• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.1
• /
• pp.19-29
• /
• 2011

The u-Healthcare system, a new paradigm, provides healthcare and medical service anytime, anywhere in daily life using wired and wireless networks. It only doesn't reach u-Hospital at home, to manage efficient personal health in fitness space, it is essential to feedback process through measuring and analyzing a personal vital signs. MBAN(Medical Body Area Network) is a core of this technology. MBAN, a new paradigm of the u-Healthcare system, can provide healthcare and medical service anytime, anywhere on real time in daily life using u-sensor networks. In this paper, an ontology-based context-awareness in MBAN proposed system development methodology. Accordingly, ontology-based context awareness system on MBAN to Elderly/severe patients/aged/, with measured respiratory rate/temperature/pulse and vital signs having small variables through u-sensor network in real-time, discovered abnormal signs and emergency situations which may happen to people at sleep or activity, alarmed and connected with members of a family or medical emergency alarm(Emergency Call) and 119 system to avoid sudden accidents for early detection. Therefore, We have proposed that accuracy of biological signal sensing and the confidence of ontology should be inspected.

• Journal of Biomedical Engineering Research
• /
• v.38 no.5
• /
• pp.237-241
• /
• 2017

Early detection of the pulmonary nodule is important for diagnosis and treatment of lung cancer. Recently, CT has been used as a screening tool for lung nodule detection. And, it has been reported that computer aided detection(CAD) systems can improve the accuracy of the radiologist in detection nodules on CT scan. The previous study has been proposed a method using Convolutional Neural Network(CNN) in Lung CAD system. But the proposed model has a limitation in accuracy due to its sparse layer structure. Therefore, we propose a Deep Convolutional Neural Network to overcome this limitation. The model proposed in this work is consist of 14 layers including 8 convolutional layers and 4 fully connected layers. The CNN model is trained and tested with 61,404 regions-of-interest (ROIs) patches of lung image including 39,760 nodules and 21,644 non-nodules extracted from the Lung Image Database Consortium(LIDC) dataset. We could obtain the classification accuracy of 91.79% with the CNN model presented in this work. To prevent overfitting, we trained the model with Augmented Dataset and regularization term in the cost function. With L1, L2 regularization at Training process, we obtained 92.39%, 92.52% of accuracy respectively. And we obtained 93.52% with data augmentation. In conclusion, we could obtain the accuracy of 93.75% with L2 Regularization and Data Augmentation.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.117-124
• /
• 2008

It improves human being's life quality that all people can have mure convenient medical service under pervasive computing environment. For a pervasive health care application for cardiac patient, we've implemented a health care system, which is composed of three parts. Various sensors monitor outer as well as inner environment of human such as temperature, humidity, light and electrocardiogram, etc. These sensors form a network based on Zigbee. And medical information server accumulates sensing values and performs back-end processing. To simply transfer these sensing values to a medical team is a simple level's medical service. So, we've designed a new service model based on back propagation neural network for more improved medical service. Our experiments show that a proposed healthcare system can give high level's medical service because it can recognize human's context more concretely.

• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.205-206
• /
• 1998

In this paper, we present the detection algorithm of interictal epileptic waveform using LVQ network and wavelet transform. First wavelet coefficients is used to represent the characteristics of a single channel EEG wave, and make a number of neural network input node smaller. Then, three-layer neural network employing LVQ network is trained and tested using parameters obtained from the first stage. This study showed that preprocessed EEG data can be successfully used to train ANNs to detect epileptogenic discharges with a high success.

• Proceedings of the Korean Magnetic Resonance Society Conference
• /
• 2002.01a
• /
• pp.28-28
• /
• 2002

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.151-154
• /
• 1996

A medical record and radiographic image transmission system has been developed using high speed communication network. The databases are designed to store and transmit the data acquired from the scanner. To maximally utilize the communication bandwidth, the medical records and radiographic images are compressed using the G3 facsimile and JPEG coding standard method respectively. TCP/IP, OOP and window based system software enables the modular design, future expandability, open system interconnectivity, and graphical user interface. In addition, the fast and easy data base access capability and diverse image manipulation functions are also implemented.

