• MALSORI
• /
• v.68
• /
• pp.65-74
• /
• 2008

A statistical parametric speech synthesis system based on the hidden Markov models (HMMs) has grown in popularity over the last few years, because it needs less memory and low computation complexity and is suitable for the embedded system in comparison with a corpus-based unit concatenation text-to-speech (TTS) system. It also has the advantage that voice characteristics of the synthetic speech can be modified easily by transforming HMM parameters appropriately. In this paper, we present experimental results of voice characteristics conversion using the HMM-based Korean speech synthesis system. The results have shown that conversion of voice characteristics could be achieved using a few sentences uttered by a target speaker. Synthetic speech generated from adapted models with only ten sentences was very close to that from the speaker dependent models trained using 646 sentences.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.32A no.9
• /
• pp.1209-1218
• /
• 1995

In this paper, we develope an ATM switch simulator in order to evaluate the HAN/B-ISDN ATM switch currently being developed by ETRI. It models the basic cell switching functions of the target ATM switch with priority control and multicasting features and it also supports such various traffic models as random or bursty traffic, balanced or unbalanced traffic, multicast traffic models. Using this simulator, we can evaluate the performances of the ATM switch in terms of various performance indices, i.e. cell delay, cell loss probability, etc., and this simulator can be utilized in the system parameter tunings such as the common buffer size and address buffer size.

• Bulletin of the Korean Chemical Society
• /
• v.32 no.7
• /
• pp.2433-2442
• /
• 2011

The three dimensional quantitative structure activity relationship (3D QSAR) models were developed using Comparative molecular field analysis (CoMFA), comparative molecular similarity indices analysis (CoMSIA) and docking studies. The fit of Quinazolinone antifolates inside the active site of modeled bovine dihydrofolate reductase (DHFR) was assessed. Both ligand based (LB) and receptor based (RB) QSAR models were generated, these models showed good internal and external statistical reliability that is evident from the $q^2_{loo}$, $r^2_{ncv}$ and $r^2_{pred}$. The identified key features enabled us to design new Quinazolinone analogues as DHFR inhibitors. This study is a building bridge between docking studies of homology modeled bovine DHFR protein as well as ligand and target based 3D QSAR techniques of CoMFA and CoMSIA approaches.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.266-271
• /
• 2002

We propose a hardware accelerated voxelization method for various 3D object model such as surface models, solid models, and volumetric CSG models. The algorithm utilizes the stencil buffer that is one of modern Open히 graphics hardware features. The stencil buffer is originally used to restrict drawing to certain portions of the screen. The volumetric representations of given 3D objects are constructed slice-by-slice. For each slice, the algorithm restricts the drawing areas constructed inner region of 3D objects using the stencil buffer, and generates slices of the volumetric representation for target objects. As a result, we can provide volume graphics support for various engineering applications such as multi-axis machining simulation, collision detection and finite element analysis.

• Journal of the Korea Society for Simulation
• /
• v.7 no.2
• /
• pp.137-152
• /
• 1998

One of the components that constitute the simulation models is the state variables whose values are determined by the time related simulation process. Embedding rule-based expert systems into the simulation models should provide a systematic way of handling these time-dependent variables without distracting the essential problem solving capabilities of the expert systems which are well suited for expressing the decision making function of complex cases. The expert system, however, is inefficient in dealing with the time elapsing characteristics of target system compare to the simulation models. To solve the problem, this paper provides an interruptible inference engine whose inferencing process can be interrupted when the variables' value, which are used as the parameters of the rules, are not yet determined due to the time dependent nature of the state variables. The process is resumed when the variables are ready. The elapse of time is calculated by time-advance function of the simulation model to which the expert system has been embedded. The example modeling shown exploits the embedded interruptible inferencing capability for the controlling and monitoring of metal grating process.

