• Journal of Biomedical Engineering Research
• /
• v.41 no.5
• /
• pp.195-202
• /
• 2020

Needle detection in ultrasound images is sometimes difficult due to obstruction of fat tissues. Accurate needle detection using continuous ultrasound (CUS) images is a vital stage of treatment planning for tissue biopsy and brachytherapy. The main goal of the study is classified into two categories. First, new detection model, i.e. D-Attention Unet, is developed by combining the context information of 3D medical data and CUS images. Second, the D-Attention Unet model was compared with other models to verify its usefulness for needle detection in continuous ultrasound images. The continuous needle images taken with ultrasonic waves were converted into still images for dataset to evaluate the performance of the D-Attention Unet. The dataset was used for training and testing. Based on the results, the proposed D-Attention Unet model showed the better performance than other 3 models (Unet, D-Unet and Attention Unet), with Dice Similarity Coefficient (DSC), Recall and Precision at 71.9%, 70.6% and 73.7%, respectively. In conclusion, the D-Attention Unet model provides accurate needle detection for US-guided biopsy or brachytherapy, facilitating the clinical workflow. Especially, this kind of research is enthusiastically being performed on how to add image processing techniques to learning techniques. Thus, the proposed method is applied in this manner, it will be more effective technique than before.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.2
• /
• pp.1079-1089
• /
• 2021

The development of information technology has promoted organizational transformation through the utilization of an electronic information system. This research aimed to identify factors that influence continuous intention to use E-HRM. This empirical research applies the Technology Acceptance Model and Cognitive Model for identifying significantly impacted areas of continuous intention to use E-HRM in a highly dynamic environment. The data were collected using questionnaires delivered directly to respondents. The sample was 100 employees of ESQ Group selected through random sampling. The variables used were subjective norms (X1), perceived behavioral control (X2), perceived innovativeness (Y1), cognitive absorption (Y2), satisfaction (Y3), and continuous intention to use E-HRM (Y4). Statistical analysis using Structural Equation Modelling (SEM) with Smart PLS was applied. The results revealed that behavioral control (X2) did not influence the continuous intention to use E-HRM (Y4) and that cognitive absorption (Y2) and satisfaction (Y3) did not significantly influence continuous intention to use E-HRM (Y4). Subjective norms (X1) significantly influenced both perceived innovativeness (Y1) and continuous intention to use E-HRM (Y4), perceived behavioral control (X2) significantly influenced both perceived innovativeness (Y1) and cognitive absorption (Y2), and perceived innovativeness (Y1) significantly influenced both satisfaction (Y3) and continuous intention to use E-HRM (Y4).

• Journal of IKEEE
• /
• v.11 no.2
• /
• pp.89-94
• /
• 2007

This paper is a study on continuous speech recognition in the Korean language using HMM-based models with continuous density functions. Here, we propose the most efficient method of continuous speech recognition for the Korean language under the condition of a continuous HMM model with 2 to 44 density functions. Two voice models were used CI-Model that uses 36 uni-phones and CD-Model that uses 3,000 tri-phones. Language model was based on N-gram. Using these models, 500 sentences and 6,486 words under speaker-independent condition were processed. In the case of the CI-Model, the maximum word recognition rate was 94.4% and sentence recognition rate was 64.6%. For the CD-Model, word recognition rate was 98.2% and sentence recognition rate was 73.6%. The recognition rate of CD-Model we obtained was stable.

• Proceedings of the Korea Association of Crystal Growth Conference
• /
• 1997.10a
• /
• pp.117-121
• /
• 1997

It is shown theoretically that uniform axial dopant concentration distribution can be made throughout the crystal by continuous Czochralski process. Numerical simulation are performed for the transient two-dimensional convection-diffusion model. A typical value of the growth and system parameters for Czochralski growth of p-type, 4 inches silicon crystal was used in the numerical calculations. Using this model with proper model parameter, the axial segregation in batchwise Czochralski growth can be described. It is studied by comparing with the experimental data. With this model parameter, the uniform axial concentration distribution of dopant is predicted in continuous Czochralski process.

