework of artificial intelligence. Speaker overlap is when two or more speakers speak at the same time during a conversation, and can lead to performance degradation in the fields of speech recognition or speaker recognition, and a lot of research is being conducted because it can prevent performance degradation. Recently, as application of artificial intelligence is increasing, there is a demand for switching between artificial intelligence frameworks. However, when switching frameworks, performance degradation is observed due to the unique characteristics of each framework, making it difficult to switch frameworks. In this paper, the process of converting the speaker overlap detection system based on the Keras framework to the pytorch-based system is explained and considers components. As a result of the framework switching, the pytorch-based system showed better performance than the existing Keras-based speaker overlap detection system, so it can be said that it is valuable as a fundamental study on systematic framework conversion.

• Applied Chemistry for Engineering
• /
• v.31 no.5
• /
• pp.520-525
• /
• 2020

In this study, we developed a machine learning-based model for predicting the production stage temperature of distillation process. It is necessary to predict an accurate temperature for control because the control of the distillation process is done through the production stage temperature. The temperature in distillation process has a nonlinear complex relationship with other variables and time series data, so we used the recurrent neural network algorithms to predict temperature. In the model development process, by adjusting three recurrent neural network based algorithms, and batch size, we selected the most appropriate model for predicting the production stage temperature. LSTM₁₂₈ was selected as the most appropriate model for predicting the production stage temperature. The prediction performance of selected model for the actual temperature is RMSE of 0.0791 and R² of 0.924.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.