• Journal of Intelligence and Information Systems
• /
• v.3 no.2
• /
• pp.33-55
• /
• 1997

A data model is a diagram that describes the properties of different categories of data and the associations among them within a business or information system. In spite of its importance and usefulness, data modeling activity requires not only a lot of time and effort but also extensive experience and expertise. The data models for similar business areas are analogous to one another. Therefore, it is reasonable to reuse the already-developed data models if the target business area is similar to what we have already analyzed before. In this research, we develop a case-based reasoning system for data model reuse, which we shall call CB-DM Reuser (Case-Based Data Model Reuser). CB-DM Reuse consists of four subsystems : the graphic user interface to interact with end user, the data model management system to build new data model, the case base to store the past data models, and the knowledge base to store data modeling and data model reusing knowledge. We present the functionality of CB-DM Reuser and show how it works on real-life a, pp.ication.

• Earthquakes and Structures
• /
• v.10 no.3
• /
• pp.563-588
• /
• 2016

In this study, solution models are proposed to obtain code-compatible ground motion record sets which can be used for both uni-directional and bi-directional dynamic analyses. Besides scaled, unscaled ground motion record sets are obtained to show the utility and efficiency of the solution models. For scaled ground motion sets the proposed model is based on hybrid HS-Solver which integrates heuristic harmony search (HS) algorithm with the spreadsheet Solver add-in. For unscaled ground motion sets HS based solution model is proposed. Design spectra defined in Eurocode-8 for different soil types are selected as target spectra. The European Strong Motion Database is used to get ground motion record sets. Also, a sensitivity analysis is conducted to evaluate the effect of different HS solution parameters on the solution accuracy. Results show that the proposed solution models can be regarded as efficient ways to develop scaled and unscaled ground motion sets compatible with code-based design spectra.

• International Journal of Computer Science & Network Security
• /
• v.21 no.1
• /
• pp.1-5
• /
• 2021

Cyberbullying is a problem that is faced in many cultures. Due to their popularity and interactive nature, social media platforms have also been affected by cyberbullying. Social media users from Arab countries have also reported being a target of cyberbullying. Machine learning techniques have been a prominent approach used by scientists to detect and battle this phenomenon. In this paper, we compare different machine learning algorithms for their performance in cyberbullying detection based on a labeled dataset of Arabic YouTube comments. Three machine learning models are considered, namely: Multinomial Naïve Bayes (MNB), Complement Naïve Bayes (CNB), and Linear Regression (LR). In addition, we experiment with two feature extraction methods, namely: Count Vectorizer and Tfidf Vectorizer. Our results show that, using count vectroizer feature extraction, the Logistic Regression model can outperform both Multinomial and Complement Naïve Bayes models. However, when using Tfidf vectorizer feature extraction, Complement Naive Bayes model can outperform the other two models.

• Microbiology and Biotechnology Letters
• /
• v.50 no.4
• /
• pp.477-487
• /
• 2022

Probiotics provide a symbiotic relationship and beneficial effects by balancing the human intestinal microbiota. The relationships between microbiota changes and various diseases may predict health abnormalities and diseases. Treatment with vitamins and probiotics is one therapeutic approach. To evaluate the effect of probiotics on vitamin absorption, we chose Lactobacillus rhamnosus CBT-LR5 treatment, which has resistance to vitamin C-inducible toxicity, with vitamins in high-fat diet (HFD)-induced obesity models. CBT-LR5 affected the absorption of micronutrients, such as ionic minerals and water-soluble vitamins. An increase in vitamin C absorption by CBT-LR5 enhanced the antioxidant response in HFD-induced obesity models. Increased vitamin B absorption by CBT-LR5 regulated lipid metabolism in HFD-induced obesity models. These favorable effects of CBT-LR5 on the absorption of vitamins should be investigated as candidate therapeutic target treatments for metabolic diseases.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.127-135
• /
• 2024

Recent studies have shown that inverse design using deep learning has the potential to rapidly generate the optimal design that satisfies the target performance without the need for iterative optimization processes. Unlike traditional methods, deep learning allows the network to rapidly generate a large number of solution candidates for the same objective after a single training, and enables the generation of diverse designs tailored to the objectives of inverse design. These inverse design techniques are expected to significantly enhance the efficiency and innovation of design processes in various fields such as aerospace, biology, medical, and engineering. We analyzes inverse design models that are mainly utilized in the nano and chemical fields, and proposes inverse design models based on supervised and unsupervised learning that can be applied to the engineering system. It is expected to present the possibility of effectively applying inverse design methodologies to the design optimization problem in the field of engineering according to each specific objective.