• Journal of Chest Surgery
• /
• v.31 no.5
• /
• pp.466-471
• /
• 1998

Purpose: The safety and efficacy of minimally invasive techniques in congenital heart surgery were tested in this study. Materal and method: Between July 1997 and November 1997, a total of 46 children were underwent minimally invasive cardiac operations at Seoul National University Children's Hospital. Age and body weight of the patients averaged 34.6${\pm}$41.8 (Range: 1∼148) months and 14.5${\pm}$9.9(Range: 3.0∼40.0) kg, respectively. Twenty eight patients were male. Preoperative surgical indications included 15 atrial septal defects, 25 ventricular septal defects, 1 foreign body in aorta, 3 partial atrioventricular septal defects, 1 total anomalous pulmonary venous connection(cardiac type), and 1 tetralogy of Fallot. After creating a small lower midline skin incision starting as down as possible from the sternal notch, a vertical midline sternotomy extended from xyphoid process to the level of the second intercostal space, where one of the T-, J-, I- or inverted C-shaped lower lying mini-sternotomy was completed with a creation of unilateral right or bilateral trap door sternal opening. A conventional direct aortic and bicaval cannulation was routine. Result: A mean length of skin incision was 6.1${\pm}$1.0(range: 4.0∼9.0) cm. A mean distance between the suprasternal notch and the upper most point of the skin incision was 4.0${\pm}$1.1 (range: 2.0∼7.0) cm. Mean cardiopulmonary bypass time, aortic cross-clamp time, and the operation time were 62.9${\pm}$20.0(range: 28∼147), 29.8${\pm}$12.8(range: 11∼79), and 161.1${\pm}$34.5 (range: 100-250) minutes. A mean total amount of postoperative blood transfusion was 71.0${\pm}$68.1 (range: 0∼267) cc. All patients were extubated mean 11.3${\pm}$13.8(range: 1∼73) hours after operation. A mean total amount of analgesics used was 0.8${\pm}$1.8(range: 0∼9) mg of morphine. The mean duration of stay in intensive care unit and hospital stay were 35.0${\pm}$32.2 (range: 10∼194) hours and 6.2${\pm}$2.0(range: 3∼11) days. There were no wound complications and hospital deaths. Conclusion: This short-term experience disclosed that the minimally invasive technique can be feasibly applied in a selected group of congenital heart disease as well as is cosmetically more attractive approach.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.