• IMMUNE NETWORK
• /
• v.21 no.3
• /
• pp.21.1-21.22
• /
• 2021

Myeloid-derived suppressor cells (MDSCs) have strong immunosuppressive activity and are morphologically similar to conventional monocytes and granulocytes. The development and classification of these cells have, however, been controversial. The activation network of MDSCs is relatively complex, and their mechanism of action is poorly understood, creating an avenue for further research. In recent years, MDSCs have been found to play an important role in immune regulation and in effectively inhibiting the activity of effector lymphocytes. Under certain conditions, particularly in the case of tissue damage or inflammation, MDSCs play a leading role in the immune response of the central nervous system. In cancer, however, this can lead to tumor immune evasion and the development of related diseases. Under cancerous conditions, tumors often alter bone marrow formation, thus affecting progenitor cell differentiation, and ultimately, MDSC accumulation. MDSCs are important contributors to tumor progression and play a key role in promoting tumor growth and metastasis, and even reduce the efficacy of immunotherapy. Currently, a number of studies have demonstrated that MDSCs play a key regulatory role in many clinical diseases. In light of these studies, this review discusses the origin of MDSCs, the mechanisms underlying their activation, their role in a variety of clinical diseases, and their function in immune response regulation.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.4
• /
• pp.1477-1482
• /
• 2012

Squamous cell carcinoma and adenocarcinoma are the major histological types of non-small cell lung cancer. Because they differ on the basis of histopathological and clinical characteristics and their relationship with smoking, their etiologies may be different; for example, different tumor suppressor genes may be related to the genesis of each type. We used microarray data to construct three regulatory networks to identify potential genes related to lung adenocarcinoma and squamous cell carcinoma and investigated the similarity and specificity of them. In the network, some of the observed transcription factors and target genes had been previously proven to be related to lung adenocarcinoma and squamous cell carcinoma. We also found some new transcription factors and target genes related to SCC. The results demonstrated that regulatory network analysis is useful in connection analysis between lung adenocarcinoma and squamous cell carcinoma.

• Science of Emotion and Sensibility
• /
• v.20 no.2
• /
• pp.161-170
• /
• 2017

Emotion affects many parts of human life such as learning ability, behavior and judgment. It is important to understand human nature. Emotion can only be inferred from facial expressions or gestures, what it actually is. In particular, emotion is difficult to classify not only because individuals feel differently about emotion but also because visually induced emotion does not sustain during whole testing period. To solve the problem, we acquired bio-signals and extracted features from those signals, which offer objective information about emotion stimulus. The emotion pattern classifier was composed of unsupervised learning algorithm with hidden nodes and feature vectors. Restricted Boltzmann machine (RBM) based on probability estimation was used in the unsupervised learning and maps emotion features to transformed dimensions. The emotion was characterized by non-linear classifiers with hidden nodes of a multi layer neural network, named deep belief network (DBN). The accuracy of DBN (about 94 %) was better than that of back-propagation neural network (about 40 %). The DBN showed good performance as the emotion pattern classifier.

• Journal of Biomedical Engineering Research
• /
• v.19 no.1
• /
• pp.39-46
• /
• 1998

In this paper, we present a neural network identification and a control of highly complicated nonlinear left ventricular assist device(LVAD) system with a pneumatically driven mock circulation system. Generally, the LVAD system needs to compensate for nonlinearities. It is necessary to apply high performance control techniques. Fortunately, the neural network can be applied to control of a nonlinear dynamic system by learning capability. In this study, we identify the LVAD system with neural network identification(NNI). Once the NNI has learned the dynamic model of the LVAD system, the other network, called neural network controller(NNC), is designed for a control of the LVAD system. The ability and effectiveness of identifying and controlling the LVAD system using the proposed algorithm will be demonstrated by computer simulation.