• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.10
• /
• pp.1891-1896
• /
• 2006

In this paper, we propose an improved Active Shape Model for extracting lip contour. Lip deformation is modeled by a statistically deformable model based Active Shape Model. Because each point is moved independently using local profile information in Active Shape Model, many error may happen. To use a global information, we define an energy function similar to an energy function in Active Contour Model, and points are moved to positions at which the total energy is minimized. The experiments have been performed for many lip images of Tulip 1 database, and show that our method extracts lip shape than a traditional ASM more exactly.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.1
• /
• pp.17-24
• /
• 2024

This paper introduces a novel approach to time-series estimation for energy load forecasting within Virtual Power Plant (VPP) systems, leveraging advanced artificial intelligence (AI) algorithms, namely Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Virtual power plants, which integrate diverse microgrids managed by Energy Management Systems (EMS), require precise forecasting techniques to balance energy supply and demand efficiently. The paper introduces a hybrid-method forecasting model combining a parametric-based statistical technique and an AI algorithm. The LSTM algorithm is particularly employed to discern pattern correlations over fixed intervals, crucial for predicting accurate future energy loads. SARIMA is applied to generate time-series forecasts, accounting for non-stationary and seasonal variations. The forecasting model incorporates a broad spectrum of distributed energy resources, including renewable energy sources and conventional power plants. Data spanning a decade, sourced from the Korea Power Exchange (KPX) Electrical Power Statistical Information System (EPSIS), were utilized to validate the model. The proposed hybrid LSTM-SARIMA model with parameter sets (1, 1, 1, 12) and (2, 1, 1, 12) demonstrated a high fidelity to the actual observed data. Thus, it is concluded that the optimized system notably surpasses traditional forecasting methods, indicating that this model offers a viable solution for EMS to enhance short-term load forecasting.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.4724-4747
• /
• 2016

To efficiently reduce on-grid energy consumption, the admission control algorithm in the hybrid energy powered cellular network (HybE-Net) with base stations (BSs) powered by on-grid energy and solar energy is studied. In HybE-Net, the fluctuation of solar energy harvesting and energy consumption may result in the imbalance of solar energy utilization among BSs, i.e., some BSs may be surplus in solar energy, while others may maintain operation with on-grid energy supply. Obviously, it makes solar energy not completely useable, and on-grid energy cannot be reduced at capacity. Thus, how to control user admission to improve solar energy utilization and to reduce on-grid energy consumption is a great challenge. Motivated by this, we first model the energy flow behavior by using stochastic queue model, and dynamic energy characteristics are analyzed mathematically. Then, fuzzy logic based admission control algorithm is proposed, which comprehensively considers admission judgment parameters, e.g., transmission rate, bandwidth, energy state of BSs. Moreover, the index of solar energy utilization balancing is proposed to improve the balance of energy utilization among different BSs in the proposed algorithm. Finally, simulation results demonstrate that the proposed algorithm performs excellently in improving solar energy utilization and reducing on-grid energy consumption of the HybE-Net.

• Progress in Superconductivity and Cryogenics
• /
• v.21 no.3
• /
• pp.6-12
• /
• 2019

Extended Drude model has been used to obtain information of correlations from measured optical spectra of strongly correlated electron systems. The optical self-energy can be defined by the extended Drude model formalism. One can extract the optical self-energy and the electron-boson spectral density function from measured reflectance spectra using a well-developed usual process, which is consistent with several steps including the extended Drude model and generalized Allen's formulas. Here we used a reverse process of the usual process to investigate the extended Drude analysis when an additional low-energy interband transition is included. We considered two typical electron-boson spectral density model functions for two different (normal and d-wave superconducting) material states. Our results show that the low-energy interband transition might give significant effects on the electron-boson spectral density function obtained using the usual process. However, we expect that the low-energy interband transition can be removed from measured spectra in a proper way if the transition is well-defined or well-known.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.3
• /
• pp.75-85
• /
• 2008

The DBMS are widely used in embedded systems. The flash memory is used as a storage device of a embedded system. The optimizer of existing database system assumes that the storage device is disk. There is overhead to overwrite on flash memory unlike disk. The block of flash memory should be erased before write. Due to this reason, query optimization model based on disk does not adequate for flash-aware database. Especially embedded system should minimize the consumption of energy, but consumes more energy because of excessive erase operations. This paper proposes new energy based cost model of embedded database and shows the comparison between disk based cost model and energy based cost model.

• International conference on construction engineering and project management
• /
• 2011.02a
• /
• pp.74-83
• /
• 2011

This paper recognized a need in the architecture, engineering, and construction industry for new programs and methods of producing reliable energy simulations using BIM (Building Information Modeling) technology. Current methods and programs for running energy simulations are not very timely, difficult to understand, and lack high interoperability between the BIM software and energy simulation software. It is necessary to improve on these drawbacks as design decision are often made without the aid of energy modeling leading to the design and construction of non-optimized buildings with respect to energy efficiency. The goal of this research project is to develop a new methodology to produce energy estimates from a BIM model in a more timely fashion and to improve interoperability between the simulation engine and BIM software. In the proposed methodology, the extracted information from a BIM model is compiled into an INP file and run in a popular energy simulation program, DOE-2, on an hourly basis for a desired time period. Case study showed that the application of this methodology could be used to expediently provide energy simulations while at the same time reproducing the BIM in a more readably three dimensional modeling program. With the aid of an easy to run and easily understood energy simulation methodology, designers will be able to make more energy conscious decisions during the design phase and as changes in design requirements arise.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.10
• /
• pp.2052-2058
• /
• 2009

The standardized and open information model called common language and information exchange format should be firstly defined for the interoperable power system and two-way information exchange among the components of the power system. The information models and information exchange formats for power facilities and power system applications are being defined in power system area, but the information model and information exchange format for the consumer area are not being yet defined besides of metering information model. An architecture and open standard for the information exchange between energy service provider and consumer are required to provide various value added services through the networking with devices in consumer premise. In this paper, an architecture for the two-way communications between energy service provider and consumer is defined and psXML(power system XML) for the information exchange is designed.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.453-456
• /
• 2022

The role of the power grid is to ensure stable power supply. It is necessary to take various measures to prepare for unstable situations without notice. After identifying the relationship between features through exploratory data analysis using weather data, a machine learning based energy production prediction model is modeled. In this study, the prediction reliability was increased by extracting the features that affect energy production prediction using principal component analysis and then applying it to the machine learning model. By using the proposed model to predict the production energy for a specific period and compare it with the actual production value at that time, the performance of the energy production prediction applying the principal component analysis was confirmed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.858-861
• /
• 2012

Distributed sensor nodes for environmental monitoring, have a problem of difficult and expensive battery change. In this case, renewable energy such as solar energy is helpful. We can use high-quality solar energy everyday. In this paper, we model photovoltaic energy prediction model for sensor nodes, which includes charge and discharge characteristics as well as seasonal and monthly characteristics of the solar energy. Our model is useful to predict energy consumption of solar-powered sensor nodes realistically using real world use data of the nodes.