• Journal of applied mathematics & informatics
• /
• v.9 no.1
• /
• pp.185-195
• /
• 2002

Previous research has shown that the flow of patients around departments of geriatric medicine and ex-patients in the community may be-modelled by the application of a mixed-exponential distribution. In this proper we considered a ave-compartment model using a continuous-time Markov process to describe the flow of patients. Using a M/ph/c queuing model, we present a way of optimizing the number of beds in order to maintain an acceptable delay probability a sufficiently low level. Finally, we constructed a Java computer simulation, using data from St George's Hospital, London.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.93-102
• /
• 2022

Dependency parsing is a decision problem of the syntactic relation between words in a sentence. Recently, deep learning models are used for dependency parsing based on the word representations in a continuous vector space. However, it causes a mislabeled tagging problem for the proper nouns that rarely appear in the training corpus because it is difficult to express out-of-vocabulary (OOV) words in a continuous vector space. To solve the OOV problem in dependency parsing, we explored the proper noun embedding method according to the embedding unit. Before representing words in a continuous vector space, we replace the proper nouns with a special token and train them for the contextual features by using the multi-layer bidirectional LSTM. Two models of the syllable-based and morpheme-based unit are proposed for proper noun embedding and the performance of the dependency parsing is more improved in the ensemble model than each syllable and morpheme embedding model. The experimental results showed that our ensemble model improved 1.69%p in UAS and 2.17%p in LAS than the same arc-eager approach-based Malt parser.

• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.99-120
• /
• 2017

As smartphones and tablets are drastically spreading, mobile IPTV service becomes very important emerging issue in addition to existing DMB broadcasting, and the consumption of personalized multimedia services is increasing in the mobile Internet environment. While the previous research focuses on influencing factors of the initial acceptance intention of the mobile IPTV Service, this study intends to find the factors that affect continuous use intention of the mobile IPTV service which has become one of core services in the mobile environment. The research model and the hypotheses of this study could be derived on the basis of four referent theories (that is, mobile service quality model (MOBISQUAL), post acceptance model (PAM), expectation confirmation theory (ECT) and extended technology acceptance model (ETAM)). In order to empirically test the hypotheses, the field survey was conducted for 278 respondents. Twelve ones of fifteen hypotheses were found to be statistically significantly adopted from the results of structural equation model analyses using Smart PLS 3.0. The theoretical contribution of this study is to empirically investigate the factors that affect the continuous use intention of mobile IPTV service. And the practical contribution is to provide the implementation guidelines of managing the service quality to enhance the competitive power of mobile IPTV business.

• Journal of Digital Convergence
• /
• v.10 no.7
• /
• pp.167-172
• /
• 2012

In vocabulary recognition using HMM(Hidden Markov Model) by model for the observation of a discrete probability distribution indicates the advantages of low computational complexity, but relatively low recognition rate has the disadvantage that require sophisticated smoothing process. Gaussian mixtures in order to improve them with a continuous probability density CHMM (Continuous Hidden Markov Model) model is proposed for the optimization of the library system. In this paper is system configuration thread control in recognition Gaussian mixtures model provides a model to optimize of the CHMM vocabulary recognition. The result of applying the proposed system, the recognition rate of 98.1% in vocabulary recognition, respectively.

• The Journal of Information Technology
• /
• v.12 no.1
• /
• pp.15-20
• /
• 2009

In this paper, we aim that it solve to problem of the database hoarding because a week connectivity of wireless networks and cutting of link, Consistency of shared data, optimizing of the log include to Mobile Continuous Query Processing System under the mobile client and server environment. and we demonstrate of the superiority for the new Mobile Continuous Query Processing System compare C-I-S(Client-Intercept -Server)model with performance. and we perform to various experiment in order to establishment of superiority compare the index architecture and method for the realtime Continuous Query Processing. in this paper.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.788-791
• /
• 1996

A mathematical model is developed for thermal solution copolymerization of styrene and acrylonitrile in a continuous stirred tank reactor(CSTR). Computational studies are carried out with the continuous copolymerization system model developed in this work to give the monomer conversion, copolymer composition and the average molecular weights of the copolymer. By performing the dynamic analysis of the reaction system, the polymer properties against the changes in the operating conditions are determined quantitatively. The cascade PID and fuzzy controller show satisfactory performances for both set point tracking and disturbance rejection. Especially, the fuzzy controller is superior to the PID controller.