• 제어로봇시스템학회논문지
• /
• 제11권12호
• /
• pp.1062-1067
• /
• 2005

This paper discusses a skeleton feature extraction method for ubiquitous robot system. The skeleton features are used to analyze human motion and pose estimation. In different conventional feature extraction environment, the ubiquitous robot system requires more robust feature extraction method because it has internal vibration and low image quality. The new hybrid silhouette extraction method and adaptive skeleton model are proposed to overcome this constrained environment. The skin color is used to extract more sophisticated feature points. Finally, the experimental results show the superiority of the proposed method.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 제13회 신호처리 합동 학술대회 논문집
• /
• pp.631-634
• /
• 2000

In this paper, we propose a method for implementing a system for decoding the parameter data based on Facial Animation Parameter (FAP) developed by MPEG-4 Synthetic/Natural Hybrid Coding (SNHC) subcommittee. The data is displayed according to FAP with human mucle model animation engine. Proposed model has the basic properties of the human skin specified by be energy funtional for realistic facial animation.

• 대한간호학회지
• /
• 제26권2호
• /
• pp.290-303
• /
• 1996

There is a need to define the concept of suffering more appropriate in the context of Korean culture. This research is an attempt to analyze and develop the concept of suffering by applying the Hybrid Model suggested by Schwartz-Barcott and Kim. The data were collected from March 20, 1995 to September 17,1995. The subjects of the study were eight persons including in-patients and out-patients of a general hospital who were diagnosed as having cancer and those resting in sanatoria for natural treatment of cancer. Qualitative research methods of in-depth interview and participant observation were used for data collection. The contents of the interviews were recorded on tape. Data-analysis progressed according to the 3 phases suggested by the Hybrid Model. For each case, in-depth interview data and participant observation data were included and the attributes of suffering revealed in these data were analyzed. Finally, by summarizing the results from each case, the attributes of suffering, its dimensions, definition, and processes observed in the field were suggested. According to the results of the study, the followlng new definition of suffering is suggested : Suffering is a fundamental and inevitable experience of all human beings. When each individual experiences loss, damage, and pain which threaten one's personal integrity, suffering is perceived differently among each individual depending on their personal inner factors, one's significant others, exterior circumstances and stimuli, and the ultimate meaning of life. Suffering brings severe and unendurable distress which accompany despair, powerlessness, anxiety, bitterness, fear, anguish, guilt, depression, withdrawal and anger. The results of this study suggest that the more responsibility and burden a cancer patient felt, the more suffering she/he experienced and it tended to be more relevant to one's significant others and exterior circumstances and stimuli : the less responsibility and burden a cancer patient had, the less suffering she/he experienced and it tended to be related to one's inner factors. These findings have implications for nursing profession. When caring for patients who experience suffering, nurses need to consider the influence of responsibility, burden, and each dimension of suffering. Moreover, appropriate nursing interventions aimed at relieving pain and satisfying the spiritual need of patients experiencing loss need to be developed and implemented more widely.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.131-139
• /
• 2021

In current time, anomaly detection is the primary concern of the administrative authorities. Suspicious activity identification is shifting from a human operator to a machine-assisted monitoring in order to assist the human operator and react to an unexpected incident quickly. These automatic surveillance systems face many challenges due to the intrinsic complex characteristics of video sequences and foreground human motion patterns. In this paper, we propose a novel approach to detect anomalous human activity using a hybrid approach of statistical model and Genetic Programming. The feature-set of local motion patterns is generated by a statistical model from the video data in an unsupervised way. This features set is inserted to an enhanced Genetic Programming based classifier to classify normal and abnormal patterns. The experiments are performed using publicly available benchmark datasets under different real-life scenarios. Results show that the proposed methodology is capable to detect and locate the anomalous activity in the real time. The accuracy of the proposed scheme exceeds those of the existing state of the art in term of anomalous activity detection.

• 인터넷정보학회논문지
• /
• 제22권3호
• /
• pp.9-16
• /
• 2021

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.

