• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.453-458
• /
• 2024

Due to global issues such as climate crisis and rising energy costs, there is an increasing focus on energy conservation and management. In the case of South Korea, approximately 53.5% of the total energy consumption comes from industrial complexes. In order to address this, we aimed to improve issues through the 'Shared Network Utility Plant' among companies using similar energy utilities to find energy-saving points. For effective energy conservation, various techniques are utilized, and stable data supply is crucial for the reliable operation of factories. Many anomaly detection and alert systems for checking the stability of data supply were dependent on Energy Management Systems (EMS), which had limitations. The construction of an EMS involves large-scale systems, making it difficult to implement in small factories with spatial and energy constraints. In this paper, we aim to overcome these challenges by constructing a data collection system and anomaly detection alert system on embedded devices that consume minimal space and power. We explore the possibilities of utilizing anomaly detection alert systems in typical institutions for data collection and study the construction process.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.137-140
• /
• 2003

In this paper, we propose a robust endpoint detection algorithm for speaker verification. Proposed algorithm uses energy and cepstral distance parameters, and it replaces the detected endpoints with endpoints of voiced speech, when the estimated signal-to-noise ratio (SNR) is low. Experimental results show that proposed algorithm is superior to energy-based endpoint detection algorithm.

• Proceedings of the Korean Society of Food Hygiene and Safety Conference
• /
• 2001.10a
• /
• pp.123-126
• /
• 2001

• Proceedings of the Korean Society of Food Hygiene and Safety Conference
• /
• 2001.10a
• /
• pp.127-130
• /
• 2001

• Proceedings of the Korean Society of Food Hygiene and Safety Conference
• /
• 2001.10a
• /
• pp.131-134
• /
• 2001

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.9-17
• /
• 2024

Due to the increase in energy consumption, and eco-friendly policies, there is a need for efficient energy consumption in buildings. Anomaly power detection based on deep learning are being used. Because of the difficulty in collecting anomaly data, anomaly detection is performed using reconstruction error with a Recurrent Neural Network(RNN) based autoencoder. However, there are some limitations such as the long time required to fully learn temporal features and its sensitivity to noise in the train data. To overcome these limitations, this paper proposes the TCN-USAD, combined with Temporal Convolution Network(TCN) and UnSupervised Anomaly Detection for multivariate data(USAD). The proposed model using TCN-based autoencoder and the USAD structure, which uses two decoders and adversarial training, to quickly learn temporal features and enable robust anomaly detection. To validate the performance of TCN-USAD, comparative experiments were performed using two building energy datasets. The results showed that the TCN-based autoencoder can perform faster and better reconstruction than RNN-based autoencoder. Furthermore, TCN-USAD achieved 20% improved F1-Score over other anomaly detection models, demonstrating excellent anomaly detection performance.

• The Journal of the Korea Contents Association
• /
• v.7 no.7
• /
• pp.60-67
• /
• 2007

The spectrum sensing is important for decision of using frequency band. It checks the frequency band for cognitive radio system. In this paper, we apply autocorrelation function to the energy detection method. We use the autocorrelation function to improve the performance of spectrum sensing method based on the energy detection method. This method is different from cyclostationary process method where parameters such as the mean or the autocorrelation function are time-varying periodically. And we propose improved method that is robust in poor radio environment. If the proposed method applies for sensing in the cognitive radio system, it will have the structural simplicity and the fast computation of spectrum sensing.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.15 no.1
• /
• pp.310-317
• /
• 1995

Crack detection technique by ultrasonics in structures and components made of austenitic stainless steel often loses its reliability due to the material characteristics during inservice inspection of nuclear power plants, especially in the area of detection and sizing in centrifugally cast stainless steel pipings. In order to understand and overcome this problem, computer program for tracing the ultrasonic rays within material has been developed to simulate the process of defect detection within weld. The program simulates through transmission and reflection technique in crack detection of austenitic stainless steel as well as ultrasonic beam propagation through multiple media including stainless steel cladding interface.

• Proceedings of the KIEE Conference
• /
• 2005.07b
• /
• pp.1705-1707
• /
• 2005

This paper proposes a novel active frequency drift(AFD) method for the islanding prevention of grid-connected photovoltaic inverter. To detect the islanding phenomenon of grid-connected photovoltaic(PV) inverters concerning about the safety hazards and the damage to other electric equipments, many kinds of anti-islanding methods have been presented. Among them, AFD method using chopping fraction(cf) enables the islanding detection to drift up(or down) the frequency of the voltage during the islanding situation. However, the performance of the conventional AFD methods, which have a certain value of cf only, is inefficient and difficult to design the appropriate cf value analytically to meet the limit of harmonics. In this paper, the periodic chopping fraction based on an AFD method is proposed. This proposed method shows the analytical design value of cf to meet the test procedure of IEEE Std. 929-2000 with the power quality and islanding detection time. To verify the validation of the proposed method, the islanding test results are presented. It is confirmed that the proposed method has not only less harmonic distortion but also good performance of islanding detection compare with the conventional AFD method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.8
• /
• pp.1404-1422
• /
• 2011

In this paper, a new clear channel assessment (CCA) method: cascaded-CCA, is proposed. The primary motivation for the proposed approach is to integrate the respective advantages of two standard CCA mechanisms, energy detect and preamble detect, to arrive at a new dual threshold CCA family that can provide greater flexibility towards tuning MAC performance. Cascaded-CCA integrates energy efficiency of the energy detector (ED) and the reliability of the preamble detector (PD). The probability of detection/false alarm and power consumption of cascaded-CCA in the CCA modules of IEEE 802.11b are analyzed and compared with ED and PD as an example. The performance of cascaded-CCA is explored via MATLAB simulations that implement the CCA modules and medium access control (MAC) protocol for IEEE 802.11 and IEEE 802.15.4. Simulation results showed that cascaded-CCA improves the energy efficiency significantly compared to ED-only or PD-only CCA. In addition, ED, PD, and cascaded CCA are applied to a cognitive network scenario to validate the effectiveness of the proposed cascaded-CCA.