• Journal of Radiation Protection and Research
• /
• 제49권1호
• /
• pp.1-18
• /
• 2024

Exponential growth has been observed in nuclear medicine procedures worldwide in the past decades. The considerable increase is attributed to the advance of positron emission tomography and single photon emission computed tomography, as well as the introduction of new radiopharmaceuticals. Although nuclear medicine procedures provide undisputable diagnostic and therapeutic benefits to patients, the substantial increase in radiation exposure to nuclear medicine patients raises concerns about potential adverse health effects and calls for the urgent need to monitor exposure levels. In the current article, model-based internal dosimetry methods were reviewed, focusing on Medical Internal Radiation Dose (MIRD) formalism, biokinetic data, human anatomy models (stylized, voxel, and hybrid computational human phantoms), and energy spectrum data of radionuclides. Key results from many articles on nuclear medicine dosimetry and comparisons of dosimetry quantities based on different types of human anatomy models were summarized. Key characteristics of seven model-based dose calculation tools were tabulated and discussed, including dose quantities, computational human phantoms used for dose calculations, decay data for radionuclides, biokinetic data, and user interface. Lastly, future research needs in nuclear medicine dosimetry were discussed. Model-based internal dosimetry methods were reviewed focusing on MIRD formalism, biokinetic data, human anatomy models, and energy spectrum data of radionuclides. Future research should focus on updating biokinetic data, revising energy transfer quantities for alimentary and gastrointestinal tracts, accounting for body size in nuclear medicine dosimetry, and recalculating dose coefficients based on the latest biokinetic and energy transfer data.

• 한국자동차공학회논문집
• /
• 제12권3호
• /
• pp.177-183
• /
• 2004

The out-of-positioned small female drivers are most likely to be injured during airbag deployment due to their stature and proximity to the steering wheel and airbag module. In order to investigate the injury mechanisms, some experimental studies with Hybrid III 5% female dummy and with female cadavers could be found from the open literatures. However, the given information from those experimental studies is quite limited to the standard conditions and might not be enough to estimate the airbag inflation aggressiveness regarding on the occupant responses and injury. In this study, a finite element analysis has been performed in order to investigate the airbag-induced injuries. A finite element 5% female human model in anatomical details has been developed. The validation results of the model are also introduced in this paper.

• Journal of Microbiology
• /
• 제35권1호
• /
• pp.21-24
• /
• 1997

The hybrid peptides, CA-ME, CA-MA and CA-BO, with the N-terminal sequence 1-8 of cecropin A and the N-terminal sequences 1-12 of melittin, magainin 2 and bombinin, respectively, have more improved antibacterial activities. CA-MA was found to have stronger antifungal activity against Trichoderma sp than other hybrid peptides and their parental peptides. In order to elucidate the relationships between the peptide structure and antifungal activity, several analogues of CA-MA or CA-BO were also designed and synthesized by the solid phase method. An tifungal activity was measured against T. reesei and T. viride, and hemolytic activity was measured by a solution method against human red blood cells. The residue 16 of CA-MA, Ser, was found to be important for antifungal activity. When the residue was substituted with Leu, showed powerful antifungal activity was dramatically decreased. CA-MA, P1, P4 and P5 designed in this study showed powerful antifungal activity against T. reesei and T. viride with low hemolytic activity against human red blood cells. These hybrid peptides will be potentially useful model to further design peptides with powerful antifungal activity for the effective therepy of fungal infection and understand the mechanisms of antifungal actions of hybrid peptides.

• 대한임베디드공학회논문지
• /
• 제3권2호
• /
• pp.91-101
• /
• 2008

For a friendly interaction between human and robot, emotional interchange has recently been more important. So many researchers who are investigating the emotion generation model tried to naturalize the robot's emotional state and to improve the usability of the model for the designer of the robot. And also the various emotion generation of the robot is needed to increase the believability of the robot. So in this paper we used the hybrid emotion generation architecture, and defined the generalized context input of emotion generation model for the designer to easily implement it to the robot. And we developed the personality and loyalty model based on the psychology for various emotion generation. Robot's personality is implemented with the emotional stability from Big-Five, and loyalty is made of familiarity generation, expression, and learning procedure which are based on the human-human social relationship such as balance theory and social exchange theory. We verify this emotion generation model by implementing it to the 'user calling and scheduling' scenario.